CN116524995A - Medicine curative effect prediction method based on artificial intelligence and related equipment - Google Patents
Medicine curative effect prediction method based on artificial intelligence and related equipment Download PDFInfo
- Publication number
- CN116524995A CN116524995A CN202310330024.2A CN202310330024A CN116524995A CN 116524995 A CN116524995 A CN 116524995A CN 202310330024 A CN202310330024 A CN 202310330024A CN 116524995 A CN116524995 A CN 116524995A
- Authority
- CN
- China
- Prior art keywords
- feature set
- target feature
- time node
- data
- target
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 239000003814 drug Substances 0.000 title claims abstract description 133
- 229940079593 drug Drugs 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 42
- 230000000694 effects Effects 0.000 title claims abstract description 34
- 238000004458 analytical method Methods 0.000 claims abstract description 58
- 239000011159 matrix material Substances 0.000 claims description 39
- 238000012549 training Methods 0.000 claims description 29
- 238000003062 neural network model Methods 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 22
- 201000010099 disease Diseases 0.000 claims description 19
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 17
- 239000013598 vector Substances 0.000 claims description 16
- 238000010201 enrichment analysis Methods 0.000 claims description 14
- 238000007621 cluster analysis Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 230000014509 gene expression Effects 0.000 claims description 9
- 230000000968 intestinal effect Effects 0.000 claims description 6
- 230000007067 DNA methylation Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 230000002452 interceptive effect Effects 0.000 claims description 4
- 108091070501 miRNA Proteins 0.000 claims description 4
- 239000002679 microRNA Substances 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 230000009145 protein modification Effects 0.000 claims description 4
- 230000002962 histologic effect Effects 0.000 claims description 3
- 238000011282 treatment Methods 0.000 abstract description 10
- 230000006870 function Effects 0.000 description 14
- 108090000623 proteins and genes Proteins 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 9
- 208000023275 Autoimmune disease Diseases 0.000 description 8
- 230000001225 therapeutic effect Effects 0.000 description 7
- 239000005557 antagonist Substances 0.000 description 5
- 206010061218 Inflammation Diseases 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000004054 inflammatory process Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 3
- 230000001363 autoimmune Effects 0.000 description 3
- 239000003124 biologic agent Substances 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000001647 drug administration Methods 0.000 description 3
- 238000000513 principal component analysis Methods 0.000 description 3
- 150000003384 small molecules Chemical class 0.000 description 3
- 230000000844 anti-bacterial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000036737 immune function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000002207 metabolite Substances 0.000 description 2
- 102000004169 proteins and genes Human genes 0.000 description 2
- 230000019491 signal transduction Effects 0.000 description 2
- 230000009385 viral infection Effects 0.000 description 2
- 108091029430 CpG site Proteins 0.000 description 1
- 102000004127 Cytokines Human genes 0.000 description 1
- 108090000695 Cytokines Proteins 0.000 description 1
- 229940125385 biologic drug Drugs 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000009274 differential gene expression Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000010195 expression analysis Methods 0.000 description 1
- 230000007365 immunoregulation Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000031146 intracellular signal transduction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000011987 methylation Effects 0.000 description 1
- 238000007069 methylation reaction Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011369 optimal treatment Methods 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 230000035755 proliferation Effects 0.000 description 1
- 230000004850 protein–protein interaction Effects 0.000 description 1
- 230000025915 regulation of apoptotic process Effects 0.000 description 1
- 230000004043 responsiveness Effects 0.000 description 1
- 108700026220 vif Genes Proteins 0.000 description 1
Classifications
-
- 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
- G16B15/00—ICT specially adapted for analysing two-dimensional or three-dimensional molecular structures, e.g. structural or functional relations or structure alignment
- G16B15/30—Drug targeting using structural data; Docking or binding prediction
-
- 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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- 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
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Medicinal Chemistry (AREA)
- Medical Informatics (AREA)
- Pharmacology & Pharmacy (AREA)
- Epidemiology (AREA)
- Public Health (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Primary Health Care (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Biotechnology (AREA)
- Theoretical Computer Science (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Crystallography & Structural Chemistry (AREA)
- Toxicology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of digital medical treatment, and provides a medicine curative effect prediction method based on artificial intelligence and related equipment, wherein the method comprises the following steps: extracting features of the original data set to obtain a first target feature set; respectively analyzing the second target feature set and the third target feature set of each time node to obtain an analysis result of the first signal path of the corresponding time node; and inputting the analysis result of the first signal path, the second target feature set, the third target feature set and the corresponding medicine curative effect result of each time node into a pre-trained time sequence prediction model to obtain the medicine curative effect prediction result of each time node. According to the invention, the medical treatment effect on the follow-up medication time node is predicted in advance, so that a doctor can more reasonably formulate a medical treatment scheme for a patient, and the working efficiency of the doctor is improved.
Description
Technical Field
The invention relates to the technical field of digital medical treatment, in particular to a medicine curative effect prediction method based on artificial intelligence and related equipment.
Background
Autoimmune patients can be treated by biological agents in early stages, but the autoimmune patients can usually be diagnosed for many years, and delay in diagnosis leads to a large number of patients missing optimal dry expectations for treatment. There is no effective cure for autoimmune diseases at present, although biological agents such as TNF antagonists are effective in reducing inflammation and pain.
However, before or during the pre-treatment of a biologic such as a TNF antagonist, a drug that predicts the responsiveness of the biologic such as a TNF antagonist cannot be found, resulting in a failure of the physician to accurately prescribe a medical regimen for the patient.
Disclosure of Invention
In view of the above, it is necessary to provide an artificial intelligence-based drug efficacy prediction method and related devices, which predict the drug efficacy on the following drug administration time node in advance, so that a doctor can more reasonably formulate a medical treatment plan for a patient, and the working efficiency of the doctor is improved.
