WO2019040996A1 - Reporting test results - Google Patents

Reporting test results Download PDF

Info

Publication number
WO2019040996A1
WO2019040996A1 PCT/AU2018/050947 AU2018050947W WO2019040996A1 WO 2019040996 A1 WO2019040996 A1 WO 2019040996A1 AU 2018050947 W AU2018050947 W AU 2018050947W WO 2019040996 A1 WO2019040996 A1 WO 2019040996A1
Authority
WO
WIPO (PCT)
Prior art keywords
biomarker
cluster
score
subject
representation
Prior art date
Application number
PCT/AU2018/050947
Other languages
French (fr)
Inventor
Alexander Miles BROWNING
Original Assignee
Fizziofit Pty Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from AU2017903566A external-priority patent/AU2017903566A0/en
Application filed by Fizziofit Pty Ltd filed Critical Fizziofit Pty Ltd
Publication of WO2019040996A1 publication Critical patent/WO2019040996A1/en

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/40—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for data related to laboratory analysis, e.g. patient specimen analysis
    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
    • C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
    • C12Q1/68—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving nucleic acids
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B20/00—ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
    • G16B40/20—Supervised data analysis
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
    • G16B40/30—Unsupervised data analysis
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B10/00—Other methods or instruments for diagnosis, e.g. instruments for taking a cell sample, for biopsy, for vaccination diagnosis; Sex determination; Ovulation-period determination; Throat striking implements
    • A61B2010/0003—Other methods or instruments for diagnosis, e.g. instruments for taking a cell sample, for biopsy, for vaccination diagnosis; Sex determination; Ovulation-period determination; Throat striking implements including means for analysis by an unskilled person
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4836—Diagnosis combined with treatment in closed-loop systems or methods
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4836—Diagnosis combined with treatment in closed-loop systems or methods
    • A61B5/4839—Diagnosis combined with treatment in closed-loop systems or methods combined with drug delivery
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7271—Specific aspects of physiological measurement analysis
    • A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/742—Details of notification to user or communication with user or patient ; user input means using visual displays
    • A61B5/7435—Displaying user selection data, e.g. icons in a graphical user interface
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/742—Details of notification to user or communication with user or patient ; user input means using visual displays
    • A61B5/7445—Display arrangements, e.g. multiple display units
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2570/00—Omics, e.g. proteomics, glycomics or lipidomics; Methods of analysis focusing on the entire complement of classes of biological molecules or subsets thereof, i.e. focusing on proteomes, glycomes or lipidomes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2800/00—Detection or diagnosis of diseases
    • G01N2800/50—Determining the risk of developing a disease
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2800/00—Detection or diagnosis of diseases
    • G01N2800/52—Predicting or monitoring the response to treatment, e.g. for selection of therapy based on assay results in personalised medicine; Prognosis
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2800/00—Detection or diagnosis of diseases
    • G01N2800/54—Determining the risk of relapse
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2800/00—Detection or diagnosis of diseases
    • G01N2800/56—Staging of a disease; Further complications associated with the disease
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2800/00—Detection or diagnosis of diseases
    • G01N2800/60—Complex ways of combining multiple protein biomarkers for diagnosis
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B45/00—ICT specially adapted for bioinformatics-related data visualisation, e.g. displaying of maps or networks

