CN113192627A - Patient and disease bipartite graph-based readmission prediction method and system - Google Patents

Patient and disease bipartite graph-based readmission prediction method and system Download PDF

Info

Publication number
CN113192627A
CN113192627A CN202110396159.XA CN202110396159A CN113192627A CN 113192627 A CN113192627 A CN 113192627A CN 202110396159 A CN202110396159 A CN 202110396159A CN 113192627 A CN113192627 A CN 113192627A
Authority
CN
China
Prior art keywords
patient
patients
disease
bipartite graph
medical
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
Application number
CN202110396159.XA
Other languages
Chinese (zh)
Inventor
郭伟
黄浩哲
崔立真
刘志奇
鹿旭东
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.)
Shandong University
Original Assignee
Shandong 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 Shandong University filed Critical Shandong University
Priority to CN202110396159.XA priority Critical patent/CN113192627A/en
Publication of CN113192627A publication Critical patent/CN113192627A/en
Pending legal-status Critical Current

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
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • 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
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Epidemiology (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Primary Health Care (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The present disclosure provides a patient and disease bipartite graph-based readmission prediction model, comprising: acquiring historical medical data of patients, and serializing the medical events of each patient by using the timestamps of diseases based on the historical medical data to obtain medical event sequence sets of all patients; constructing a bipartite graph of the patients and the medical events based on the medical event sequence sets of all the patients, expressing the historical illness information of the patients and establishing indirect connection between the patients suffering from the same illness; processing the bipartite graph of the patients and the medical events by using an embedded generation algorithm to obtain a final vector representation of each patient; predicting a readmission behavior of the patient based on the final vector representation.