The first aspect of the invention provides an artificial intelligence-based drug efficacy prediction method, which comprises the following steps:
acquiring an original data set of a user, wherein the original data set comprises a plurality of time sequence data sets from before-medication to a plurality of time nodes in a medication process of the user;
Extracting features of the original data set to obtain a first target feature set, wherein the first target feature set comprises a first public component feature set and a first key component feature set of each time node;
extracting a second target feature set from the first common component feature set of each time node, and extracting a third target feature set from the first key component feature set of each time node;
respectively analyzing the second target feature set and the third target feature set of each time node to obtain an analysis result of the first signal path of the corresponding time node;
and inputting the analysis result of the first signal path, the second target feature set, the third target feature set and the corresponding medicine curative effect result of each time node into a pre-trained time sequence prediction model to obtain the medicine curative effect prediction result of each time node.
Optionally, the analyzing the second target feature set and the third target feature set of each time node respectively, to obtain an analysis result of the first signal path of the corresponding time node includes:
performing enrichment analysis on the second target feature set and the third target feature set to obtain an enrichment analysis result;
Carrying out channel analysis on the enrichment analysis result to obtain a first signal channel;
and performing cluster analysis on the first signal paths to obtain analysis results of the first signal paths corresponding to the time nodes.
Optionally, the original data set includes: gene expression data, miRNA expression data, DNA methylation data, proteomic data, protein modification histologic data, metabonomic data, intestinal flora 16sRNA data.
Optionally, before the analysis result of the first signal path, the second target feature set, the third target feature set and the corresponding drug efficacy result of each time node are input into the pre-trained time sequence prediction model, the method further includes:
acquiring a plurality of user history sequence data sets, wherein each user history sequence data set comprises history sequence data of a plurality of time nodes from before the user takes a medicine to the medicine taking process;
extracting features of the historical sequence data set to obtain a first historical feature set, wherein the first historical feature set comprises a common component feature set and a key component feature set of each time node;
Extracting a second historical feature set from the common component feature set of each time node, and extracting a third historical feature set from the key component feature set of each time node;
respectively analyzing the second historical feature set and the third historical feature set of each time node to obtain an analysis result of a historical signal path;
taking analysis results of a plurality of historical signal paths of a plurality of time nodes of the plurality of users, a plurality of second historical feature sets, a plurality of third historical feature sets and corresponding medicament curative effect results as training sets;
and training a preset graph neural network based on the training set to obtain a time sequence prediction model.
Optionally, the performing feature extraction on the original data set to obtain a first target feature set includes:
carrying out standardization processing on the original data in the original data set to obtain a standardized matrix;
calculating an average value of sample data of each sample in the normalization matrix;
subtracting the corresponding average value from the sample data of each sample to obtain a target matrix;
calculating a covariance matrix of the target matrix, and eigenvalues and eigenvectors of the covariance matrix;
The feature values are ordered in a descending order, a plurality of feature values which are ordered in front are selected from the ordering result, and a plurality of feature vectors of the feature values are respectively used as row vectors to form a new feature vector matrix;
and projecting the target matrix onto the new feature vector matrix to obtain a first target feature set.
Optionally, the method further comprises:
extracting a data set before the user is ill from the original data set;
extracting features of the data set to obtain a fourth target feature set, wherein the fourth target feature set comprises a second common component feature set and a second key component feature set;
extracting a fifth target feature set from the fourth target feature set;
performing cluster analysis on the fifth target feature set to obtain a second signal path;
inputting the data set and the second signal path into a pre-trained heterogeneous graph neural network model to obtain a disease prediction result of the user.
Optionally, before inputting the data set and the second signal path into a pre-trained heterogeneous graph neural network model to obtain a morbidity prediction result of the user, the method further comprises:
Acquiring a plurality of users and historical data of each user before morbidity;
acquiring a heterogeneous graph corresponding to the heterogeneous medical knowledge graph of the historical data;
acquiring a signal path with interactive relation with the heterogeneous graph;
taking a plurality of historical data and signal paths of the plurality of users as a training set;
training the pre-trained heterogeneous graph neural network model according to the training set to obtain the heterogeneous graph neural network model.
A second aspect of the present invention provides an artificial intelligence based drug efficacy prediction device, the device comprising:
the acquisition module is used for acquiring an original data set of a user, wherein the original data set comprises a plurality of time sequence data sets from the time before the user takes the medicine to a plurality of time nodes in the medicine taking process;
the first extraction module is used for extracting features of the original data set to obtain a first target feature set, wherein the first target feature set comprises a first public component feature set and a first key component feature set of each time node;
the second extraction module is used for extracting a second target feature set from the first common component feature set of each time node and extracting a third target feature set from the first key component feature set of each time node;
The analysis module is used for respectively analyzing the second target feature set and the third target feature set of each time node to obtain an analysis result of the first signal path of the corresponding time node;
the input module is used for inputting the analysis result of the first signal path, the second target feature set, the third target feature set and the corresponding medicine curative effect result of each time node into a pre-trained time sequence prediction model to obtain the medicine curative effect prediction result of each time node.
A third aspect of the present invention provides an electronic device comprising a processor and a memory, the processor being adapted to implement the artificial intelligence based drug efficacy prediction method when executing a computer program stored in the memory.
A fourth aspect of the present invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the artificial intelligence based drug efficacy prediction method.
In summary, according to the artificial intelligence-based drug efficacy prediction method and related equipment, the second target feature set is extracted from the first common component feature set of each time node, and the third target feature set is extracted from the first key component feature set of each time node, so that the second target feature set and the third target feature set which have a larger influence on drug efficacy prediction are considered, and the accuracy of drug efficacy prediction is improved. The second target feature set and the third target feature set of each time node are respectively analyzed to obtain an analysis result of the first signal path of the corresponding time node, the analysis result of the first signal path of each time node, the second target feature set, the third target feature set and the corresponding medicine curative effect result are input into a pre-trained time sequence prediction model to obtain a medicine curative effect prediction result of each time node, and in the process of obtaining the medicine curative effect prediction result, consideration is carried out from multiple dimensions, so that the accuracy of the medicine curative effect prediction result is improved.
Drawings
Fig. 1 is a flowchart of an artificial intelligence-based drug efficacy prediction method according to an embodiment of the present invention.