Definitions

  • the present invention relates to a method and apparatus for reporting results of a biological test performed on a subject.
  • an aspect of the present invention seeks to provide a system for use in treating a biological subject in accordance with a test result for a biological test performed on the subject, the system including one or more processing devices that: for each of a plurality of biomarkers, determine a respective biomarker value as a result of a measurement of the biomarker performed as part of the test; determine a biomarker score associated with each biomarker based on the respective biomarker value; for each of multiple biomarker clusters, calculate a cluster score based on a combination of biomarker scores associated with each of a number of biomarkers forming part of the biomarker cluster; determine a ranking of the multiple biomarker clusters using the cluster score for each biomarker cluster; generate a representation including one or more cluster representations, the one or more cluster representations being presented in accordance with the ranking, and wherein each cluster representation is associated with a respective one of the multiple biomarker clusters and includes: an indication of the cluster score; and, an indication of the
  • At least one cluster representation includes: a score region indicative of the cluster score; and, a biomarker region including a number of biomarker sub- regions, each biomarker sub-region being indicative of the biomarker score for a respective biomarker.
  • the score region is a central region; and, a biomarker region is an annular region extending around the central region.
  • the score region includes an alpha numeric representation of the cluster score; and, a biomarker region including biomarker sub-regions that indicate the biomarker score through one or more of: sizing; shading; colouring; and, filling.
  • the cluster sub-regions are ordered in accordance with the ranking.
  • each biomarker cluster is associated with a respective health aspect of the subject.
  • the one or more processing devices selectively display information including at least one of: cluster information associated with a biomarker cluster; one or more health risks associated with the cluster; one or more health benefits associated with the cluster; one or more actions associated with the cluster, biomarker information associated with a biomarker; one or more health risks associated with the biomarker; one or more health benefits associated with the biomarker; one or more actions associated with the biomarker; and, recommendations relating to one or more of: diet; sleep; movement; exercise; stress; supplementation; medical interventions; and, target values for one or more subject parameters.
  • the one or more processing devices determine a user selection in accordance with user input commands; determine information; and, display the information as part of the representation.
  • the one or more processing devices determine subject parameter values indicative of values for one or more subject parameters; comparing the target values to at least one of: subject parameter values; and, changes in subject parameter values over time; and, use results of the comparison to at least one of: track progress of completion of one or more actions; determine a new target value; and, generate a progress representation.
  • the one or more subject parameters include one or more of: physical characteristic parameters selected from the group including: a sex; an ethnicity; an age; a height; a weight; a body mass index; one or more body state parameters selected from the group including: a healthy body state; an unhealthy body state; and, one or more disease states; one or more medical parameters selected from the group including: medical symptoms; a blood potassium level; a temperature; a blood pressure; a respiratory rate; a heart rate; a blood oxygenation level; one or more lifestyle parameters selected from the group including: sleeping habits; a fitness level; an exercise frequency; an exercise duration; an exercise type; an exercise intensity; and, a diet.
  • the one or more processing devices calculate the cluster score using at least one of: biomarker scores; a weighted sum of biomarker scores; a combination of biomarker scores and at least one of: subject parameter values indicative of values for one or more subject parameters; and, changes in subject parameter values over time; and, a combination of biomarker scores and results of a comparison between target values and at least one of: subject parameter values; and, changes in subject parameter values over time.
  • the one or more processing devices calculate the cluster score using a cluster score model, the cluster score model being derived using machine learning techniques applied to training data derived from multiple subjects.
  • the one or more processing devices determine a cluster score at least partially in accordance with biomarker values that change over time.
  • the one or more processing devices track changes in cluster scores over time.
  • biomarker scores are numerical scores that are one or more of: retrieved from stored biomarker score data using the biomarker value; and, calculated from the biomarker value.
  • the one or more processing devices creates the clusters using machine learning techniques applied to training data derived from multiple subjects.
  • the system includes: a sampling device that obtains a sample from the biological subject; and, a measurement device that measures at least one biomarker value for a biomarker in the sample.
  • the one or more processing devices calculate the action score using biomarker scores for at least one of: cluster biomarkers; and, other biomarkers.
  • Figure 4 is a schematic diagram of an example of a computer system of Figure 2;
  • Figures 5A to 5D are a flow chart of a specific example of a method for reporting a test result for a biological test performed on a biological subject;
  • Figure 6D is a schematic diagram of an example of a composite cluster representation.
  • the processing device(s) determine a respective biomarker value for each of a plurality of biomarkers.
  • the biomarker values are obtained as a result of a measurement of the biomarkers performed as part of the biological test, and the nature of the biomarkers and the manner in which the biomarker values are measured will vary depending on the nature of the test being performed.
  • this could involve measurement of one or more of a single-nucleotide polymorphism (SNP), copy number variation (CNV), loss of heterozygosity (LOH), genomic rearrangement, such as translocation, for one or more genes in the genome.
  • SNP single-nucleotide polymorphism
  • CNV copy number variation
  • LH loss of heterozygosity
  • genomic rearrangement such as translocation
  • testing can involve detecting DNA methylation, histone modification, chromatin accessibility, transcription factor (TF) binding and micro RNA (miPvNA), telomere length or the like.
  • TF transcription factor
  • miPvNA micro RNA
  • testing can detect gene expression and alternative splicing, whilst at the proteome level protein expression and post- translational modification can be detected, whilst metabolite profiling can be performed at the metabolome level.
  • the test could be a multi-omic test that involves combining results for tests performed on the genome, proteome, transcriptome, epigenome, and microbiome.
  • biomarker values are determined will vary depending upon the preferred implementation and this could include receiving biomarker values from one or more measurement devices, retrieving biomarker values previously stored in a data store, such as a memory or database, obtaining biomarker values from user input commands provided via a user interface, or the like. It will therefore be appreciated that the term "determining" could encompass the processing device being actively involved in the measurement process or could include the processing device simply receiving or retrieving the biomarker values generated as a result of the measurement process.
  • the biomarker value could be an indication of the identity and location of a SNP within a gene, in which case this could be allocated a specific numerical score. The score would typically be predefined for each of a number of known SNPs, allowing this to be simply retrieved.
  • biomarker values such as concentrations of gene expression products in a sample obtained from the subject, could be compared to thresholds, allocating a score based on the result of the comparison.
  • biomarker scores are typically integer values, and are defined to reflect an impact of the biomarker value on the subject, for example whether the respective biomarker value will have a positive, negative or null effect on the subject's health, although it will be appreciated that this is not essential and any suitable scoring system could be used.
  • a cluster score is calculated for each of multiple biomarker clusters.
  • the biomarker clusters are groups of a number of biomarkers that are related by virtue of their impact on the subject, and more typically because they have an impact on a particular aspect of the subject's health.
  • the biomarkers within any one cluster might all have an impact on the subject's cardiovascular health, whilst another cluster could be indicative of a propensity for breast cancer, or the like.
  • biomarkers may be present in multiple clusters in the event that they have an effect on different health aspects. In general, such clusters will be determined based on outcomes of scientific research and/or machine learning from training data, with the clusters typically being pre-defined and simply retrieved from a database as required.
  • the cluster score may also take into account values of subject parameters measured for the subject and examples of this will be described in more detail below.
  • the cluster score could be based on tests performed on one of the genome, proteome, transcriptome, epigenome, and microbiome, or a combination thereof.
  • the cluster score could include a genotype score, based on first biomarker values such as the presence or absence of certain SNPs, and a phenotype score, based on second biomarker values, such as the results of DNA methylation testing, with the genotype and phenotype scores being used to determine the cluster score.
  • the biomarker clusters are ranked using the cluster scores for each biomarker cluster. This can be achieved in any appropriate manner, for example using known ranking algorithms, and is performed to identify the likely relative health impact of the biomarker clusters, for example to identify one or more biomarker clusters likely to have a greatest overall impact on the health of the subject.
  • the representation can be then displayed to a user at step 150 and/or stored for later retrieval. It will be appreciated that this step could include transferring the representation to another device for display and does not require that the representation is displayed using the processing device. It should also be noted that the user could be the subject, but this is not necessarily the case, and alternatively the user could be any individual wishing and/or authorised to view the results of the biological test, including but not limited to a medical practitioner advising the subject, or the like. [0067] By presenting the cluster representation in this manner, in particular by displaying the cluster representations in accordance with the ranking and by including an indication of the cluster score, this allows a user to rapidly understand which cluster or clusters are likely to have the greatest impact on the health of the subject.
  • the ranking facilitates the user understanding which is the most important cluster, whilst the cluster score allows the user to understand the relative importance of the different clusters.
  • This in effect allows the representation to act as a risk profile, highlighting the issues that should be greatest concern to the subject.
  • an indication of the biomarker score associated with each of the number of biomarkers is provided, allowing this to be used by the user in order to understand which biomarkers are having the greatest effect on the subject.
  • the above described process provides a simple, straightforward mechanism for the user to understand and interpret test results for biological tests performed on a biological subject, which is particularly important given the complexity of interpreting such tests. Additionally, providing a graphical representation of the results in this manner enables the results to be displayed on a mobile device, such as a tablet, in a manner which is easy to view. Furthermore, the approach allows more limited amounts of data to be presented at any one time, which in turn allow the results to be more rapidly displayed on devices having limited processing capabilities.
  • the representation includes a cluster region including multiple cluster sub-regions, with each cluster sub-region being associated with a respective one of the multiple clusters.
  • the cluster region is an annular shaped region presented outwardly of a currently displayed cluster representation, with the cluster sub- regions typically being arranged circumferentially, ordered in accordance with the ranking, for example with the first ranked cluster presented at 12 o'clock and the other clusters spaced clockwise in order of ranking.
  • the cluster sub-regions may also be presented in a manner which visually indicates the relative importance of the respective cluster, for example by sizing the cluster sub-regions based on the cluster score.
  • each biomarker cluster is associated with a respective aspect of the subject's health.
  • the nature of the aspect will vary depending on the implementation, and the health aspects that can be associated with different clusters of biomarkers.
  • the clusters and the health aspects to which the cluster relates will be based on an analysis of scientific literature and/or by performing data mining in respect of biomarker values and other subject parameter values from one or more subjects.
  • the one or more processing devices creates the clusters using machine learning techniques applied to training data derived from multiple subjects, and in particular from biomarker and subject parameter values from multiple subjects.
  • the one or more processing devices further selectively display cluster information for one or more biomarker clusters, with the cluster information being indicative of one or more health risks/benefits associated with the health aspect and optionally one or more actions associated with the respective health attribute.
  • this is achieved by having a user select a cluster representation within the representation, allowing the processing device(s) to determine cluster information for the selected biomarker cluster and display the retrieved cluster information.
  • Similar process can be performed allowing a user to view specific information regarding individual biomarkers, for example through selection of a biomarker sub-region, thereby viewing potential risk/benefits associated with the biomarker. It will be appreciated that this allows the representation to act as a user interface so that the user can in effect "drill down” and obtain further information regarding the impact of a selected cluster and individual biomarkers within the cluster.
  • the actions could be presented at a high level, for example to suggest increasing levels of exercise, but in one preferred example, the information is at least partially quantified, defining target values which can act as a goal, encouraging and guiding the user to make lifestyle changes and/or seek other interventions as needed.
  • the target values are typically determined based on the biomarker values or biomarker scores, so that for different combinations of scores, different target values and hence different goals, are presented to the user. This ensures that the user is only ever presented with details of goals that are appropriate to their particular combination of biomarker values or scores.
  • the one or more processing devices can determine the target values based on subject parameter values indicative of one or more subject parameters.
  • target values are tailored not only based on the biomarker values and/or score, but also based on subject parameter values and/or change in subject parameter values. This is performed to ensure that the interventions are appropriate for the respective subject, in particular customising the target values based on the subject's capabilities or needs. For example, if a subject has a cluster prioritised which relates to cardiovascular disease, it may be necessary for the subject to increase a level of exercise in order to mitigate the risk of heart disease. In this instance, the level of exercise which is recommended for the subject will be different if the subject is a 70 year old subject to if the subject is a 20 year old subject.
  • the subject parameters typically relate to aspects of the subject's anatomy, physiology and/or psychology, and could include any quantifiable attribute, including attributes determined by subject/objective assessments. Most typically, the subject parameter values are determined by performing measurements on the subject and/or asking questions of the subject, for example by having the subject describe a fitness level, quantify a difficult associated with performing a respective exercise, or describe medical symptoms. Information regarding subject parameter values could be entered via a user interface, received from a measuring and/or retrieved from existing stored data, such as previously recorded historical subject parameter values and/or medical record data.
  • Specific example subject parameters may include any one or more of physical characteristic parameters selected from the group including: a sex, an ethnicity, an age, a height, a weight, a body mass index, one or more body state parameters selected from the group including: a healthy body state, an unhealthy body state, and, one or more disease states, one or more medical parameters selected from the group including: medical symptoms, a blood potassium level, a temperature, a blood pressure, a respiratory rate, a heart rate, a blood oxygenation level, one or more lifestyle parameters selected from the group including: sleeping habits, a fitness level, an exercise frequency, an exercise duration, an exercise type, an exercise intensity, and, a diet.
  • Subject parameters may also be indicative of participation in or completion of one or more medical interventions. However, it will be appreciated that this is not intended to be limiting, and in practice any suitable subject parameters could be used.
  • the target values could be determined in any one of a number of manners.
  • the processing system could determine base target values in accordance with the biomarker values and then modify the base target values to determine the target values using on the subject parameters.
  • templates of target values could be created, with a respective template being selected based on the biomarker values measured for the subject.
  • the template might specify particular actions to be performed in broad terms, such as to perform exercise, reduce fat intake, increase vitamin B 12 consumption, or the like.
  • the specific parameter values could then be used to select other templates that define respective target values for each action, for example defining an exercise routine, particular consumption levels or the like.
  • the target values could be gradually increased. In one example, this is performed based on results of a comparison of a target value to corresponding subject parameter values or changes in subject parameter values, so that for example if a target value is exceeded, a new increased target value can be defined.
  • the processing devices are used to determine subject parameter values and/or changes in subject parameter values and then compare these to the target values in order to assess progress on actions and in particular to determine if goals have been met.
  • a progress representation such as a line chart showing changes in subject parameter values relative to the target values, can be generated based on results of the comparison, with this being displayed to a user, allowing the user to assess whether the subject is working towards achieving the goals so as to mitigate any health issues associated with the biomarker values.
  • biomarker scores are then combined using a simple sum of biomarker scores.
  • a weighted sum of biomarker scores may be used, in which case the weighting can be assigned based on a relative magnitude of the risk/benefit, so for example biomarkers for which a risk has a potentially more severe outcome can be given a greater weighting, and hence contribute more to the overall cluster score.
  • the cluster score is scaled so that this represents a value between "0" and " 100", making this easier for the user to understand, although this is not essential and any suitable scoring technique could be used.
  • biomarker scores may change over time.
  • a subject's phenotype will typically vary in response to changes in environmental factors, subject behaviours, interventions or the like.
  • the one or more processing devices determine a cluster score at least partially based on biomarkers that change over time, and typically based on pheno typically biomarkers.
  • the processing devices determine a genotype score based on first biomarker values and a phenotype score based on second marker values, combining these to determine a cluster score at least in part using a combination of the genotype and phenotype scores.
  • the one or more processing devices can then track changes in cluster scores over time based on changes in the second biomarker values.
  • biomarker values may not necessarily reflect action taken by the individual.
  • the cluster score would remain unchanged, even if the user has taken significant action to address a risk.
  • the cluster scores could be based on a combination of biomarker scores and subject parameter values and/or changes in subject parameter values over time, or could be based on biomarker scores and results of a comparison between target values subject parameter values and/or changes in subject parameter values over time.
  • the cluster scores adjust as the subject parameter values change, such as when exercise levels are increased, diet improved, or the like.
  • This provides a mechanism to track the user's progress in addressing risks, and in particular allows users to move on and address other risks once more important risks are under control, based on re- ranking of the biomarker clusters, which in turn represents a change in the subjects risk profile.
  • biomarker scores could be calculated using any other appropriate technique.
  • the processing device(s) could calculate the cluster score using a cluster score model, which is derived using machine learning techniques applied to training data derived from multiple subjects.
  • the system can also be configured to display actions, such as interventions, in accordance with an action score, for example to allow actions to be prioritised.
  • the processing device(s) calculate an action score for each of a plurality of actions associated with a cluster and then display an indication of actions in accordance with the action score, typically by ranking the actions in accordance with the action score so that the actions are displayed in a ranked list. This allows users to rapidly assess actions, and in particular interventions, which are likely to have the biggest impact.
  • the action score is typically calculated based on biomarker scores that are relevant to the action, which could include one or more biomarkers within the cluster and/or other biomarkers. For example, other biomarkers might be used in assessing action score as biomarkers outside the cluster might have a bystander effect. Thus it will be appreciated that this allows actions to be prioritised taking into account not only the effect of biomarkers within the cluster, but also other biomarkers, enabling this to more accurately reflect the potential benefit for the user.
  • the processing devices can determine a risk level for a cluster in accordance with the cluster score and then either display an indication of the risk level and/or selectively display actions in accordance with the risk level.
  • the system can be used simply for reporting the test result of a biological test, it will be appreciated that more typically the system can be used as part of a treatment regime for a biological subject, with the treatment corresponding to performing respective actions in order to mitigate risks or other issues identified by the biological test results. In one example, this is achieved by displaying one or more actions and tracking progress towards completion of the actions based on subject parameter values and/or changes in subject parameter values.
