CN111009316A - Doctor-patient matching method based on Bayesian network - Google Patents

Doctor-patient matching method based on Bayesian network Download PDF

Info

Publication number
CN111009316A
CN111009316A CN201911356327.1A CN201911356327A CN111009316A CN 111009316 A CN111009316 A CN 111009316A CN 201911356327 A CN201911356327 A CN 201911356327A CN 111009316 A CN111009316 A CN 111009316A
Authority
CN
China
Prior art keywords
disease
patient
doctor
bayesian network
matching
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.)
Granted
Application number
CN201911356327.1A
Other languages
Chinese (zh)
Other versions
CN111009316B (en
Inventor
李德彪
陈思平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fuzhou University
Original Assignee
Fuzhou University
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 Fuzhou University filed Critical Fuzhou University
Priority to CN201911356327.1A priority Critical patent/CN111009316B/en
Publication of CN111009316A publication Critical patent/CN111009316A/en
Application granted granted Critical
Publication of CN111009316B publication Critical patent/CN111009316B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/29—Graphical models, e.g. Bayesian networks
    • 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

Abstract

The invention relates to a doctor-patient matching method based on a Bayesian network, which comprises the following steps: step S1: collecting electronic medical record data, determining disease and symptom nodes and values thereof, and using the nodes and the values as training set data; step S2, constructing a disease-disease/disease-symptom self-interaction matrix as a constraint of the Bayesian network; step S3, constructing a Bayesian network model, and performing structure learning and parameter learning; step S4, the patient inputs the disease into a Bayesian network pre-diagnosis model to obtain all possible disease combinations for calculating the complication of the main disease and the complication; step S5 calculating matching index of doctor and patient step S6, constructing doctor recommendation model based on matching index of doctor and patient; and step S7, obtaining the optimal allocation of the patient and the doctor according to the patient preference index. The invention combines the pre-diagnosis result, the expertise of doctors, the workload of doctors and the preference of patients to carry out doctor-patient matching, and solves the defect that the existing doctor-patient matching technology is not accurate enough.