Fig. 2 is a block diagram of an artificial intelligence-based drug efficacy prediction device according to a second embodiment of the present invention.
Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. It should be noted that, without conflict, the embodiments of the present invention and features in the embodiments may be combined with each other.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
Example 1
Fig. 1 is a flowchart of an artificial intelligence-based drug efficacy prediction method according to an embodiment of the present invention.
In this embodiment, the drug efficacy prediction method based on artificial intelligence may be applied to an electronic device, and for an electronic device that needs to perform drug efficacy prediction based on artificial intelligence, the function of drug efficacy prediction based on artificial intelligence provided by the method of the present invention may be directly integrated on the electronic device, or may be run in the electronic device in the form of a software development kit (Software Development Kit, SDK).
The embodiment of the invention can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning, deep learning and other directions.
As shown in FIG. 1, the method for predicting the therapeutic effect of the drug based on artificial intelligence specifically comprises the following steps, the sequence of the steps in the flowchart can be changed according to different requirements, and some steps can be omitted.
101, obtaining an original data set of a user, wherein the original data set comprises a plurality of time series data sets from the time before the user takes a medicine to a plurality of time nodes in the medicine taking process.
In this embodiment, in the digital medical field, autoimmune patients can usually be diagnosed only 6-10 years after the onset of the disease, and delaying the diagnosis can lead to the patients missing the optimal dry treatment expectation and causing irreparable bone damage. When autoimmune diseases occur, the medicine curative effect of the patient after the medicine is taken can be predicted in advance according to a plurality of time sequence data sets of a plurality of time nodes before the medicine taking and in the medicine taking process of the patient, the phenomenon of missing the optimal treatment expectation is avoided, and the accurate prediction of the autoimmune diseases is realized.
In this embodiment, a drug efficacy prediction request sent by a user terminal is received, the received drug efficacy prediction request is parsed, a request message is obtained, a patient identification code is obtained from the request message, and an original data set of the user is obtained from a preset data source according to the patient identification code.
Specifically, the original data set includes: gene expression data, miRNA expression data, DNA methylation data, proteomic data, protein modification histologic data, metabonomic data, intestinal flora 16sRNA data.
In this embodiment, the patient identification code is configured to uniquely identify the patient, and the preset data source may be a platform on which the patient medication and the treatment process are recorded.
102, extracting features of the original data set to obtain a first target feature set, wherein the first target feature set comprises a first public component feature set and a first key component feature set of each time node.
In this embodiment, the first common component refers to a characteristic of the same component of the data in the original dataset, and the first key component refers to a characteristic of a unique component of the data in the original dataset.
In this embodiment, PCA (Principal Component Analysis), that is, a principal component analysis method may be used to analyze principal components in the original data set to obtain the first target feature set. The PCA is to sequentially find a set of mutually orthogonal coordinate axes from an original space, map n-dimensional features onto k-dimensions, where the k-dimensions are completely new orthogonal features, also called principal components, are k-dimensional features reconstructed on the basis of the original n-dimensional features, and determine the k-dimensional features as a first target feature set.
In an alternative embodiment, the performing feature extraction on the original data set to obtain a first target feature set includes:
carrying out standardization processing on the original data in the original data set to obtain a standardized matrix;
Calculating an average value of sample data of each sample in the normalization matrix;
subtracting the corresponding average value from the sample data of each sample to obtain a target matrix;
calculating a covariance matrix of the target matrix, and eigenvalues and eigenvectors of the covariance matrix;
the feature values are ordered in a descending order, a plurality of feature values which are ordered in front are selected from the ordering result, and a plurality of feature vectors of the feature values are respectively used as row vectors to form a new feature vector matrix;
and projecting the target matrix onto the new feature vector matrix to obtain a first target feature set.
In this embodiment, since the original data set includes multiple sets of mathematical data, the covariance matrix of the target matrix obtained by calculation satisfies the two-dimensional feature.
In this embodiment, the eigenvalues and eigenvectors of the covariance matrix may be calculated by using an eigenvalue decomposition method.
In this embodiment, the first common component feature set and the first key component feature set of each time node are extracted from the original data set, so as to ensure that components can be orthogonal, that is, the components do not have information redundancy, the feature sets are represented to the greatest extent by using as few components as possible, the number of feature sets is reduced, and meanwhile, the first common component feature set and the first key component feature set are considered when the drug efficacy is predicted subsequently, so that the efficiency of the drug efficacy prediction is improved.
103 extracting a second target feature set from the first common component feature set of each time node, and extracting a third target feature set from the first key component feature set of each time node.
In this embodiment, a feature having a large influence on the therapeutic effect of the drug may be set in advance for each autoimmune disease, and the second target feature set and the third target feature set refer to features having a large influence on the therapeutic effect of the drug.
In this embodiment, the features having a larger influence on the prediction of the therapeutic effect of the drug are extracted from the first common component feature set and the first key component feature set of each time node, and when the therapeutic effect of the drug is predicted, the second target feature set and the third target feature set having a larger influence on the prediction of the therapeutic effect of the drug are considered, so that the accuracy of the prediction of the therapeutic effect of the drug is improved.
104, respectively analyzing the second target feature set and the third target feature set of each time node to obtain an analysis result of the first signal path of the corresponding time node.
In this embodiment, the signal path refers to an intracellular signal transduction path closely related to a cytokine, and participates in many important physiological processes such as proliferation, differentiation, apoptosis and immunoregulation of cells, if the first signal path is abnormally activated, it may cause virus infection and decrease of antibacterial immune function, aggravate inflammation of a patient, and by analyzing the signal paths of the second target feature set and the third target feature set of each time node, it can be predicted in advance whether the first signal path is abnormally activated, so that the problems such as virus infection and decrease of antibacterial immune function caused by the abnormal activation of the first signal path, aggravate inflammation of the patient can be avoided.