  • the above described system provides a mechanism to present the results of a biological test to a user, and then track subject parameter values in the subject in order to track progress towards completion of defined actions.
  • the representation can be updated, allowing the user to receive feedback as to the degree of progress made, including through re-ranking of the clusters to reflect a change in risk profile for the subject.
  • a number of processing systems 210 are provided coupled to one or more client devices 230, via one or more communications networks 240, such as the Internet, and/or a number of local area networks (LANs).
  • networks 240 such as the Internet, and/or a number of local area networks (LANs).
  • Any number of processing systems 210 and client devices 230 could be provided, and the current representation is for the purpose of illustration only.
  • the configuration of the networks 240 is also for the purpose of example only, and in practice the processing systems 210 and client devices 230 can communicate via any appropriate mechanism, such as via wired or wireless connections, including, but not limited to mobile networks, private networks, such as an 802.11 networks, the Internet, LANs, WANs, or the like, as well as via direct or point-to-point connections, such as Bluetooth, or the like.
  • the processing systems 210 are adapted to acquire and process data, generate representations and provide access to results allowing these to be displayed via the client devices 230. Whilst the processing systems 210 are shown as single entities, it will be appreciated they could include a number of processing systems distributed over a number of geographically separate locations, for example as part of a cloud based environment. Thus, the above described arrangements are not essential and other suitable configurations could be used.
  • processing system could be any electronic processing device such as a microprocessor, microchip processor, logic gate configuration, firmware optionally associated with implementing logic such as an FPGA (Field Programmable Gate Array), or any other electronic device, system or arrangement.
  • a microprocessor microchip processor
  • logic gate configuration firmware optionally associated with implementing logic
  • firmware optionally associated with implementing logic
  • FPGA Field Programmable Gate Array
  • the client device 230 includes at least one microprocessor 400, a memory 401, an input/output device 402, such as a keyboard and/or display, an external interface 403, and typically a card reader 404, interconnected via a bus 405 as shown.
  • the external interface 403 can be utilised for connecting the transaction terminal 220 to peripheral devices, such as the communications networks 230 databases, other storage devices, or the like.
  • peripheral devices such as the communications networks 230 databases, other storage devices, or the like.
  • a single external interface 403 is shown, this is for the purpose of example only, and in practice multiple interfaces using various methods (eg. Ethernet, serial, USB, wireless or the like) may be provided.
  • the card reader 404 can be of any suitable form and could include a magnetic card reader, or contactless reader for reading smartcards, or the like.
  • the microprocessor 400 executes instructions in the form of applications software stored in the memory 401, and to allow communication with one of the processing systems 210.
  • one or more respective processing systems 210 are servers.
  • the servers 210 host results processing services that are accessed by the client devices 230, allowing results to be processed and allowing representations to be generated and provided to the client devices 230 for display. This could be performed via a specific application and/or could be by way of webpages or similar, depending on the preferred implementation.
  • User inputs are made via a user interface of the client device 230, with commands interpreted by the client device 230, allowing actions to be performed either by the client device 230 or the server 210, as required.
  • the servers 210 typically execute processing device software, allowing relevant actions to be performed, with actions performed by the server 210 being performed by the processor 300 in accordance with instructions stored as applications software in the memory 301 and/or input commands received from a user via the I/O device 302. It will also be assumed that actions performed by the client devices 230, are performed by the processor 400 in accordance with instructions stored as applications software in the memory 401 and/or input commands received from a user via the I/O device 402.
  • the subject undergoes a biological test.
  • the biological test could be a gene sequence analysis, such as a saliva-based genomic test similar to that performed by 23andMe , and/or could be an analysis of the subject's proteome, transcriptome, epigenome, or microbiome.
  • test results are processed, typically in accordance with standard techniques, and used in order to generate biomarker values which are indicative of either SNPs, CNVs or translocations associated with the genome, or other suitable biomarkers, depending on the nature of the test performed.
  • the test and determination of biomarker values may be performed by a third party and the results made available to the server 210, typically via electronic transfer from a third party server, retrieval from a database, or the like.
  • the results are typically recorded, for example by storing these in a database 211 as part of subject data associated with the respective subject at step 504.
  • the subject data could be of any appropriate form, and could include a profile or the like, with the subject data typically being used to store other information, such as current and/or historic subject parameter values.
  • the biomarker values are used to determine biomarker scores.
  • a database 211 typically includes a look-up table, which specifies the biomarker score that should be utilised for different biomarker values or ranges of biomarker values.
  • the look-up table will simply state a biomarker score for each different SNP.
  • the biomarker value represents a concentration of a gene expression product or similar
  • the look-up table can include one or more threshold values, with an indication of the score that should apply depending on comparison of the biomarker value to the threshold.
  • one or more cluster definitions are retrieved from a cluster database 211.
  • the cluster definitions define the number of biomarkers that relate to particular health aspects.
  • the clusters can be derived based on analysis of scientific literature, or based on an analysis of subject data for a plurality of subjects, for example by using machine learning to identify relationships between a number of biomarkers and specific aspects of health. Such machine learning typically involves clustering groups of subjects having similar health issues, and then identify patterns in biomarkers common to the subjects.
  • Such analysis can include any one or more of decision tree learning, random forest, logistic regression, association rule learning, artificial neural networks, deep learning, inductive logic programming, support vector machines, clustering, Bayesian networks, reinforcement learning, representation learning, similarity and metric learning, genetic algorithms, rule- based machine learning, learning classifier systems, or the like. As such schemes are known, these will not be described in any further detail.
  • the cluster definition typically also include an indication of the manner in which a cluster score should be calculated, including whether this is based solely on the biomarker scores and/or takes into account subject parameter values, depending on the preferred implementation.
  • the cluster score could be determined based on a specific calculation, such as a weighted sum of biomarker scores, with the weighting reflecting a relative impact of the respective biomarker on the health aspect to which the cluster relates.
  • a specific calculation such as a weighted sum of biomarker scores, with the weighting reflecting a relative impact of the respective biomarker on the health aspect to which the cluster relates.
  • some biomarkers may have a negligible impact on a subject's health whereas other biomarkers within the cluster may have a much greater impact, in which case these will be given a more significant weighting.
  • cluster scores could be determined from a model derived from training data using machine learning techniques, for example by using subject data, and in particular biomarker scores and/or subject parameter values from other subjects, to train one or more computational models.
  • the nature of the model and the training performed can be of any appropriate form and could include any one or more of decision tree learning, random forest, logistic regression, association rule learning, artificial neural networks, deep learning, inductive logic programming, support vector machines, clustering, Bayesian networks, reinforcement learning, representation learning, similarity and metric learning, genetic algorithms, rule-based machine learning, learning classifier systems, or the like. As such schemes are known, these will not be described in any further detail.
  • the cluster score is based on a combination of genotype and phenotype scores, for example based on the outcome of genetic tests, such as the presence or absence of SNPs and based on a phenotype score, such as DNA methylation.
  • the score for each of these can be weighted, depending for example on the severity of the risk associated with an SNP, or the relative accuracy of the test performed, for example scoring DNA methylation results higher based on the fact that this is a gold standard measure.
  • the scores can then be combined, so the effect of each SNP is weighted based on corresponding DNA methylation results, so that the resulting score provides the current true representation of genetic risk and actual risk.
  • the combined genetic and phenotypic score can alter, depending for example on subject health, so that the combined result reflecting the changes from various interventions.
  • the cluster scores are used to quantify the risk associated with each cluster, with this taking into account factors including the relative likelihood and severity of the risk. For example, the overall risk for a cluster may be greater if the impact of an issue is large, even if the likelihood of the issue arising is small. Having determined the cluster scores at step 516, the cluster scores are used to rank the clusters at step 518, in particular ordering the clusters based on the increasing or decreasing cluster score so that the cluster associated with the greatest risk is listed first.
  • the cluster scores are calculated to provide a value between "0" and " 100", with extremes representing very low or very high risks, thereby allowing a user to easily understand the relative risk associated with each biomarker cluster, although this is not essential and other values could be used.
  • step 520 one or more cluster representations are generated.
  • a respective cluster representation is generated for each cluster, and examples are shown in Figures 6A and 6B.
  • the cluster representation 600 includes a first central region 601, which typically includes an alphanumeric representation of the cluster score.
  • a biomarker region 602 is provided as an annular region surrounding the central region 601, with the annular region being segmented into a number of biomarker sub-regions 602.1, 602.2, 602.3, 602.4. It will be appreciated that whilst four biomarker sub-regions are shown in this example, this is for the purpose of illustration only and in practice the number of sub-regions will depend on the number of biomarkers within the cluster.
  • Each sub-region can be used to represent the biomarker score for a respective biomarker, for example based on a degree of in-filling, shading, or the like.
  • the relative sizes of the biomarker sub-regions is indicative of the relative contribution of the biomarker score to the cluster score.
  • the biomarker sub-region can also act as a user input, allowing a user to view additional information regarding the biomarker and risk associated with the respective biomarker values.
  • a respective cluster representation is generated for each of the clusters, with an example of this being shown in Figure 6C, in which six cluster representations 600.1, 600.2, 600.3, 600.4, 600.5, 600.6 as part of an ordered list, with the lowest cluster score in this example being associated with the cluster representing the greatest risk to subject health.
  • FIG. 6D An alternative representation is shown in Figure 6D.
  • the representation 600 includes a cluster region 603 in the form of a ring positioned annularly outwardly of the biomarker region 602.
  • the cluster region 603 includes sub-regions 603.1, 603.2, 603.3, 603.4, 603.5 relating to five different clusters, with five being shown for the purpose of illustration only.
  • Each cluster sub-region is used to represent the biomarker scores through shading, with the relative sizes of the cluster sub-regions being indicative of the relative cluster score.
  • the cluster sub-regions are accompanied by indications of the health aspect to which the cluster relates, with the indication this being displayed when the cluster is selected, which can be achieved by having the user select a respective sub-region, for example using a mouse click or similar. It will therefore be appreciated that the cluster sub-regions again act as user inputs allowing cluster representations for different clusters to be displayed.
  • the intervention score and hence ranking could be based on biomarker scores for biomarkers within the cluster, but could additionally and/or alternatively be based on biomarker scores for biomarkers in other clusters, for example to account for bystander effects.
  • a cluster relating to skin health could be ranked based on biomarkers relating to skin health, but also other biomarkers, such as inflammation biomarkers.
  • the number of interventions displayed to the user could be tailored based on a risk level associated with the cluster score.
  • the cluster score could be categorised according with risk levels associated with the cluster, so that if the cluster has a cluster score corresponding to a low risk level (meaning there is a reduced likelihood of adverse effects associated with the biomarker scores), fewer interventions would be displayed or at least implemented by the user, than if the cluster has a high risk score.
  • step 530 user interaction with a displayed biomarker is detected, and used to identify user selection of the biomarker.
  • Biomarker information for that cluster is then retrieved from the cluster database 211 by the server 210 at step 532, with this being presented to the user at step 534, as shown in Figure 7C.
  • step 536 user selection of an action is determined, for example through selection of a generic action displayed as part of the cluster or biomarker information.
  • the server 210 determines required subject parameter values needed to calculate a specific tailored action, typically from an action definition stored in an action database 211. For example, if the cluster relates to cardiovascular disease, calculation of specific actions may require knowledge of the subject's current diet, exercise, stress or sleep patterns, whereas if the cluster relates to vitamin deficiencies, the calculation of specific action may only need information relating to the subject's diet.
  • custom actions are generated, for example by retrieving default actions, using the biomarker values, and then tailoring these based on the subject parameter values.
  • This typically involves defining one or more customised target values, such as a defined amount of one or more particular exercises, details of recommended supplement amounts, specific diet recommendations, such as a daily required amount of fruit and vegetables, or the like.
  • custom values could be defined using tables of manually defined target values, which are selected based on the subject parameter values, or could be determined using a target model generated by training a generic model using subject data.
  • the customised actions can then be displayed to the user at step 544, allowing the subject to take actions in order to mitigate the respective health risks.
  • This process is typically performed for a cluster, at a time, to provide the subject with a limited and hence manageable number of actions. However, it will be appreciated that the process can return to step 524, allowing another cluster to be selected, enabling plan for addressing the identified risks.
  • ongoing monitoring of the subject can be performed.
  • this involves updating subject parameter values at step 546 and optionally biomarker values at step 548 on a periodic basis.
  • subject parameter values will typically change over time as the subject's behaviour is modified, thereby allowing changes in subject parameter values to be relatively easily tracked. For example if the subject was given a particular exercise regimen the user can be required to provide information regarding whether this regimen has been met. Similarly, changes in physical attributes, such as weight, and changes in diet and sleep can be updated in a similar manner. Details of completion of any test and/or medical interventions can also be provided, including providing test results, details of medication taken, or the like.
  • biomarker values if the biomarkers are genes, these will not change. However, the proteome, transcriptome, epigenome, or microbiome will change over time and accordingly if necessary, some or all of the biological test may need to be re-run, allowing new biomarker values to be determined. For example, this could include re-running tests relating to the subject's phenotype, such as tests relating to DNA methylation, telomere length, or the like, allowing this to be used to determine new cluster scores.
  • the above described system takes results from biological tests and generates a representation including information regarding biomarker values presented as clusters, with the most important issues to address being prioritised using a simple cluster scoring system.
  • the biomarkers can be combined in clusters to represent different system-wide physiological responses, such as inflammation, obesity, or the like, with this being used to produce a cluster score for each health aspect, which provides a relativity to other clusters. This can then be used to determine the first health intervention to be addressed.
  • the above described system can be used to provide a fully automated direct to consumer biological test interpretation and treatment/intervention strategy. This can include genetic testing, as well as other biomarkers/pathology which can improve the effectiveness of the intervention.
  • the above described system leverages cluster representations that are able to simplify the presentation of what is traditionally a complicated report, presenting this in a manner which is clear and concise, making this understandable by even unskilled individuals. This is in contrast to traditional techniques, that typically take a practitioner time to understand and review, and at least an hour with a patient to explain. Furthermore, this can be presented in an interactive manner with low computational overheads, allowing this to be reviewed on portable devices, such as mobile phones or the like, which is not the case with the traditional multiple page textual report.
  • the biological test can be used to provide guidance on specific health issues by testing a suite of genes that influence lifestyle health issues such as weight management, food intolerances, skin health and appearance, carbohydrate processing, sports and exercise performance, or vitamin D deficiency.
  • lifestyle health issues such as weight management, food intolerances, skin health and appearance, carbohydrate processing, sports and exercise performance, or vitamin D deficiency.
  • the configuration is performed by or with the assistance of an expert, such as clinician, research scientist, or other similarly qualified person, which understands the impact of biomarkers on different health aspects.
  • an expert such as clinician, research scientist, or other similarly qualified person, which understands the impact of biomarkers on different health aspects.
  • the biomarkers are genes, and that the biomarkers are measured to detect alleles, although this is not essential.
  • the biomarker panel is defined at step 800. This is typically a process involving having the expert select the biomarkers to be measured, with details of these, including name, RS number and known alleles, being entered into the system and stored in a database, typically as biomarker panel data, by the server 210. However, additionally and/or alternatively, details of previously defined biomarker panels, such as commercially available panels could be retrieved, for example, from a supplier or other entity.
  • biomarkers from the panel are selected.
  • the expert will use their knowledge to select those biomarkers that have an impact on the corresponding health aspect associated with the cluster.
  • the biomarkers could include the genes COL- lA-1, COL-5A-1, ELN, AQP-3, or the like.
  • the expert selects alleles for the respective biomarkers, and assigns a biomarker score to each respective allele, based on the known impact of the allele on the user's skin health.
  • One or more interventions are then defined at step 850. This could be performed manually for example by having the expert define the intervention and/or could involve retrieving details of previously defined interventions from the database. In this regard, it will be appreciated that some interventions, such as exercise, diet and relaxation techniques, can apply to a wide range of different health aspects, and hence there may already be relevant interventions defined which can simply be retrieved as needed.
  • one or more biomarkers are selected, which are associated with the respective intervention, allowing biomarker scores associated with the biomarkers to be used in calculating an intervention score.
  • the biomarkers could be selected in a manner similar to that described above, and could be different to those associated with the cluster, potentially being used to calculate an intervention score using different biomarker scores. Thus it will be appreciated that this process could be performed in a manner similar to that described above with respect to steps 830 and 840. Details of the selected interventions and their corresponding biomarkers used in calculating the intervention score are then stored as part of the cluster data.
  • Step 870 a number of interventions is defined for each risk level, representing the number of interventions the user should perform, with this information being added to the cluster data. [0159] Steps 820 to 870 can then be repeated for additional clusters associated with the respective biomarker panel.
  • Each cluster has an overall cluster score, which can be used to rank the clusters in order of adverse health impact, and/or categorise clusters using risk levels, for example to indicate that the cluster score represents a potential severe, negative or no impact on subject health.
  • Interventions associated with each cluster can be displayed in a ranked list, together with recommendations as to the number of interventions that should be pursued being based on the category risk level.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Epidemiology (AREA)
  • Chemical & Material Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Biophysics (AREA)
  • Primary Health Care (AREA)
  • Biotechnology (AREA)
  • Databases & Information Systems (AREA)
  • Proteomics, Peptides & Aminoacids (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Organic Chemistry (AREA)
  • Evolutionary Biology (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Theoretical Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Pathology (AREA)
  • Artificial Intelligence (AREA)
  • Bioethics (AREA)
  • Analytical Chemistry (AREA)
  • Zoology (AREA)
  • Genetics & Genomics (AREA)
  • Software Systems (AREA)
  • Wood Science & Technology (AREA)
  • Molecular Biology (AREA)
  • Microbiology (AREA)
  • Immunology (AREA)
  • Biochemistry (AREA)
  • General Engineering & Computer Science (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