Description

Doctor-patient matching method based on Bayesian network
Technical Field
The invention relates to the field of doctor-patient matching, in particular to a doctor-patient matching method based on a Bayesian network.
Background
The doctor-patient matching technology which is disclosed and used at present mainly focuses on the fields of intelligent diagnosis guidance, doctor recommendation and the like, for example, an intelligent diagnosis guidance AI engine developed by Tencent corporation has the advantages of clear and informed, and aims to extract rich medical knowledge from massive documents, reason the corresponding relation between symptoms and diseases and establish an expert system for disease pre-diagnosis; the purpose of extracting the disease condition of the patient is achieved through an interpersonal interactive intelligent inquiry system; and finally, doctor recommendation is carried out by integrating doctor expertise information. The technology can give accurate doctor recommendations to patients, so that the medical service quality is improved, and the technology is one of the newly-rising intelligent medical technologies. The problem of blind selection of patients for doctors is a challenge to medical resources which are in tension today, and the technology does not consider reasonable allocation of medical resources and cannot fundamentally solve the problem.
Disclosure of Invention
In view of this, the invention aims to provide a doctor-patient matching method based on a bayesian network, which combines the pre-diagnosis result, the expertise of a doctor, the workload of the doctor and the preference of a patient to match the doctor and the patient, and solves the defect that the existing doctor-patient matching technology is not accurate enough.
In order to achieve the purpose, the invention adopts the following technical scheme:
a doctor-patient matching method based on a Bayesian network comprises the following steps:
step S1: collecting words for diseases and symptoms in electronic medical record data, summarizing the disease symptoms, determining nodes and values of the diseases and symptoms, and using the nodes and the values as training set data;
step S2, constructing a disease-disease/disease-symptom self-interaction matrix as a constraint of the Bayesian network;
step S3, constructing a Bayesian network model, and performing structure learning and parameter learning to obtain a complete Bayesian network pre-diagnosis model;
step S4, the patient inputs the disease into a Bayesian network pre-diagnosis model to obtain all possible disease combinations for calculating the complication of the main disease and the complication;
step S5, calculating the matching index of the doctor and the patient according to all possible disease combinations of the complication of the main disease and the complication;
step S6, constructing a doctor recommendation model based on the matching indexes of the doctor and the patient;
and step S7, obtaining the optimal allocation of the patients and the doctors according to the patient preference index based on the doctor recommendation model.
Further, the value of the connected disease/symptom elements in the 'disease-disease/disease-symptom' self-interaction matrix is 1, the value of the irrelevant elements is-1, and the value of the unknown part is 0;
wherein: the connected relation is converted into an initial network structure of the Bayesian network, and the irrelevant relation is converted into a search forbidden part of the Bayesian network.
Further, the bayesian network structure learning adopts a heuristic algorithm based on tabu search, specifically:
the AIC score is chosen as the objective function for optimization, which is formulated as follows:
Figure BDA0002336029840000021
wherein r ismIs the total number of all values that the node m may take, qmIs the total amount of all possible combinations of possible values of the father node, and the number of the nodes is nm; n is a radical ofmjkWhen the jth sampling value is taken for the father node of the node m, the value of the node m is the total amount of k quantity; n is a radical ofmjN being all possible values for mmjkSumming; (N) is a function for measuring the information quantity of the nodes in the graph, and 1 is taken from the AIC score; c (G) is used for measuring the complexity of the graph, and the calculation formula is as follows:
Figure BDA0002336029840000031
the length of a parameter tabu table of emergency search is determined as the number nm of nodes, and the search stopping condition is that the optimal objective function value is not updated for 100 iterations.
Further, the Bayesian network parameter learning requires computing a conditional profile of each nodeRate thetamjkAnd its conditional probability table, using maximum likelihood estimation method,
the formula for calculating the parameters is as follows:
Figure BDA0002336029840000032
wherein N ismjkWhen the jth sampling value is taken for the father node of the node m, the value of the node m is the total amount of k quantity; n is a radical ofmjN being all possible values for mmjkAnd (6) summing.
Further, the step S4 is specifically:
after the patient inputs symptoms, the model calculates all possible disease combinations of the main disease and complication complications, thereby obtaining more accurate depiction of the patient's condition. The calculation formula is as follows:
Figure BDA0002336029840000033
and obtaining a conditional probability matrix of all disease combinations of the patient based on the calculated disease conditional probability.
Further, the matching index calculation of doctor and patient measures the matching degree of the disease status of patient i and the expertise of doctor p, and the calculation formula is as follows:
Figure BDA0002336029840000041
wherein Eidd′The degree of expertise for a certain combination of diseases is quantified using the following formula:
Epdd′＝αypd+(1-α)ypd′
wherein y ispdIs a 0-1 variable indicating whether doctor p is specialized for disease d, α being the weight between the primary disease and complications.
Compared with the prior art, the invention has the following beneficial effects:
the invention combines the pre-diagnosis result, the expertise of doctors, the workload of doctors and the preference of patients to carry out doctor-patient matching, and solves the defect that the existing doctor-patient matching technology is not accurate enough.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The invention is further explained below with reference to the drawings and the embodiments.
