WO2020006306A1 - Systèmes et méthodes pour conseils cliniques de tests génétiques - Google Patents

Systèmes et méthodes pour conseils cliniques de tests génétiques Download PDF

Info

Publication number
WO2020006306A1
WO2020006306A1 PCT/US2019/039613 US2019039613W WO2020006306A1 WO 2020006306 A1 WO2020006306 A1 WO 2020006306A1 US 2019039613 W US2019039613 W US 2019039613W WO 2020006306 A1 WO2020006306 A1 WO 2020006306A1
Authority
WO
WIPO (PCT)
Prior art keywords
clinical
operator
subject
view
clinical indication
Prior art date
Application number
PCT/US2019/039613
Other languages
English (en)
Inventor
Eyal Odiz
Devina DO
Original Assignee
Hygea Precision Medicine, Inc.
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
Application filed by Hygea Precision Medicine, Inc. filed Critical Hygea Precision Medicine, Inc.
Publication of WO2020006306A1 publication Critical patent/WO2020006306A1/fr

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
    • G16H70/00—ICT specially adapted for the handling or processing of medical references
    • G16H70/20—ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
    • 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
    • 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

Definitions

  • Physicians such as primary care physicians and family doctors may not be familiar with genetic testing. In many clinical cases, such physicians may not be aware if a genetic test is needed for a particular subject, what tests to order for the subject, and how to interpret the lab results. As a result, genetic testing may not be used as part of physicians’ daily clinical diagnostics procedures for patients.
  • genetic tests There are currently more than 74 thousand genetic tests commercially available in the United States, which collectively are clinically relevant to many diseases. For example, genetic tests can be used to determine drugs’ effectiveness (pharmacogenomics), pro-active diagnostics (e.g., carrier screening), or to assist with clinical diagnostics of diseases. Since many physicians may not be using these tests in the clinical setting, patents’ treatment may not be optimally effective.
  • the present disclosure provides systems and methods for clinical guidance of genetic testing using machine learning.
  • an operator may generate a genomic health record of a subject by evaluating a clinical indication of a subject, determining genomic data relevant to the clinical indication, and recommending genomic data be obtained for the subject.
  • the genomic data may be obtained by performing one or more genetic tests on the subject.
  • the present disclosure provides a system for enabling an operator to generate a genomic health record of a subject, comprising: a database comprising clinical indications; a communications interface in communication with a computer of said operator; and a computer processor operatively coupled to said database and said communications interface, wherein said computer processor is programmed to (i) receive a request from said computer of said operator to evaluate a clinical indication of said subject, (ii) upon receiving said request, determine genomic data relevant to said clinical indication, and (iii) generate an output, which output comprises a recommendation that said operator have said genomic data obtained for said subject.
  • the system is compatible with the Health Insurance Portability and Accountability Act (HIPAA) and the General Data Protection Regulation (GDPR).
  • HIPAA Health Insurance Portability and Accountability Act
  • GDPR General Data Protection Regulation
  • the system is certified by the HITRUST Alliance.
  • said operator is a physician.
  • said computer processor is further programmed to navigate said operator to a clinical view
  • said computer processor is further programmed to navigate said operator from said clinical view to a disease category view. In some embodiments, said computer processor is further programmed to navigate said operator from said disease category view to a disease view. In some embodiments, said computer processor is further programmed to navigate said operator from said disease view to a genes view.
  • said genomic data relevant to said clinical indication is determined based at least in part on information of said subject selected from the group consisting of clinical symptoms, patient history, and family history. In some embodiments, said computer processor is further programmed to apply a machine learning algorithm to said clinical indication and said information of said subject to determine said genomic data relevant to said clinical indication.
  • said recommendation comprises one or more genetic tests to obtain said genomic data for said subject.
  • said machine learning algorithm comprises an optimization based on a constraint comprising one or more of: a number of said one or more genetic tests, a cost of said one or more genetic tests, an accuracy of said evaluation of said clinical indication, and a confidence of said evaluation of said clinical indication.
  • said recommendation is customized to a hospital population.
  • said hospital population is based on a geographical location.
  • the present disclosure provides a method for enabling an operator to generate a genomic health record of a subject, comprising: (a) receiving a request from said operator to evaluate a clinical indication of said subject; (b) upon receiving said request, determining genomic data relevant to said clinical indication; and (c) generating an output, which output comprises a recommendation that said operator have said genomic data obtained for said subject.
  • the method is compatible with the Health Insurance Portability and Accountability Act (HIPAA) and the General Data Protection Regulation (GDPR).
  • HIPAA Health Insurance Portability and Accountability Act
  • GDPR General Data Protection Regulation
  • the method is certified by the HITRUST Alliance.
  • said operator is a physician.
  • the method further comprises navigating said operator to a clinical view subsequent to receiving said request from said computer of said operator to evaluate said clinical indication.
  • the method further comprises navigating said operator from said clinical view to a disease category view.
  • the method further comprises navigating said operator from said disease category view to a disease view.
  • the method further comprises navigating said operator from said disease view to a genes view.
  • the method further comprises determining said genomic data relevant to said clinical indication based at least in part on information of said subject selected from the group consisting of clinical symptoms, patient history, and family history.
  • the method further comprises applying a machine learning algorithm to said clinical indication and said information of said subject to determine said genomic data relevant to said clinical indication.
  • said recommendation comprises one or more genetic tests to obtain said genomic data for said subject.
  • said machine learning algorithm comprises an optimization based on a constraint comprising one or more of: a number of said one or more genetic tests, a cost of said one or more genetic tests, an accuracy of said evaluation of said clinical indication, and a confidence of said evaluation of said clinical indication.
  • said recommendation is customized to a hospital population. In some embodiments, said hospital population is based on a geographical location.
  • the present disclosure provides a method for enabling a physician to generate genetic test results for a patient, comprising: (a) receiving a clinical indication from said physician; (b) determining genomic data relevant to said clinical indication; and (c) making recommendations of genetic tests relevant to said clinical indication from said physician based at least in part on said genomic data.
  • the method is compatible with the Health Insurance Portability and Accountability Act (HIPAA) and the General Data Protection Regulation (GDPR).
  • HIPAA Health Insurance Portability and Accountability Act
  • GDPR General Data Protection Regulation
  • the method is certified by the HITRUST Alliance.
  • FIG. 1 illustrates an example of an architecture of a graphical genome system, in accordance with disclosed embodiments.
  • FIG. 2 illustrates an example of a typical geneticist workflow, in accordance with disclosed embodiments.
  • FIG. 3 illustrates an example of a navigator diagnostic workflow, in accordance with disclosed embodiments.
  • FIG. 4 illustrates an example of a navigator pharmacogenetics workflow, in accordance with disclosed embodiments.
  • FIG. 5 illustrates an example of a hereditary breast cancer report, which includes results of genetic analysis of a breast cancer gene panel with color coding, and reviewable events, in accordance with disclosed embodiments.
  • FIG. 6 illustrates an example of a hereditary breast cancer report, which includes results of genetic analysis of a breast cancer gene panel with color coding, in accordance with disclosed embodiments.
  • FIG. 7 illustrates an example of how gene size may be visualized to reflect probability and quality of data in the genome bank.
  • FIG. 8 illustrates a computer system that is programmed or otherwise configured to implement methods provided herein.
  • FIG. 9 illustrates an example of an architecture of a graphical genome system, in accordance with disclosed embodiments.
  • FIG. 10A-10C illustrates an example of a graphical genome system, in accordance with disclosed embodiments, wherein machine learning-based gene panel selections are customized to a hospital population.
  • FIGs. 11A-11D illustrate examples of a navigator software of a graphical genome system for use by clinical providers, including a view of a list of clinical pathways (FIG. 11 A), views of a proprietary genes panel (FIGs. 11B-11C), and a view of a list of curated lab panels (FIG. 11D), in accordance with disclosed embodiments.
  • FIGs. 12A-12D illustrate examples of a navigator software of a graphical genome system for use by ordering clinical providers, including a view of a test order history (FIG.
  • FIG. 12A a view of clinical guidances for different diseases or disorders
  • FIG. 12B a view of clinical guidances for different diseases or disorders
  • FIGS. 12C-12D views of a list of positive genes
  • FIG. 13 illustrates an example of the design and functionality of a navigator software of a graphical genome system for use with pharmacogenomic data, in accordance with disclosed embodiments.
  • Physicians such as primary care physicians and family doctors may not be familiar with genetic testing. In many clinical cases, such physicians may not be aware if a genetic test is needed for a particular subject, what tests to order for the subject, and how to interpret the lab results. As a result, genetic testing may not be used as part of physicians’ daily clinical diagnostics procedures for patients.
  • the present disclosure provides systems and methods for clinical guidance of genetic testing using machine learning. Using systems and methods of the present disclosure, an operator may generate a genomic health record of a subject by evaluating a clinical indication of a subject, determining genomic data relevant to the clinical indication, and recommending genomic data be obtained for the subject.
  • the genomic data may be obtained by performing one or more genetic tests on the subject.