A system for reporting a test result for a biological test performed on a biological subject, the system including one or more processing devices that for each of a plurality of biomarkers and determine a respective biomarker value as a result of a measurement of the biomarker performed as part of the test, determine a biomarker score associated with each biomarker based on the respective biomarker value. For each of multiple biomarker clusters, a cluster score is calculated based on a combination of biomarker scores associated with each of a number of biomarkers forming part of the biomarker cluster, with this being used to determine a ranking of the multiple biomarker clusters using the cluster score for each biomarker cluster. A representation including one or more cluster representations can be presented in accordance with the ranking.

Description

REPORTING TEST RESULTS Background of the Invention
[0001] The present invention relates to a method and apparatus for reporting results of a biological test performed on a subject.
Description of the Prior Art
[0002] The reference in this specification to any prior publication (or information derived from it), or to any matter which is known, is not, and should not be taken as an acknowledgment or admission or any form of suggestion that the prior publication (or information derived from it) or known matter forms part of the common general knowledge in the field of endeavour to which this specification relates.
[0003] It is known to perform tests of biological subjects to study the status of the subject's genome, proteome, transcriptome, epigenome, or microbiome and ascertain the impact or potential impact on the subject's health. Such tests typically generate data relating to a large number of biomarkers, meaning the results can be difficult to interpret and understand. This issue is exacerbated in the situation of direct to consumer based testing, in which the subject often receives the results of the test directly and often has little expertise in interpreting the test results.
[0004] Additionally, the results are typically displayed as part of a report containing large amounts of information. As a result, this tends to run over several pages, with a high text content, which can make displaying and viewing of the content on mobile devices, such as smart phones difficult. Particularly in locations with limited infrastructure, this can make accessing the results of such test difficult.
Summary of the Present Invention
[0005] In one broad form an aspect of the present invention seeks to provide a system for reporting a test result for a biological test performed on a biological subject, the system including one or more processing devices that: for each of a plurality of biomarkers, determine a respective biomarker value as a result of a measurement of the biomarker performed as part of the test; determine a biomarker score associated with each biomarker based on the respective biomarker value; for each of multiple biomarker clusters, calculate a cluster score based on a combination of biomarker scores associated with each of a number of biomarkers forming part of the biomarker cluster; determine a ranking of the multiple biomarker clusters using the cluster score for each biomarker cluster; generate a representation including one or more cluster representations, the one or more cluster representations being presented in accordance with the ranking, and wherein each cluster representation is associated with a respective one of the multiple biomarker clusters and includes: an indication of the cluster score; and, an indication of the biomarker score associated with each of the number of biomarkers; and, cause the representation to be displayed to a user.
[0006] In one broad form an aspect of the present invention seeks to provide a method for reporting a test result for a biological test performed on a biological subject, the method including, in one or more processing devices: for each of a plurality of biomarkers, determining a respective biomarker value as a result of a measurement of the biomarker performed as part of the test; determining a biomarker score associated with each biomarker based on the respective biomarker value; for each of multiple biomarker clusters, calculating a cluster score based on a combination of biomarker scores associated with each of a number of biomarkers forming part of the biomarker cluster; determining a ranking of the multiple biomarker clusters using the cluster score for each biomarker cluster; generating a representation including one or more cluster representations, the one or more cluster representations being presented in accordance with the ranking, and wherein each cluster representation is associated with a respective one of the multiple biomarker clusters and includes: an indication of the cluster score; and, an indication of the biomarker score associated with each of the number of biomarkers; and, causing the representation to be displayed to a user.
[0007] In one broad form an aspect of the present invention seeks to provide a computer program product for use in reporting a test result for a biological test performed on a biological subject, the computer program product including computer executable code, which when executed by one or more suitably programmed processing devices, cause the processing devices to: for each of a plurality of biomarkers, determine a respective biomarker value as a result of a measurement of the biomarker performed as part of the test; determine a biomarker score associated with each biomarker based on the respective biomarker value; for each of multiple biomarker clusters, calculate a cluster score based on a combination of biomarker scores associated with each of a number of biomarkers forming part of the biomarker cluster; determine a ranking of the multiple biomarker clusters using the cluster score for each biomarker cluster; generate a representation including one or more cluster representations, the one or more cluster representations being presented in accordance with the ranking, and wherein each cluster representation is associated with a respective one of the multiple biomarker clusters and includes: an indication of the cluster score; and, an indication of the biomarker score associated with each of the number of biomarkers; and, cause the representation to be displayed to a user.
[0008] In one broad form an aspect of the present invention seeks to provide a system for use in treating a biological subject in accordance with a test result for a biological test performed on the subject, the system including one or more processing devices that: for each of a plurality of biomarkers, determine a respective biomarker value as a result of a measurement of the biomarker performed as part of the test; determine a biomarker score associated with each biomarker based on the respective biomarker value; for each of multiple biomarker clusters, calculate a cluster score based on a combination of biomarker scores associated with each of a number of biomarkers forming part of the biomarker cluster; determine a ranking of the multiple biomarker clusters using the cluster score for each biomarker cluster; generate a representation including one or more cluster representations, the one or more cluster representations being presented in accordance with the ranking, and wherein each cluster representation is associated with a respective one of the multiple biomarker clusters and includes: an indication of the cluster score; and, an indication of the biomarker score associated with each of the number of biomarkers; and, cause the representation to be displayed to a user, selectively display cluster information associated with a biomarker cluster, the cluster information being indicative of: one or more health risks associated with the cluster; and, one or more actions associated with the cluster, the one or more actions including a medical treatment; determine subject parameter values indicative of values for one or more subject parameters; and, track progress of completion of one or more actions by comparing the target values to at least one of: subject parameter values; and, changes in subject parameter values over time.
[0009] In one broad form an aspect of the present invention seeks to provide a method for use in treating a biological subject in accordance with a test result for a biological test performed on the subject, the method including, in one or more processing devices: for each of a plurality of biomarkers, determining a respective biomarker value as a result of a measurement of the biomarker performed as part of the test; determining a biomarker score associated with each biomarker based on the respective biomarker value; for each of multiple biomarker clusters, calculating a cluster score based on a combination of biomarker scores associated with each of a number of biomarkers forming part of the biomarker cluster; determining a ranking of the multiple biomarker clusters using the cluster score for each biomarker cluster; generating a representation including one or more cluster representations, the one or more cluster representations being presented in accordance with the ranking, and wherein each cluster representation is associated with a respective one of the multiple biomarker clusters and includes: an indication of the cluster score; and, an indication of the biomarker score associated with each of the number of biomarkers; and, causing the representation to be displayed to a user; selectively displaying cluster information associated with a biomarker cluster, the cluster information being indicative of: one or more health risks associated with the cluster; and, one or more actions associated with the cluster, the one or more actions including a medical treatment; determining subject parameter values indicative of values for one or more subject parameters; and, tracking progress of completion of one or more actions by comparing the target values to at least one of: subject parameter values; and, changes in subject parameter values over time.
[0010] In one broad form an aspect of the present invention seeks to provide a computer program product for use in treating a biological subject in accordance with a test result for a biological test performed on the subject, the computer program product including computer executable code, which when executed by one or more suitably programmed processing devices, cause the processing devices to: for each of a plurality of biomarkers, determine a respective biomarker value as a result of a measurement of the biomarker performed as part of the test; determine a biomarker score associated with each biomarker based on the respective biomarker value; for each of multiple biomarker clusters, calculate a cluster score based on a combination of biomarker scores associated with each of a number of biomarkers forming part of the biomarker cluster; determine a ranking of the multiple biomarker clusters using the cluster score for each biomarker cluster; generate a representation including one or more cluster representations, the one or more cluster representations being presented in accordance with the ranking, and wherein each cluster representation is associated with a respective one of the multiple biomarker clusters and includes: an indication of the cluster score; and, an indication of the biomarker score associated with each of the number of biomarkers; and, cause the representation to be displayed to a user.
[0011] In one embodiment at least one cluster representation includes: a score region indicative of the cluster score; and, a biomarker region including a number of biomarker sub- regions, each biomarker sub-region being indicative of the biomarker score for a respective biomarker.
[0012] In one embodiment: the score region is a central region; and, a biomarker region is an annular region extending around the central region.
[0013] In one embodiment the score region includes an alpha numeric representation of the cluster score; and, a biomarker region including biomarker sub-regions that indicate the biomarker score through one or more of: sizing; shading; colouring; and, filling.
[0014] In one embodiment the cluster representation include visual markings associated with each biomarker sub-region, the visual markings being indicative of an identity of the biomarker associated with the biomarker sub-region. [0015] In one embodiment the representation includes a cluster region including multiple cluster sub-regions, each cluster sub-region being associated with a respective one of the multiple clusters.
[0016] In one embodiment the cluster sub-regions are ordered in accordance with the ranking.
[0017] In one embodiment the one or more processing devices: determine user selection of a cluster sub-region in accordance with user input commands; and, display a respective cluster representation in response to the user selection.
[0018] In one embodiment the cluster region is an annular region extending around a biomarker region.
[0019] In one embodiment each biomarker cluster is associated with a respective health aspect of the subject.
[0020] In one embodiment the one or more processing devices selectively display information including at least one of: cluster information associated with a biomarker cluster; one or more health risks associated with the cluster; one or more health benefits associated with the cluster; one or more actions associated with the cluster, biomarker information associated with a biomarker; one or more health risks associated with the biomarker; one or more health benefits associated with the biomarker; one or more actions associated with the biomarker; and, recommendations relating to one or more of: diet; sleep; movement; exercise; stress; supplementation; medical interventions; and, target values for one or more subject parameters.
[0021] In one embodiment the one or more processing devices: determine a user selection in accordance with user input commands; determine information; and, display the information as part of the representation.
[0022] In one embodiment the one or more processing devices determine user selection of at least one of: a biomarker cluster by at least one of: determining user selection of a cluster representation associated with the biomarker cluster in accordance with user input commands; and, determining user selection of a cluster sub-region associated with the biomarker cluster in accordance with user input commands; and, a biomarker by selection of a biomarker sub -region.
[0023] In one embodiment the one or more processing devices determine the one or more target values using at least one of: one or more biomarker values; one or more biomarker scores; and, subject parameter values indicative of values for one or more subject parameters.
[0024] In one embodiment the one or more processing devices: determine base target values in accordance with the biomarker values; and, modify the base target values to determine the target values based on subject parameter values indicative of values for one or more subject parameters.
[0025] In one embodiment the one or more processing devices determine target values by applying biomarker values or biomarker scores and subject parameter values to a target model, the target model being derived using machine learning techniques applied to training data derived from multiple subjects.
[0026] In one embodiment the one or more processing devices: determine subject parameter values indicative of values for one or more subject parameters; comparing the target values to at least one of: subject parameter values; and, changes in subject parameter values over time; and, use results of the comparison to at least one of: track progress of completion of one or more actions; determine a new target value; and, generate a progress representation.
[0027] In one embodiment the one or more subject parameters include one or more of: physical characteristic parameters selected from the group including: a sex; an ethnicity; an age; a height; a weight; a body mass index; one or more body state parameters selected from the group including: a healthy body state; an unhealthy body state; and, one or more disease states; one or more medical parameters selected from the group including: medical symptoms; a blood potassium level; a temperature; a blood pressure; a respiratory rate; a heart rate; a blood oxygenation level; one or more lifestyle parameters selected from the group including: sleeping habits; a fitness level; an exercise frequency; an exercise duration; an exercise type; an exercise intensity; and, a diet.
[0028] In one embodiment the one or more processing devices calculate the cluster score using at least one of: biomarker scores; a weighted sum of biomarker scores; a combination of biomarker scores and at least one of: subject parameter values indicative of values for one or more subject parameters; and, changes in subject parameter values over time; and, a combination of biomarker scores and results of a comparison between target values and at least one of: subject parameter values; and, changes in subject parameter values over time.
[0029] In one embodiment the one or more processing devices calculate the cluster score using a cluster score model, the cluster score model being derived using machine learning techniques applied to training data derived from multiple subjects.
[0030] In one embodiment the one or more processing devices determine a cluster score at least partially in accordance with biomarker values that change over time.
[0031] In one embodiment the one or more processing devices: determine a genotype score based on first biomarker values; determine a phenotype score based on second marker values; and, determine a cluster score at least in part using a combination of the genotype and phenotype scores.
[0032] In one embodiment the one or more processing devices track changes in cluster scores over time.
[0033] In one embodiment the biomarker scores are numerical scores that are one or more of: retrieved from stored biomarker score data using the biomarker value; and, calculated from the biomarker value.
[0034] In one embodiment the one or more processing devices creates the clusters using machine learning techniques applied to training data derived from multiple subjects. [0035] In one embodiment the system includes: a sampling device that obtains a sample from the biological subject; and, a measurement device that measures at least one biomarker value for a biomarker in the sample.
[0036] In one embodiment the biomarkers are indicative of a status of at least one of the subject's genome, proteome, transcriptome, epigenome, or microbiome.
[0037] In one embodiment the one or more processing devices: calculate an action score for each of a plurality of actions associated with a cluster; and display an indication of actions in accordance with the action score.
[0038] In one embodiment the one or more processing devices display a ranked list of actions.
[0039] In one embodiment the one or more processing devices calculate the action score using biomarker scores for at least one of: cluster biomarkers; and, other biomarkers.
[0040] In one embodiment the one or more processing devices: determine a risk level for a cluster in accordance with the cluster score; and, at least one of: display an indication of the risk level; and, selectively display actions in accordance with the risk level.
[0041] It will be appreciated that the broad forms of the invention and their respective features can be used in conjunction, interchangeably and/or independently, and reference to separate broad forms is not intended to be limiting.
Brief Description of the Drawings
[0042] Various examples and embodiments of the present invention will now be described with reference to the accompanying drawings, in which: -
[0043] Figure 1 is a flow chart of a method of reporting a test result for a biological test performed on a biological subject;
[0044] Figure 2 is a schematic diagram of an example of a distributed computer architecture;
[0045] Figure 3 is a schematic diagram of an example of a processing system of Figure 2;
[0046] Figure 4 is a schematic diagram of an example of a computer system of Figure 2; [0047] Figures 5A to 5D are a flow chart of a specific example of a method for reporting a test result for a biological test performed on a biological subject;
[0048] Figure 6A is a schematic diagram of a first example of a cluster representation;
[0049] Figure 6B is a schematic diagram of a second example of a cluster representation;
[0050] Figure 6C is schematic diagram of an example of a representation including multiple ranked cluster representations;
[0051] Figure 6D is a schematic diagram of an example of a composite cluster representation; and,
[0052] Figures 7A to 7C are schematic diagrams of examples screenshots of a user interface of a system for reporting a test result of a biological test performed on a biological subject.
Detailed Description of the Preferred Embodiments
[0053] An example of a process for reporting a test result for a biological test performed on a biological subject will now be described to reference to Figure 1.
[0054] Whilst the biological test could be of any appropriate form, the biological test is typically performed on one or more of the subject's genome, proteome, transcriptome, epigenome, or microbiome.
[0055] For the purpose of illustration, it is assumed that the process is performed at least in part using one or more electronic processing devices forming part of one or more processing systems, such as servers, personal computers or the like, and which may optionally be connected to one or more other processing systems, data sources or the like, via a network architecture, as will be described in more detail below.