Referring to fig. 1, the present invention provides a doctor-patient matching method based on bayesian network, comprising the following steps:
step S1: collecting words for diseases and symptoms in the electronic medical record data, summarizing the disease symptoms, determining nodes of the diseases and the symptoms and values of the nodes to reduce the total number of the nodes, and thus obtaining data for pre-diagnosis Bayesian network training;
s2, constructing a disease-disease/disease-symptom self-interaction matrix, wherein values of connected disease/symptom elements are 1, values of irrelevant elements are-1, and values of unknown parts are 0; wherein: the relation with the relation is converted into an initial network structure of the Bayesian network, and the irrelevant relation is converted into a search forbidden part of the Bayesian network;
step S3, constructing a Bayesian network model, and performing structure learning and parameter learning to obtain a complete Bayesian network pre-diagnosis model;
step S4, the patient inputs the disease into a Bayesian network pre-diagnosis model to obtain all possible disease combinations for calculating the complication of the main disease and the complication;
step S5, calculating the matching index of the doctor and the patient according to all possible disease combinations of the complication of the main disease and the complication;
step S6, constructing a doctor recommendation model based on the matching indexes of the doctor and the patient;
and step S7, obtaining the optimal allocation of the patients and the doctors according to the patient preference index based on the doctor recommendation model.
In this embodiment, the bayesian network structure learning adopts a heuristic algorithm based on tabu search, specifically:
the AIC score is chosen as the objective function for optimization, which is formulated as follows:
Figure BDA0002336029840000051
wherein r ismIs the total number of all values that the node m may take, qmIs the total amount of all possible combinations of possible values of the father node, and the number of the nodes is nm; n is a radical ofmjkWhen the jth sampling value is taken for the father node of the node m, the value of the node m is the total amount of k quantity; n is a radical ofmjN being all possible values for mmjkSumming; (N) is a function for measuring the information quantity of the nodes in the graph, and 1 is taken from the AIC score; c (G) is used for measuring the complexity of the graph, and the calculation formula is as follows:
Figure BDA0002336029840000061
the length of a parameter tabu table of emergency search is determined as the number nm of nodes, and the search stopping condition is that the optimal objective function value is not updated for 100 iterations.
In this embodiment, the bayesian network parameter learning requires calculating the conditional probability θ of each nodemjkAnd its conditional probability table, using maximum likelihood estimation method,
the formula for calculating the parameters is as follows:
Figure BDA0002336029840000064
wherein N ismjkWhen the jth sampling value is taken for the father node of the node m, the value of the node m is the total amount of k quantity; n is a radical ofmjN being all possible values for mmjkAnd (6) summing.
Further, the step S4 is specifically:
after the patient inputs symptoms, the model calculates all possible disease combinations of the main disease and complication complications, thereby obtaining more accurate depiction of the patient's condition. The calculation formula is as follows:
Figure BDA0002336029840000062
and obtaining a conditional probability matrix of all disease combinations of the patient based on the calculated disease conditional probability.
In this embodiment, the matching index calculation of doctor and patient measures the matching degree between the disease status of patient i and the expertise of doctor p, and the calculation formula is as follows:
Figure BDA0002336029840000063
wherein Eidd′The degree of expertise for a certain combination of diseases is quantified using the following formula:
Epdd′＝αypd+(1-α)ypd′
wherein y ispdIs a 0-1 variable indicating whether doctor p is specialized for disease d, α being the weight between the primary disease and complications.
In this embodiment, the doctor-patient matching model is a model that is built based on patient preferences and physician workload in the case where multiple patients seek matching in the system. The model defines a Patient Preference Index (PPI) to measure the preference degree of a patient for a doctor, and a Weighted Matching Index (WMI) is obtained by a method of weighted average with the doctor matching index.
A patient preference index PPI is defined, whose formula is calculated, for example, with the patient's preference for physician, as follows:
Figure BDA0002336029840000071
wherein gamma is ∈ [0,1 ]]For representing a patient's preferred cost metric to the physician. When gamma isi1, indicates that patient i is not sensitive to the physician's head portrait preference, so PPI assigns physician-patient matching, as it doesip1. When gamma isi0 means that patient i is extremely sensitive to the preference of the doctor's avatar, PPI only when assigned to the chief doctorip＝1。
To balance patient matching index and patient preference, weighted matching index is definedNumber WMIipThe formula is as follows:
WMIip＝β·PMIip+(1-β)·PPIip
the disease matching index calculated as above can measure the matching degree of the doctor expertise and the patient disease state, and after the matching degree of all doctors to the patient is calculated, the highest PMI can be usedipOr WMIipDoctor recommendations for top-n can be made.
Considering the constraint of the number of doctor visits per day, the system is optimized by simply basing on the first-come-first-serve principle or building a knapsack model. The system optimization of the backpack model needs to be carried out in view of doctor-patient matching within a period t, and the period t can be debugged according to the actual condition of a hospital.
The above description is only a preferred embodiment of the present invention, and all equivalent changes and modifications made in accordance with the claims of the present invention should be covered by the present invention.