  • the present disclosure further provides systems and methods for hospitals to track and analyze genomic health records across a population of patients (e.g., for population profiling and tracking of metrics such as total genetic test spend for a population of patients).
  • the present disclosure provides a system to provide guidance to physicians regarding how to incorporate genetic tests into their clinical workflows. Given a patient’s symptoms and a clinical guidance, the system may be configured to suggest to the physician if genetic tests are needed. If so, then the system may then determine a set of necessary tests. The system may allow physicians to order the needed genetic tests. In addition, the system may then represent the test results in a visual manner that is easy to understand and interpret, thereby facilitating the physician’s clinical decisions regarding subsequent necessary clinical actions.
  • the system may perform one or more of the following functions: (i) given a patient’s symptoms and a clinical guidance, recommend (e.g., using machine learning optimization) one or more genetic tests that may be clinically necessary or helpful toward a clinical diagnostic or prognostic determination; (ii) allow physicians to order the needed genetic tests; (iii) visually display the test results to facilitate the physician’s understanding and interpretation and to take necessary subsequent clinical actions; and (iv) store and manage patients’ raw data and lab reports.
  • recommend e.g., using machine learning optimization
  • clinical providers may face challenges such as limited genetic knowledge, which may result in ordering a wrong test or having to refer to genetics experts.
  • clinical providers may use clinical support software that helps them order the most effective test.
  • clinical providers may face challenges such as difficulty in comparing between laboratories offering tests, which may require logging into multiple labs to compare cost, turnaround time, reimbursement, quality, etc.
  • clinical providers may use one log-in that gives providers access to all labs for comparison.
  • clinical providers may face challenges such as difficulty in understanding what action to take, in part because genetic test results are long and complicated.
  • clinical providers may use clinical support software that visualizes test results to highlight actionable data.
  • the present disclosure provides a system for enabling an operator to generate a genomic health record of a subject, comprising: a database comprising clinical indications; a communications interface in communication with a computer of said operator; and a computer processor operatively coupled to said database and said communications interface, wherein said computer processor is programmed to (i) receive a request from said computer of said operator to evaluate a clinical indication of said subject, (ii) upon receiving said request, determine genomic data relevant to said clinical indication, and (iii) generate an output, which output comprises a recommendation that said operator have said genomic data obtained for said subject.
  • the system is compatible with the Health Insurance Portability and Accountability Act (HIPAA) and the General Data Protection Regulation (GDPR).
  • HIPAA Health Insurance Portability and Accountability Act
  • GDPR General Data Protection Regulation
  • said operator is a physician.
  • said computer processor is further programmed to navigate said operator to a clinical view
  • said computer processor is further programmed to navigate said operator from said clinical view to a disease category view. In some embodiments, said computer processor is further programmed to navigate said operator from said disease category view to a disease view. In some embodiments, said computer processor is further programmed to navigate said operator from said disease view to a genes view.
  • said genomic data relevant to said clinical indication is determined based at least in part on information of said subject selected from the group consisting of clinical symptoms, patient history, and family history. In some embodiments, said computer processor is further programmed to apply a machine learning algorithm to said clinical indication and said information of said subject to determine said genomic data relevant to said clinical indication.
  • said recommendation comprises one or more genetic tests to obtain said genomic data for said subject.
  • said machine learning algorithm comprises an optimization based on a constraint comprising one or more of: a number of said one or more genetic tests, a cost of said one or more genetic tests, an accuracy of said evaluation of said clinical indication, and a confidence of said evaluation of said clinical indication.
  • the present disclosure provides a method for enabling an operator to generate a genomic health record of a subject, comprising: (a) receiving a request from said operator to evaluate a clinical indication of said subject; (b) upon receiving said request, determining genomic data relevant to said clinical indication; and (c) generating an output, which output comprises a recommendation that said operator have said genomic data obtained for said subject.
  • the method is compatible with the Health Insurance Portability and Accountability Act (HIPAA) and the General Data Protection Regulation
  • the method is certified by the HITRUST Alliance.
  • said operator is a physician.
  • the method further comprises navigating said operator to a clinical view subsequent to receiving said request from said computer of said operator to evaluate said clinical indication.
  • the method further comprises navigating said operator from said clinical view to a disease category view.
  • the method further comprises navigating said operator from said disease category view to a disease view.
  • the method further comprises navigating said operator from said disease view to a genes view.
  • the method further comprises determining said genomic data relevant to said clinical indication based at least in part on information of said subject selected from the group consisting of clinical symptoms, patient history, and family history.
  • the method further comprises applying a machine learning algorithm to said clinical indication and said information of said subject to determine said genomic data relevant to said clinical indication.
  • said recommendation comprises one or more genetic tests to obtain said genomic data for said subject.
  • said machine learning algorithm comprises an optimization based on a constraint comprising one or more of: a number of said one or more genetic tests, a cost of said one or more genetic tests, an accuracy of said evaluation of said clinical indication, and a confidence of said evaluation of said clinical indication.
  • the present disclosure provides a system to provide guidance to physicians regarding how to incorporate genetic tests into their clinical workflows.
  • the system may be configured to generate a recommendation to a physician in a hospital regarding whether genetic tests are needed for the patient. If so, the system may then generate a recommendation of a set of necessary tests to be prescribed to the patient.
  • the system may allow physicians in a hospital to order the recommended genetic tests, given the patient’s symptoms and clinical guidance.
  • the system may then represent the test results in a visual manner that is easy to understand and interpret, thereby facilitating the physician’s clinical decisions regarding subsequent necessary clinical actions for the patient.
  • the system allows hospitals to track and analyze across a population of patients (e.g., for population profiling and tracking of metrics such as total genetic test spend for a population of patients).
  • the system is compatible with the Health Insurance Portability and Accountability Act (HIPAA) and the General Data Protection Regulation (GDPR).
  • HIPAA Health Insurance Portability and Accountability Act
  • GDPR General Data Protection Regulation
  • the system is certified by the HITRUST Alliance.
  • the present disclosure provides a method for enabling a physician to generate genetic test results for a patient, comprising: (a) receiving a clinical indication from said physician; (b) determining genomic data relevant to said clinical indication; and (c) making recommendations of genetic tests relevant to said clinical indication from said physician based at least in part on said genomic data.
  • the method is compatible with the Health Insurance Portability and Accountability Act (HIPAA) and the General Data Protection Regulation (GDPR).
  • HIPAA Health Insurance Portability and Accountability Act
  • GDPR General Data Protection Regulation
  • the method is certified by the HITRUST Alliance.
  • the system for enabling an operator to generate a genomic health record of a subject may comprise two components: a graphical navigator and a genome vault (database).
  • FIG. 1 illustrates an example of an architecture of a graphical genome system, in accordance with disclosed embodiments.
  • a graphical navigator that is clinically aware provides guidance to physicians regarding how to manage genetic tests in a clinical workflow.
  • the navigator connects to a genome database that stores patients’ sequencing data and lab reports, and to the electronic health record (EHR) of the hospital where the patients are receiving clinical care. Physicians may run pro-active and symptomatic scenarios through the navigator.
  • the graphical navigator may comprise an algorithm that combines artificially intelligence-based optimization with powerful graphical representations of clinical knowledge and the relevant genomic information. These graphical representations may provide guidance to physicians through the workflow needed to order and manage genetic tests.
  • the navigator may connect to the Vault and to the EHR (Electronic Health Record) and that is how physicians may access it.
  • EHR Electronic Health Record
  • the genome vault may comprise a cloud database that stores patients’ raw
  • patients may be able to open an account on their name and deposit into the vault their sequencing raw data and lab reports.
  • patients may grant physicians access to the data so physicians may leverage it to provide better care and share with other physicians.
  • patients may share their data with family members.
  • patients may grant access to their data to family members thereby allowing family members to access and use the data to provide better health care to the patient.
  • patients may grant access to their data to a nominated individual thereby allowing the nominated individual to access and use the data to provide better health care to the patient.
  • the nominated individual is a spouse, a family member, a friend, a caretaker, an assistant, an aide, or an individual granted power of attorney by the patient.
  • patients may revoke a previously granted access to their data from the family member or nominated individual.
  • the family member or nominated individual may grant or revoke access to the patient’s data to a physician, clinician, nurse, genetic counselor, or other health care provider.
  • the navigator may be configured to receive a patient’s specific data such as: clinical symptoms, physician clinical guidance, patient history (HX) and family history (HX).
  • the navigator may apply machine learning-based algorithms to the patient’s data to compare the data with its knowledge base to identify disease categories and inheritance patterns.