[0056] In this example, at step 100 the processing device(s) determine a respective biomarker value for each of a plurality of biomarkers. The biomarker values are obtained as a result of a measurement of the biomarkers performed as part of the biological test, and the nature of the biomarkers and the manner in which the biomarker values are measured will vary depending on the nature of the test being performed. [0057] For example, in the case of genetic testing this could involve measurement of one or more of a single-nucleotide polymorphism (SNP), copy number variation (CNV), loss of heterozygosity (LOH), genomic rearrangement, such as translocation, for one or more genes in the genome. For epigenetic testing, this can involve detecting DNA methylation, histone modification, chromatin accessibility, transcription factor (TF) binding and micro RNA (miPvNA), telomere length or the like. At the transcriptome level, testing can detect gene expression and alternative splicing, whilst at the proteome level protein expression and post- translational modification can be detected, whilst metabolite profiling can be performed at the metabolome level. It will also be appreciated that the test could be a multi-omic test that involves combining results for tests performed on the genome, proteome, transcriptome, epigenome, and microbiome.
[0058] The manner in which the biomarker values are determined will vary depending upon the preferred implementation and this could include receiving biomarker values from one or more measurement devices, retrieving biomarker values previously stored in a data store, such as a memory or database, obtaining biomarker values from user input commands provided via a user interface, or the like. It will therefore be appreciated that the term "determining" could encompass the processing device being actively involved in the measurement process or could include the processing device simply receiving or retrieving the biomarker values generated as a result of the measurement process.
[0059] A biomarker score associated with each biomarker is determined based on the respective biomarker value at 110. In its simplest form the biomarker score could simply be the biomarker value. More typically however the biomarker value is interpreted in order to generate a biomarker score in the form of a numerical value, and the manner in which this is performed will vary depending on the nature of the biomarker value.
[0060] For example, in the case of a genetic test, the biomarker value could be an indication of the identity and location of a SNP within a gene, in which case this could be allocated a specific numerical score. The score would typically be predefined for each of a number of known SNPs, allowing this to be simply retrieved. Alternatively, biomarker values, such as concentrations of gene expression products in a sample obtained from the subject, could be compared to thresholds, allocating a score based on the result of the comparison. The biomarker scores are typically integer values, and are defined to reflect an impact of the biomarker value on the subject, for example whether the respective biomarker value will have a positive, negative or null effect on the subject's health, although it will be appreciated that this is not essential and any suitable scoring system could be used.
[0061] At step 120 a cluster score is calculated for each of multiple biomarker clusters. In this regard, the biomarker clusters are groups of a number of biomarkers that are related by virtue of their impact on the subject, and more typically because they have an impact on a particular aspect of the subject's health. For example, the biomarkers within any one cluster might all have an impact on the subject's cardiovascular health, whilst another cluster could be indicative of a propensity for breast cancer, or the like. It will also be appreciated that biomarkers may be present in multiple clusters in the event that they have an effect on different health aspects. In general, such clusters will be determined based on outcomes of scientific research and/or machine learning from training data, with the clusters typically being pre-defined and simply retrieved from a database as required.
[0062] The cluster score is typically based on a combination of biomarker scores and is used to quantify the risk and/or benefits associated with the cluster in terms of a health impact on the subject. The cluster score is calculated to take into account factors including both the likelihood of an issue arising and the severity of the impact should the issue arise. So that for example a risk that may result in premature death could be given a higher risk than a lesser condition, even if there is a relatively low likelihood that this will arise. The cluster score could be calculated using a simple sum. More typically however, the cluster score is based on a weighted sum, allowing the relative degree of impact of each biomarker value on the subject, to be taken into account. So for example, a biomarker associated with a greater risk or health impact is given a higher weighting than other biomarkers in the cluster. The cluster score may also take into account values of subject parameters measured for the subject and examples of this will be described in more detail below. [0063] The cluster score could be based on tests performed on one of the genome, proteome, transcriptome, epigenome, and microbiome, or a combination thereof. For example, the cluster score could include a genotype score, based on first biomarker values such as the presence or absence of certain SNPs, and a phenotype score, based on second biomarker values, such as the results of DNA methylation testing, with the genotype and phenotype scores being used to determine the cluster score.
[0064] At step 130, the biomarker clusters are ranked using the cluster scores for each biomarker cluster. This can be achieved in any appropriate manner, for example using known ranking algorithms, and is performed to identify the likely relative health impact of the biomarker clusters, for example to identify one or more biomarker clusters likely to have a greatest overall impact on the health of the subject.
[0065] At step 140 a representation is generated including one or more cluster representations. Each cluster representation is associated with a respective one of the multiple biomarker clusters and includes an indication of the cluster score and an indication of the biomarker score associated with each of the number of biomarkers. The representation is generated so as to present the one or more cluster representations at least partially based on the ranking, for example by displaying only the most important cluster representation(s), displaying a list of cluster representations ordered based on the ranking, or the like. Alternatively, a single cluster representation may be shown with input options allowing different clusters to be selected, in which case the input options can be ordered based on the ranking.
[0066] Once generated, the representation can be then displayed to a user at step 150 and/or stored for later retrieval. It will be appreciated that this step could include transferring the representation to another device for display and does not require that the representation is displayed using the processing device. It should also be noted that the user could be the subject, but this is not necessarily the case, and alternatively the user could be any individual wishing and/or authorised to view the results of the biological test, including but not limited to a medical practitioner advising the subject, or the like. [0067] By presenting the cluster representation in this manner, in particular by displaying the cluster representations in accordance with the ranking and by including an indication of the cluster score, this allows a user to rapidly understand which cluster or clusters are likely to have the greatest impact on the health of the subject. In this regard, it will be appreciated that the ranking facilitates the user understanding which is the most important cluster, whilst the cluster score allows the user to understand the relative importance of the different clusters. This in effect allows the representation to act as a risk profile, highlighting the issues that should be greatest concern to the subject. In addition to this, an indication of the biomarker score associated with each of the number of biomarkers is provided, allowing this to be used by the user in order to understand which biomarkers are having the greatest effect on the subject.
[0068] Accordingly it will be appreciated that the above described process provides a simple, straightforward mechanism for the user to understand and interpret test results for biological tests performed on a biological subject, which is particularly important given the complexity of interpreting such tests. Additionally, providing a graphical representation of the results in this manner enables the results to be displayed on a mobile device, such as a tablet, in a manner which is easy to view. Furthermore, the approach allows more limited amounts of data to be presented at any one time, which in turn allow the results to be more rapidly displayed on devices having limited processing capabilities.
[0069] A number of further features will now be described.
[0070] In one example, each biomarker cluster includes a score region indicative of the cluster score and a biomarker region including a number of biomarker sub-regions, each biomarker sub-region being indicative of the biomarker score for a respective biomarker. Whilst any particular layout of regions could be used, in a preferred example the score region is a central region and the biomarker region is an annular region extending around the central region. The score region can include an alphanumeric or other graphical representation of the cluster score, whilst the biomarker region includes biomarker sub-regions that indicate the biomarker score or value through one or more of relative sizing, shading, colouring and/or filling. For example, this can include shading of segments to represent the number of SNPs associated with a respective biomarker.
[0071] The cluster representation can also include visual markings associated with each sub- region, the visual markings being indicative of an identity of the biomarker associated with the sub-region. Thus, this could include simply specifying the name or another identifier, such as a sequence name and/or number for the particular biomarker. The above described features result in a representation that is easy to understand visually, ensuring the user is not overwhelmed by information and allowing the relative importance of the clusters and the biomarkers within each cluster to be rapidly evaluated by the user.
[0072] In a further example, the representation includes a cluster region including multiple cluster sub-regions, with each cluster sub-region being associated with a respective one of the multiple clusters. In one particular example, the cluster region is an annular shaped region presented outwardly of a currently displayed cluster representation, with the cluster sub- regions typically being arranged circumferentially, ordered in accordance with the ranking, for example with the first ranked cluster presented at 12 o'clock and the other clusters spaced clockwise in order of ranking. Additionally and/or alternatively the cluster sub-regions may also be presented in a manner which visually indicates the relative importance of the respective cluster, for example by sizing the cluster sub-regions based on the cluster score.
[0073] In one example, the cluster sub-regions can act as both indicators and user inputs, so that when user selection of a cluster sub-region is detected using user-input commands, a respective cluster representation is displayed, and the respective cluster sub-region highlighted. It will be appreciated that this provides a mechanism for allowing the representation to show only a single cluster representation at any one time, with other ones of the multiple cluster representations being displayed as needed, based on user selection of a cluster. This can result in a user interface that is less cluttered and in particular, allows additional information to be displayed in conjunction with the cluster representations.
[0074] In one example, each biomarker cluster is associated with a respective aspect of the subject's health. The nature of the aspect will vary depending on the implementation, and the health aspects that can be associated with different clusters of biomarkers. Typically the clusters and the health aspects to which the cluster relates will be based on an analysis of scientific literature and/or by performing data mining in respect of biomarker values and other subject parameter values from one or more subjects. In one particular example, the one or more processing devices creates the clusters using machine learning techniques applied to training data derived from multiple subjects, and in particular from biomarker and subject parameter values from multiple subjects.
[0075] Typically the one or more processing devices further selectively display cluster information for one or more biomarker clusters, with the cluster information being indicative of one or more health risks/benefits associated with the health aspect and optionally one or more actions associated with the respective health attribute. Typically this is achieved by having a user select a cluster representation within the representation, allowing the processing device(s) to determine cluster information for the selected biomarker cluster and display the retrieved cluster information. As similar process can be performed allowing a user to view specific information regarding individual biomarkers, for example through selection of a biomarker sub-region, thereby viewing potential risk/benefits associated with the biomarker. It will be appreciated that this allows the representation to act as a user interface so that the user can in effect "drill down" and obtain further information regarding the impact of a selected cluster and individual biomarkers within the cluster.
[0076] In one example, the information includes a breakdown on a potential risk associated with each biomarker value in the cluster, together with advice regarding the actions that can be taken to mitigate the issues. The actions could take the form of lifestyle recommendations, such as recommendations for sleep, diet, movement, or exercise patterns, stress management techniques, or the like. The actions could additionally and/or alternatively recommend interventions, such as medication and/or supplements that can be taken to mitigate issue, or could suggest further investigations be performed, such as to take tests to monitor for conditions, disease states, or the like. The actions could be presented at a high level, for example to suggest increasing levels of exercise, but in one preferred example, the information is at least partially quantified, defining target values which can act as a goal, encouraging and guiding the user to make lifestyle changes and/or seek other interventions as needed.
[0077] The target values are typically determined based on the biomarker values or biomarker scores, so that for different combinations of scores, different target values and hence different goals, are presented to the user. This ensures that the user is only ever presented with details of goals that are appropriate to their particular combination of biomarker values or scores.
[0078] Additionally, the one or more processing devices can determine the target values based on subject parameter values indicative of one or more subject parameters. Thus, target values are tailored not only based on the biomarker values and/or score, but also based on subject parameter values and/or change in subject parameter values. This is performed to ensure that the interventions are appropriate for the respective subject, in particular customising the target values based on the subject's capabilities or needs. For example, if a subject has a cluster prioritised which relates to cardiovascular disease, it may be necessary for the subject to increase a level of exercise in order to mitigate the risk of heart disease. In this instance, the level of exercise which is recommended for the subject will be different if the subject is a 70 year old subject to if the subject is a 20 year old subject.
[0079] The subject parameters typically relate to aspects of the subject's anatomy, physiology and/or psychology, and could include any quantifiable attribute, including attributes determined by subject/objective assessments. Most typically, the subject parameter values are determined by performing measurements on the subject and/or asking questions of the subject, for example by having the subject describe a fitness level, quantify a difficult associated with performing a respective exercise, or describe medical symptoms. Information regarding subject parameter values could be entered via a user interface, received from a measuring and/or retrieved from existing stored data, such as previously recorded historical subject parameter values and/or medical record data.
[0080] Specific example subject parameters may include any one or more of physical characteristic parameters selected from the group including: a sex, an ethnicity, an age, a height, a weight, a body mass index, one or more body state parameters selected from the group including: a healthy body state, an unhealthy body state, and, one or more disease states, one or more medical parameters selected from the group including: medical symptoms, a blood potassium level, a temperature, a blood pressure, a respiratory rate, a heart rate, a blood oxygenation level, one or more lifestyle parameters selected from the group including: sleeping habits, a fitness level, an exercise frequency, an exercise duration, an exercise type, an exercise intensity, and, a diet. Subject parameters may also be indicative of participation in or completion of one or more medical interventions. However, it will be appreciated that this is not intended to be limiting, and in practice any suitable subject parameters could be used.
[0081] In practice the target values could be determined in any one of a number of manners. For example, the processing system could determine base target values in accordance with the biomarker values and then modify the base target values to determine the target values using on the subject parameters. Thus, templates of target values could be created, with a respective template being selected based on the biomarker values measured for the subject. The template might specify particular actions to be performed in broad terms, such as to perform exercise, reduce fat intake, increase vitamin B 12 consumption, or the like. The specific parameter values could then be used to select other templates that define respective target values for each action, for example defining an exercise routine, particular consumption levels or the like.
[0082] In a further example, the one or more processing devices determine target values by applying biomarker values or biomarker scores and subject parameter values to a target model. The target model is a mathematical model that relates specific biomarker values/scores and/or subject parameter values to specific target values, and can be derived using machine learning techniques applied to training data obtained from multiple subjects. Thus, machine learning can be used to perform data mining on information associated with other subjects, allowing this to be used to develop the relevant model. [0083] It will also be appreciated that other mechanisms could be used to define target values. For example target values could be manually defined by an advisor, such as a supervising clinician, or the like, or could be based on previous target values for the user. For example, as a user's capability to exercise increases, for example as a result of increased levels of fitness, the target values could be gradually increased. In one example, this is performed based on results of a comparison of a target value to corresponding subject parameter values or changes in subject parameter values, so that for example if a target value is exceeded, a new increased target value can be defined.
[0084] In one example, the processing devices are used to determine subject parameter values and/or changes in subject parameter values and then compare these to the target values in order to assess progress on actions and in particular to determine if goals have been met. A progress representation, such as a line chart showing changes in subject parameter values relative to the target values, can be generated based on results of the comparison, with this being displayed to a user, allowing the user to assess whether the subject is working towards achieving the goals so as to mitigate any health issues associated with the biomarker values.
[0085] The one or more processing devices can calculate the cluster score utilising a suitable technique, and the manner in which this is performed can vary depending on the nature of the biomarker scores. In this regard, the biomarker scores are typically numerical scores that are either retrieved from stored biomarker score data using the biomarker value or calculated from the biomarker value. For example, in the event that the biomarker values are SNPs, the presence or absence of a particular SNP is used to allocate a particular biomarker score value, whereas if the biomarker values are concentrations of gene expression products, these may be compared to a threshold with a value being assigned depending on whether or not the threshold is exceeded. The values are typically assigned based on a risk/benefit associated with the biomarker value, for example allocating a value depending on whether the risk is positive, negative or null.
[0086] In one example the biomarker scores are then combined using a simple sum of biomarker scores. However, alternatively a weighted sum of biomarker scores may be used, in which case the weighting can be assigned based on a relative magnitude of the risk/benefit, so for example biomarkers for which a risk has a potentially more severe outcome can be given a greater weighting, and hence contribute more to the overall cluster score. In one example, the cluster score is scaled so that this represents a value between "0" and " 100", making this easier for the user to understand, although this is not essential and any suitable scoring technique could be used.