In an optional embodiment, the analyzing the second target feature set and the third target feature set of each time node separately, to obtain an analysis result of the first signal path of the corresponding time node includes:
performing enrichment analysis on the second target feature set and the third target feature set to obtain an enrichment analysis result;
carrying out channel analysis on the enrichment analysis result to obtain a first signal channel;
and performing cluster analysis on the first signal paths to obtain analysis results of the first signal paths corresponding to the time nodes.
In this embodiment, the enrichment refers to a process of classifying the target features according to genome annotation information corresponding to the target features by using the target features in the second target feature set and the third target feature set, and after the target features are classified, the commonalities of the searched target features can be identified, where the commonalities may be functions, compositions and the like between the target features.
In this embodiment, before enrichment analysis is performed on the second target feature set and the third target feature set, a gene annotation database corresponding to the target feature is pre-built, classification is performed on the second target feature set and the third target feature set according to annotations of the gene annotation database through a preset algorithm, the classification results are clustered, redundant results are removed, and an enrichment analysis result is obtained, wherein the enrichment classification result comprises differential gene expression analysis, differential genes are screened out, path analysis is performed on the differential genes, a first signal path is obtained, and cluster analysis is performed on the first signal path.
In this embodiment, the cluster analysis refers to an analysis process of grouping a set of physical or abstract objects into multiple classes composed of similar objects, and performing cluster analysis on a first signal path to obtain an analysis result of the first signal path corresponding to a time node, that is, a cluster analysis result of the signal path obtained by integrating multiple groups of learning data, where the analysis result includes an abnormal activation probability value of the first signal path.
In this embodiment, the gene annotation database is obtained by annotating the functions of genes from the viewpoint of different biological models and storing the annotated genes.
In this embodiment, by respectively analyzing the second target feature set and the third target feature set of different time nodes, an abnormal activation probability value of the signal path of the corresponding time node is obtained, so that the problem of inaccurate drug prediction caused by performing drug efficacy prediction by using the feature set of a single time node is avoided, and the accuracy of drug efficacy prediction is improved.
And 105, inputting the analysis result of the first signal path, the second target feature set, the third target feature set and the corresponding medicine efficacy result of each time node into a pre-trained time sequence prediction model to obtain the medicine efficacy prediction result of each time node.
In this embodiment, a time series prediction model may be pre-trained, which may be used to predict the efficacy of the drug at each time node.
For example, if the TNF biological agent is taken by the user, a plurality of time series data sets of a plurality of time nodes during the administration of the user, for example, a first time series data set, a second time series data set, etc., are obtained, the data sets in the plurality of time series data sets are adjusted, extracted and analyzed, and the analysis result of the first signal path, the second target feature set, the third target feature set and the corresponding drug efficacy result of each time node obtained by the analysis are input into a pre-trained time series prediction model, so as to obtain the drug efficacy prediction result of each time node. I.e., the efficacy of the TNF biologic can be predicted, e.g., the efficacy of the TNF biologic drug in reducing inflammation and pain is predicted to be effective after the second course of administration.
In an optional embodiment, before the analyzing result of the first signal path of each time node, the second target feature set, the third target feature set and the corresponding drug efficacy result are input into the pre-trained time series prediction model, the method further includes:
Acquiring a plurality of user history sequence data sets, wherein each user history sequence data set comprises history sequence data of a plurality of time nodes from before the user takes a medicine to the medicine taking process;
extracting features of the historical sequence data set to obtain a first historical feature set, wherein the first historical feature set comprises a common component feature set and a key component feature set of each time node;
extracting a second historical feature set from the common component feature set of each time node, and extracting a third historical feature set from the key component feature set of each time node;
respectively analyzing the second historical feature set and the third historical feature set of each time node to obtain an analysis result of a historical signal path;
taking analysis results of a plurality of historical signal paths of a plurality of time nodes of the plurality of users, a plurality of second historical feature sets, a plurality of third historical feature sets and corresponding medicament curative effect results as training sets;
and training a preset graph neural network based on the training set to obtain a time sequence prediction model.
In this embodiment, the historical sequence data set includes historical sequence data from a time point before the user takes the drug to a time point of the drug administration process, for example, the historical sequence data set includes gene expression data, miRNA expression data, DNA methylation data, proteomic data, metabonomic data, and intestinal flora 16sRNA data, and for the DNA methylation data, the first course of treatment data of the drug administration process is that the methylation level of CpG sites is m=log2 (M/U), where m=2.4, and u=2.5.
In this embodiment, after the historical sequence dataset is obtained, feature extraction is performed on the historical dataset, and the graph neural network is trained based on the feature extraction result, so as to obtain the time sequence prediction model.
In this embodiment, the graph neural network is a deep learning method, and can implement prediction on nodes, edges or graphs. By training a preset graph neural network based on a training set, the variation difference of clinical phenotypes on different time nodes can be predicted, and the drug efficacy on the subsequent administration time nodes can be predicted based on the variation difference.
In this embodiment, the analysis result of the first signal path, the second target feature set, the third target feature set and the corresponding drug efficacy result of each time node are input into the pre-trained time sequence prediction model, so as to obtain the drug efficacy prediction result of each time node, and in the process of obtaining the drug efficacy prediction result, the analysis result is considered from multiple dimensions, so that the accuracy of the drug efficacy prediction result is improved.
In other alternative embodiments, the method further comprises:
extracting a data set before the user is ill from the original data set;
extracting features of the data set to obtain a fourth target feature set, wherein the fourth target feature set comprises a second common component feature set and a second key component feature set;
Extracting a fifth target feature set from the fourth target feature set;
performing cluster analysis on the fifth target feature set to obtain a second signal path;
inputting the data set and the second signal path into a pre-trained heterogeneous graph neural network model to obtain a disease prediction result of the user.
In this embodiment, the fifth target feature set includes a feature set extracted from the second common component feature set of the fourth target feature set and a feature set extracted from the second key component feature set of the fourth target feature set, where features in the fifth target feature set represent features having a large influence on the onset, and a plurality of classes composed of similar features are analyzed by performing cluster analysis on the features to obtain the second signal path.