  • the navigator may be configured to, based on the identified disease categories and inheritance patterns, propose one or more gene panels as necessary genetic tests. The more accurately the system may match the patient data with patterns in its knowledge base, the more effective the set of identified genetic tests is expected to be (e.g., a smaller gene panel with higher accuracy).
  • FIG. 9 illustrates another example of an architecture of a graphical genome system, in accordance with disclosed embodiments.
  • a graphical navigator that is clinically aware provides guidance to physicians regarding how to manage genetic tests in a clinical workflow.
  • the navigator connects to a genome database that stores each patient’s sequencing data and lab reports, and to the electronic health record (EHR) of the hospital where each patient is receiving clinical care. Physicians may run proactive and symptomatic scenarios using the navigator.
  • the graphical genome system is also connected to a patient’s mobile device (e.g., cell phone, tablet computer, laptop computer, desktop computer, smart watch).
  • EHR electronic health record
  • patients may use their mobile device to navigate and operate the graphical genome system (e.g., managing access to their data, providing feedback such as symptoms, and viewing reports and summaries of their data).
  • the patients may navigate and operate the graphical genome system using a graphical user interface (GUI).
  • GUI graphical user interface
  • the graphical navigator may comprise an algorithm that combines machine learning- based optimization with powerful graphical representations of clinical knowledge and the relevant genomic information. These graphical representations may provide guidance to physicians through the workflow needed to order and manage genetic tests.
  • the navigator may connect to the Vault and to the EHR (Electronic Health Record) thereby allowing physicians to access it.
  • the genome vault may comprise a cloud database that stores patients’ raw sequencing data and lab reports.
  • the genome vault may also store patients’ feedback provided from their mobile device. Patients may be able to open an account on their name and deposit into the vault (e.g. by uploading) their sequencing raw data and lab reports.
  • EHR Electronic Health Record
  • patients may grant physicians access to the data so physicians may leverage it to provide better care and share with other physicians.
  • patients may share their data with family members or nominated individuals.
  • the navigator may be configured to receive a patient’s specific data such as: clinical symptoms, physician clinical guidance, patient history (HX) and family history (HX).
  • the navigator may apply machine learning-based algorithms to the patient’s data to compare the data with its knowledge base to identify disease categories and inheritance patterns.
  • the navigator may be configured to, based on the identified disease categories and inheritance patterns, generate a recommendation of one or more gene panels as necessary genetic tests for the patient.
  • the term“subject,” as used herein, generally refers to a human or an animal (e.g., a non-human mammal, ape, monkey, chimpanzee, reptile, amphibian, or bird).
  • the subject may be a person with a disease or disorder, or a person that is suspected of having the disease or disorder, or a person that does not have or is not suspected of having the disease or disorder.
  • the disease or disorder may be an infectious disease, an immune disorder or disease, a cancer, a genetic disease, a degenerative disease, a lifestyle disease, an injury, a rare disease, or an age- related disease.
  • the infectious disease may be caused by bacteria, viruses, fungi, and/or parasites.
  • the subject may be a person with a disease or disorder, or a person that is suspected of having the disease or disorder, or a person that does not have or is not suspected of having the disease or disorder.
  • the disease or disorder may be an infectious disease, an immune disorder or disease, a cancer, a genetic disease, a degenerative disease, a lifestyle disease, an injury, a rare disease or an age related disease.
  • the infectious disease may be caused by bacteria, viruses, fungi and/or parasites.
  • a physician may generate a clinical indication from one or more initial clinical tests or information.
  • a subject may be present at a clinic with a presence of one or more symptoms, outcomes of general tests, family history, or a combination thereof.
  • a plurality of different genetic tests may be performed for the subject based on the clinical indication.
  • a genetic test may be performed before and/or after treatment of a subject with a disease or disorder.
  • a genetic test may be performed during a treatment or a treatment regime. Examples of a genetic test may include tests for hereditary risk of diseases or disorders such as
  • cardiomyopathy e.g., epilepsy, and progressive ataxia.
  • a physician guidance indicates a movement disorder such as Parkinson disease
  • a machine learning-based optimization may help reduce the number of tests needed to effectively determine a clinical decision.
  • the physician may provide better diagnostics and better care.
  • a faxed clinical report provided by a laboratory may appear fuzzy and may be difficult to read.
  • the report may present results of a deletion/duplication analysis of a multiple-gene panel that contains elaborate information requiring an experienced user to interpret and understand.
  • the report may be obtained by the patient’s doctor after about an hour of communication over the phone, and may contain variants that may have been detectable in parents on carrier screening.
  • the present disclosure provides a graphical genome system that may advantageously streamline the information management of genetic tests and laboratory reports in a clinical setting.
  • the graphical genome system may include a navigator configured to provide guidance to physicians regarding how to order and manage genetic tests.
  • Lab reports may be stored in a genomic database of the graphical genome system together with the patient’s raw data, and the genomic database may be configured to be accessible by any physician who has access to the genomic database (genome bank).
  • the reports may be digitized and may be viewed graphically with actionable parts highlighted.
  • FIG. 2 illustrates an example of a typical geneticist workflow, in accordance with disclosed embodiments. Given a patient’s symptoms and family medical history, a geneticist may proceed through the following workflow.
  • the geneticist may determine whether genetic testing is necessary and whether to use genetic testing at all. Such a determination may be made based on the patient information and patient and family history. For example, there may be many known (pre-curated) cases in which genetic tests are necessary to make a clinical decision (e.g., diagnosis, prognosis, or treatment selection).
  • the geneticist may determine what tests to order for the given subject (patient).
  • a set of one or more genetic tests may be identified based on the genes that are related to the symptoms. For example, for hereditary breast cancer screening, a BRCA1/BRCA2 panel may be ordered.
  • machine learning-based optimization may narrow down the initial set of genetic tests to an optimal reduced set of tests (e.g., no more than 1, no more than 2, no more than 3, no more than 4, or no more than 5).
  • Such an optimal reduced set of sets may comprise the recommended genetic tests.
  • the navigator may emulate the typical geneticist workflow depicted in FIG. 2 in a simple graphical way to help guide physicians through the process.
  • FIG. 3 illustrates an example of a navigator diagnostic workflow, in accordance with disclosed embodiments.
  • FIG. 4 illustrates an example of a navigator pharmacogenetics workflow, in accordance with disclosed embodiments.
  • the navigator may include a clinical view and a genes view.
  • the clinical view may guide the physician based on the clinical guidance he or she provides.
  • the first clinical view may display a number of different clinical departments, such as: Cardiology, Immunology, Oncology, Neurology, Dermatology, etc.
  • the physician chooses Neurology as the clinical department in the clinical view.
  • the navigator may generate a disease view that displays a number of different disease categories, such as: Epilepsy, Vascular diseases, White matter diseases, Movement disorders, Dementia, etc.
  • the patient’s symptoms are related to movement disorder and that the physician suspects Parkinson disease.
  • the physician may select Movement disorders as the disease category in the disease view, and the navigator may generate a disease view panel that displays a number of different diseases, such as: Parkinson, Ataxia, Dystonia, etc., from which the physician may select Parkinson.
  • the navigator may generate a view of a gene panel and display a set of one or more genes that, if mutated, may cause hereditary effects of Parkinson.
  • a set of genes may include: LRPK2, PARK7, PINK1, PRKN, SNCA, GBA, UCHL1, etc.
  • the navigator may generate a genes view, which may display the recommended genetic tests. After the genetic tests have been ordered by the physician and performed for the subject, the same view may be then populated with the corresponding test results. For the recommended genetic test, the genes to be tested may be displayed. The genes will be annotated with a size that reflects the probability that a mutation in that gene may trigger the disease.
  • Genetic test results may be displayed with annotations on the same view.
  • the genes may be displayed with visuals of color, size, crosses, and hyperlinks to commentary.
  • the navigator display may be configured in such a way to provide an easy way for the physician to interpret the results, determine the quality of the data, the severity of the clinical indication, and the clinical relevance of the test results, without having to read through many pages of a complex lab report which may be difficult to interpret. Therefore, such a navigator display may advantageously facilitate understanding and interpretation of genetic test results.
  • FIGs. 5-7 illustrate visuals that may help physicians to understand genetic tests and test results and to make clinical decisions based on the test results.
  • FIG. 5 illustrates an example of a hereditary breast cancer report, which includes results of genetic analysis of a breast cancer gene panel with color coding, and reviewable events, in accordance with disclosed embodiments.
  • FIG. 6 illustrates an example of a hereditary breast cancer report, which includes results of genetic analysis of a breast cancer gene panel with color coding, in accordance with disclosed embodiments.
  • a gene may be colored green to indicate that no variations of that gene were detected in the genetic test of the subject.
  • a gene may be colored red along with a displayed flag with a number that reflects the number of reviewable events for this gene.
  • a reviewable event may indicate that a pathogenic variant may been found and that the physician should take a second look.
  • a hyperlink may be provided to bring up management guidelines, and the complete lab report if needed.
  • a special color coding may be used to indicate if a genetic variation is heterozygous or homozygous.
  • a gene may be colored yellow to indicate that a single variant of uncertain significance has been found for the gene.
  • a gene may be colored red to indicate that pathogenic variations have been found for the gene.