[0087] Progress on actions can also be used to adapt the cluster score, so that as the user addresses risks associated with particular biomarkers, this can be used to modify the score and hence elevate other clusters within the ranking. For example, if the user has undergone significant exercise in a three month period, this can be used to lower the risk associated with a cardiovascular cluster.
[0088] Depending on the nature of the biological test, biomarker scores may change over time. For example, a subject's phenotype will typically vary in response to changes in environmental factors, subject behaviours, interventions or the like. To account for this, in one example, the one or more processing devices determine a cluster score at least partially based on biomarkers that change over time, and typically based on pheno typically biomarkers. In one specific example, the processing devices determine a genotype score based on first biomarker values and a phenotype score based on second marker values, combining these to determine a cluster score at least in part using a combination of the genotype and phenotype scores. In this example, the one or more processing devices can then track changes in cluster scores over time based on changes in the second biomarker values.
[0089] In this case such changes are reflected in the cluster score as the biological test is repeated, with this resulting in a new cluster ranking. This allows the user to take action to address other risks once the most important risks have been addressed or mitigated.
[0090] However, biomarker values may not necessarily reflect action taken by the individual. For example, in the case of genetic tests, as the genome remains substantially static, the cluster score would remain unchanged, even if the user has taken significant action to address a risk. Accordingly, in another example, the cluster scores could be based on a combination of biomarker scores and subject parameter values and/or changes in subject parameter values over time, or could be based on biomarker scores and results of a comparison between target values subject parameter values and/or changes in subject parameter values over time. In this instance, it will be appreciated that the cluster scores adjust as the subject parameter values change, such as when exercise levels are increased, diet improved, or the like. This provides a mechanism to track the user's progress in addressing risks, and in particular allows users to move on and address other risks once more important risks are under control, based on re- ranking of the biomarker clusters, which in turn represents a change in the subjects risk profile.
[0091] It will also be appreciated that the biomarker scores could be calculated using any other appropriate technique. For example, the processing device(s) could calculate the cluster score using a cluster score model, which is derived using machine learning techniques applied to training data derived from multiple subjects.
[0092] The system can also be configured to display actions, such as interventions, in accordance with an action score, for example to allow actions to be prioritised. In this example, the processing device(s) calculate an action score for each of a plurality of actions associated with a cluster and then display an indication of actions in accordance with the action score, typically by ranking the actions in accordance with the action score so that the actions are displayed in a ranked list. This allows users to rapidly assess actions, and in particular interventions, which are likely to have the biggest impact.
[0093] The action score is typically calculated based on biomarker scores that are relevant to the action, which could include one or more biomarkers within the cluster and/or other biomarkers. For example, other biomarkers might be used in assessing action score as biomarkers outside the cluster might have a bystander effect. Thus it will be appreciated that this allows actions to be prioritised taking into account not only the effect of biomarkers within the cluster, but also other biomarkers, enabling this to more accurately reflect the potential benefit for the user. [0094] In one further example, the processing devices can determine a risk level for a cluster in accordance with the cluster score and then either display an indication of the risk level and/or selectively display actions in accordance with the risk level. Thus, clusters could have defined risk thresholds, with cluster scores being compared to the risk level to understand if the cluster score represents a high, medium or low risk. This information can be presented to the user and/or used in displaying actions, such as interventions. For example, if a cluster has a low risk level, then it may be desirable for the user to only perform a limited number of interventions, whilst if the cluster has a higher risk, the user may wish to perform additional interventions to mitigate the greater risk associated with the cluster.
[0095] Whilst the above described system can be used simply for reporting the test result of a biological test, it will be appreciated that more typically the system can be used as part of a treatment regime for a biological subject, with the treatment corresponding to performing respective actions in order to mitigate risks or other issues identified by the biological test results. In one example, this is achieved by displaying one or more actions and tracking progress towards completion of the actions based on subject parameter values and/or changes in subject parameter values.
[0096] It will therefore be appreciated that the above described system provides a mechanism to present the results of a biological test to a user, and then track subject parameter values in the subject in order to track progress towards completion of defined actions. As this occurs, the representation can be updated, allowing the user to receive feedback as to the degree of progress made, including through re-ranking of the clusters to reflect a change in risk profile for the subject.
[0097] As mentioned above, in one example, the process is performed by one or more processing systems operating as part of a distributed architecture, an example of which will now be described with reference to Figure 2.
[0098] In this example, a number of processing systems 210 are provided coupled to one or more client devices 230, via one or more communications networks 240, such as the Internet, and/or a number of local area networks (LANs). [0099] Any number of processing systems 210 and client devices 230 could be provided, and the current representation is for the purpose of illustration only. The configuration of the networks 240 is also for the purpose of example only, and in practice the processing systems 210 and client devices 230 can communicate via any appropriate mechanism, such as via wired or wireless connections, including, but not limited to mobile networks, private networks, such as an 802.11 networks, the Internet, LANs, WANs, or the like, as well as via direct or point-to-point connections, such as Bluetooth, or the like.
[0100] In this example, the processing systems 210 are adapted to acquire and process data, generate representations and provide access to results allowing these to be displayed via the client devices 230. Whilst the processing systems 210 are shown as single entities, it will be appreciated they could include a number of processing systems distributed over a number of geographically separate locations, for example as part of a cloud based environment. Thus, the above described arrangements are not essential and other suitable configurations could be used.
[0101] An example of a suitable processing system 210 is shown in Figure 3. In this example, the processing system 210 includes at least one microprocessor 300, a memory 301, an optional input/output device 302, such as a keyboard and/or display, and an external interface 303, interconnected via a bus 304 as shown. In this example the external interface 303 can be utilised for connecting the processing system 210 to peripheral devices, such as the communications networks 230, one or more databases 211, other storage devices, or the like. Although a single external interface 303 is shown, this is for the purpose of example only, and in practice multiple interfaces using various methods (eg. Ethernet, serial, USB, wireless or the like) may be provided.
[0102] In use, the microprocessor 300 executes instructions in the form of applications software stored in the memory 301 to allow the required processes to be performed. The applications software may include one or more software modules, and may be executed in a suitable execution environment, such as an operating system environment, or the like. [0103] Accordingly, it will be appreciated that the processing system 210 may be formed from any suitable processing system, such as a suitably programmed PC, web server, network server, or the like. In one particular example, the processing system 210 is a standard processing system such as an Intel Architecture based processing system, which executes software applications stored on non-volatile (e.g., hard disk) storage, although this is not essential. However, it will also be understood that the processing system could be any electronic processing device such as a microprocessor, microchip processor, logic gate configuration, firmware optionally associated with implementing logic such as an FPGA (Field Programmable Gate Array), or any other electronic device, system or arrangement.
[0104] As shown in Figure 4, in one example, the client device 230 includes at least one microprocessor 400, a memory 401, an input/output device 402, such as a keyboard and/or display, an external interface 403, and typically a card reader 404, interconnected via a bus 405 as shown. In this example the external interface 403 can be utilised for connecting the transaction terminal 220 to peripheral devices, such as the communications networks 230 databases, other storage devices, or the like. Although a single external interface 403 is shown, this is for the purpose of example only, and in practice multiple interfaces using various methods (eg. Ethernet, serial, USB, wireless or the like) may be provided. The card reader 404 can be of any suitable form and could include a magnetic card reader, or contactless reader for reading smartcards, or the like.
[0105] In use, the microprocessor 400 executes instructions in the form of applications software stored in the memory 401, and to allow communication with one of the processing systems 210.
[0106] Accordingly, it will be appreciated that the client device 230 be formed from any suitably programmed processing system and could include suitably programmed PCs, Internet terminal, lap-top, or hand-held PC, a tablet, a smart phone, or the like. However, it will also be understood that the client device 230 can be any electronic processing device such as a microprocessor, microchip processor, logic gate configuration, firmware optionally associated with implementing logic such as an FPGA (Field Programmable Gate Array), or any other electronic device, system or arrangement.
[0107] Examples of the processes for displaying results of test will now be described in further detail. For the purpose of these examples it is assumed that one or more respective processing systems 210 are servers. In one example, the servers 210 host results processing services that are accessed by the client devices 230, allowing results to be processed and allowing representations to be generated and provided to the client devices 230 for display. This could be performed via a specific application and/or could be by way of webpages or similar, depending on the preferred implementation. User inputs are made via a user interface of the client device 230, with commands interpreted by the client device 230, allowing actions to be performed either by the client device 230 or the server 210, as required.
[0108] The servers 210 typically execute processing device software, allowing relevant actions to be performed, with actions performed by the server 210 being performed by the processor 300 in accordance with instructions stored as applications software in the memory 301 and/or input commands received from a user via the I/O device 302. It will also be assumed that actions performed by the client devices 230, are performed by the processor 400 in accordance with instructions stored as applications software in the memory 401 and/or input commands received from a user via the I/O device 402.
[0109] However, it will be appreciated that the above described configuration assumed for the purpose of the following examples is not essential, and numerous other configurations may be used. It will also be appreciated that the partitioning of functionality between the different processing systems may vary, depending on the particular implementation.
[0110] A specific example of the process for reporting a test result for a biological test performed on a subject will now be described with reference to Figures 5A to 5D.
[0111] In this example, at step 500 the subject undergoes a biological test. The biological test could be a gene sequence analysis, such as a saliva-based genomic test similar to that performed by 23andMe , and/or could be an analysis of the subject's proteome, transcriptome, epigenome, or microbiome. At step 502, test results are processed, typically in accordance with standard techniques, and used in order to generate biomarker values which are indicative of either SNPs, CNVs or translocations associated with the genome, or other suitable biomarkers, depending on the nature of the test performed.
[0112] The test and determination of biomarker values may be performed by a third party and the results made available to the server 210, typically via electronic transfer from a third party server, retrieval from a database, or the like. Once received by the server 210, the results are typically recorded, for example by storing these in a database 211 as part of subject data associated with the respective subject at step 504. In this regard, it will be appreciated that the subject data could be of any appropriate form, and could include a profile or the like, with the subject data typically being used to store other information, such as current and/or historic subject parameter values.
[0113] In this regard, concurrently with this process, or at a different time, the subject can undergo an assessment at step 506. The assessment could be of any appropriate form and could be performed by a medical practitioner, for example as part of a specific assessment or part of a normal health check-up. The assessment could be performed using measuring devices and/or could involve having the subject answer questions, for example displayed via the interface presented on the client device 230. The results are used to determine subject parameter values at step 508, with these being recorded by adding them to the subject data at step 510. As part of this process, a user interface could be displayed on a client device 230, allowing the subject or another user to enter the parameter values. Additionally and/or alternatively, the server 210 may interface directly with a medical records server 210, allowing parameter values to be retrieved. Example subject parameters have previously been provided and these will not be reiterated for simplicity.
[0114] At step 512, the biomarker values are used to determine biomarker scores. In this regard, a database 211 typically includes a look-up table, which specifies the biomarker score that should be utilised for different biomarker values or ranges of biomarker values. Thus, in the case of SNPs, the look-up table will simply state a biomarker score for each different SNP. In contrast, where the biomarker value represents a concentration of a gene expression product or similar, the look-up table can include one or more threshold values, with an indication of the score that should apply depending on comparison of the biomarker value to the threshold.
[0115] At step 514 one or more cluster definitions are retrieved from a cluster database 211. The cluster definitions define the number of biomarkers that relate to particular health aspects. The clusters can be derived based on analysis of scientific literature, or based on an analysis of subject data for a plurality of subjects, for example by using machine learning to identify relationships between a number of biomarkers and specific aspects of health. Such machine learning typically involves clustering groups of subjects having similar health issues, and then identify patterns in biomarkers common to the subjects. Such analysis can include any one or more of decision tree learning, random forest, logistic regression, association rule learning, artificial neural networks, deep learning, inductive logic programming, support vector machines, clustering, Bayesian networks, reinforcement learning, representation learning, similarity and metric learning, genetic algorithms, rule- based machine learning, learning classifier systems, or the like. As such schemes are known, these will not be described in any further detail.
[0116] The cluster definition typically also include an indication of the manner in which a cluster score should be calculated, including whether this is based solely on the biomarker scores and/or takes into account subject parameter values, depending on the preferred implementation. The cluster score could be determined based on a specific calculation, such as a weighted sum of biomarker scores, with the weighting reflecting a relative impact of the respective biomarker on the health aspect to which the cluster relates. In particular, it will be appreciated that some biomarkers may have a negligible impact on a subject's health whereas other biomarkers within the cluster may have a much greater impact, in which case these will be given a more significant weighting. [0117] Alternatively, cluster scores could be determined from a model derived from training data using machine learning techniques, for example by using subject data, and in particular biomarker scores and/or subject parameter values from other subjects, to train one or more computational models. The nature of the model and the training performed can be of any appropriate form and could include any one or more of decision tree learning, random forest, logistic regression, association rule learning, artificial neural networks, deep learning, inductive logic programming, support vector machines, clustering, Bayesian networks, reinforcement learning, representation learning, similarity and metric learning, genetic algorithms, rule-based machine learning, learning classifier systems, or the like. As such schemes are known, these will not be described in any further detail.
[0118] In one example, the cluster score is based on a combination of genotype and phenotype scores, for example based on the outcome of genetic tests, such as the presence or absence of SNPs and based on a phenotype score, such as DNA methylation. The score for each of these can be weighted, depending for example on the severity of the risk associated with an SNP, or the relative accuracy of the test performed, for example scoring DNA methylation results higher based on the fact that this is a gold standard measure. The scores can then be combined, so the effect of each SNP is weighted based on corresponding DNA methylation results, so that the resulting score provides the current true representation of genetic risk and actual risk. Thus, in contrast to using the genetic score alone, which cannot change, the combined genetic and phenotypic score can alter, depending for example on subject health, so that the combined result reflecting the changes from various interventions.
[0119] Irrespective of how the calculation is performed, the cluster scores are used to quantify the risk associated with each cluster, with this taking into account factors including the relative likelihood and severity of the risk. For example, the overall risk for a cluster may be greater if the impact of an issue is large, even if the likelihood of the issue arising is small. Having determined the cluster scores at step 516, the cluster scores are used to rank the clusters at step 518, in particular ordering the clusters based on the increasing or decreasing cluster score so that the cluster associated with the greatest risk is listed first. In general, the cluster scores are calculated to provide a value between "0" and " 100", with extremes representing very low or very high risks, thereby allowing a user to easily understand the relative risk associated with each biomarker cluster, although this is not essential and other values could be used.
[0120] At step 520 one or more cluster representations are generated. In one example, a respective cluster representation is generated for each cluster, and examples are shown in Figures 6A and 6B.
[0121] In the first example of Figure 6A, the cluster representation 600 includes a first central region 601, which typically includes an alphanumeric representation of the cluster score. A biomarker region 602 is provided as an annular region surrounding the central region 601, with the annular region being segmented into a number of biomarker sub-regions 602.1, 602.2, 602.3, 602.4. It will be appreciated that whilst four biomarker sub-regions are shown in this example, this is for the purpose of illustration only and in practice the number of sub-regions will depend on the number of biomarkers within the cluster. Each sub-region can be used to represent the biomarker score for a respective biomarker, for example based on a degree of in-filling, shading, or the like. Additionally, in this example, the relative sizes of the biomarker sub-regions is indicative of the relative contribution of the biomarker score to the cluster score. The biomarker sub-region can also act as a user input, allowing a user to view additional information regarding the biomarker and risk associated with the respective biomarker values.