Description

Patient and disease bipartite graph-based readmission prediction method and system
Technical Field
The disclosure belongs to the technical field of computers, and particularly relates to a patient and disease bipartite graph-based readmission prediction method and system.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The study of a predictive model for readmission based on medical data is a current technique that is focused on a behavioral model for predicting whether a patient will be readmitted for a particular disease in a future period of time. Readmission events occur frequently and are costly, placing a significant burden on both the patient and the medical system. The rate of readmission, which is an important index for measuring the quality of medical services, is receiving increasing attention from governments, medical insurance companies, medical institutions, and patients. Therefore, dealing with the readmission prediction problem from the data analysis perspective is receiving increasing attention in the research field. Accurate prediction of readmission not only helps patients to know own physical health condition, guides healthy life behaviors. Therefore, how to build a model to accurately predict patient readmission becomes a critical issue.
The inventor finds that, in the research, most of the early researches use various regression techniques to establish a prediction model after reviewing the previous researches on the readmission prediction, and in recent decades, machine learning algorithms such as a decision tree and a support vector machine are increasingly widely applied to the readmission prediction. Recently, with the rise of deep learning, people use the recurrent neural network or its variants in deep learning to predict the readmission behavior using the serialized medical health record.
In summary, current approaches to dealing with readmission prediction problems typically use traditional machine learning classification algorithms, or utilize recurrent neural networks and their variants in deep learning. However, most of the existing methods only use the characteristic information of the patients to perform prediction, and the potential correlation relationship between the patients is rarely considered, so that the robustness of the prediction effect for similar people is not good, and especially, the patient with short hospitalization history, i.e. less case data, is difficult to perform the re-hospitalization prediction, so that the behavior prediction of how to perform re-hospitalization is the technical problem solved by the application for the situations of short hospitalization history data and less case data.
Disclosure of Invention
In order to overcome the defects of the prior art, the present disclosure provides a method and a system for predicting readmission based on a bipartite graph of a patient and a disease, wherein the bipartite graph of the patient and the disease is constructed according to medical data of the patient, and the readmission behavior is predicted based on an embedded generation algorithm.
In order to achieve the above object, one or more embodiments of the present disclosure provide the following technical solutions:
in one aspect, a patient and disease bipartite graph-based readmission prediction method is disclosed, comprising:
acquiring historical medical data of patients, and serializing the medical events of each patient by using the timestamps of diseases based on the historical medical data to obtain medical event sequence sets of all patients;
constructing a bipartite graph of the patients and the medical events based on the medical event sequence sets of all the patients, expressing the historical illness information of the patients and establishing indirect connection between the patients suffering from the same illness;
processing the bipartite graph of the patients and the medical events by using an embedded generation algorithm to obtain a final vector representation of each patient;
predicting a readmission behavior of the patient based on the final vector representation.
Further, the medical events of each patient are serialized using time stamps of the disease, each disease sequence snExpressed as:
Figure BDA0003018636370000021
wherein L isnIs a disease sequence snLength of (d)niThe ith disease, t, confirmed by the nth patient is shownniThe time stamp of when the nth patient confirmed the ith disease is indicated, and for all p<q,tnp≤tnq。
In a further technical scheme, when constructing the bipartite graph of the patient and the medical event, all the patients are used as two partsSet of patient nodes of graph, set of diseases
Figure BDA0003018636370000022
The set of disease nodes after deduplication as a bipartite graph, the edges between the patient and the disease indicate that the patient has suffered from the disease.
In another aspect, a hospitalization behavior prediction system based on an embedded generation algorithm is disclosed, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the program, including:
acquiring historical medical data of patients, and serializing the medical events of each patient by using the timestamps of diseases based on the historical medical data to obtain medical event sequence sets of all patients;
constructing a bipartite graph of the patients and the medical events based on the medical event sequence sets of all the patients, expressing the historical illness information of the patients and establishing indirect connection between the patients suffering from the same illness;
processing the bipartite graph of the patients and the medical events by using an embedded generation algorithm to obtain a final vector representation of each patient;
predicting a readmission behavior of the patient based on the final vector representation.
In another aspect, a rehospitalization behavior prediction apparatus based on an embedded generation algorithm is disclosed, comprising:
a data serialization module configured to: acquiring historical medical data of patients, and serializing the medical events of each patient by using the timestamps of diseases based on the historical medical data to obtain medical event sequence sets of all patients;
a bipartite graph construction module configured to: constructing a bipartite graph of the patients and the medical events based on the medical event sequence sets of all the patients, expressing the historical illness information of the patients and establishing indirect connection between the patients suffering from the same illness;
a readmission behavior prediction module configured to: processing the bipartite graph of the patients and the medical events by using an embedded generation algorithm to obtain a final vector representation of each patient;
predicting a readmission behavior of the patient based on the final vector representation.
The above one or more technical solutions have the following beneficial effects:
the technical scheme includes that medical events of all patients are serialized by utilizing timestamps of diseases to obtain medical event sequence sets of all patients, a bipartite graph of the patients and the medical events is constructed based on the medical event sequence sets of all the patients, and original data are compressed in the representation form of the bipartite graph to enable the bipartite graph to be more compact, so that the problems of sparsity of medical data and short medical history data and few case data are effectively solved, the bipartite graph of the patients and the medical events is provided for scattered data of each patient, and medical history conditions of all the patients can be comprehensively displayed.
Most of the previous methods for predicting readmission are not good, but only use the characteristic information of the patient, and particularly, the readmission prediction is difficult for the patient with short hospitalization history, i.e. less case data. The invention can express the historical illness information of the patient and the indirect relation between the patients suffering from the same illness by constructing the bipartite graph of the patient and the illness, thereby utilizing the characteristic information of other potential related patients to assist in the prediction of readmission and improving the prediction effect.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and are not to limit the disclosure.
FIG. 1 is a flow chart of a patient and disease bipartite graph based readmission prediction method.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. 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 disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
Referring to fig. 1, the present embodiment discloses a hospital readmission prediction method based on a patient and disease bipartite graph, which constructs a patient and disease bipartite graph according to medical data of a patient, obtains a final vector representation of the patient through an embedded generation algorithm of the patient and disease bipartite graph, and performs prediction 5 by using the final vector representation of the patient.