  • FIG. 7 illustrates an example of how gene size may be visualized to reflect probability and quality of data in the genome bank.
  • the genes may be displayed as circles with different sizes, with the size of the gene indicating the probability that the disease attributes to this gene. In other words, the larger the size of a circle displayed to represent a given gene, the higher the probability that the disease may be attributed to this gene mutation.
  • the graphical genome system may analyze acquired information from a subject (patient) and a clinical indication determined by a physician of the subject to generate an output of genomic information of the subject having the clinical indication.
  • the system may apply a classification algorithm to the acquired information from the subject and the clinical indication (e.g., a clinical guidance) determined by the physician of the subject to generate the output of genomic information (e.g., a list of genes) of the subject having the clinical indication.
  • the classification algorithm may comprise a machine learning-based classifier, such as a machine learning based classifier, configured to process the acquired information from the subject and the clinical indication determined by the physician of the subject to generate the output of genomic information of the subject having the clinical indication.
  • the machine learning classifier may be trained using datasets from one or more sets of subjects with a given clinical indication as inputs and known genomic information (e.g., genes which experience a significantly higher or significantly lower mutation rate as compared to a reference genome) of the subjects as outputs to the machine learning classifier.
  • known genomic information e.g., genes which experience a significantly higher or significantly lower mutation rate as compared to a reference genome
  • the machine learning classifier may comprise one or more machine learning-based algorithms.
  • the machine learning-based algorithm comprises a machine learning algorithm.
  • the machine learning algorithm is selected from the group consisting of: a support vector machine (SVM), a Naive Bayes classification, a random forest, and a neural network.
  • SVM support vector machine
  • Examples of machine learning algorithms may include a support vector machine (SVM), a naive Bayes classification, a random forest, a neural network, deep learning, or other supervised learning algorithm or unsupervised learning algorithm for classification and regression.
  • the machine learning classifier may be trained using one or more training datasets corresponding to subject data.
  • Training datasets may be generated from, for example, one or more sets of subjects having common characteristics (e.g., features such as clinical indications) and outcomes (e.g., labels such as known genomic information (e.g., genes which experience a significantly higher or significantly lower mutation rate as compared to a reference genome) of the subjects).
  • characteristics e.g., features such as clinical indications
  • outcomes e.g., labels such as known genomic information (e.g., genes which experience a significantly higher or significantly lower mutation rate as compared to a reference genome) of the subjects).
  • Training datasets may comprise a set of features and labels corresponding to the features.
  • Features may comprise characteristics such as, for example, categories of clinical indications, such as a disease or a disorder.
  • Labels may comprise outcomes such as, for example, genomic information (e.g., including gene mutations) of the subject having the clinical indication.
  • Outcomes may include a characteristic associated with the clinical indication of the subject.
  • Training sets may be selected by random sampling of a set of data corresponding to one or more sets of subjects.
  • training sets e.g., training datasets
  • the machine learning classifier may be trained until certain predetermined conditions for accuracy or performance is satisfied, such as having minimum desired values corresponding to accuracy measures.
  • the accuracy measure may correspond to classification of known genomic information of a clinical indication in the subject.
  • the machine learning algorithm may comprise an optimization based on a constraint comprising one or more of: a number of the one or more genetic tests, a cost (e.g., a total cost or a cost reimbursed by insurance) of the one or more genetic tests, a total number of genes assayed by (e.g., coverage of) or the quality of the one or more genetic tests, and a diagnostic metric (e.g., accuracy, confidence, sensitivity, specificity, positive predictive value, or negative predictive value) of the evaluation of the clinical indication.
  • a cost e.g., a total cost or a cost reimbursed by insurance
  • a diagnostic metric e.g., accuracy, confidence, sensitivity, specificity, positive predictive value, or negative predictive value
  • the constraint on a number of genetic tests to be recommended may be no more than 1, no more than 2, no more than 3, no more than 4, no more than 5, no more than 6, no more than 7, no more than 8, no more than 9, or no more than 10 genetic tests.
  • the constraint on a cost of genetic tests to be recommended may be no more than $100, no more than $200, no more than $500, no more than $1,000, no more than $2,000, no more than $5,000, no more than $10,000, no more than $20,000, no more than $50,000, or no more than $100,000 to perform all of the set of genetic tests.
  • the constraint on a diagnostic metric e.g., accuracy, confidence, sensitivity, specificity, positive predictive value, or negative predictive value
  • a diagnostic metric e.g., accuracy, confidence, sensitivity, specificity, positive predictive value, or negative predictive value
  • the diagnostic metric of the evaluation of the clinical indication may be that the diagnostic metric of the evaluation of the clinical indication meet a predetermined threshold criterion.
  • the predetermined threshold criterion (e.g., corresponding to an accuracy, confidence, sensitivity, specificity, positive predictive value, or negative predictive value) may be at least about 50%, at least about 55%, at least about 60%, at least about 65%, at least about 70%, at least about 71%, at least about 72%, at least about 73%, at least about 74%, at least about 75%, at least about 76%, at least about 77%, at least about 78%, at least about 79%, at least about 80%, at least about 81%, at least about 82%, at least about 83%, at least about 84%, at least about 85%, at least about 86%, at least about 87%, at least about 88%, at least about 89%, at least about 90%, at least about 91%, at least about 92%, at least about 93%, at least about 94%, at least about 95%, at least about 96%, at least about 97%, at least about 98%, or at least about 99%.
  • the system further comprises allowing hospitals to track and analyze data (e.g., genomic health records) across a population of patients.
  • hospitals track and analyze data for population profiling.
  • hospitals track and analyze data for tracking of metrics such as total genetic test spend for a population of patients.
  • the system allows hospitals to track and analyze information with respect to genetic tests.
  • hospitals track and analyze information as to who is requesting genomic health data, what genomic health data is being requested, when genomic health data is being requested, or where the genomic health data is being requested from.
  • the system allows hospitals to track and analyze information with respect to a patient’s feedback.
  • hospitals track and analyze information as to whether patients are receiving the correct therapeutic regime for their diagnosis.
  • hospitals track and analyze information as to whether recommendations by physicians are being followed (e.g., recommended genetic tests, prescribed therapeutics, or diet, behavioral, or other lifestyle changes or habits).
  • hospitals track and analyze information in order to correlate health outcomes and side effects.
  • the system allows hospitals to track and analyze information with respect to population profiling.
  • hospitals track and analyze information about undiagnosed patients.
  • hospitals track and analyze data correlating genetic variants with various diseases (e.g., correlating patient’s diseases or disorders with their genomic health data and other health information).
  • hospitals track and analyze data to determine the number of patients being diagnosed with various diseases (e.g., correlating patient diagnoses with their genomic health data and other health information).
  • hospitals track and analyze data to determine the number of patients being diagnosed with a rare disease.
  • the system allows hospitals to track and analyze information with respect to the quality of the genomic health data. In a further embodiment, hospitals track and analyze how often patients receive their genomic health data. In a further embodiment, hospitals track and analyze whether genetic risks are being documented in the EHR. In a further embodiment, hospitals track and analyze whether patients are avoiding exposures in line with their genomic health data e.g., by following physician recommendations regarding diet, behavioral, or other lifestyle changes or habits).
  • the present disclosure provides a system that would allow for an increase of genetic tests being ordered by operators and patients. In some embodiments, this may results in an increased of genetic tests ordered by CLIA-certified laboratories.
  • the present disclosure provides a system where patients upload genetic or genomic sequencing data.
  • patients use the system to store sequencing data.
  • patients use the system to access genetic or genomic sequencing data at any location or at any time.
  • patients use the system to share data with other individuals.
  • patients use the system to share data with healthcare professionals.
  • patients use the system to share data with family members.
  • patients use the system to securely store genetic data e.g., using a secure cloud server, encrypted communications, encrypted storage systems, password-protected system access, access logs, or a combination thereof).
  • patients may be granted a commitment that the system will not allow access to third parties.
  • patients use the system to connect with other patients with similar diseases. This may provide support and guidance to these patients.
  • patients pay a membership fee to use the system or to grant others access to the system.
  • the graphical genomic system comprises machine learning-based gene panel selection that is customized to a hospital population.
  • FIG. 10A - 10C illustrates an example of a navigator diagnostic workflow, in accordance with disclosed embodiments.
  • the navigator may be a context sensitive user interface that responds in real time.
  • a curated gene panel may be from open source or literature. This curated gene panel may have gene mutations that come from various demographics. The curated genes may be different by demographic and if customized to the hospital patient population, it may be more accurate and yield better care for the patients. For example younger population may have more early onset gene panels.
  • the navigator may include a clinical view (see FIG. 10A).
  • the clinical view may guide the physician based on the clinical guidance he or she provides.
  • the clinical view may display a number of different clinical departments, such as: Cardiology, Immunology, Oncology, Neurology, Dermatology, etc.