[0122] It will be appreciated however that whilst the circular representation is particularly easy to understand, this is not essential and an alternative linear representation is shown in Figure 6B, with similar reference numerals identifying similar features, albeit increased by 10.
[0123] In one example, a respective cluster representation is generated for each of the clusters, with an example of this being shown in Figure 6C, in which six cluster representations 600.1, 600.2, 600.3, 600.4, 600.5, 600.6 as part of an ordered list, with the lowest cluster score in this example being associated with the cluster representing the greatest risk to subject health. [0124] An alternative representation is shown in Figure 6D. In this example, the representation 600 includes a cluster region 603 in the form of a ring positioned annularly outwardly of the biomarker region 602. The cluster region 603 includes sub-regions 603.1, 603.2, 603.3, 603.4, 603.5 relating to five different clusters, with five being shown for the purpose of illustration only. Each cluster sub-region is used to represent the biomarker scores through shading, with the relative sizes of the cluster sub-regions being indicative of the relative cluster score. The cluster sub-regions are accompanied by indications of the health aspect to which the cluster relates, with the indication this being displayed when the cluster is selected, which can be achieved by having the user select a respective sub-region, for example using a mouse click or similar. It will therefore be appreciated that the cluster sub-regions again act as user inputs allowing cluster representations for different clusters to be displayed.
[0125] Having generated the cluster representations at step 520, these are then displayed to the user at step 522 as part of a user interface, optionally together with other information, such as information regarding an overall health profile, or the like, and an example of this is shown in Figure 7A. It will be appreciated that this provides an overall summary which allows a user to ascertain quickly what needs to be addressed. In this particular example, a 56 y old female needs to address, in turn, Vitamin D, CV Health, +/- inflammation. The user interface allows the user to view the relevant information, providing clearly defined health targets including an indication of the first issues to tackle, streamlining the task of understanding the key impacts. Additionally, the representations provide a mechanism to allow further optional user interaction, using this as a mechanism to access further information, such as guidance regarding exercise, dietary and supplement prescription.
[0126] To achieve this, at step 524 user interaction with the displayed clusters is detected, and used to identify user selection of a particular cluster. Cluster information for that cluster is then retrieved from the cluster database 211 by the server 210 at step 526, with this being presented to the user at step 528, as shown in Figure 7B. [0127] The cluster information may include generic information, such as the particular health risks associated with the cluster and may be optionally tailored based on the particular biomarker values, for example only displaying risks associated with adverse biomarker values. Thus, only the relevant information is provided for that subject, and there is no need for them to understand what implications less adverse indicators. Additionally, the cluster information may include recommended actions to mitigate any risks, with these typically being provided initially at a very high level, such as to recommend increased exercise, improved diet or the like.
[0128] In one example, actions in the form of interventions are displayed. The display of interventions can be performed in accordance with a ranking derived from the biomarker scores. In this regard, each intervention can be associated with one or more biomarkers, with the biomarker scores being used to calculate an intervention score, which is then used in ranking the interventions. This can be used to allow users to assess interventions that will have the greatest impact to their particular biomarker profile.
[0129] The intervention score and hence ranking could be based on biomarker scores for biomarkers within the cluster, but could additionally and/or alternatively be based on biomarker scores for biomarkers in other clusters, for example to account for bystander effects. For example, a cluster relating to skin health could be ranked based on biomarkers relating to skin health, but also other biomarkers, such as inflammation biomarkers.
[0130] Additionally, in a further example, the number of interventions displayed to the user could be tailored based on a risk level associated with the cluster score. In this regard, the cluster score could be categorised according with risk levels associated with the cluster, so that if the cluster has a cluster score corresponding to a low risk level (meaning there is a reduced likelihood of adverse effects associated with the biomarker scores), fewer interventions would be displayed or at least implemented by the user, than if the cluster has a high risk score.
[0131] In an analogous process, at step 530 user interaction with a displayed biomarker is detected, and used to identify user selection of the biomarker. Biomarker information for that cluster is then retrieved from the cluster database 211 by the server 210 at step 532, with this being presented to the user at step 534, as shown in Figure 7C. Thus, it will be appreciated that this provides a mechanism for users to drill down and see information relating to individual biomarkers, as well as viewing overall cluster information.
[0132] At step 536, user selection of an action is determined, for example through selection of a generic action displayed as part of the cluster or biomarker information. At step 538, the server 210 determines required subject parameter values needed to calculate a specific tailored action, typically from an action definition stored in an action database 211. For example, if the cluster relates to cardiovascular disease, calculation of specific actions may require knowledge of the subject's current diet, exercise, stress or sleep patterns, whereas if the cluster relates to vitamin deficiencies, the calculation of specific action may only need information relating to the subject's diet.
[0133] If subject parameter values have been previously provided at steps 506 to 510, these can be simply retrieved from the subject data. Otherwise, an indication of required parameter values can be displayed, allowing the user to obtain and enter these details as needed at step 540. Alternatively, subject parameter values could be obtained from other sources, such as medical records, which could be achieved by querying a remote server or the like, as required.
[0134] At step 542 custom actions are generated, for example by retrieving default actions, using the biomarker values, and then tailoring these based on the subject parameter values. This typically involves defining one or more customised target values, such as a defined amount of one or more particular exercises, details of recommended supplement amounts, specific diet recommendations, such as a daily required amount of fruit and vegetables, or the like. Such custom values could be defined using tables of manually defined target values, which are selected based on the subject parameter values, or could be determined using a target model generated by training a generic model using subject data. The nature of the model and the training performed can be of any appropriate form and could include any one or more of decision tree learning, random forest, logistic regression, association rule learning, artificial neural networks, deep learning, inductive logic programming, support vector machines, clustering, Bayesian networks, reinforcement learning, representation learning, similarity and metric learning, genetic algorithms, rule-based machine learning, learning classifier systems, or the like. As such schemes are known, these will not be described in any further detail.
[0135] It will be appreciated that customisation could be performed by recommending actions based on an intervention score, as outlined above.
[0136] The customised actions can then be displayed to the user at step 544, allowing the subject to take actions in order to mitigate the respective health risks. This process is typically performed for a cluster, at a time, to provide the subject with a limited and hence manageable number of actions. However, it will be appreciated that the process can return to step 524, allowing another cluster to be selected, enabling plan for addressing the identified risks.
[0137] Following this, ongoing monitoring of the subject can be performed. In one example, this involves updating subject parameter values at step 546 and optionally biomarker values at step 548 on a periodic basis. In this regard, it will be appreciated that subject parameter values will typically change over time as the subject's behaviour is modified, thereby allowing changes in subject parameter values to be relatively easily tracked. For example if the subject was given a particular exercise regimen the user can be required to provide information regarding whether this regimen has been met. Similarly, changes in physical attributes, such as weight, and changes in diet and sleep can be updated in a similar manner. Details of completion of any test and/or medical interventions can also be provided, including providing test results, details of medication taken, or the like. In the case of biomarker values, if the biomarkers are genes, these will not change. However, the proteome, transcriptome, epigenome, or microbiome will change over time and accordingly if necessary, some or all of the biological test may need to be re-run, allowing new biomarker values to be determined. For example, this could include re-running tests relating to the subject's phenotype, such as tests relating to DNA methylation, telomere length, or the like, allowing this to be used to determine new cluster scores.
[0138] At step 550 this can be used to track progress against targets, for example by displaying a change in subject parameter values over time, and optionally in comparison to respective target values to determine if targets are being met. As part of this, it will be appreciated that the above described process can be repeated, with targets being recalculated and cluster scores modified as required, for example based on changes in subject parameter values and/or biomarker values. This can lead to changes in target values, encouraging subject to take further action to mitigate risks, as well as re-ranking of the clusters, with clusters being down- or up-graded as needed, which in turn allows the subject to modify their actions and address different risks once more important risks have been mitigated.
[0139] Accordingly, the above described system takes results from biological tests and generates a representation including information regarding biomarker values presented as clusters, with the most important issues to address being prioritised using a simple cluster scoring system.
[0140] The biomarkers can be combined in clusters to represent different system-wide physiological responses, such as inflammation, obesity, or the like, with this being used to produce a cluster score for each health aspect, which provides a relativity to other clusters. This can then be used to determine the first health intervention to be addressed.
[0141] In one example, the clusters are associated with actions representing treatment recommendations, which in one example include interventions falling into categories including exercise, diet and supplementation, and/or further categories such as medical interventions or the like. The interventions can be quantified by providing target values, with these optionally being customised for the subject based on subject parameter values, such as age, experience, disease history, or the like. [0142] It will be appreciated that in some instances, clusters themselves may be further subdivided into a series of sub-clusters, looking for very specific biomarker groupings associated with known problem areas, such as obesity or the like.
[0143] In one example, the above described system can be used to provide a fully automated direct to consumer biological test interpretation and treatment/intervention strategy. This can include genetic testing, as well as other biomarkers/pathology which can improve the effectiveness of the intervention.
[0144] To achieve some of these benefits, the above described system leverages cluster representations that are able to simplify the presentation of what is traditionally a complicated report, presenting this in a manner which is clear and concise, making this understandable by even unskilled individuals. This is in contrast to traditional techniques, that typically take a practitioner time to understand and review, and at least an hour with a patient to explain. Furthermore, this can be presented in an interactive manner with low computational overheads, allowing this to be reviewed on portable devices, such as mobile phones or the like, which is not the case with the traditional multiple page textual report.
[0145] It will also be appreciated that the above described system will collect a large amount of subject data over time, allowing machine learning techniques to be used to refine the clusters, the scoring techniques and recommended actions, making the system more effective.
[0146] Recommended actions can include exercise, dietary modification and supplementation, with recommendations being tailored to specific subject's depending on the available information. This can be performed in an automated fashion, avoiding the need for time consuming intervention by medical practitioners.
[0147] These benefits allow a direct-to-consumer model or can be used to assist practitioners determine the best dietary, nutritional and lifestyle choices to meet patients' goals.
[0148] In one example the biological test can be used to provide guidance on specific health issues by testing a suite of genes that influence lifestyle health issues such as weight management, food intolerances, skin health and appearance, carbohydrate processing, sports and exercise performance, or vitamin D deficiency. However, it will be appreciated that this is not intended to be limiting, and in practice these techniques could apply to a wide range of different aspects of health.
[0149] An example of a process for configuring the system will now be described with reference to Figure 8.
[0150] In this example, it is assumed that the configuration is performed by or with the assistance of an expert, such as clinician, research scientist, or other similarly qualified person, which understands the impact of biomarkers on different health aspects. For the purpose of this example it is assumed that the biomarkers are genes, and that the biomarkers are measured to detect alleles, although this is not essential.
[0151] In this example, the biomarker panel is defined at step 800. This is typically a process involving having the expert select the biomarkers to be measured, with details of these, including name, RS number and known alleles, being entered into the system and stored in a database, typically as biomarker panel data, by the server 210. However, additionally and/or alternatively, details of previously defined biomarker panels, such as commercially available panels could be retrieved, for example, from a supplier or other entity.
[0152] At step 810, one or more risk thresholds are defined. The risk thresholds are defined to allow a cluster to be assigned to a risk level representing the relative risk associated with the respective cluster score. In one example, the cluster score is scaled to have a value between 0 and 100, with 0 representing a high risk (i.e. all alleles within the cluster are adverse) and 100 a low risk (i.e. all alleles within the cluster are good). Any number of risk levels could be used, and in one example three levels are defined representing significant genetic vulnerability, increased genetic vulnerability, or healthy, respectively. However, different numbers of risk levels could be defined, depending on the preferred implementation. Additionally, whilst the same risk levels are typically defined for each cluster, this is not essential and different levels could be defined depending on the preferred implementation. Once defined, the risk levels can be stored in the database, for example as part of the panel data. [0153] At step 820, a next cluster is specified. The cluster is typically defined manually by the expert, based on the expert's knowledge regarding aspects of the user's health that can be measured using the biomarkers in the panel. At this stage, the expert will typically define a cluster name and any other information, such as a description of the health aspect, what the implications of different risk levels are for the cluster, or the like, with this information then being stored in the database as cluster data, associated with the respective panel data.
[0154] At step 830, biomarkers from the panel are selected. In this regard, the expert will use their knowledge to select those biomarkers that have an impact on the corresponding health aspect associated with the cluster. For example, in the event that the cluster relates to the structure, integrity and resilience of skin, the biomarkers could include the genes COL- lA-1, COL-5A-1, ELN, AQP-3, or the like. The expert then selects alleles for the respective biomarkers, and assigns a biomarker score to each respective allele, based on the known impact of the allele on the user's skin health.
[0155] In general, the expert will initially be presented with a list of each gene on the biomarker panel, as retrieved from the biomarker panel data, including the associated alleles and default scores, and an example of this is shown in Table 1 below, allowing the expert to select the relevant genes for the cluster and customise the scores as needed, with this information being stored as part of the cluster data at step 840.
Table 1
Gene RS Number Green Orange Red
Allele Score Allele Score Allele Score
IL-la-1 1800587 CC 1 TC - 1 TT -2
IL-la-2 17561 GG 1 GT - 1 TT -2
IL-1-β 16944 GG 1 AG - 1 AA -2
IL-6 1800795 GG 1 GC - 1 CC -2
IL-8 4073 TT 1 TA - 1 AA -2
IL-18 1946518 TT 1 GT - 1 GG -2
TNFa 1800629 GG 1 GA - 1 AA -2 CRP-1 2794520 CC 1 CT - 1 TT -2
CRP-2 2592887 AA 1 AG - 1 GG -2
CRP-3 1205 TT 1 CT - 1 CC -2
COX-2-3 689466 GG 1 AG - 1 AA -2
COX-2-4 5275 TT 1 CT - 1 CC -2
IL-10-1 1800896 GG 1 GA - 1 AA -2
IL-10-2 1800871 CC 1 CT - 1 TT -2
IL-10-3 1800872 CC 1 CA AA -2
[0156] One or more interventions are then defined at step 850. This could be performed manually for example by having the expert define the intervention and/or could involve retrieving details of previously defined interventions from the database. In this regard, it will be appreciated that some interventions, such as exercise, diet and relaxation techniques, can apply to a wide range of different health aspects, and hence there may already be relevant interventions defined which can simply be retrieved as needed.
[0157] At step 860, one or more biomarkers are selected, which are associated with the respective intervention, allowing biomarker scores associated with the biomarkers to be used in calculating an intervention score. The biomarkers could be selected in a manner similar to that described above, and could be different to those associated with the cluster, potentially being used to calculate an intervention score using different biomarker scores. Thus it will be appreciated that this process could be performed in a manner similar to that described above with respect to steps 830 and 840. Details of the selected interventions and their corresponding biomarkers used in calculating the intervention score are then stored as part of the cluster data.
[0158] Finally at step 870, a number of interventions is defined for each risk level, representing the number of interventions the user should perform, with this information being added to the cluster data. [0159] Steps 820 to 870 can then be repeated for additional clusters associated with the respective biomarker panel.
[0160] Thus it will be appreciated that the above described process allows clusters to be created for different biomarker panels. This allows results of biomarker measurements, performed using respective biomarker panels to be rapidly processed and displayed to users in an intuitive and easy to understand fashion.
[0161] For example, this allows results to be presented to users as clusters, with each cluster representing a respective aspect of their health. Each cluster has an overall cluster score, which can be used to rank the clusters in order of adverse health impact, and/or categorise clusters using risk levels, for example to indicate that the cluster score represents a potential severe, negative or no impact on subject health. Interventions associated with each cluster can be displayed in a ranked list, together with recommendations as to the number of interventions that should be pursued being based on the category risk level.
[0162] This approach allows users to easily understand the greatest health risk associated with the measured biomarkers, and the respective interventions that can be used to mitigate these risks.
[0163] Throughout this specification and claims which follow, unless the context requires otherwise, the word "comprise", and variations such as "comprises" or "comprising", will be understood to imply the inclusion of a stated integer or group of integers or steps but not the exclusion of any other integer or group of integers.
[0164] Persons skilled in the art will appreciate that numerous variations and modifications will become apparent. All such variations and modifications which become apparent to persons skilled in the art, should be considered to fall within the spirit and scope that the invention broadly appearing before described.