Claims (6)

1. A doctor-patient matching method based on a Bayesian network is characterized by comprising the following steps:
step S1: collecting words for diseases and symptoms in electronic medical record data, summarizing the disease symptoms, determining nodes and values of the diseases and symptoms, and using the nodes and the values as training set data;
step S2, constructing a disease-disease/disease-symptom self-interaction matrix as a constraint of the Bayesian network;
step S3, constructing a Bayesian network model, and performing structure learning and parameter learning to obtain a complete Bayesian network pre-diagnosis model;
step S4, the patient inputs the disease into a Bayesian network pre-diagnosis model to obtain all possible disease combinations for calculating the complication of the main disease and the complication;
step S5, calculating the matching index of the doctor and the patient according to all possible disease combinations of the complication of the main disease and the complication;
step S6, constructing a doctor recommendation model based on the matching indexes of the doctor and the patient;
and step S7, obtaining the optimal allocation of the patients and the doctors according to the patient preference index based on the doctor recommendation model.
2. The bayesian network based doctor-patient matching method according to claim 1, wherein: the value among the connected disease/symptom elements in the 'disease-disease/disease-symptom' self-interaction matrix is 1, the value of irrelevant elements is-1, and the value of the unknown part is 0;
wherein: the connected relation is converted into an initial network structure of the Bayesian network, and the irrelevant relation is converted into a search forbidden part of the Bayesian network.
3. The doctor-patient matching method based on bayesian network according to claim 1, wherein the bayesian network structure learning adopts a heuristic algorithm based on tabu search, specifically:
the AIC score is chosen as the objective function for optimization, which is formulated as follows:
Figure FDA0002336029830000021
wherein r ismIs the total number of all values that the node m may take, qmIs the total amount of all possible combinations of possible values of the father node, and the number of the nodes is nm; n is a radical ofmjkWhen the jth sampling value is taken for the father node of the node m, the value of the node m is the total amount of k quantity; n is a radical ofmjN being all possible values for mmjkSumming; (N) is a function for measuring the information quantity of the nodes in the graph, and 1 is taken from the AIC score; c (G) is used for measuring the complexity of the graph, and the calculation formula is as follows:
Figure FDA0002336029830000022
the length of a parameter tabu table of emergency search is determined as the number nm of nodes, and the search stopping condition is that the optimal objective function value is not updated for 100 iterations.
4. Root of herbaceous plantThe Bayesian network-based doctor-patient matching method as recited in claim 1, wherein the Bayesian network parameter learning requires calculation of a conditional probability θ for each nodemjkAnd its conditional probability table, using maximum likelihood estimation method,
the formula for calculating the parameters is as follows:
Figure FDA0002336029830000023
wherein N ismjkWhen the jth sampling value is taken for the father node of the node m, the value of the node m is the total amount of k quantity; n is a radical ofmjN being all possible values for mmjkAnd (6) summing.
5. The doctor-patient matching method based on bayesian network according to claim 1, wherein the step S4 is specifically:
after the patient inputs symptoms, the model calculates all possible disease combinations of the main disease and complication complications, thereby obtaining more accurate depiction of the patient's condition. The calculation formula is as follows:
Figure FDA0002336029830000031
and obtaining a conditional probability matrix of all disease combinations of the patient based on the calculated disease conditional probability.
6. The Bayesian network-based doctor-patient matching method as recited in claim 5, wherein the doctor-patient matching index is calculated as a matching degree that measures the disease status of patient i and the expertise of doctor p, and is calculated according to the following formula:
Figure FDA0002336029830000032
wherein Eidd′The degree of expertise for a certain combination of diseases is quantified using the following formula:
Epdd′＝αypd+(1-α)ypd′
wherein y ispdIs a 0-1 variable indicating whether doctor p is specialized for disease d, α being the weight between the primary disease and complications.
CN201911356327.1A 2019-12-25 2019-12-25 Doctor-patient matching method based on Bayesian network Active CN111009316B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911356327.1A CN111009316B (en) 2019-12-25 2019-12-25 Doctor-patient matching method based on Bayesian network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911356327.1A CN111009316B (en) 2019-12-25 2019-12-25 Doctor-patient matching method based on Bayesian network

Publications (2)

Publication Number Publication Date
CN111009316A true CN111009316A (en) 2020-04-14
CN111009316B CN111009316B (en) 2022-06-21

Family

ID=70118309

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911356327.1A Active CN111009316B (en) 2019-12-25 2019-12-25 Doctor-patient matching method based on Bayesian network

Country Status (1)

Country Link
CN (1) CN111009316B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111539866A (en) * 2020-04-28 2020-08-14 湖南创星科技股份有限公司 Emergency rescue remote medical support service system
CN111554387A (en) * 2020-04-26 2020-08-18 医渡云（北京）技术有限公司 Doctor information recommendation method and device, storage medium and electronic equipment
CN116386856A (en) * 2023-06-05 2023-07-04 之江实验室 Multi-label disease auxiliary diagnosis system based on doctor decision mode identification