In other optional embodiments, a heterogeneous graph neural network model may be trained in advance, where the heterogeneous graph neural network model is used to predict the risk of developing an autoimmune disease, and after obtaining an original dataset before developing a disease of a user, the dataset is input into the heterogeneous graph neural network model to obtain a predicted result of developing the disease of the user, where the predicted result of developing the disease of the user includes the predicted probability of developing the disease.
In an alternative embodiment, before inputting the dataset and the second signal path into a pre-trained heterogeneous graph neural network model to obtain a morbidity prediction result for the user, the method further comprises:
acquiring a plurality of users and historical data of each user before morbidity;
acquiring a heterogeneous graph corresponding to the heterogeneous medical knowledge graph of the historical data;
acquiring a signal path with interactive relation with the heterogeneous graph;
taking a plurality of historical data and signal paths of the plurality of users as a training set;
training the pre-trained heterogeneous graph neural network model according to the training set to obtain the heterogeneous graph neural network model.
In this embodiment, the heterogeneous medical knowledge graph method is used to predict the risk of autoimmune disease, specifically, the known knowledge graph of signal paths is composed of n+1 heterogeneous graphs, where N is the signal path having an interaction relationship with the heterogeneous graphs, and for example, the heterogeneous graphs may include one or more of the following combinations: a directed graph of protein-protein interactions; a relational heterogram between small molecule metabolites; different patterns of relationships between gene expression; protein-modified relational maps; an isomerism map of the relationship between intestinal flora; directed graph of the interrelationship between biosignal pathways. Wherein, there is a cross relationship between n+1 isomerism patterns, i.e. there is a cross relationship between proteins, small molecule metabolites, genes, protein modification sites, intestinal flora and biological signal pathways, and there is a side connection between each subclass pattern in the isomerism medical knowledge patterns and the autoimmune disease and TNF antagonist curative effects. Training of the heterogeneous map neural network model is performed based on the pre-onset data set (such as proteins, small molecules, genes and the like) of the user and the characteristics of the second signal pathway, which are extracted from the original data set, and data of different time nodes are distinguished, namely, prediction of autoimmune disease onset risk and treatment effects of the TNF antagonist on the different time nodes is achieved through multiple sets of mathematical data input.
In the embodiment, the disease risk prediction is performed by adopting the isomerism map corresponding to the isomerism medical knowledge graph, so that the disease prediction performance is enhanced, the influence of insufficient data and data deviation is made up, the matching degree of the disease prediction result and clinical knowledge is improved, and the accuracy of the disease prediction result is improved.
In summary, according to the artificial intelligence-based drug efficacy prediction method of the present embodiment, the second target feature set and the third target feature set, which have a greater influence on drug efficacy prediction, are considered by extracting the second target feature set from the first common component feature set of each time node and extracting the third target feature set from the first key component feature set of each time node, so that the accuracy of drug efficacy prediction is improved. The second target feature set and the third target feature set of each time node are respectively analyzed to obtain an analysis result of the first signal path of the corresponding time node, the analysis result of the first signal path of each time node, the second target feature set, the third target feature set and the corresponding medicine curative effect result are input into a pre-trained time sequence prediction model to obtain a medicine curative effect prediction result of each time node, and in the process of obtaining the medicine curative effect prediction result, consideration is carried out from multiple dimensions, so that the accuracy of the medicine curative effect prediction result is improved.
Example two
Fig. 2 is a block diagram of an artificial intelligence-based drug efficacy prediction device according to a second embodiment of the present invention.
In some embodiments, the artificial intelligence based drug efficacy prediction device 20 may include a plurality of functional modules comprised of program code segments. Program code for each of the program segments in the artificial intelligence based drug efficacy prediction apparatus 20 may be stored in a memory of an electronic device and executed by the at least one processor to perform (see fig. 1 for details) the functions of artificial intelligence based drug efficacy prediction.
In this embodiment, the drug efficacy prediction device 20 based on artificial intelligence may be divided into a plurality of functional modules according to the functions performed by the device. The functional module may include: the device comprises an acquisition module 201, a first extraction module 202, a second extraction module 203, an analysis module 204 and an input module 205. The module referred to herein is a series of computer readable instructions capable of being executed by at least one processor and of performing a fixed function, stored in a memory. In the present embodiment, the functions of the respective modules will be described in detail in the following embodiments.
An acquisition module 201 is configured to acquire an original data set of a user, where the original data set includes a plurality of time-series data sets from before-medication to a plurality of time nodes in a medication process of the user.
A first extraction module 202 is configured to perform feature extraction on the original data set to obtain a first target feature set, where the first target feature set includes a first common component feature set and a first key component feature set of each time node.
A second extraction module 203, configured to extract a second target feature set from the first common component feature set of each time node, and extract a third target feature set from the first key component feature set of each time node.
And the analysis module 204 is configured to analyze the second target feature set and the third target feature set of each time node respectively, so as to obtain an analysis result of the first signal path of the corresponding time node.
The input module 205 is configured to input the analysis result of the first signal path, the second target feature set, the third target feature set, and the corresponding drug efficacy result of each time node to a pre-trained time sequence prediction model, so as to obtain a drug efficacy prediction result of each time node.
In an alternative embodiment, the first extraction module 202 is configured to: carrying out standardization processing on the original data in the original data set to obtain a standardized matrix; calculating an average value of sample data of each sample in the normalization matrix; subtracting the corresponding average value from the sample data of each sample to obtain a target matrix; calculating a covariance matrix of the target matrix, and eigenvalues and eigenvectors of the covariance matrix; the feature values are ordered in a descending order, a plurality of feature values which are ordered in front are selected from the ordering result, and a plurality of feature vectors of the feature values are respectively used as row vectors to form a new feature vector matrix; and projecting the target matrix onto the new feature vector matrix to obtain a first target feature set.
