CN109616168A - A kind of medical field Intelligent management model construction method based on electronic health record - Google Patents
A kind of medical field Intelligent management model construction method based on electronic health record Download PDFInfo
- Publication number
- CN109616168A CN109616168A CN201811536456.4A CN201811536456A CN109616168A CN 109616168 A CN109616168 A CN 109616168A CN 201811536456 A CN201811536456 A CN 201811536456A CN 109616168 A CN109616168 A CN 109616168A
- Authority
- CN
- China
- Prior art keywords
- data
- intelligent management
- management model
- health record
- electronic health
- 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
- 230000036541 health Effects 0.000 title claims abstract description 19
- 238000010276 construction Methods 0.000 title claims abstract description 18
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 238000007418 data mining Methods 0.000 claims abstract description 8
- 230000009466 transformation Effects 0.000 claims abstract description 5
- 238000004458 analytical method Methods 0.000 claims abstract description 4
- 238000006243 chemical reaction Methods 0.000 claims abstract description 4
- 230000010354 integration Effects 0.000 claims abstract description 4
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000007726 management method Methods 0.000 claims description 27
- 238000007637 random forest analysis Methods 0.000 claims description 12
- 238000007689 inspection Methods 0.000 claims description 11
- 206010012601 diabetes mellitus Diseases 0.000 claims description 10
- 238000007477 logistic regression Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 6
- 208000017442 Retinal disease Diseases 0.000 claims description 4
- 206010038923 Retinopathy Diseases 0.000 claims description 4
- 238000003066 decision tree Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 230000002596 correlated effect Effects 0.000 claims description 2
- 230000003902 lesion Effects 0.000 claims description 2
- 238000012217 deletion Methods 0.000 claims 1
- 230000037430 deletion Effects 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 2
- 239000007787 solid Substances 0.000 abstract description 2
- 238000011160 research Methods 0.000 description 8
- DDRJAANPRJIHGJ-UHFFFAOYSA-N creatinine Chemical compound CN1CC(=O)NC1=N DDRJAANPRJIHGJ-UHFFFAOYSA-N 0.000 description 4
- 238000005457 optimization Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 229940109239 creatinine Drugs 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 210000002700 urine Anatomy 0.000 description 2
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 208000002249 Diabetes Complications Diseases 0.000 description 1
- 208000008960 Diabetic foot Diseases 0.000 description 1
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 1
- 102000003886 Glycoproteins Human genes 0.000 description 1
- 108090000288 Glycoproteins Proteins 0.000 description 1
- 206010019280 Heart failures Diseases 0.000 description 1
- 206010029164 Nephrotic syndrome Diseases 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- -1 blood pressure Substances 0.000 description 1
- 238000013070 change management Methods 0.000 description 1
- 208000029078 coronary artery disease Diseases 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 208000030533 eye disease Diseases 0.000 description 1
- 239000008103 glucose Substances 0.000 description 1
- 230000002641 glycemic effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 150000002632 lipids Chemical class 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000010125 myocardial infarction Diseases 0.000 description 1
- 208000009928 nephrosis Diseases 0.000 description 1
- 231100001027 nephrosis Toxicity 0.000 description 1
- 210000001640 nerve ending Anatomy 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 210000001525 retina Anatomy 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 208000001072 type 2 diabetes mellitus Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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)
- Public Health (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of medical field Intelligent management model construction method based on electronic health record, this method mainly include the following steps: to manage data needed for exporting in systems, derived data are stored in the form of Excel table.Derived data are subjected to data cleansing, data integration, data conversion, hough transformation, eventually form target data set result database.Optimal algorithm is chosen after carrying out data mining analysis comparison to result database using traditional data mining algorithm and is optimized, and is chosen most correlative factor using the algorithm chosen and is constructed Intelligent management model.The present invention faces a large amount of structurings and unstructured electronic health record information, summarizes the data cleansing process of complete set in data preprocessing phase, lays a solid foundation for the building of intelligent management model construction.
Description
Technical field
The present invention relates to the buildings of medical field model method, are related to a kind of intelligence pipe of medical field based on electronic health record
Manage model building method, the in particular to medical Intelligent management model structure of a kind of random forests algorithm indicator combination based on optimization
Construction method.