  • Cardiology a number of different clinical departments
  • the navigator may generate a disease view that displays a number of different disease categories, such as: Arrhythmias and Cardiomyopathies, Congenital heart defects, Hyperlipidemia and hypolipidemia, Aeropathy, etc.
  • the physician chooses Neurology as the clinical department in the clinical view. Then the navigator may generate a disease view that displays a number of different categories, such as: Dementia, Movement disorder, White Matter disease, Epilepsy, Fatigue syndrome, etc.
  • the physician chooses Oncology as the clinical department in the clinical view. Then the navigator may generate a disease view that displays a number of different categories, such as: Lung, Colon, Bladder, Paint, Ovarian, Melanoma, etc.
  • the lab results of the patient may be stored for clinical guidance.
  • the physician selects a certain disease categories, further disease subcategories may be displayed and in each of these disease subcategories, panels may be shown. For example, if the physician selects the disease category of Arrhythmias and
  • cardiomyopathies then further disease categories may be displayed such as: Sudden death, Cardiomyopathies, Arrhythmias, etc.
  • a panel may be displayed that shows genes that may be actionable.
  • machine learning may provide a curated gene panel (see FIG. 10B).
  • This curated gene panel may improve in accuracy as more patients’ results are added.
  • a number of parameters may be used to filter the panels. These parameters may be gene coverage, the cost of the test, the quality of the data, turnaround time (TAT), insurance (in-network, out-of-network), deletion/duplication, variation coverage, etc.
  • a series of recommended gene panels may be displayed (see FIG. 10C). At least one recommended gene panel may be displayed.
  • FIG. 8 shows a computer system 801 that is programmed or otherwise configured to, for example, (i) receive a request from a computer of an operator to evaluate a clinical indication of a subject, (ii) upon receiving the request, determine genomic data relevant to the clinical indication, and (iii) generate an output comprising a recommendation that the operator have the genomic data obtained for the subject.
  • the computer system 801 can regulate various aspects of analysis, calculation, and generation of the present disclosure, such as, for example, (i) receiving a request from a computer of an operator to evaluate a clinical indication of a subject, (ii) upon receiving the request, determining genomic data relevant to the clinical indication, and (iii) generating an output comprising a recommendation that the operator have the genomic data obtained for the subject.
  • the computer system 801 can be an electronic device of a user or a computer system that is remotely located with respect to the electronic device.
  • the electronic device can be a mobile electronic device.
  • the computer system 801 includes a central processing unit (CPU, also“processor” and“computer processor” herein) 805, which can be a single core or multi core processor, or a plurality of processors for parallel processing.
  • the computer system 801 also includes memory or memory location 810 (e.g., random-access memory, read-only memory, flash memory), electronic storage unit 815 (e.g., hard disk), communication interface 820 (e.g., network adapter) for communicating with one or more other systems, and peripheral devices 825, such as cache, other memory, data storage and/or electronic display adapters.
  • the memory 810, storage unit 815, interface 820 and peripheral devices 825 are in communication with the CPU 805 through a communication bus (solid lines), such as a motherboard.
  • the storage unit 815 can be a data storage unit (or data repository) for storing data.
  • the computer system 801 can be operatively coupled to a computer network (“network”) 850 with the aid of the communication interface 820.
  • the network 830 can be the Internet, an internet and/or extranet, or an intranet and/or extranet that is in communication with the Internet.
  • the network 830 in some cases is a telecommunication and/or data network.
  • the network 830 can include one or more computer servers, which can enable distributed computing, such as cloud computing.
  • one or more computer servers may enable cloud computing over the network 830 (“the cloud”) to perform various aspects of analysis, calculation, and generation of the present disclosure, such as, for example, (i) receiving a request from a computer of an operator to evaluate a clinical indication of a subject, (ii) upon receiving the request, determining genomic data relevant to the clinical indication, and (iii) generating an output comprising a recommendation that the operator have the genomic data obtained for the subject.
  • cloud computing may be provided by cloud computing platforms such as, for example, Amazon Web Services (AWS), Microsoft Azure, Google Cloud Platform, and IBM cloud.
  • the network 830 in some cases with the aid of the computer system 801, can implement a peer-to-peer network, which may enable devices coupled to the computer system 801 to behave as a client or a server.
  • the CPU 805 may comprise one or more computer processors and/or one or more graphics processing units (GPUs).
  • the CPU 805 can execute a sequence of machine-readable instructions, which can be embodied in a program or software.
  • the instructions may be stored in a memory location, such as the memory 810.
  • the instructions can be directed to the CPU 805, which can subsequently program or otherwise configure the CPU 805 to implement methods of the present disclosure. Examples of operations performed by the CPU 805 can include fetch, decode, execute, and writeback.
  • the CPU 805 can be part of a circuit, such as an integrated circuit.
  • a circuit such as an integrated circuit.
  • One or more other components of the system 801 can be included in the circuit.
  • the circuit is an application specific integrated circuit (ASIC).
  • ASIC application specific integrated circuit
  • the storage unit 815 can store files, such as drivers, libraries and saved programs.
  • the storage unit 815 can store user data, e.g., user preferences and user programs.
  • the computer system 801 in some cases can include one or more additional data storage units that are external to the computer system 801, such as located on a remote server that is in communication with the computer system 801 through an intranet or the Internet.
  • the computer system 801 can communicate with one or more remote computer systems through the network 830.
  • the computer system 801 can communicate with a remote computer system of a user.
  • remote computer systems include personal computers (e.g., portable PC), slate or tablet PC’s (e.g., Apple ® iPad, Samsung ® Galaxy Tab), telephones, Smart phones (e.g., Apple ® iPhone, Android-enabled device, Blackberry ® ), or personal digital assistants.
  • the user can access the computer system 801 via the network 830.
  • Methods as described herein can be implemented by way of machine (e.g., computer processor) executable code stored on an electronic storage location of the computer system 801, such as, for example, on the memory 810 or electronic storage unit 815.
  • the machine executable or machine readable code can be provided in the form of software.
  • the code can be executed by the processor 805.
  • the code can be retrieved from the storage unit 815 and stored on the memory 810 for ready access by the processor 805.
  • the electronic storage unit 815 can be precluded, and machine-executable instructions are stored on memory 810.
  • the code can be pre-compiled and configured for use with a machine having a processer adapted to execute the code, or can be compiled during runtime.
  • the code can be supplied in a programming language that can be selected to enable the code to execute in a pre- compiled or as-compiled fashion.
  • aspects of the systems and methods provided herein can be embodied in programming.
  • Various aspects of the technology may be thought of as “products” or“articles of manufacture” typically in the form of machine (or processor) executable code and/or associated data that is carried on or embodied in a type of machine readable medium.
  • Machine-executable code can be stored on an electronic storage unit, such as memory (e.g., read-only memory, random-access memory, flash memory) or a hard disk.
  • “Storage” type media can include any or all of the tangible memory of the computers, processors or the like, or associated modules thereof, such as various semiconductor memories, tape drives, disk drives and the like, which may provide non-transitory storage at any time for the software programming. All or portions of the software may at times be communicated through the Internet or various other telecommunication networks. Such communications, for example, may enable loading of the software from one computer or processor into another, for example, from a management server or host computer into the computer platform of an application server.
  • another type of media that may bear the software elements includes optical, electrical and electromagnetic waves, such as used across physical interfaces between local devices, through wired and optical landline networks and over various air-links.
  • a machine readable medium such as computer-executable code
  • a tangible storage medium such as computer-executable code
  • Non-volatile storage media include, for example, optical or magnetic disks, such as any of the storage devices in any computer(s) or the like, such as may be used to implement the databases, etc. shown in the drawings.
  • Volatile storage media include dynamic memory, such as main memory of such a computer platform.
  • Tangible transmission media include coaxial cables; copper wire and fiber optics, including the wires that comprise a bus within a computer system.
  • Carrier-wave transmission media may take the form of electric or electromagnetic signals, or acoustic or light waves such as those generated during radio frequency (RF) and infrared (IR) data communications.
  • RF radio frequency
  • IR infrared
  • Common forms of computer-readable media therefore include for example: a floppy disk, a flexible disk, hard disk, magnetic tape, any other magnetic medium, a CD-ROM, DVD or DVD-ROM, any other optical medium, punch cards paper tape, any other physical storage medium with patterns of holes, a RAM, a ROM, a PROM and EPROM, a FLASH-EPROM, any other memory chip or cartridge, a carrier wave transporting data or instructions, cables or links transporting such a carrier wave, or any other medium from which a computer may read programming code and/or data.
  • Many of these forms of computer readable media may be involved in carrying one or more sequences of one or more instructions to a processor for execution.
  • the computer system 801 can include or be in communication with an electronic display 835 that comprises a user interface (Ed) 840 for providing, for example, a visual display indicative of a clinical view, a disease category view, a disease view, and/or a genes view.
  • a user interface Ed
  • UFs examples include, without limitation, a graphical user interface (GUI) and web-based user interface.
  • GUI graphical user interface
  • Methods and systems of the present disclosure can be implemented by way of one or more algorithms.
  • An algorithm can be implemented by way of software upon execution by the central processing unit 805.