The method specifically comprises the following steps:
the method comprises the following steps: constructing a patient and disease bipartite graph, first extracting all diseases from the patient's medical historyName of (1) Scale and time stampThe medical history of each patient is serialized according to the time stamp of the disease to obtain a disease sequence set, which is like { sn1,2,3, N, where N is the number of disease sequences. Each disease sequence snWatch capable of showing
Figure BDA0003018636370000051
Wherein L isnIs a disease sequence snLength of (d)niThe ith disease, t, confirmed by the nth patient is shownniThe time stamp of when the nth patient confirmed the ith disease is indicated, and for all p<q,tnp≤tnq. Then, a patient-to-disease bipartite graph is constructed based on the disease sequence sets of all patients. All patients are taken as a patient node set of the bipartite graph, anddisease collection
Figure BDA0003018636370000052
Figure BDA0003018636370000053
And after the duplication removal, the disease node set is used as a bipartite graph. The border between the patient and the disease indicates that the patient has suffered from the disease. Then, the reciprocal of the time interval is normalized as the weight of the edge,the time interval here refers to the time difference between the patient's predicted time of illness and the patient's time of illness, the weighting of edges will be used later to indicate the degree of importance of a feature in a certain situation, the higher the final score, the easier it is to send And (4) generating.
Specifically, the weight formula for calculating the edge is as follows:
Figure BDA0003018636370000054
eija weight representing the edge between patient i and disease j; t is tipRepresents the predicted time of patient i; t is tijIndicating the time when patient i suffers from disease j; n is a radical ofiRepresenting all neighbor nodes of patient i, i.e., all diseases patient i has.
Step two: information from the disease and potentially related patients is aggregated for each patient by an embedded generation algorithm of the patient and disease bipartite graph, resulting in a final vector representation for each patient. The algorithm aggregates neighborhood information of each node layer by layer, a patient node aggregates neighbor node characteristic information by using a patient aggregation module, a disease node aggregates neighbor node characteristic information by using a disease aggregation module, and the patient node and the disease node acquire more and more information from farther positions of a patient bipartite graph and a disease bipartite graph along with the continuation of iteration. The inputs of the two types of combination modules are the same, and are both two groups of node characteristics, hp＝{hp1,hp2,...,hpm},
Figure BDA0003018636370000061
Is a patient node feature, where m is a patient nodeNumber of dots, FpIs the dimension of each patient node feature. h isd＝{hd1,hd2,...,hdn},
Figure BDA0003018636370000062
Is a disease node characteristic, where n is the number of disease nodes, FdIs the dimension of each disease node feature. They will generate two sets of new node signatures h 'respectively'p＝{h′p1,h′p2,...,h′pm},
Figure BDA0003018636370000063
And h'd＝{h′d1,h′d2,...,h′dm},
Figure BDA0003018636370000064
As its output.
Specifically, the formula of the edge weight, the patient aggregation module and the disease aggregation module is as follows:
1) the weight update formula of the edge:
Figure BDA0003018636370000065
wherein · -TRepresenting transposition, | | representing join operation, NpiRepresenting the neighbors of the patient node i, hpiIs a patient node characteristic, hdjIs a disease node characteristic, eijIs the current attention coefficient, which is the attention coefficient of the previous layer, and if it is at the first layer, it is the initial weight of the edge.
2) A patient aggregation module:
Figure BDA0003018636370000066
3) a disease aggregation module:
Figure BDA0003018636370000067
wherein
Figure BDA0003018636370000068
Features representing patient node i at level l-1;
Figure BDA0003018636370000069
represents the characteristics of disease node j at layer l-1;
Figure BDA00030186363700000610
is the weight of the edge connecting the node j and the node i on the l-1 layer; wl-1The weight matrix corresponding to the l-1 layer is used for transmitting information between different layers of the model; α is the previously-spoken attention coefficient calculation function; σ is a non-linear function.
Step three: the aggregated information is used to predict a patient's readmission. Aggregating information from the disease and related patients for each patient using a patient-to-disease bipartite graph embedding generation algorithm, wherein the aggregated information is used by a softmax layer to predict patient readmissionFor the last layer of the full connection layer, corresponding data is converted into a model Values enclosed between [ 0-1 ] and the sum being one, can be approximated as a probability, indicating the likelihood of a certain condition occurring。
The specific calculation process is as follows:
1) using the patient final vector zpAs an input to softmax, an output value between 0 and 1 is obtained.All knots The result sum is 1, resulting in similar probability results, the larger the value, the more likely.
y′＝softmax(zp)
2) The loss function can be obtained according to the following formula:
Figure BDA0003018636370000071
the function of this function is to discriminate the difference between the calculated result and the true value, the larger the loss function is,the larger the difference from the true value is, the smaller the opposite. It can be used to amplify values close to the true value to reduce the loss function to approach the true value。
In summary, according to the embodiments of the present invention, the patient's readmission condition is predicted by the readmission prediction method based on the patient and the disease bipartite graph, the potential association relationship between the patients is considered, the health information of the patients is fully utilized, and the prediction accuracy is improved.
The object of the present embodiment is to provide a hospitalization behavior prediction system based on embedded generation algorithm, which includes a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the specific steps of the above embodiment.
An object of the present embodiment is to provide a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, performs the specific steps of the above-described implementation example.
The embodiment aims to provide a rehospitalization behavior prediction device based on an embedded generation algorithm, which comprises:
a data serialization module configured to: acquiring historical medical data of patients, and serializing the medical events of each patient by using the timestamps of diseases based on the historical medical data to obtain medical event sequence sets of all patients;
a bipartite graph construction module configured to: constructing a bipartite graph of the patients and the medical events based on the medical event sequence sets of all the patients, expressing the historical illness information of the patients and establishing indirect connection between the patients suffering from the same illness;
a readmission behavior prediction module configured to: processing the bipartite graph of the patients and the medical events by using an embedded generation algorithm to obtain a final vector representation of each patient;
predicting a readmission behavior of the patient based on the final vector representation.
The steps involved in the apparatus of the above embodiment correspond to the first embodiment of the method, and the detailed description thereof can be found in the relevant description of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media containing one or more sets of instructions; it should also be understood to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any of the methods of the present disclosure.
Those skilled in the art will appreciate that the modules or steps of the present disclosure described above can be implemented using general purpose computer means, or alternatively, they can be implemented using program code executable by computing means, whereby the modules or steps may be stored in memory means for execution by the computing means, or separately fabricated into individual integrated circuit modules, or multiple modules or steps thereof may be fabricated into a single integrated circuit module. The present disclosure is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Although the present disclosure has been described with reference to specific embodiments, it should be understood that the scope of the present disclosure is not limited thereto, and those skilled in the art will appreciate that various modifications and changes can be made without departing from the spirit and scope of the present disclosure.