Background technique
It is several for managing patient for medical field Intelligent management model construction method, commonly referred to as clinical pattern
A possibility that various complication of Nian Houqi are fallen ill and order of occurrence etc..There is more grind in foreign countries for this class model at present
Study carefully, and develop and form some assessment softwares, the more well-known perspective diabetes study diabetes for having UK Classic are pre-
Model (UKPDS) model is surveyed, which is the prediction for the diagnosis and treatment of type II diabetes difference carried out in Britain in 1977
Property multicenter randomized control clinical trial group research, research object be related to 23 research points of Britain amount to 5120 diabetics, last 20
Year, until terminating for 1997.The model is common mainly for 7 kinds of the Major Clinical index (blood glucose, blood pressure, blood lipid etc.) of diabetes
Complication (apoplexy, coronary heart disease, myocardial infarction, heart failure, diabetic foot, nephrosis and eye disease) and associated death event generation
Probability and time of occurrence are simulated, so that can study strict glycemic control reduce the morbidity of type 2 diabetic patient's complication
Risk has been widely used among the scientific research and management of diabetes.If the research in this direction of China is only indiscriminately imitated merely
Foreign study model causes result of study to deviate due to the difference of crowd, therefore domestic research should be according to China
National conditions are predicted for diabetic.Li Zhangping in 2009 et al. using prediction model Logistic regression model in three,
Decision-tree model and neural network model, respectively to the hair of lesion around diabetes B nerve ending under conditions of small sample
Raw probability predicted, be compared by the area under ROC curve obtain area it is maximum be neural network model, predict energy
Power is best, is secondly Logistic regression model, group rear guard's decision-tree model;But it is back in the research using data set
Care for Journal of Sex Research, sample content is less, and is related to that variable is more, therefore the accuracy of the model need further to test
Card.
Summary of the invention
In view of above-mentioned existing deficiency, the purpose of the present invention is to provide a kind of, and the medical treatment based on electronic health record data is led
Domain intelligent management construction method, it is intended to propose a kind of new methods of risk assessment.
The technical scheme adopted by the invention to solve the technical problem is that: a kind of new intelligence of the method based on electronic health record
Change management construction method, this method mainly includes the following steps:
Step 1: managing data needed for export in systems, derived data are stored in the form of Excel table.
Step 2: derived data being subjected to data cleansing, data integration, data conversion, hough transformation, eventually form mesh
Mark data set result database.
Step 3: being chosen most after carrying out data mining analysis comparison to result database using traditional data mining algorithm
Excellent algorithm simultaneously optimizes, and chooses most correlative factor using the algorithm chosen and constructs Intelligent management model.
Further, the method that building obtains electronic health record data described in step 1 of the present invention, step specifically include:
Step 1-1: with authorized user identities login system database.
Step 1-2: electronic health record Basic Information Table is exported from system database using SQL statement, then from another
Export, which is examined, in system number library checks data.
Step 1-3: by export data with the storage of Excel table.
Further, data preprocessing method described in step 2 of the present invention, step specifically include:
Step 2-1: by derived essential information and examine inspection data with unique No. id for external key using VBA language
It matches Basic Information Table and examines and check tables of data.
Step 2-2: the dimension column for lacking mass data and the check item and information unrelated with objective result are deleted, is deleted
Lack a large amount of data lines examined and check information.
Step 2-3: lacking a small amount of examine and check data, and all inspection numbers inspection inspection is found out in initial data from extracting
Data are looked into, fill up data using averaging method.
Step 2-4: text data is become into numeric type data.Diabetes complicated retinopathy becomes label 1, and diabetes are not
Suffer from retina and labels 0.
Further, the method for data digging method described in step 3 of the present invention, step specifically include:
Step 3-1: target data is assessed and is managed with Logistic, decision tree, KNN, Random Forest model respectively.
Step 3-2: most correlative factor, and benefit are found to every prominence score for examining Index for examination according to random forest
With Logistic regression analysis other factors relevance score relevant to the factor.
Step 3-3: according to Index for examination and A/C relevance score is examined, it will be positively correlated index respectively and managed in conjunction with A/C
Retinopathy eventually finds the highest indicator combination of accuracy rate.
Step 3-4: each forecast result of model is assessed.
Further step 3-4 comments index: assess respectively the prediction effects of various algorithms using precision ratio P, recall rate R with
And the harmomic mean F of exact value and recall rate, with assessment algorithm, calculation formula difference is as follows:
Precision ratio:
Recall rate:
The harmomic mean of exact value and recall rate:
A kind of best algorithm prediction of assessment result is chosen, and utilizes random forest prominence score coherence check index
Factor combination improves predictablity rate.
The present invention is a kind of new medical intelligent management construction method.