  • the algorithm can, for example, (i) receive a request from a computer of an operator to evaluate a clinical indication of a subject, (ii) upon receiving the request, determine genomic data relevant to the clinical indication, and (iii) generate an output comprising a recommendation that the operator have the genomic data obtained for the subject.
  • a 25-year-old patient presents with symptoms of chest pains, which occur especially when exercising.
  • the patient’s father had a heart attack in his 50s.
  • the patient’s physician is aware that having heart problems at such a young age may be indicative of a hereditary disease or disorder. He refers the patient for basic clinical testing first (EKG, Echocardiogram, etc.). Laboratory reports provide a clinical indication of Hypertrophic cardiomyopathy. The physician is aware that this disease may be hereditary but is not sure which genetic tests to order for the patient. There are about 600 different genetic tests commercially available for cardiomyopathy in the United States, offered by about 40 different laboratories. The physician decides to order the core cardiology panel which he is familiar with. Laboratory results for this core cardiology panel come back negative, and no further clinical action is taken for the patient. The physician is not aware that there are extended gene panels available which he can order for the patient.
  • the physician runs the navigator and provides the patient’s information, clinical history, and Hypertrophic cardiomyopathy as a clinical guidance.
  • the navigator identifies a core gene panel and an extended gene panel in response to the physician’s input data, and provides a recommendation for the physician to order the extended gene panel for the patient.
  • the physician orders the extended gene panel through the navigator, and three days later, receives a notification on his computer that the genetic test results are ready.
  • the navigator presents a visual view of the genetic test results. Every analyzed gene is shown as a circle, each of which is green except for one gene, which is colored red. This gene has a pathogenic variant.
  • the genetic test results reveal that the patient has inherited cardiomyopathy, and the physician was able to perform an accurate diagnosis and provide customize care for the patient, using the navigator.
  • the geneticist is easily able to access the patient’s test report and raw data, and can see the precise genetic testing results, even those not reported clearly by the lab. It is clearly communicated to the neurologist that the patient’s DNA does not contain a second variant and that CLN3 is likely not a diagnosis, because the navigator has an improved interface that clearly indicates in a graphical manner which gene variants are found and which gene variants are not found. When new exome results are available, they are easily transmitted to the geneticist, who can review them. Using the navigator, both the patient and the neurologist can send the results to the geneticist.
  • a 15-year-old boy presents with symptoms of progressive ataxia for the past year without a definitive clinical diagnosis.
  • the patient received a brain MRI with abnormal results, indicating an injury in the brain.
  • the patient s family recalls having genetic testing started, but is unsure if such genetic testing was completed, when it was performed, or who received the results.
  • the geneticist who ordered the genetic tests had recently moved to another institution. After making several phone calls and submitting forms over more than a day, it was determined that the genetic results had been available for 3 weeks and that a genetic diagnosis had been made. In the meantime, the patient has received several unnecessary and risky therapies and was literally minutes away from being exposed to a high-dose radiation therapy for another, unnecessary, imaging study.
  • the patient is continuously made aware of genetic test results.
  • the patient and his physicians are automatically alerted when genetic test results become available, since the patient’s family, having previously been granted access, can give approval to provide a navigator user account (with login and password), allowing immediate access of the patient’s genetic testing history to any clinical provider.
  • FIGs. 11A-11D illustrate examples of a navigator software of a graphical genome system for use by clinical providers, including a view of a list of clinical pathways (FIG. 11 A), views of a proprietary curated genes panel (FIGs. 11B-11C), and a view of a list of curated lab panels (FIG. 11D).
  • the clinical provider can use the view of a list of clinical pathways (FIG. 11 A) to select a disease or a taxonomy.
  • the clinical provider chooses the Department of Cardiology, which causes the Navigator software to display a list of cardiology-related clinical pathways, including arrhythmias and cardiomyopathies, congenital heart defects, hyperlipidemia and hypolipidemia, and aortopathies and vascular malformations.
  • the clinical provider can select a given clinical pathway from the list of clinical pathways, which causes the Navigator software to display a proprietary genes panel (FIGs. 11B- 11C).
  • the proprietary genes panel is generated based on analysis of a combination of expert opinions, primary literature, gene and variant databases, and laboratory panels to determine which genes are known to be associated with a condition.
  • the proprietary genes panel can include a list of high-evidence genes (or convincing-evidence) genes, probable- evidence genes, and limited-evidence genes.
  • High-evidence (or convincing-evidence) genes refer to those genes that have a well-established association with a condition.
  • Probable-evidence genes refer to those genes with reasonable evidence of an association with a condition.
  • Limited- evidence genes have limited, newer, and/or conflicting evidence with respect to an association with a condition.
  • the proprietary genes panel can indicate high-evidence genes (or convincing- evidence) genes, probable-evidence genes, and limited-evidence genes visually using different color codes and/or different symbols.
  • the clinical provider can select one or more genes for further patient testing based on their description and/or categorization as high-evidence genes (or convincing-evidence) genes, probable-evidence genes, or limited-evidence genes, which causes the Navigator software to display a list of curated lab panels (FIG. 11D).
  • These curated lab panels are a collection of gene panels which are commercially available for genetic testing from a large set of certified labs (e.g., about 200 different certified labs) at different prices.
  • an arrhythmogenic right ventricular cardiomyopathy panel can contain 10 out of 10 high-evidence genes and 4 out of 4 limited-evidence genes, which is offered by a certain laboratory at, for example, a price of $7,250 with a turnaround time (TAT) of 28 days and the ability to automatically handle the billing of commercial insurance.
  • TAT turnaround time
  • the clinical provider can automatically order the required genetic tests electronically, without the need to manually fill out and submit different forms for each individual gene panel or genetic test ordered.
  • a different laboratory offers a similar panel for only $399.
  • the navigator software will enable providers to choose the most cost-effective gene panel for the relevant patient.
  • the clinical provider can view a user-selected subset of lab panels, such as only panels that support private billing, only panels that fall within a selected price range, only panels that fall within a selected range of turnaround time, or a combination thereof.
  • FIGs. 12A-12D illustrate examples of analytics tools of a navigator software of a graphical genome system for use by ordering clinical providers, including a view of a test order history (FIG. 12 A), a view of clinical guidances for different diseases or disorders (FIG. 12B), and views of a list of positive genes that were found pathogen, per clinical guidance (FIGs. 12C- 12D).
  • the view of the test order history displays a plot of the number of tests ordered by the clinical provider over time (e.g., across different months) (FIG. 12A).
  • the view of the clinical guidances for different diseases or disorders shows the number of clinical guidances selected or indicated by the clinical provider over a period of time (FIG. 12B).
  • the list of clinical guidances includes aortophathy, arrhythmias, arrhythmogenic cardiomyopathy, cardiomyopathies, catecholaminergic polymorphic ventricular tachycardia, dilated cardiomyopathy, familial hypercholesterolemia, hypertrophic cardiomyopathy, RASopathies, thoracic aortic aneurysm and dissection, Ehlers Danlos Syndrome, Loeys-Dietz Syndrome, Brugada syndrome, long QT syndrome, and short QT syndrome; with numbers of clinical guidances ranging from 1 to 20 during the time period of 1/1/2018 to 4/29/2019 across all ordering providers and testing labs.
  • the views of lists of positive genes shows positive genes that are positively associated with different conditions (e.g., diseases or disorders) using shaded boxes (FIGs. 12C-12D).
  • the positive gene associations include COL3 Al and COL5A1 genes for aortopathy; AKAP9, CALM1, KCNQ1, MYL3, and SCN5A genes for arrhythmias; JUP gene for arrhythmogenic cardiomyopathy; SCN5A gene for Brugada syndrome; TNNT2 gene for cardiomyopathies; no genes for catecholaminergic polymorphic ventricular tachycardia; no genes for dilated cardiomyopathy; GORAB gene for Ehlers Danlos Syndrome; APOB gene for familial hypercholesterolemia (with a strong positive association); MYH7 gene for hypertrophic cardiomyopathy; no genes for Loeys-Dietz Syndrome; KCNH2 gene for long QT syndrome; no genes for RASopathies; no genes for short QT syndrome; ACTA2, FBN1, and TGFBR2 genes for thoracic aortic aneurysm and dissection; etc.
  • pharmacogenomic data can be integrated into patients’ clinical data for further analysis.
  • Pharmacogenomic data generally refers to data related to the role of the genome in drug response, which is related to analysis of how the genetic makeup of an individual affects his or her response to drugs.
  • FIG. 13 illustrates an example of the design and functionality of a Navigator software of a graphical genome system for use with pharmacogenomic data.
  • a patient s medical conditions (e.g., diseases and/or disorders) are listed on the far left, which are organized by date of diagnosis (with the most recent being at the top).
  • Medications e.g., prescription drugs
  • the first medication(s) listed are the most recently prescribed and medications the patient is actively taking. Medications are color-coded based on the pharmacogenomic data (e.g., a green check indicating an excellent response such that a condition is managed, a yellow square indicating an intermediate response such that a condition is controlled on increased dosage, or a red“X” indicating a poor response). For medications with poor responses, alternative medications may be suggested to the provider. Additionally, when pharmacogenomic testing may be beneficial for a given medical condition or medication of the patient, then a notification “Test available” is displayed.
  • Pharmacogenomic data can be linked to a patient’s health record based on the medical conditions and medications present in the patient’s health record. Generally,