Claims (10)

1. A patient and disease bipartite graph-based readmission prediction method, comprising:
acquiring historical medical data of patients, and serializing the medical events of each patient by using the timestamps of diseases based on the historical medical data to obtain medical event sequence sets of all patients;
constructing a bipartite graph of the patients and the medical events based on the medical event sequence sets of all the patients, expressing the historical illness information of the patients and establishing indirect connection between the patients suffering from the same illness;
processing the bipartite graph of the patients and the medical events by using an embedded generation algorithm to obtain a final vector representation of each patient;
predicting a readmission behavior of the patient based on the final vector representation.
2. The bi-graph patient-to-disease based readmission prediction method of claim 1, wherein the time stamps of the disease are used to sequence the medical events of each patient, and each disease sequence snExpressed as:
Figure FDA0003018636360000011
wherein L isnIs a disease sequence snLength of (d)niThe ith disease, t, confirmed by the nth patient is shownniThe time stamp of when the nth patient confirmed the ith disease is indicated, and for all p<q,tnp≤tnq。
3. The method of claim 1, wherein constructing the bipartite graph of patients and medical events comprises constructing the bipartite graph of patients and medical events by using all patients as a set of patient nodes in the bipartite graph and using the set of diseases as a set of nodes in the bipartite graph
Figure FDA0003018636360000012
The set of disease nodes after deduplication as a bipartite graph, the edges between the patient and the disease indicate that the patient has suffered from the disease.
4. A patient-to-disease bipartite graph-based readmission prediction method as claimed in claim 1, wherein the final vector is used as input for softmax, resulting in an output value between 0 and 1.
5. The method of claim 1, wherein the reciprocal of the time interval is normalized as a weight of the patient-to-medical event bipartite graph edge.
6. A rehospitalization behavior prediction device based on an embedded generation algorithm is characterized by comprising:
a data serialization module configured to: acquiring historical medical data of patients, and serializing the medical events of each patient by using the timestamps of diseases based on the historical medical data to obtain medical event sequence sets of all patients;
a bipartite graph construction module configured to: constructing a bipartite graph of the patients and the medical events based on the medical event sequence sets of all the patients, expressing the historical illness information of the patients and establishing indirect connection between the patients suffering from the same illness;
a readmission behavior prediction module configured to: processing the bipartite graph of the patients and the medical events by using an embedded generation algorithm to obtain a final vector representation of each patient;
predicting a readmission behavior of the patient based on the final vector representation.
7. The embedded generation algorithm based rehospitalization behavior prediction device of claim 6, wherein said bipartite graph building module constructs a bipartite graph of patients and medical events, takes all patients as a patient node set of the bipartite graph, and takes a disease set as a disease set
Figure FDA0003018636360000021
The set of disease nodes after deduplication as a bipartite graph, the edges between the patient and the disease indicate that the patient has suffered from the disease.
8. The apparatus of claim 7, further comprising: a patient aggregation module and a disease aggregation module;
the patient aggregation module is configured to: aggregating the characteristic information of the neighbor nodes of the patient nodes;
the disease aggregation module is configured to: and aggregating the disease nodes with the characteristic information of the neighbor nodes.
9. A rehospitalization behavior prediction system based on an embedded generation algorithm, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the following steps when executing the program, comprising:
acquiring historical medical data of patients, and serializing the medical events of each patient by using the timestamps of diseases based on the historical medical data to obtain medical event sequence sets of all patients;
constructing a bipartite graph of the patients and the medical events based on the medical event sequence sets of all the patients, expressing the historical illness information of the patients and establishing indirect connection between the patients suffering from the same illness;
processing the bipartite graph of the patients and the medical events by using an embedded generation algorithm to obtain a final vector representation of each patient;
predicting a readmission behavior of the patient based on the final vector representation.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method steps of any one of the preceding claims 1-6.
CN202110396159.XA 2021-04-13 2021-04-13 Patient and disease bipartite graph-based readmission prediction method and system Pending CN113192627A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110396159.XA CN113192627A (en) 2021-04-13 2021-04-13 Patient and disease bipartite graph-based readmission prediction method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110396159.XA CN113192627A (en) 2021-04-13 2021-04-13 Patient and disease bipartite graph-based readmission prediction method and system