The utility model has the advantages that
1. the present invention faces a large amount of structurings and unstructured electronic health record information in data preprocessing phase, summarize
The data cleansing process of complete set is laid a solid foundation for the building of intelligent management model construction.
2. the data analysis mining stage of the present invention constructs Intelligent management model using traditional data digging method, utilizes
Grid optimization method optimizes best model-Random Forest model, and is found using the prominence score of random forests algorithm most related
Factor is further found and the maximum inspection check item of correlative factor positive correlation coefficient using Logistic regression analysis.
3. the present invention constructs the stage in medical field Intelligent management model, using the random forests algorithm of optimization, utilize
The correlative factor of Logistic regression analysis predicts objective result, to construct complete Intelligent management model.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the medical field Intelligent management model construction method based on electronic health record of the present invention.
Fig. 2 is the specific flow chart of step 2.
Fig. 3 is the important scoring figure of random forest of step 3.
Fig. 4 is Random Forest model algorithm flow chart.
Fig. 5 is Logistic Regression Analysis Result figure.
Fig. 6 is algorithm comparing result table.
Fig. 7 is management result table of the influence factor combination to target data.
Specific embodiment
The present invention provides a kind of medical field disease forecasting construction method based on electronic health record, to make mesh of the invention
, technical solution and effect it is clearer, clear, the present invention is described in more detail below.It should be appreciated that described herein
Specific embodiment be only used to explain the present invention, be not intended to limit the present invention.
Please refer to Fig. 1.Fig. 1 be a kind of medical field Intelligent management model construction method based on electronic health record of the present invention compared with
The flow chart of good embodiment, as shown, implementation step, includes the following:
Step 1: export relevant to target data essential information in system and examine inspection data, by derived data with
The form of Excel table stores.
Step 2: derived data being subjected to data cleansing, data integration, data conversion, hough transformation, eventually form mesh
Mark data result database.
Step 3: being chosen most after carrying out data mining analysis comparison to result database using traditional data mining algorithm
Excellent algorithm simultaneously optimizes, and chooses and constructs risk Intelligent management model using the algorithm chosen with target data most correlative factor, finally
Obtain medical field Intelligent management model mould construction method.
It as seen from Figure 3, is up to significantly Urine proteins creatinine ratio (A/C) with the scoring of target Correlative Influence Factors, by Fig. 5
As can be seen that sorting with glycoprotein urine creatinine than factor positive correlation factor, Fig. 7 can be seen that the management when index for selection combination
Model has best effect.
It should be understood that the application of the present invention is not limited to the above for those of ordinary skills can
With improvement or transformation based on the above description, all these modifications and variations all should belong to the guarantor of appended claims of the present invention
Protect range.
Claims (4)
1. a kind of medical field Intelligent management model construction method based on electronic health record, it is characterised in that: this method is mainly wrapped
Include following steps,
Step 1: managing data needed for export in systems, derived data are stored in the form of Excel table;
Step 2: derived data being subjected to data cleansing, data integration, data conversion, hough transformation, eventually form number of targets
According to collection result database;
Step 3: choosing optimal calculation after carrying out data mining analysis comparison to result database using traditional data mining algorithm
Method simultaneously optimizes, and chooses most correlative factor using the algorithm chosen and constructs Intelligent management model.
2. a kind of medical field Intelligent management model construction method based on electronic health record according to claim 1, special
Sign is: the method that building obtains electronic health record data described in step 1, step specifically include:
Step 1-1: with authorized user identities login system database;
Step 1-2: electronic health record Basic Information Table is exported from system database using SQL statement, then from another system
Export, which is examined, in number library checks data;
Step 1-3: by export data with the storage of Excel table.
3. a kind of medical field Intelligent management model construction method based on electronic health record according to claim 1, special
Sign is: data preprocessing method described in step 2, step specifically include:
Step 2-1: by derived essential information and inspection data is examined to match with unique No. id for external key using VBA language
Basic Information Table and inspection check tables of data;
Step 2-2: deleting the dimension column for lacking mass data and the check item and information unrelated with objective result, deletion lack
It is a large amount of to examine the data line for checking information;
Step 2-3: lacking a small amount of examine and check data, and all inspection numbers inspection inspection number is found out in initial data from extracting
According to filling up data using averaging method;
Step 2-4: text data is become into numeric type data;Diabetes complicated retinopathy becomes label 1, and diabetes are not suffering from view
Nethike embrane labels 0.