  • pharmacogenomic data is most informative when it is integrated with the medications (and potential conditions) that are associated with a given patient. Therefore, a database is maintained with the medications for which pharmacogenomic data is most beneficial, and the medications are linked to the medical conditions for which they are commonly prescribed. This allows the software to note when pharmacogenomic testing should be considered based on the patient’s condition prior to a medication being prescribed.
  • Tim As another example of a user story, suppose Dr. Adams, another clinical provider, receives concerning blood work results back on her patient, Tim. She logs into Tim’s chart in the Navigator software and updates his clinical health record information to note that Tim is now diagnosed with diabetes, based on the blood work results and his symptoms. Tim had previously chosen to have PGx testing several years earlier. Had he not had this testing, the Navigator software would have alerted Dr. Adams that PGx testing may be beneficial before prescribing any medication. As Dr. Adams, another clinical provider, receives concerning blood work results back on her patient, Tim. She logs into Tim’s chart in the Navigator software and updates his clinical health record information to note that Tim is now diagnosed with diabetes, based on the blood work results and his symptoms. Tim had previously chosen to have PGx testing several years earlier. Had he not had this testing, the Navigator software would have alerted Dr. Adams that PGx testing may be beneficial before prescribing any medication. As Dr. Adams
  • Adams looks for a suitable medication for Tim, she notices that each medication is accompanied by a color-coded indicator showing as green, yellow, or red, based on Tim’s prior PGx results, and therefore is able to quickly and efficiently choose the best medication to prescribe for Tim, based on his condition and prior PGx testing.
  • Patient data needs to be updated regularly or in real time with the integrated EMR system. This can be performed by the Navigator, which updates all patient data, assesses the new data (e.g., a new medication or condition) to determine if there are issues or concerns as it relates to PGx, and generates a color-coded notification to the provider indicating the issue.
  • the Navigator may handle or facilitate the prescribing process in order to make this easier for a provider.
  • the Navigator may have built-in functionality to allow prescribing of medications or may be integrated with the prescribing system of the clinical provider.
  • the provider avoids the need to log into the Navigator, review which medications are potential issues for the patient given his or her PGx data, identify an appropriate medication for the patient’s condition, and then log into their prescribing software and find and choose the same medication.
  • Dr. Sloan A new patient is being seen in the office of cardiologist Dr. Sloan. Rosalie Estrada was referred due to arrhythmia and an abnormality of right ventricle. Dr. Sloan discusses management of her condition. Dr. Sloan believes that her symptoms (syncope, ventricular tachycardia, and right ventricular dyskinesia) as well as her family history (cardiomyopathy) are consistent with a condition known as ARVC (arrhythmogenic right ventricular cardiomyopathy). Dr. Sloan is aware that there are several genes known to cause ARVC and that there are multiple panels available to test for ARVC.
  • Dr. Sloan uses the
  • the Navigator to aid in selecting and ordering genetic tests.
  • the Navigator supports the ability to enroll multiple providers from the same institution and practice.
  • Dr. Sloan logs into the Navigator using his username and password.
  • dashboard provides the provider with information about his patients divided up based on the status of their genetic testing.
  • On the left sidebar there are three circles, notifications that provide messages about the status of testing, settings, and log out.
  • dashboard There are also five links: dashboard (to bring the provider back to the dashboard when they are in another page), clinical guidance (to start a guidance), draft guidances (to return to a guidance that was incomplete), ordered tests (a list of all pending and completed genetic tests ordered), and patients (a list of all patients).
  • the dashboard also provides a list of the most recent completed tests, a list of all pending tests, and a search bar to look up any patient in the Navigator.
  • the completed tests section lists out any patients who have had a recently completed genetic test organized by the most recently completed. On his dashboard, he also has a list of pending tests and is able to quickly see that he has 3 genetic tests pending and when they were ordered. On the dashboard, the provider scrolls down to the pending tests section.
  • These lists can also be organized by each of the categories listed (e.g. patient name, test name).
  • the provider can click on“Name” to reorganize the list in alphabetical order.
  • the Navigator supports additional features including Pharmacogenomics, ICD-10 linked to the clinical and family history, and the addition of other providers in this patient’s care team for ease of sharing results.
  • the provider can also search by the condition name and ICD-10 codes with a one to one match to the condition.
  • Above cardiology is the ontology search bar, where the provider types in“i42” to display dilated cardiomyopathy and restrictive cardiomyopathy.
  • the provider can delete“i42” and type in“rig” to show that ARVC can also be found by searching the condition name.
  • the Navigator can also support searching by common acronyms.
  • the provider is able to click through a hierarchy of available options, categorized by department to find the patient’s condition, ARVC. Once he captures this condition, the navigator displays a curated list of genes that are associated with the condition.
  • the curated gene panel is based on a combination of expert opinion (such as ClinGen ® ), primary literature, gene and variant databases, and laboratory panels to determine the strength of association between genes and the condition.
  • the Navigator software uses an algorithm to match this curated list against all possible genetic panels to provide a list of the closest matches to the curated list.
  • the provider notes that he is able to view a curated list of genes that is associated with the condition classified as high evidence and limited evidence genes.
  • the provider can find out more information about the gene by clicking on the three dots.
  • the provider can click on the three dots for RYR2, then click on the OMIM link to bring up the OMIM page for this gene.
  • the Navigator can also support adding, deleting, and editing genes not listed as high or limited evidence to a curated list to create a custom panel for that provider.
  • the Navigator displays a list of available genetic tests that matches best with the gene list, maximizing the number of high evidence genes included while minimizing the number of additional genes (those not listed as high or limited evidence).
  • the list of available tests is easily comparable based on price, turn around time, methodology, and the genes included.
  • the provider drops the right side price filter from $7250 to $1999 to remove the highest priced panels.
  • Providers may also search for a panel name or laboratory.
  • the provider types“Ambry” to show that only the panel from Ambry Genetics ® is displayed.
  • the Navigator can support additional filters to modify the algorithm (e.g.
  • the provider notes that the ARVCNextTM panel has all of the noted high evidence genes and has the least expensive price.
  • the patient consents to this test.
  • an order form is populated based on the information in the Navigator and the order can be sent to the selected laboratory electronically through the Navigator.
  • the provider selects ARVCNexTMt from Ambry Genetics ® .
  • a test order form for the laboratory is now displayed with information pulled from the patient record.
  • the Navigator can support populating clinical history and family history with ICD-10 codes.
  • the Navigator can also support providing detailed instructions for the provider for the chosen test/laboratory.
  • the results are sent back through the Navigator, then stored in the software.
  • the provider returns to the dashboard by clicking dashboard.
  • the doctor logs into the Navigator and clicks on the view results tab to see the PDF of the result. He notes the patient has a positive result.
  • the Navigator can support notification features that sends a message to the provider once the results are ready, sharing these results with other providers and to the patient, and flagging important results to quickly identify at a future time.
  • the Navigator also displays a list of clinical guidance that were run for patient but for which testing was not ordered.
  • the Navigator can support returning to the point in the guidance where the user previously left off.
  • the Navigator also allows for viewing all ordered tests (pending and completed) through the“Ordered Test” link on the left sidebar as well as viewing all patients from the Patients link on the left sidebar.
  • the provider can use analytics tools of the Navigator as follows. First, the provider logs into the system using his username and password.
  • the analytics section provides statistical information organized by categories: institution, clinical guidance, physician, and testing lab.
  • the user wishes to view how many tests were ordered in the month of November.
  • the user changes the order date to list Nov 1, 2018 to Nov 30, 2018.
  • the user can see 46 orders were placed in that month.
  • the user can also subdivide these by lab or by provider.
  • the user scrolls down to view the number of tests ordered by each doctor and the average cost of each test by doctor.
  • the user wishes to view how many patients with thoracic aortic aneurysms are having genetic testing.
  • the user filters the list for“Thoracic Aortic
  • Dr. Karev is ordering testing under the more generic clinical guidance terms arrhythmias and cardiomyopathies which will likely lead to large, high cost panels being routinely ordered.
  • the user scrolls down to see positive genes by clinical guidance and the clinical guidance per laboratory.
  • the user returns to institution, and scrolls down to view the average cost of testing per physician noting that Dr. Karev has the highest average cost.
  • the user may sort by provider to see the breakdown of results classification per provider, the tests ordered by laboratory and a complete list of patients. The user chooses Alex Karev, and notes that only 3 tests were positive from this providers’ orders. If there are concerns he is ordering too many large panels and perhaps on inappropriate sets of patients, this value can be useful to track.
  • Advantages of the system may include: ease of navigation of a hierarchy of genetic conditions; a curated list of genes associated with the selected genetic conditions; a list of U.S. -based genetic panels matched based on the curated list of genes; a design that allows for ease of comparing several factors between laboratories and filter based on these factors; the ability to fill out order forms based on information stored in the software; the ability to send orders electronically directly to the laboratory; result being sent back electronically to the Navigator software; and analytics tools, including a list of genetic tests ordered by physician, by laboratory, by clinical guidance, which notes information about price and turnaround time (TAT).
  • TAT price and turnaround time