Claims

THE CLAIMS DEFINING THE INVENTION ARE AS FOLLOWS:
1) A system for reporting a test result for a biological test performed on a biological subject, the system including one or more processing devices that:
a) for each of a plurality of biomarkers, determine a respective biomarker value as a result of a measurement of the biomarker performed as part of the test;
b) determine a biomarker score associated with each biomarker based on the respective biomarker value;
c) for each of multiple biomarker clusters, calculate a cluster score based on a combination of biomarker scores associated with each of a number of biomarkers forming part of the biomarker cluster;
d) determine a ranking of the multiple biomarker clusters using the cluster score for each biomarker cluster;
e) generate a representation including one or more cluster representations, the one or more cluster representations being presented in accordance with the ranking, and wherein each cluster representation is associated with a respective one of the multiple biomarker clusters and includes:
i) an indication of the cluster score; and,
ii) an indication of the biomarker score associated with each of the number of biomarkers; and,
f) cause the representation to be displayed to a user.
2) A system according to claim 1, wherein at least one cluster representation includes:
a) a score region indicative of the cluster score; and,
b) a biomarker region including a number of biomarker sub-regions, each biomarker sub-region being indicative of the biomarker score for a respective biomarker.
3) A system according to claim 2, wherein:
a) the score region is a central region; and,
b) a biomarker region is an annular region extending around the central region.
4) A system according to claim 2 or claim 3, wherein:
a) the score region includes an alpha numeric representation of the cluster score; and, b) a biomarker region including biomarker sub-regions that indicate the biomarker score through one or more of:
i) sizing;
ii) shading;
iii) colouring; and,
iv) filling.
5) A system according to any one of the claims 2 to 4, wherein the cluster representation include visual markings associated with each biomarker sub-region, the visual markings being indicative of an identity of the biomarker associated with the biomarker sub-region.
6) A system according to any one of the claims 1 to 5, wherein the representation includes a cluster region including multiple cluster sub-regions, each cluster sub-region being associated with a respective one of the multiple clusters.
7) A system according to claim 6, wherein the cluster sub-regions are ordered in accordance with the ranking.
8) A system according to claim 6 or claim 7, wherein the one or more processing devices: a) determine user selection of a cluster sub-region in accordance with user input commands; and,
b) display a respective cluster representation in response to the user selection.
9) A system according to any one of the claims 6 to 8, wherein the cluster region is an annular region extending around a biomarker region.
10) A system according to any one of the claims 1 to 9, wherein each biomarker cluster is associated with a respective health aspect of the subject.
11) A system according to any one of the claims 1 to 10, wherein the one or more processing devices selectively display information including at least one of:
a) cluster information associated with a biomarker cluster;
b) one or more health risks associated with the cluster;
c) one or more health benefits associated with the cluster;
d) one or more actions associated with the cluster;
e) biomarker information associated with a biomarker;
f) one or more health risks associated with the biomarker; g) one or more health benefits associated with the biomarker;
h) one or more actions associated with the biomarker; and,
i) recommendations relating to one or more of:
i) diet;
ii) sleep;
iii) movement;
iv) exercise;
v) stress;
vi) supplementation;
vii) medical interventions; and,
viii) target values for one or more subject parameters.
12) A system according to claim 11, wherein the one or more processing devices:
a) determine a user selection in accordance with user input commands;
b) determine information; and,
c) display the information as part of the representation.
13) A system according to claim 12, wherein the one or more processing devices determine user selection of at least one of:
a) a biomarker cluster by at least one of:
i) determining user selection of a cluster representation associated with the biomarker cluster in accordance with user input commands; and,
ii) determining user selection of a cluster sub-region associated with the biomarker cluster in accordance with user input commands; and,
b) a biomarker by selection of a biomarker sub-region.
14) A system according to any one of the claims 11 to 13, wherein the one or more processing devices determine the one or more target values using at least one of:
a) one or more biomarker values;
b) one or more biomarker scores; and,
c) subject parameter values indicative of values for one or more subject parameters.
15) A system according to claim 14, wherein the one or more processing devices:
a) determine base target values in accordance with the biomarker values; and, b) modify the base target values to determine the target values based on subject parameter values indicative of values for one or more subject parameters.
16) A system according to claim 14 or claim 15, wherein the one or more processing devices determine target values by applying biomarker values or biomarker scores and subject parameter values to a target model, the target model being derived using machine learning techniques applied to training data derived from multiple subjects.
17) A system according to any one of the claims 11 to 16, wherein the one or more processing devices:
a) determine subject parameter values indicative of values for one or more subject parameters;
b) comparing the target values to at least one of:
i) subject parameter values; and,
ii) changes in subject parameter values over time; and,
c) use results of the comparison to at least one of:
i) track progress of completion of one or more actions;
ii) determine a new target value; and,
iii) generate a progress representation.
18) A system according to any one of the claims 14 to 17, wherein the one or more subject parameters include one or more of:
a) physical characteristic parameters selected from the group including:
i) a sex;
ii) an ethnicity;
iii) an age;
iv) a height;
v) a weight;
vi) a body mass index;
b) one or more body state parameters selected from the group including:
i) a healthy body state;
ii) an unhealthy body state; and,
iii) one or more disease states; c) one or more medical parameters selected from the group including:
i) medical symptoms;
ii) a blood potassium level;
iii) a temperature;
iv) a blood pressure;
v) a respiratory rate;
vi) a heart rate;
vii) a blood oxygenation level;
d) one or more lifestyle parameters selected from the group including:
i) sleeping habits;
ii) a fitness level;
iii) an exercise frequency;
iv) an exercise duration;
v) an exercise type;
vi) an exercise intensity; and,
vii) a diet.
19) A system according to any one of the claims 1 to 18, wherein the one or more processing devices calculate the cluster score using at least one of:
a) biomarker scores;
b) a weighted sum of biomarker scores;
c) a combination of biomarker scores and at least one of:
i) subject parameter values indicative of values for one or more subject parameters; and,
ii) changes in subject parameter values over time; and,
d) a combination of biomarker scores and results of a comparison between target values and at least one of:
i) subject parameter values; and,
ii) changes in subject parameter values over time. 20) A system according to claim 19, wherein the one or more processing devices calculate the cluster score using a cluster score model, the cluster score model being derived using machine learning techniques applied to training data derived from multiple subjects.
21) A system according to any one of the claims 1 to 20, wherein the one or more processing devices determine a cluster score at least partially in accordance with biomarker values that change over time.
22) A system according to any one of the claims 1 to 21, wherein the one or more processing devices:
a) determine a genotype score based on first biomarker values;
b) determine a phenotype score based on second marker values; and,
c) determine a cluster score at least in part using a combination of the genotype and phenotype scores.
23) A system according to claim 21 or claim 22, wherein the one or more processing devices track changes in cluster scores over time.
24) A system according to any one of the claims 1 to 23, wherein the biomarker scores are numerical scores that are one or more of:
a) retrieved from stored biomarker score data using the biomarker value; and, b) calculated from the biomarker value.
25) A system according to any one of the claims 1 to 24, wherein the one or more processing devices creates the clusters using machine learning techniques applied to training data derived from multiple subjects.
26) A system according to any one of the claims 1 to 25, wherein the system includes:
a) a sampling device that obtains a sample from the biological subject; and,
b) a measurement device that measures at least one biomarker value for a biomarker in the sample.
27) A system according to any one of the claims 1 to 26, wherein the biomarkers are indicative of a status of at least one of the subject's genome, proteome, transcriptome, epigenome, or microbiome.
28) A system according to any one of the claims 1 to 27, wherein the one or more processing devices: a) calculate an action score for each of a plurality of actions associated with a cluster; and
b) display an indication of actions in accordance with the action score.
29) A system according to claim 28, wherein the one or more processing devices display a ranked list of actions.
30) A system according to claim 28 or claim 29, wherein the one or more processing devices calculate the action score using biomarker scores for at least one of:
a) cluster biomarkers; and,
b) other biomarkers.
31) A system according to any one of the claims 1 to 30, wherein the one or more processing devices:
a) determine a risk level for a cluster in accordance with the cluster score; and, b) at least one of:
i) display an indication of the risk level; and,
ii) selectively display actions in accordance with the risk level.
32) A method for reporting a test result for a biological test performed on a biological subject, the method including, in one or more processing devices:
a) for each of a plurality of biomarkers, determining a respective biomarker value as a result of a measurement of the biomarker performed as part of the test;
b) determining a biomarker score associated with each biomarker based on the respective biomarker value;
c) for each of multiple biomarker clusters, calculating a cluster score based on a combination of biomarker scores associated with each of a number of biomarkers forming part of the biomarker cluster;
d) determining a ranking of the multiple biomarker clusters using the cluster score for each biomarker cluster;
e) generating a representation including one or more cluster representations, the one or more cluster representations being presented in accordance with the ranking, and wherein each cluster representation is associated with a respective one of the multiple biomarker clusters and includes: i) an indication of the cluster score; and,
ii) an indication of the biomarker score associated with each of the number of biomarkers; and,
f) causing the representation to be displayed to a user.
33) A method according to claim 32, wherein the method is performed using a system according to any one of the claims 1 to 31.
34) A computer program product for use in reporting a test result for a biological test performed on a biological subject, the computer program product including computer executable code, which when executed by one or more suitably programmed processing devices, cause the processing devices to:
a) for each of a plurality of biomarkers, determine a respective biomarker value as a result of a measurement of the biomarker performed as part of the test;
b) determine a biomarker score associated with each biomarker based on the respective biomarker value;
c) for each of multiple biomarker clusters, calculate a cluster score based on a combination of biomarker scores associated with each of a number of biomarkers forming part of the biomarker cluster;
d) determine a ranking of the multiple biomarker clusters using the cluster score for each biomarker cluster;
e) generate a representation including one or more cluster representations, the one or more cluster representations being presented in accordance with the ranking, and wherein each cluster representation is associated with a respective one of the multiple biomarker clusters and includes:
i) an indication of the cluster score; and,
ii) an indication of the biomarker score associated with each of the number of biomarkers; and,
f) cause the representation to be displayed to a user.
35) A computer program product according to claim 34, wherein the computer program product is used in a system according to any one of the claims 1 to 31. 36) A system for use in treating a biological subject in accordance with a test result for a biological test performed on the subject, the system including one or more processing devices that:
a) for each of a plurality of biomarkers, determine a respective biomarker value as a result of a measurement of the biomarker performed as part of the test;
b) determine a biomarker score associated with each biomarker based on the respective biomarker value;
c) for each of multiple biomarker clusters, calculate a cluster score based on a combination of biomarker scores associated with each of a number of biomarkers forming part of the biomarker cluster;
d) determine a ranking of the multiple biomarker clusters using the cluster score for each biomarker cluster;
e) generate a representation including one or more cluster representations, the one or more cluster representations being presented in accordance with the ranking, and wherein each cluster representation is associated with a respective one of the multiple biomarker clusters and includes:
i) an indication of the cluster score; and,
ii) an indication of the biomarker score associated with each of the number of biomarkers; and,
f) cause the representation to be displayed to a user.
g) selectively display cluster information associated with a biomarker cluster, the cluster information being indicative of:
i) one or more health risks associated with the cluster; and,
ii) one or more actions associated with the cluster, the one or more actions including a medical treatment;
h) determine subject parameter values indicative of values for one or more subject parameters; and,
i) track progress of completion of one or more actions by comparing the target values to at least one of:
i) subject parameter values; and, ii) changes in subject parameter values over time.
37) A method for use in treating a biological subject in accordance with a test result for a biological test performed on the subject, the method including, in one or more processing devices:
a) for each of a plurality of biomarkers, determining a respective biomarker value as a result of a measurement of the biomarker performed as part of the test;
b) determining a biomarker score associated with each biomarker based on the respective biomarker value;
c) for each of multiple biomarker clusters, calculating a cluster score based on a combination of biomarker scores associated with each of a number of biomarkers forming part of the biomarker cluster;
d) determining a ranking of the multiple biomarker clusters using the cluster score for each biomarker cluster;
e) generating a representation including one or more cluster representations, the one or more cluster representations being presented in accordance with the ranking, and wherein each cluster representation is associated with a respective one of the multiple biomarker clusters and includes:
i) an indication of the cluster score; and,
ii) an indication of the biomarker score associated with each of the number of biomarkers; and,
f) causing the representation to be displayed to a user.
g) selectively displaying cluster information associated with a biomarker cluster, the cluster information being indicative of:
i) one or more health risks associated with the cluster; and,
ii) one or more actions associated with the cluster, the one or more actions including a medical treatment;
h) determining subject parameter values indicative of values for one or more subject parameters; and,
i) tracking progress of completion of one or more actions by comparing the target values to at least one of: i) subject parameter values; and,
ii) changes in subject parameter values over time.
38) A computer program product for use in treating a biological subject in accordance with a test result for a biological test performed on the subject, the computer program product including computer executable code, which when executed by one or more suitably programmed processing devices, cause the processing devices to:
a) for each of a plurality of biomarkers, determine a respective biomarker value as a result of a measurement of the biomarker performed as part of the test;
b) determine a biomarker score associated with each biomarker based on the respective biomarker value;
c) for each of multiple biomarker clusters, calculate a cluster score based on a combination of biomarker scores associated with each of a number of biomarkers forming part of the biomarker cluster;
d) determine a ranking of the multiple biomarker clusters using the cluster score for each biomarker cluster;
e) generate a representation including one or more cluster representations, the one or more cluster representations being presented in accordance with the ranking, and wherein each cluster representation is associated with a respective one of the multiple biomarker clusters and includes:
i) an indication of the cluster score; and,
ii) an indication of the biomarker score associated with each of the number of biomarkers; and,
f) cause the representation to be displayed to a user.
g) selectively display cluster information associated with a biomarker cluster, the cluster information being indicative of:
i) one or more health risks associated with the cluster; and,
ii) one or more actions associated with the cluster, the one or more actions including a medical treatment;
h) determine subject parameter values indicative of values for one or more subject parameters; and, i) track progress of completion of one or more actions by comparing the target values to at least one of:
i) subject parameter values; and,
ii) changes in subject parameter values over time.
PCT/AU2018/050947 2017-09-04 2018-09-03 Reporting test results WO2019040996A1 (en)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
AU2017903566A AU2017903566A0 (en) 2017-09-04 Reporting test results
AU2017903566 2017-09-04
AU2018900084A AU2018900084A0 (en) 2018-01-11 Reporting test results
AU2018900084 2018-01-11

Publications (1)

Publication Number Publication Date
WO2019040996A1 true WO2019040996A1 (en) 2019-03-07

Family

ID=65524589

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/AU2018/050947 WO2019040996A1 (en) 2017-09-04 2018-09-03 Reporting test results

Country Status (1)

Country Link
WO (1) WO2019040996A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140372953A1 (en) * 2011-08-03 2014-12-18 Ingenuity Systems, Inc. Methods and Systems for Biological Data Analysis
US20150095064A1 (en) * 2013-09-27 2015-04-02 Orbicule Bvba Method for Storage and Communication of Personal Genomic or Medical Information
WO2016166975A1 (en) * 2015-04-16 2016-10-20 Sony Corporation Multiple parameters of biological information represented on a display as portions of a living plant
WO2017059190A1 (en) * 2015-09-30 2017-04-06 Rejuvenan Global Health, Inc. Treatment recommendations based on biomarker values
US20170132357A1 (en) * 2015-11-10 2017-05-11 Human Longevity, Inc. Platform for visual synthesis of genomic, microbiome, and metabolome data

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140372953A1 (en) * 2011-08-03 2014-12-18 Ingenuity Systems, Inc. Methods and Systems for Biological Data Analysis
US20150095064A1 (en) * 2013-09-27 2015-04-02 Orbicule Bvba Method for Storage and Communication of Personal Genomic or Medical Information
WO2016166975A1 (en) * 2015-04-16 2016-10-20 Sony Corporation Multiple parameters of biological information represented on a display as portions of a living plant
WO2017059190A1 (en) * 2015-09-30 2017-04-06 Rejuvenan Global Health, Inc. Treatment recommendations based on biomarker values
US20170132357A1 (en) * 2015-11-10 2017-05-11 Human Longevity, Inc. Platform for visual synthesis of genomic, microbiome, and metabolome data

Similar Documents

Publication Publication Date Title
Kruse et al. Machine learning principles can improve hip fracture prediction
US10366624B2 (en) Differentially weighted modifiable prescribed history reporting apparatus, systems, and methods for decision support and health
JP6127160B2 (en) Personalized healthcare system and method
US10930372B2 (en) Solution for drug discovery
US9861308B2 (en) Method and system for monitoring stress conditions
WO2018020239A1 (en) Determining an optimal wellness regime
US20150324527A1 (en) Learning health systems and methods
US20120271612A1 (en) Predictive modeling
EP3430545A1 (en) Relevance feedback to improve the performance of clustering model that clusters patients with similar profiles together
US20220172841A1 (en) Methods of identifying individuals at risk of developing a specific chronic disease
WO2014052921A2 (en) Patient health record similarity measure
WO2019040996A1 (en) Reporting test results
US11610677B2 (en) Patient health monitoring system
JP6138824B2 (en) Method, system and computer program for generating a patient-specific ordered list of self-care actions
US11983099B1 (en) Graphical intervention test development system
JP2020135489A (en) Health care data analyzer and health care data analysis method
US20230238145A1 (en) Health score and predictive analysis
US11915807B1 (en) Machine learning extraction of clinical variable values for subjects from clinical record data
US20240105345A1 (en) Automatic ranking and rank order disply of medical information, and associated devices, systems, and methods
US20240096482A1 (en) Decision support systems for determining conformity with medical care quality standards
Li et al. MixEHR-SurG: a joint proportional hazard and guided topic model for inferring mortality-associated topics from electronic health records
Panagiota Business analytics in healthcare operations and the use of mobile applications for decision making by health professionals
Herdian et al. The Use of Feature Engineering and Hyperparameter Tuning for Machine Learning Accuracy Optimization: A Case Study on Heart Disease Prediction
Sengupta et al. Statistical Approaches for Healthcare Recommendation Systems Enhancing Personalized Healthcare
Talukder Clinical decision support system: an explainable AI approach

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18850892

Country of ref document: EP

Kind code of ref document: A1