4. a kind of medical field Intelligent management model construction method based on electronic health record according to claim 1, special
Sign is: the method for data digging method described in step 3, step specifically include:
Step 3-1: target data is assessed and is managed with Logistic, decision tree, KNN, Random Forest model respectively;
Step 3-2: most correlative factor is found to every prominence score for examining Index for examination according to random forest, and is utilized
Logistic regression analysis other factors relevance score relevant to the factor;
Step 3-3: according to Index for examination and A/C relevance score is examined, it will be positively correlated index respectively and manage view in conjunction with A/C
Film lesion eventually finds the highest indicator combination of accuracy rate;
Step 3-4: each model intelligent management effect is assessed;
Further step 3-4 comments index: assessing looking into the intelligent management effect utilization of retinopathy for various algorithms respectively
The harmomic mean F of quasi- rate P, recall rate R and exact value and recall rate, with assessment algorithm, calculation formula difference is as follows:
Precision ratio:
Recall rate:
The harmomic mean of exact value and recall rate:
It chooses a kind of best algorithm model of assessment result and constructs Intelligent management model, and utilize random forest prominence score
The combination of coherence check index factor improves Intelligent management model and constructs a kind of new optimal Intelligent management model of effect.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811536456.4A CN109616168A (en) | 2018-12-14 | 2018-12-14 | A kind of medical field Intelligent management model construction method based on electronic health record |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811536456.4A CN109616168A (en) | 2018-12-14 | 2018-12-14 | A kind of medical field Intelligent management model construction method based on electronic health record |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109616168A true CN109616168A (en) | 2019-04-12 |
Family
ID=66010009
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811536456.4A Pending CN109616168A (en) | 2018-12-14 | 2018-12-14 | A kind of medical field Intelligent management model construction method based on electronic health record |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109616168A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110164524A (en) * | 2019-04-29 | 2019-08-23 | 北京国润健康医学投资有限公司 | A kind of hemiplegia patient training mission adaptive matching method and its system |
CN110853764A (en) * | 2019-11-28 | 2020-02-28 | 成都中医药大学 | Diabetes syndrome prediction system |
CN111554401A (en) * | 2020-03-26 | 2020-08-18 | 肾泰网健康科技(南京)有限公司 | Method for constructing AI (artificial intelligence) chronic kidney disease screening model, and chronic kidney disease screening method and system |
CN111710420A (en) * | 2020-05-15 | 2020-09-25 | 深圳先进技术研究院 | Complication morbidity risk prediction method, system, terminal and storage medium based on electronic medical record big data |
CN111986754A (en) * | 2020-08-21 | 2020-11-24 | 南通大学 | Electronic medical record management model construction method based on diabetes |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120060216A1 (en) * | 2010-09-01 | 2012-03-08 | Apixio, Inc. | Medical information navigation engine (mine) system |
CN107423560A (en) * | 2017-06-27 | 2017-12-01 | 天方创新(北京)信息技术有限公司 | Based on Rating Model type-II diabetes are carried out with the method and device of risk score |
CN108416371A (en) * | 2018-02-11 | 2018-08-17 | 艾视医疗科技成都有限公司 | A kind of diabetic retinopathy automatic testing method |
CN108492872A (en) * | 2017-07-21 | 2018-09-04 | 湖州师范学院 | Intelligent auxiliary diagnosis system |
CN108717869A (en) * | 2018-05-03 | 2018-10-30 | 中国石油大学(华东) | Diabetic retinopathy diagnosis aid system based on convolutional neural networks |
CN108877943A (en) * | 2018-06-21 | 2018-11-23 | 天津医科大学 | Type-2 diabetes mellitus risk evaluation model based on evidence-based medical |
-
2018
- 2018-12-14 CN CN201811536456.4A patent/CN109616168A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120060216A1 (en) * | 2010-09-01 | 2012-03-08 | Apixio, Inc. | Medical information navigation engine (mine) system |
CN107423560A (en) * | 2017-06-27 | 2017-12-01 | 天方创新(北京)信息技术有限公司 | Based on Rating Model type-II diabetes are carried out with the method and device of risk score |
CN108492872A (en) * | 2017-07-21 | 2018-09-04 | 湖州师范学院 | Intelligent auxiliary diagnosis system |
CN108416371A (en) * | 2018-02-11 | 2018-08-17 | 艾视医疗科技成都有限公司 | A kind of diabetic retinopathy automatic testing method |
CN108717869A (en) * | 2018-05-03 | 2018-10-30 | 中国石油大学(华东) | Diabetic retinopathy diagnosis aid system based on convolutional neural networks |