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Bioethics (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

La présente invention concerne des systèmes et des méthodes de conseils cliniques de tests génétiques utilisant l'apprentissage automatique. Selon un aspect, la présente invention concerne un système permettant à un opérateur de générer un registre de santé génomique d'un sujet, comprenant : une base de données, comprenant des indications cliniques ; une interface de communication, en communication avec un ordinateur de l'opérateur ; et un processeur informatique, fonctionnellement couplé auxdites base de données et interface de communication, ledit processeur informatique étant programmé pour (i) recevoir une demande de l'ordinateur de l'opérateur, pour évaluer une indication clinique du sujet, (ii) lors de la réception de la requête, déterminer des données génomiques pertinentes pour l'indication clinique et (iii) générer une sortie, laquelle sortie comprend une recommandation indiquant que ledit opérateur a obtenu les données génomiques pour le sujet.
PCT/US2019/039613 2018-06-28 2019-06-27 Systèmes et méthodes pour conseils cliniques de tests génétiques WO2020006306A1 (fr)

Applications Claiming Priority (8)

Application Number Priority Date Filing Date Title
US201862691371P 2018-06-28 2018-06-28
US62/691,371 2018-06-28
US201862726910P 2018-09-04 2018-09-04
US62/726,910 2018-09-04
US201862756375P 2018-11-06 2018-11-06
US62/756,375 2018-11-06
US201962846262P 2019-05-10 2019-05-10
US62/846,262 2019-05-10

Publications (1)

Publication Number Publication Date
WO2020006306A1 true WO2020006306A1 (fr) 2020-01-02

Family

ID=68987509

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2019/039613 WO2020006306A1 (fr) 2018-06-28 2019-06-27 Systèmes et méthodes pour conseils cliniques de tests génétiques

Country Status (1)

Country Link
WO (1) WO2020006306A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112863605A (zh) * 2021-02-03 2021-05-28 中国人民解放军总医院第七医学中心 一种确定智力障碍基因的平台、方法、计算机设备和介质

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170132371A1 (en) * 2015-10-19 2017-05-11 Parkland Center For Clinical Innovation Automated Patient Chart Review System and Method
US20170199977A1 (en) * 2008-02-26 2017-07-13 Purdue Research Foundation Method for patient genotyping

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170199977A1 (en) * 2008-02-26 2017-07-13 Purdue Research Foundation Method for patient genotyping
US20170132371A1 (en) * 2015-10-19 2017-05-11 Parkland Center For Clinical Innovation Automated Patient Chart Review System and Method

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112863605A (zh) * 2021-02-03 2021-05-28 中国人民解放军总医院第七医学中心 一种确定智力障碍基因的平台、方法、计算机设备和介质

Similar Documents

Publication Publication Date Title
Galetsi et al. Big data analytics in health sector: Theoretical framework, techniques and prospects
US10902953B2 (en) Clinical outcome tracking and analysis
Tresp et al. Going digital: a survey on digitalization and large-scale data analytics in healthcare
US20200357526A1 (en) Systems and methods for clinical guidance of genetic testing for patients via a mobile application
Teixeira et al. Evaluating electronic health record data sources and algorithmic approaches to identify hypertensive individuals
Zhou et al. Defining disease phenotypes in primary care electronic health records by a machine learning approach: a case study in identifying rheumatoid arthritis
US20160203269A1 (en) Systems and Methods of Clinical Tracking
Hombach et al. MutationDistiller: user-driven identification of pathogenic DNA variants
CA2858355C (fr) Systemes, procedes et supports pour des services de test en laboratoire
CN110709938A (zh) 用于生成患者数字孪生的方法和系统
US11309060B2 (en) System and method for real time clinical questions presentation and management
US20130197922A1 (en) Method and system for discovery and continuous improvement of clinical pathways
WO2014117149A1 (fr) Gestion des soins d'un client dans un système de gestion des soins
JP2008532104A (ja) 複数の医療関連アウトカムの予測を行い、インターベンション計画の評価を行い、更に同時にバイオマーカー因果性検証を行うことのできる、予測モデルを生成して適用する方法、そのシステム、及びそのコンピュータ・プログラム製品
Ji et al. Clinical exome reanalysis: current practice and beyond
US20130282404A1 (en) Integrated access to and interation with multiplicity of clinica data analytic modules
US20130275153A1 (en) Method of optimizing patient-related outcomes
Barnado et al. Phenome-wide association study identifies marked increased in burden of comorbidities in African Americans with systemic lupus erythematosus
Shah et al. Big data in cardiology
Burke et al. Seeking genomic knowledge: the case for clinical restraint
Fasola et al. Health information technology in oncology practice: a literature review
US20200020421A1 (en) A method and apparatus for collaborative variant selection and therapy matching reporting
Murphy et al. Grappling with the future use of big data for translational medicine and clinical care
US11355222B2 (en) Analytics at the point of care
US10867698B2 (en) Systems and methods for improved health care cohort reporting

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19824945

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19824945

Country of ref document: EP

Kind code of ref document: A1