Publications (1)

Publication Number Publication Date
CN113192627A true CN113192627A (en) 2021-07-30

Family

ID=76975640

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110396159.XA Pending CN113192627A (en) 2021-04-13 2021-04-13 Patient and disease bipartite graph-based readmission prediction method and system

Country Status (1)

Country Link
CN (1) CN113192627A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114496283A (en) * 2022-02-15 2022-05-13 山东大学 Disease prediction system based on path reasoning, storage medium and equipment
WO2022136978A1 (en) * 2020-12-22 2022-06-30 International Business Machines Corporation Medical event prediction by health record monitoring

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107591204A (en) * 2017-08-01 2018-01-16 山东大学 Be in hospital again Forecasting Methodology and system based on sequential portrait figure
CN110310740A (en) * 2019-04-15 2019-10-08 山东大学 Based on see a doctor again information forecasting method and the system for intersecting attention neural network

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107591204A (en) * 2017-08-01 2018-01-16 山东大学 Be in hospital again Forecasting Methodology and system based on sequential portrait figure
CN110310740A (en) * 2019-04-15 2019-10-08 山东大学 Based on see a doctor again information forecasting method and the system for intersecting attention neural network

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
刘志奇: "基于病人疾病二部图的再入院预测研究", 《中国优秀博硕士学位论文全文数据库（硕士）基础科学辑》 *
藤田一弥等 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022136978A1 (en) * 2020-12-22 2022-06-30 International Business Machines Corporation Medical event prediction by health record monitoring
GB2617947A (en) * 2020-12-22 2023-10-25 Ibm Medical event prediction by health record monitoring
CN114496283A (en) * 2022-02-15 2022-05-13 山东大学 Disease prediction system based on path reasoning, storage medium and equipment

Similar Documents

Publication Publication Date Title
Sun et al. Disease prediction via graph neural networks
CN109659033B (en) Chronic disease state of an illness change event prediction device based on recurrent neural network
WO2018171533A1 (en) Review machine learning system
CN113196314B (en) Adapting a predictive model
Zheng et al. Resolving the bias in electronic medical records
CN104572583B (en) Method and system for data densification
US20110112380A1 (en) Method and System for Optimal Estimation in Medical Diagnosis
Zheng et al. Capturing feature-level irregularity in disease progression modeling
CN113192627A (en) Patient and disease bipartite graph-based readmission prediction method and system
TWI814154B (en) Method for predicting disease based on medical image
CN109213871A (en) Patient information knowledge mapping construction method, readable storage medium storing program for executing and terminal
CN112925857A (en) Digital information driven system and method for predicting associations based on predicate type
WO2023025956A1 (en) Method and system for deconvolution of bulk rna-sequencing data
CN110335160B (en) Medical care migration behavior prediction method and system based on grouping and attention improvement Bi-GRU
WO2014130287A1 (en) Method and system for propagating labels to patient encounter data
Teo et al. Current trends in readmission prediction: an overview of approaches
Ranjini et al. An ensemble of heterogeneous incremental classifiers for assisted reproductive technology outcome prediction
Sampath et al. Ensemble Nonlinear Machine Learning Model for Chronic Kidney Diseases Prediction
CN116403728B (en) Data processing device for medical treatment data and related equipment
Bhat et al. An efficient prediction model for diabetic database using soft computing techniques
Andersson Predicting Patient Length Of Stay at Time of Admission Using Machine Learning
Sumathi et al. Machine learning based pattern detection technique for diabetes mellitus prediction
Sisimayi et al. AI-enabled case detection model for infectious disease outbreaks in resource-limited settings
CN115240843A (en) Fairness prediction system based on structure causal model
JP2024500470A (en) Lesion analysis methods in medical images

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20210730

RJ01 Rejection of invention patent application after publication