In this embodiment, the first common component feature set and the first key component feature set of each time node are extracted from the original data set, so as to ensure that components can be orthogonal, that is, the components do not have information redundancy, the feature sets are represented to the greatest extent by using as few components as possible, the number of feature sets is reduced, and meanwhile, the first common component feature set and the first key component feature set are considered when the drug efficacy is predicted subsequently, so that the efficiency of the drug efficacy prediction is improved.
In an alternative embodiment, the analysis module 204 is configured to: performing enrichment analysis on the second target feature set and the third target feature set to obtain an enrichment analysis result; carrying out channel analysis on the enrichment analysis result to obtain a first signal channel; and performing cluster analysis on the first signal paths to obtain analysis results of the first signal paths corresponding to the time nodes.
In an optional embodiment, before the analysis result of the first signal path of each time node, the second target feature set, the third target feature set and the corresponding drug efficacy result are input into a pre-trained time sequence prediction model to obtain a drug efficacy prediction result of each time node, a historical sequence data set of a plurality of users is obtained, wherein the historical sequence data set of each user comprises historical sequence data of a plurality of time nodes from before-use to during-use of the user; extracting features of the historical sequence data set to obtain a first historical feature set, wherein the first historical feature set comprises a common component feature set and a key component feature set of each time node; extracting a second historical feature set from the common component feature set of each time node, and extracting a third historical feature set from the key component feature set of each time node; respectively analyzing the second historical feature set and the third historical feature set of each time node to obtain an analysis result of a historical signal path; taking analysis results of a plurality of historical signal paths of a plurality of time nodes of the plurality of users, a plurality of second historical feature sets, a plurality of third historical feature sets and corresponding medicament curative effect results as training sets; and training a preset graph neural network based on the training set to obtain a time sequence prediction model.
In this embodiment, the graph neural network is a deep learning method, and can implement prediction on nodes, edges or graphs. By training a preset graph neural network based on a training set, the variation difference of clinical phenotypes on different time nodes can be predicted, and the drug efficacy on the subsequent administration time nodes can be predicted based on the variation difference.
In this embodiment, the analysis result of the first signal path, the second target feature set, the third target feature set and the corresponding drug efficacy result of each time node are input into the pre-trained time sequence prediction model, so as to obtain the drug efficacy prediction result of each time node, and in the process of obtaining the drug efficacy prediction result, the analysis result is considered from multiple dimensions, so that the accuracy of the drug efficacy prediction result is improved.
In other alternative embodiments, the pre-user morbidity dataset is extracted from the raw dataset; extracting features of the data set to obtain a fourth target feature set, wherein the fourth target feature set comprises a second common component feature set and a second key component feature set; extracting a fifth target feature set from the fourth target feature set; performing cluster analysis on the fifth target feature set to obtain a second signal path; inputting the data set and the second signal path into a pre-trained heterogeneous graph neural network model to obtain a disease prediction result of the user.
In other optional embodiments, the heterogeneous graph neural network model may be trained in advance, and after the original dataset before the onset of the user is obtained, the onset prediction result of the user is obtained by inputting the dataset into the heterogeneous graph neural network model.
In an alternative embodiment, before inputting the data set and the second signal path into a pre-trained heterogeneous graph neural network model to obtain a disease prediction result of the user, acquiring a plurality of users and historical data before disease occurrence of each user; acquiring a heterogeneous graph corresponding to the heterogeneous medical knowledge graph of the historical data; acquiring a signal path with interactive relation with the heterogeneous graph; taking a plurality of historical data and signal paths of the plurality of users as a training set; training the pre-trained heterogeneous graph neural network model according to the training set to obtain the heterogeneous graph neural network model.
In the embodiment, the disease risk prediction is performed by adopting the isomerism map corresponding to the isomerism medical knowledge graph, so that the disease prediction performance is enhanced, the influence of insufficient data and data deviation is made up, the matching degree of the disease prediction result and clinical knowledge is improved, and the accuracy of the disease prediction result is improved.
In summary, according to the artificial intelligence-based drug efficacy prediction device of the present embodiment, the second target feature set and the third target feature set, which have a greater influence on drug efficacy prediction, are considered by extracting the second target feature set from the first common component feature set of each time node and extracting the third target feature set from the first key component feature set of each time node, so that the accuracy of drug efficacy prediction is improved. The second target feature set and the third target feature set of each time node are respectively analyzed to obtain an analysis result of the first signal path of the corresponding time node, the analysis result of the first signal path of each time node, the second target feature set, the third target feature set and the corresponding medicine curative effect result are input into a pre-trained time sequence prediction model to obtain a medicine curative effect prediction result of each time node, and in the process of obtaining the medicine curative effect prediction result, consideration is carried out from multiple dimensions, so that the accuracy of the medicine curative effect prediction result is improved.
Example III
Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention. In the preferred embodiment of the invention, the electronic device 3 comprises a memory 31, at least one processor 32, at least one communication bus 33 and a transceiver 34.
It will be appreciated by those skilled in the art that the configuration of the electronic device shown in fig. 3 is not limiting of the embodiments of the present invention, and that either a bus-type configuration or a star-type configuration is possible, and that the electronic device 3 may also include more or less other hardware or software than that shown, or a different arrangement of components.
In some embodiments, the electronic device 3 is an electronic device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and its hardware includes, but is not limited to, a microprocessor, an application specific integrated circuit, a programmable gate array, a digital processor, an embedded device, and the like. The electronic device 3 may further include a client device, where the client device includes, but is not limited to, any electronic product that can interact with a client by way of a keyboard, a mouse, a remote control, a touch pad, or a voice control device, such as a personal computer, a tablet computer, a smart phone, a digital camera, etc.
It should be noted that the electronic device 3 is only used as an example, and other electronic products that may be present in the present invention or may be present in the future are also included in the scope of the present invention by way of reference.
In some embodiments, the memory 31 is used to store program code and various data, such as an artificial intelligence based drug efficacy prediction device 20 installed in the electronic device 3, and to enable high speed, automated access to programs or data during operation of the electronic device 3. The Memory 31 includes Read-Only Memory (ROM), programmable Read-Only Memory (PROM), erasable programmable Read-Only Memory (EPROM), one-time programmable Read-Only Memory (One-time Programmable Read-Only Memory, OTPROM), electrically erasable rewritable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disc Memory, magnetic tape Memory, or any other medium that can be used for computer-readable carrying or storing data.