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105512981A (en) * 2014-09-22 2016-04-20 北京朱李叶健康科技有限公司 System and method for medical service supply and demand matching based on network
CN106227880A (en) * 2016-08-01 2016-12-14 挂号网（杭州）科技有限公司 Doctor searches for the implementation method of recommendation
CN106951719A (en) * 2017-04-10 2017-07-14 荣科科技股份有限公司 The construction method and constructing system of clinical diagnosis model, clinical diagnosing system
KR101830314B1 (en) * 2017-07-26 2018-02-20 재단법인 구미전자정보기술원 A method of providing information for the diagnosis of pancreatic cancer using bayesian network based on artificial intelligence, computer program, and computer-readable recording media using the same
CN108565019A (en) * 2018-04-13 2018-09-21 合肥工业大学 Multidisciplinary applicable clinical examination combined recommendation method and device
CN108922608A (en) * 2018-06-13 2018-11-30 平安医疗科技有限公司 Intelligent hospital guide's method, apparatus, computer equipment and storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105512981A (en) * 2014-09-22 2016-04-20 北京朱李叶健康科技有限公司 System and method for medical service supply and demand matching based on network
CN106227880A (en) * 2016-08-01 2016-12-14 挂号网（杭州）科技有限公司 Doctor searches for the implementation method of recommendation
CN106951719A (en) * 2017-04-10 2017-07-14 荣科科技股份有限公司 The construction method and constructing system of clinical diagnosis model, clinical diagnosing system
KR101830314B1 (en) * 2017-07-26 2018-02-20 재단법인 구미전자정보기술원 A method of providing information for the diagnosis of pancreatic cancer using bayesian network based on artificial intelligence, computer program, and computer-readable recording media using the same
CN108565019A (en) * 2018-04-13 2018-09-21 合肥工业大学 Multidisciplinary applicable clinical examination combined recommendation method and device
CN108922608A (en) * 2018-06-13 2018-11-30 平安医疗科技有限公司 Intelligent hospital guide's method, apparatus, computer equipment and storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
杨晓夫等: "基于电子病历利用矩阵乘法构建医生推荐模型", 《计算机与现代化》 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111554387A (en) * 2020-04-26 2020-08-18 医渡云（北京）技术有限公司 Doctor information recommendation method and device, storage medium and electronic equipment
CN111554387B (en) * 2020-04-26 2023-05-23 医渡云（北京）技术有限公司 Doctor information recommendation method and device, storage medium and electronic equipment
CN111539866A (en) * 2020-04-28 2020-08-14 湖南创星科技股份有限公司 Emergency rescue remote medical support service system
CN111539866B (en) * 2020-04-28 2024-03-01 湖南创星科技股份有限公司 Emergency rescue remote medical support service system
CN116386856A (en) * 2023-06-05 2023-07-04 之江实验室 Multi-label disease auxiliary diagnosis system based on doctor decision mode identification
CN116386856B (en) * 2023-06-05 2023-10-20 之江实验室 Multi-label disease auxiliary diagnosis system based on doctor decision mode identification

Also Published As

Publication number Publication date
CN111009316B (en) 2022-06-21

Similar Documents

Publication Publication Date Title
CN111009316B (en) Doctor-patient matching method based on Bayesian network
US20090093686A1 (en) Multi Automated Severity Scoring
Talmor et al. Simple triage scoring system predicting death and the need for critical care resources for use during epidemics
CN110051324B (en) Method and system for predicting death rate of acute respiratory distress syndrome
US20120265549A1 (en) System and Computer Readable Medium for Predicting Patient Outcomes
CN112204671A (en) Personalized device recommendation for active health monitoring and management
KR20160000522A (en) System and method of emergency telepsychiatry using emergency psychiatric mental state prediction model
US20210257095A1 (en) Medical machine learning system and method
WO2021073255A1 (en) Time series clustering-based medication reminder method and related device
CN113539460A (en) Intelligent diagnosis guiding method and device for remote medical platform
CN115798734B (en) New burst infectious disease prevention and control method and device based on big data and storage medium
KR20210112041A (en) Smart Healthcare Monitoring System and Method for Heart Disease Prediction Based On Ensemble Deep Learning and Feature Fusion
Mueller et al. Predicting extubation outcome in preterm newborns: a comparison of neural networks with clinical expertise and statistical modeling
CN116525117B (en) Data distribution drift detection and self-adaption oriented clinical risk prediction system
Fansi Tchango et al. Towards trustworthy automatic diagnosis systems by emulating doctors' reasoning with deep reinforcement learning
Jiang et al. Assessing the impact of healthcare service risks on healthcare demand under evolving economic and social structures: An improved GLDS decision making method considering risk attitudes
Chen et al. A multi-channel convolutional neural network for ICD coding
Prasad Methods for reinforcement learning in clinical decision support
Joymangul et al. Data-oriented approach to improve adherence to cpap therapy during the initiation phase
Hamza et al. Smart Healthcare System Implementation Challenges: A stakeholder perspective
CN111524564A (en) Pneumonia clinical auxiliary monitoring method and system
Papayiannis et al. A functional supervised learning approach to the study of blood pressure data
EP4276843A1 (en) Method and system for automatically providing adapted electronic training plans to individuals of a targeted group of individuals
Shukla et al. MentalHealthAI: Utilizing Personal Health Device Data to Optimize Psychiatry Treatment
US20220223284A1 (en) Systems and methods for modelling a human subject

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
GR01 Patent grant
GR01 Patent grant