CN108877943A (en) * | 2018-06-21 | 2018-11-23 | 天津医科大学 | Type-2 diabetes mellitus risk evaluation model based on evidence-based medical |
Non-Patent Citations (1)
Title |
---|
曹文哲 等: "基于Logistic回归和随机森林算法的2型糖尿病并发视网膜病变风险预测及对比研究", 《中国医疗设备》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110164524A (en) * | 2019-04-29 | 2019-08-23 | 北京国润健康医学投资有限公司 | A kind of hemiplegia patient training mission adaptive matching method and its system |
CN110853764A (en) * | 2019-11-28 | 2020-02-28 | 成都中医药大学 | Diabetes syndrome prediction system |
CN110853764B (en) * | 2019-11-28 | 2023-11-14 | 成都中医药大学 | Diabetes syndrome prediction system |
CN111554401A (en) * | 2020-03-26 | 2020-08-18 | 肾泰网健康科技(南京)有限公司 | Method for constructing AI (artificial intelligence) chronic kidney disease screening model, and chronic kidney disease screening method and system |
CN111554401B (en) * | 2020-03-26 | 2020-12-29 | 肾泰网健康科技(南京)有限公司 | AI (AI) chronic kidney disease risk screening and modeling method, chronic kidney disease risk screening method and system |
WO2021190300A1 (en) * | 2020-03-26 | 2021-09-30 | 肾泰网健康科技(南京)有限公司 | Method for constructing ai chronic kidney disease risk screening model, and chronic kidney disease risk screening method and system |
CN111710420A (en) * | 2020-05-15 | 2020-09-25 | 深圳先进技术研究院 | Complication morbidity risk prediction method, system, terminal and storage medium based on electronic medical record big data |
CN111710420B (en) * | 2020-05-15 | 2024-03-19 | 深圳先进技术研究院 | Complication onset risk prediction method, system, terminal and storage medium based on electronic medical record big data |
CN111986754A (en) * | 2020-08-21 | 2020-11-24 | 南通大学 | Electronic medical record management model construction method based on diabetes |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109616168A (en) | A kind of medical field Intelligent management model construction method based on electronic health record | |
Dritsas et al. | Cardiovascular Disease Risk Prediction with Supervised Machine Learning Techniques. | |
Richards et al. | Data mining for indicators of early mortality in a database of clinical records | |
CN112365978A (en) | Method and device for establishing early risk assessment model of tachycardia event | |
Rutishauser et al. | The challenge posed by newly discovered cryptic species: Disentangling the environmental niches of long‐eared bats | |
Butt et al. | Diagnosing the stage of hepatitis C using machine learning | |
CN109785973A (en) | The quantitative forecasting technique of complication occurs in peri-operation period for a kind of patient with operation | |
Pavithra et al. | Hybrid feature selection technique for prediction of cardiovascular diseases | |
Musacchio et al. | Transparent machine learning suggests a key driver in the decision to start insulin therapy in individuals with type 2 diabetes | |
Mahajan et al. | Diabetes mellitus prediction using supervised machine learning techniques | |
CN117079815A (en) | Cardiovascular disease risk prediction model construction method based on graph neural network | |
CN113838577A (en) | Convenient layered old people MODS early death risk assessment model, device and establishment method | |
CN111986814A (en) | Modeling method of lupus nephritis prediction model of lupus erythematosus patient | |
CN116564521A (en) | Chronic disease risk assessment model establishment method, medium and system | |
Das et al. | A comparative study of machine learning approaches for heart stroke prediction | |
Padmapritha | Prediction of Blood Glucose Level by using an LSTM based Recurrent Neural networks | |
Ashoori et al. | A model to predict the sequential behavior of healthy blood donors using data mining | |
Feng et al. | Applications of data mining methods in the integrative medical studies of coronary heart disease: progress and prospect | |
Zhang et al. | Prediction of gestational diabetes mellitus under cascade and ensemble learning algorithm | |
Tahsin et al. | Predictive analysis & brief study of early-stage diabetes using multiple classifier models | |
Katiyar et al. | Recent advancements using machine learning & deep learning approaches for diabetes detection: a systematic review | |
Sharma | Data Mining Prediction Techniques in Health Care Sector | |
CN111986815B (en) | Project combination mining method based on co-occurrence relation and related equipment | |
Patil et al. | Diabetes Disease Prediction Using Machine Learning | |
Almansa et al. | Measurement and description of underlying dimensions of comorbid mental disorders using factor mixture models: results of the ESEMeD project |
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: 20190412 |
|
RJ01 | Rejection of invention patent application after publication |