In some embodiments, the at least one processor 32 may be comprised of an integrated circuit, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The at least one processor 32 is a Control Unit (Control Unit) of the electronic device 3, connects the respective components of the entire electronic device 3 using various interfaces and lines, and executes various functions of the electronic device 3 and processes data by running or executing programs or modules stored in the memory 31 and calling data stored in the memory 31.
In some embodiments, the at least one communication bus 33 is arranged to enable connected communication between the memory 31 and the at least one processor 32 or the like.
Although not shown, the electronic device 3 may further include a power source (such as a battery) for powering the various components, and optionally, the power source may be logically connected to the at least one processor 32 via a power management device, thereby implementing functions such as managing charging, discharging, and power consumption by the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 3 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The integrated units implemented in the form of software functional modules described above may be stored in a computer readable storage medium. The software functional modules described above are stored in a storage medium and include instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device, etc.) or a processor (processor) to perform portions of the methods described in the various embodiments of the invention.
In a further embodiment, in connection with fig. 2, the at least one processor 32 may execute the operating means of the electronic device 3 as well as various installed applications (e.g., the artificial intelligence based drug efficacy prediction device 20), program code, etc., such as the various modules described above.
The memory 31 has program code stored therein, and the at least one processor 32 can invoke the program code stored in the memory 31 to perform related functions. For example, the various modules depicted in FIG. 2 are program code stored in the memory 31 and executed by the at least one processor 32 to perform the functions of the various modules for the purpose of artificial intelligence-based drug efficacy prediction.
Illustratively, the program code may be partitioned into one or more modules/units that are stored in the memory 31 and executed by the processor 32 to complete the present application. The one or more modules/units may be a series of computer readable instruction segments capable of performing the specified functions, which instruction segments describe the execution of the program code in the electronic device 3. For example, the program code may be divided into an acquisition module 201, a first extraction module 202, a second extraction module 203, an analysis module 204, and an input module 205.
In one embodiment of the invention, the memory 31 stores a plurality of computer readable instructions that are executed by the at least one processor 32 to implement the functionality of artificial intelligence based drug efficacy prediction.
Specifically, the specific implementation method of the above instruction by the at least one processor 32 may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it will be obvious that the term "comprising" does not exclude other elements or that the singular does not exclude a plurality. The units or means stated in the invention may also be implemented by one unit or means, either by software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. An artificial intelligence-based drug efficacy prediction method, comprising:
acquiring an original data set of a user, wherein the original data set comprises a plurality of time sequence data sets from before-medication to a plurality of time nodes in a medication process of the user;
extracting features of the original data set to obtain a first target feature set, wherein the first target feature set comprises a first public component feature set and a first key component feature set of each time node;
extracting a second target feature set from the first common component feature set of each time node, and extracting a third target feature set from the first key component feature set of each time node;
respectively analyzing the second target feature set and the third target feature set of each time node to obtain an analysis result of the first signal path of the corresponding time node;
And inputting the analysis result of the first signal path, the second target feature set, the third target feature set and the corresponding medicine curative effect result of each time node into a pre-trained time sequence prediction model to obtain the medicine curative effect prediction result of each time node.
2. The method of claim 1, wherein the analyzing the second target feature set and the third target feature set of each time node to obtain the analysis result of the first signal path of the corresponding time node comprises:
performing enrichment analysis on the second target feature set and the third target feature set to obtain an enrichment analysis result;
carrying out channel analysis on the enrichment analysis result to obtain a first signal channel;
and performing cluster analysis on the first signal paths to obtain analysis results of the first signal paths corresponding to the time nodes.
3. The artificial intelligence based drug efficacy prediction method according to claim 1, wherein the raw data set comprises: gene expression data, miRNA expression data, DNA methylation data, proteomic data, protein modification histologic data, metabonomic data, intestinal flora 16sRNA data.
4. The artificial intelligence based drug efficacy prediction method according to claim 1, wherein before inputting the analysis result of the first signal path, the second target feature set, the third target feature set and the corresponding drug efficacy result of each time node into the pre-trained time series prediction model, the method further comprises:
acquiring a plurality of user history sequence data sets, wherein each user history sequence data set comprises history sequence data of a plurality of time nodes from before the user takes a medicine to the medicine taking process;
extracting features of the historical sequence data set to obtain a first historical feature set, wherein the first historical feature set comprises a common component feature set and a key component feature set of each time node;
extracting a second historical feature set from the common component feature set of each time node, and extracting a third historical feature set from the key component feature set of each time node;
respectively analyzing the second historical feature set and the third historical feature set of each time node to obtain an analysis result of a historical signal path;
Taking analysis results of a plurality of historical signal paths of a plurality of time nodes of the plurality of users, a plurality of second historical feature sets, a plurality of third historical feature sets and corresponding medicament curative effect results as training sets;
and training a preset graph neural network based on the training set to obtain a time sequence prediction model.
5. The artificial intelligence based drug efficacy prediction method of claim 1, wherein the performing feature extraction on the raw dataset to obtain a first target feature set comprises:
carrying out standardization processing on the original data in the original data set to obtain a standardized matrix;
calculating an average value of sample data of each sample in the normalization matrix;
subtracting the corresponding average value from the sample data of each sample to obtain a target matrix;
calculating a covariance matrix of the target matrix, and eigenvalues and eigenvectors of the covariance matrix;
the feature values are ordered in a descending order, a plurality of feature values which are ordered in front are selected from the ordering result, and a plurality of feature vectors of the feature values are respectively used as row vectors to form a new feature vector matrix;
and projecting the target matrix onto the new feature vector matrix to obtain a first target feature set.
6. The artificial intelligence based drug efficacy prediction method according to claim 1, wherein the method further comprises:
extracting a data set before the user is ill from the original data set;
extracting features of the data set to obtain a fourth target feature set, wherein the fourth target feature set comprises a second common component feature set and a second key component feature set;
extracting a fifth target feature set from the fourth target feature set;
performing cluster analysis on the fifth target feature set to obtain a second signal path;
inputting the data set and the second signal path into a pre-trained heterogeneous graph neural network model to obtain a disease prediction result of the user.
7. The artificial intelligence based drug efficacy prediction method according to claim 6, wherein before inputting the data set and the second signal path into a pre-trained heterogeneous graph neural network model to obtain the predicted outcome of the user's morbidity, the method further comprises:
acquiring a plurality of users and historical data of each user before morbidity;
acquiring a heterogeneous graph corresponding to the heterogeneous medical knowledge graph of the historical data;
Acquiring a signal path with interactive relation with the heterogeneous graph;
taking a plurality of historical data and signal paths of the plurality of users as a training set;
training the pre-trained heterogeneous graph neural network model according to the training set to obtain the heterogeneous graph neural network model.
8. An artificial intelligence based drug efficacy prediction device, the device comprising:
the acquisition module is used for acquiring an original data set of a user, wherein the original data set comprises a plurality of time sequence data sets from the time before the user takes the medicine to a plurality of time nodes in the medicine taking process;
the first extraction module is used for extracting features of the original data set to obtain a first target feature set, wherein the first target feature set comprises a first public component feature set and a first key component feature set of each time node;
the second extraction module is used for extracting a second target feature set from the first common component feature set of each time node and extracting a third target feature set from the first key component feature set of each time node;
the analysis module is used for respectively analyzing the second target feature set and the third target feature set of each time node to obtain an analysis result of the first signal path of the corresponding time node;
The input module is used for inputting the analysis result of the first signal path, the second target feature set, the third target feature set and the corresponding medicine curative effect result of each time node into a pre-trained time sequence prediction model to obtain the medicine curative effect prediction result of each time node.
9. An electronic device comprising a processor and a memory, wherein the processor is configured to implement the artificial intelligence based drug efficacy prediction method of any one of claims 1 to 7 when executing a computer program stored in the memory.
10. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the artificial intelligence based drug efficacy prediction method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310330024.2A CN116524995A (en) | 2023-03-24 | 2023-03-24 | Medicine curative effect prediction method based on artificial intelligence and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310330024.2A CN116524995A (en) | 2023-03-24 | 2023-03-24 | Medicine curative effect prediction method based on artificial intelligence and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116524995A true CN116524995A (en) | 2023-08-01 |
Family
ID=87393084
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310330024.2A Pending CN116524995A (en) | 2023-03-24 | 2023-03-24 | Medicine curative effect prediction method based on artificial intelligence and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116524995A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117079762A (en) * | 2023-09-25 | 2023-11-17 | 腾讯科技（深圳）有限公司 | Drug effect prediction model training method, drug effect prediction method and device thereof |
| CN117747121A (en) * | 2023-12-19 | 2024-03-22 | 首都医科大学宣武医院 | Diabetes risk prediction system based on multiple models |
-
2023
- 2023-03-24 CN CN202310330024.2A patent/CN116524995A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117079762A (en) * | 2023-09-25 | 2023-11-17 | 腾讯科技（深圳）有限公司 | Drug effect prediction model training method, drug effect prediction method and device thereof |
| CN117079762B (en) * | 2023-09-25 | 2024-01-23 | 腾讯科技（深圳）有限公司 | Drug effect prediction model training method, drug effect prediction method and device thereof |
| CN117747121A (en) * | 2023-12-19 | 2024-03-22 | 首都医科大学宣武医院 | Diabetes risk prediction system based on multiple models |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10930372B2 (en) | Solution for drug discovery | |
| CN116524995A (en) | Medicine curative effect prediction method based on artificial intelligence and related equipment | |
| CN110929752B (en) | Grouping method based on knowledge driving and data driving and related equipment | |
| CN112700838A (en) | Big data-based medication scheme recommendation method and device and related equipment | |
| Yadav et al. | Detection of common risk factors for diagnosis of cardiac arrhythmia using machine learning algorithm | |
| CN111145910A (en) | Abnormal case identification method and device based on artificial intelligence and computer equipment | |
| CN112216361A (en) | Follow-up plan list generation method, device, terminal and medium based on artificial intelligence | |
| WO2017017554A1 (en) | Reliability measurement in data analysis of altered data sets | |
| EP3338211A1 (en) | Multi-level architecture of pattern recognition in biological data | |
| CN113870974A (en) | Risk prediction method and device based on artificial intelligence, electronic equipment and medium | |
| CN111833984A (en) | Medicine quality control analysis method, device, equipment and medium based on machine learning | |
| CN113658662A (en) | Medicine dispensing method, device, equipment and storage medium based on big medication data | |
| CN114220541A (en) | Disease prediction method, disease prediction device, electronic device, and storage medium | |
| CN113744845A (en) | Medical image processing method, device, equipment and medium based on artificial intelligence | |
| CN112530602A (en) | Method and device for analyzing side effect of medicine, electronic equipment and computer storage medium | |
| CN116129988B (en) | Model construction method, device, equipment and medium | |
| CN111933246A (en) | Medical prescription analysis method, system, electronic device and storage medium | |
| CN111916202A (en) | Clinical decision support equipment and method based on reinforcement learning | |
| Ebada et al. | Applying cloud based machine learning on biosensors streaming data for health status prediction | |
| CN113436743B (en) | Representation learning-based multi-outcome efficacy prediction method, device and storage medium | |
| CN113963413A (en) | Epidemic situation investigation method and device based on artificial intelligence, electronic equipment and medium | |
| CN113990514A (en) | Abnormality detection device for doctor diagnosis and treatment behavior, computer device and storage medium | |
| CN116130117B (en) | Access database-based method and device for realizing administration of anticoagulant drugs | |
| CN113066531A (en) | Risk prediction method and device, computer equipment and storage medium | |
| CN113808731A (en) | Intelligent medical diagnosis system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |