CN113380407A - Method for constructing intelligent prediction of cognitive impairment - Google Patents
Method for constructing intelligent prediction of cognitive impairment Download PDFInfo
- Publication number
- CN113380407A CN113380407A CN202110596294.9A CN202110596294A CN113380407A CN 113380407 A CN113380407 A CN 113380407A CN 202110596294 A CN202110596294 A CN 202110596294A CN 113380407 A CN113380407 A CN 113380407A
- Authority
- CN
- China
- Prior art keywords
- intelligent
- prediction
- constructing
- cognitive impairment
- data
- 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
- 208000010877 cognitive disease Diseases 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 32
- 208000028698 Cognitive impairment Diseases 0.000 title claims abstract description 24
- 238000011156 evaluation Methods 0.000 claims abstract description 17
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 238000012216 screening Methods 0.000 claims abstract description 13
- 238000002790 cross-validation Methods 0.000 claims abstract description 7
- 208000024827 Alzheimer disease Diseases 0.000 claims abstract description 4
- 206010039966 Senile dementia Diseases 0.000 claims abstract description 4
- 238000004140 cleaning Methods 0.000 claims abstract description 4
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 239000013598 vector Substances 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 230000010354 integration Effects 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 2
- 230000001131 transforming effect Effects 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 description 8
- 238000003066 decision tree Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000012217 deletion Methods 0.000 description 3
- 230000037430 deletion Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000007637 random forest analysis Methods 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 238000007418 data mining Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G16H50/30—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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- 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
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
-
- 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)
- Medical Informatics (AREA)
- Public Health (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Software Systems (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for constructing an intelligent prediction method of cognitive impairment, which comprises the following steps of (1) obtaining original questionnaire data by S1; s2, data cleaning; s3, preprocessing and visualizing the data; s4, combining expert knowledge feature screening and intelligent algorithm feature screening to obtain a feature subset; s5, constructing an intelligent cognitive disorder prediction model; s6, verifying effectiveness of the cognitive impairment intelligent prediction model by adopting cross validation, and debugging and optimizing the model by combining expert knowledge S7; s8 early screening for senile dementia by adopting cognitive impairment intelligent prediction. The method has the advantages of simple and understandable evaluation items, simple operation, no need of guidance of professional medical personnel, suitability for mass self-evaluation and high prediction accuracy.
Description
Technical Field
The application relates to the technical field of internet, in particular to an intelligent prediction method for constructing cognitive impairment.
Background
The onset of cognitive impairment is closely related to the basic condition, lifestyle habits, physical condition, medical history and treatment of the patient. It is not fully understood at present which factors are highly correlated with the onset of cognitive impairment. There is also no effective model that enables prediction of cognitive impairment risk.
In traditional AD screening, scoring tools such as MMSE (minimum mean square error), MOCA (mean of average molecular weight), and the like are used. Such scales often require the person being evaluated to be guided by medical personnel and professionally quantified scores to arrive at a result. A more complete system questionnaire involves hundreds of questions, the filling time is very time-consuming, and the final assessment results take a long time to calculate.
The intelligent prediction and detection of cognitive impairment in the prior art is time-consuming and labor-consuming, and rapid automatic detection cannot be realized.
Disclosure of Invention
In order to solve the problems that the intelligent prediction detection of the cognitive disorder in the prior art is time-consuming and labor-consuming and cannot realize rapid automatic detection, the invention provides a method for constructing the intelligent prediction of the cognitive disorder, which comprises the following steps that S1 obtains original questionnaire data;
s2, data cleaning;
s3, preprocessing and visualizing the data;
s4, combining expert knowledge feature screening and intelligent algorithm feature screening to obtain a feature subset;
s5, constructing an intelligent cognitive disorder prediction model;
s6, verifying effectiveness of the cognitive disorder intelligent prediction model by adopting cross validation;
s7, debugging and optimizing the model by combining expert knowledge;
s8 early screening for senile dementia by adopting cognitive impairment intelligent prediction.
Further, the step S3 specifically includes, for the integration and transformation of features, the discretization and reduction of data, expanding 277 original query terms to obtain a vector of 324 variables, and generating 1121 binary variables.
Further, step S4 specifically includes two links of expert knowledge feature selection and intelligent algorithm feature selection, in the first link, some question items known to be biased in the data collection process and not suitable as predictors are removed based on expert knowledge, and question items requiring professional evaluation and not easy are removed, so that the dimension of the vector of 324 variables is reduced to the vector of 212 variables, and in the second link, the vector of 212 variables is reduced to the vector of the key 20 variables with high prediction capability through intelligent algorithm feature selection.
Further, the step S6 includes constructing a sample size ratio of 9 by using a random hierarchical sampling technique: 1, 10 groups of training set and test set pairing data sets; any sampling or weighting operation related to the modeling algorithm for changing the proportion or weight of the positive and negative samples is only limited to a training set, and a test set is only used for performance evaluation of a trained model, so that the rigor of the performance evaluation of the model is ensured; the average performance of predictive modeling of 10 sets of paired data sets was calculated for evaluating the effectiveness of the modeling method of the present invention.
Further, the step S7 includes, in combination with expert knowledge, performing addition, deletion, integration, and transformation on the data feature variables, and adjusting the model parameters to achieve the best performance of the prediction model.
The method has the advantages that according to the basic condition, the living habits, the physical conditions, the medical history, the treatment and other relevant factors of the patient, through data mining, 20 prediction factors which are most relevant to the onset of the cognitive disorder and are suitable for public self-evaluation are analyzed. The constructed intelligent prediction model can control the question items to be about 20 items, only needs little time to fill in, and can immediately obtain an evaluation result after filling in, including risk height classification and risk probability estimation, so that the clinical practice requirements can be met, the model prediction accuracy reaches 70%, the recall rate at least reaches 70%, and the constructed intelligent prediction model is simple and easy to understand in evaluation, simple to operate, free of guidance of professional medical personnel, suitable for public self-evaluation, and high in prediction accuracy.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a schematic cross-validation diagram in ten folds.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings by way of specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, the present invention provides a method for constructing an intelligent prediction of cognitive impairment, comprising the following steps,
s1, acquiring original questionnaire data;
s2, data cleaning;
s3, preprocessing and visualizing the data;
s4, combining expert knowledge feature screening and intelligent algorithm feature screening to obtain a feature subset;
s5, constructing an intelligent cognitive disorder prediction model;
s6, verifying effectiveness of the cognitive disorder intelligent prediction model by adopting cross validation;
s7, debugging and optimizing the model by combining expert knowledge;
s8 early screening for senile dementia by adopting cognitive impairment intelligent prediction.
Step S2 of the present invention specifically includes missing value processing, smooth noise data processing, isolated point identification and deletion, and inconsistency processing for data.
Step S3 of the present invention specifically includes integrating and transforming features, discretizing data, and reducing, and expanding 277 original query terms to obtain 324 variable vectors, and generating 1121 binary variables.
Step S4 of the present invention specifically includes two links of expert knowledge feature selection and intelligent algorithm feature selection. In the first step, some question items known to be biased in the data collection process, question items not suitable as prediction factors and question items requiring professional evaluation and not easy are eliminated based on expert knowledge, so that the dimensionality of the vectors is reduced from 324 variables to 212 variables. In the second step, the vectors of 212 variables are reduced to the vectors of 20 key variables with high prediction capability through intelligent algorithm feature selection to meet the requirements of accuracy and usability of a final model, and the intelligent algorithm comprises a variance selection method, a correlation coefficient method, chi-square test, mutual information, recursive feature elimination method and decision tree method.
The step S5 includes the steps of,
a plurality of prediction/classification algorithms (decision trees, random forests, cognitive impairment intelligent prediction models provided by the invention, Bayesian networks, support vector machines, neural networks and the like) in the field of data mining and machine learning are adopted as a candidate modeling algorithm library. And constructing a candidate model library by searching different combinations of a modeling algorithm and parameters thereof. And selecting an optimal model from the candidate model library according to model prediction performance evaluation indexes such as prediction Accuracy (Accuracy), recall rate, AUC (area understrator ROC) and the like through a 10-fold cross validation (10-fold cross validation) mode.
The model construction comprises medical interpretation of the feature selection result and the parameters and/or structures of the final model, so that model overfitting (over-fitting) caused by data snooping is avoided, and balance of prediction performance and reasonableness of the model is realized.
The step S6 includes the steps of,
the random hierarchical sampling technology is adopted to construct a sample size ratio of 9: 1, 10 groups of training set and test set pairing data sets; any sampling or weighting operation related to the modeling algorithm for changing the proportion or weight of the positive and negative samples is only limited to a training set, and a test set is only used for performance evaluation of a trained model, so that the rigor of the performance evaluation of the model is ensured; the average performance of predictive modeling of 10 sets of paired data sets was calculated for evaluating the effectiveness of the modeling method of the present invention.
The step S7 includes, in combination with expert knowledge, performing addition, deletion, integration, and transformation on the data feature variables, and adjusting model parameters to achieve the best performance of the prediction model.
The method compares kNN, decision tree (decisionTree), random forest (RandomForest), cognitive impairment intelligent prediction model of the invention and naive Bayes network (f)
Bayes), Support Vector Machine (SVM), AdaBoost, etc. And obtaining a multi-model performance comparison result shown in the following table by taking common performance evaluation indexes such as AUC, CA, F1-measure and the like as metrics. Experimental results show that the AUC index of the model provided by the invention is highest.
Candidate model performance comparison table based on 212 features
The intelligent cognitive disorder prediction model provided by the invention comprises the following steps,
the vector x' of the p independent variables obtained in step S4 is (x)1，x2，xp) Assuming that the conditional probability P (Y ═ 1| x) ═ P is the probability of occurrence of an observation amount with respect to a cognitive impairment event, the cognitive impairment intelligent prediction model can be expressed as
Changing nominal variables contained in the test data into virtual variables, namely changing the nominal variables with k values into k-1 virtual variables, wherein D is a virtual variable;
j and l represent intermediate variables.
Parameter beta0，β1，…，βpEstimating parameters for maximum flame;
defining a conditional probability of not developing cognitive impairment as
Then, the ratio of the probability of occurrence of cognitive disorder to the probability of non-occurrence of cognitive disorder is
Logarithmic by the above formula to obtain
For n observation samples x1, x2, … and xn, the observed values are y1，y2，…，yn，
Each joint distribution can be represented as a product of each marginal distribution.
Logarithm of the function
And (5) carrying out derivation on the functions to obtain a likelihood equation.
j is 1,2, p, p is the number of independent vectors,
the second partial derivative is calculated for L (beta),
writing the above formula into a matrix form, wherein H represents the matrix, and X represents
Order to
Then H ═ XTVX。
Reissue to order
Transformation of marketing into form of Newton's iterative method
Wnew＝Wold-H-1U
In the above formula, the matrix H is positive and definite, and H is solved-1U is the matrix X in U for solving linear equation H X, and H is expressed as the decomposition of the product of a lower triangular matrix L and its transpose.
The asymptotic variance and covariance of the maximum likelihood estimate are estimated from the inverse of the information matrix.
The information matrix is actually the negative of the second derivative of L (β), expressed as
The variance and covariance of the estimates are denoted as var (β) ═ I-1，
Estimate betajIs a value on the diagonal of the inverse of the matrix I, and the estimate value betajAnd betalCovariance of (β)jAnd betalIs equal to
) At values other than diagonal
Using the estimated value of betajIs expressed as
Solving for parameter beta0，β1，…，βpThe value of (c).
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
It will be apparent to those skilled in the art that the steps of the present invention described above may be implemented in a general purpose computing device, centralized on a single computing device or distributed across a network of computing devices, or alternatively, in program code executable by a computing device, such that the steps shown and described may be performed by a computing device stored on a computer storage medium (ROM/RAM, magnetic or optical disk), and in some cases, performed in a different order than that shown and described herein, or separately fabricated into individual integrated circuit modules, or fabricated into a single integrated circuit module from multiple ones of them. Thus, the present invention is not limited to any specific combination of hardware and software.
The foregoing is a more detailed description of the present invention that is presented in conjunction with specific embodiments, and the practice of the invention is not to be considered limited to those descriptions. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (5)
1. The method for constructing the intelligent prediction method of the cognitive impairment is characterized by comprising the following steps,
s1, acquiring original questionnaire data;
s2, data cleaning;
s3, preprocessing and visualizing the data;
s4, combining expert knowledge feature screening and intelligent algorithm feature screening to obtain a feature subset;
s5, constructing an intelligent cognitive disorder prediction model;
s6, verifying effectiveness of the cognitive disorder intelligent prediction model by adopting cross validation;
s7, debugging and optimizing the model by combining expert knowledge;
s8 early screening for senile dementia by adopting cognitive impairment intelligent prediction.
2. The method for constructing an intelligent prediction of cognitive impairment as defined in claim 1, wherein the step S3 specifically comprises expanding 277 original query terms into a 324-variable vector for feature integration and transformation, data discretization and reduction, and generating 1121 binary variables.
3. The method for constructing the intelligent cognitive impairment prediction method according to claim 1, wherein the step S4 specifically includes two links of expert knowledge feature selection and intelligent algorithm feature selection, in the first link, some question items known to have bias in data collection process, question items not suitable as prediction factors, and question items requiring professional evaluation and non-simplification are removed based on expert knowledge, so that the vectors of 324 variables are reduced to the vectors of 212 variables, and in the second link, the vectors of 212 variables are reduced to the vectors of key 20 variables with high prediction ability through the intelligent algorithm feature selection.
4. The method for constructing an intelligent prediction of cognitive impairment as defined in claim 1, wherein the step S6 includes constructing the ratio of sample size to 9: 1, 10 groups of training set and test set pairing data sets; any sampling or weighting operation related to the modeling algorithm for changing the proportion or weight of the positive and negative samples is only limited to a training set, and a test set is only used for performance evaluation of a trained model, so that the rigor of the performance evaluation of the model is ensured; the average performance of predictive modeling of 10 sets of paired data sets was calculated for evaluating the effectiveness of the modeling method of the present invention.
5. The method for constructing an intelligent prediction of cognitive impairment as claimed in claim 1, wherein the step S7 includes adding or deleting or integrating, transforming the data feature variables and adjusting the model parameters in combination with expert knowledge.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110596294.9A CN113380407A (en) | 2021-05-30 | 2021-05-30 | Method for constructing intelligent prediction of cognitive impairment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110596294.9A CN113380407A (en) | 2021-05-30 | 2021-05-30 | Method for constructing intelligent prediction of cognitive impairment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113380407A true CN113380407A (en) | 2021-09-10 |
Family
ID=77574874
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110596294.9A Pending CN113380407A (en) | 2021-05-30 | 2021-05-30 | Method for constructing intelligent prediction of cognitive impairment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113380407A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114023452A (en) * | 2021-11-10 | 2022-02-08 | 中国科学院心理研究所 | Multi-dimensional early warning model construction method for screening high risk of cognitive impairment and evaluation system thereof |
| CN114068012A (en) * | 2021-11-15 | 2022-02-18 | 北京智精灵科技有限公司 | Cognitive decision-oriented multi-dimensional hierarchical drift diffusion model modeling method |
| CN114420300A (en) * | 2022-01-20 | 2022-04-29 | 北京大学第六医院 | Chinese old cognitive impairment prediction model |
| CN114550918A (en) * | 2022-02-23 | 2022-05-27 | 中国科学院心理研究所 | Mental disorder evaluation method and system based on drawing characteristic data |
| WO2023087917A1 (en) * | 2021-11-17 | 2023-05-25 | 北京智精灵科技有限公司 | Cognitive decision-making evaluation method and system based on multi-dimensional hierarchical drift diffusion model |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104834983A (en) * | 2014-12-25 | 2015-08-12 | 平安科技（深圳）有限公司 | Business data processing method and device |
| CN104881591A (en) * | 2015-06-25 | 2015-09-02 | 贾建平 | Cognitive disorder data processing method and system |
| CN105653833A (en) * | 2014-11-12 | 2016-06-08 | 腾讯科技（深圳）有限公司 | Method and device for recommending game community |
| CN107909453A (en) * | 2017-12-18 | 2018-04-13 | 南京理工大学 | One kind, which is paid in advance, supplements intelligent analysis system and method with money |
| CN110085314A (en) * | 2019-04-11 | 2019-08-02 | 上海翼依信息技术有限公司 | Intelligent analysis method, system and the equipment of medical test data |
| CN110400022A (en) * | 2019-07-31 | 2019-11-01 | 中国工商银行股份有限公司 | Self-help teller machine cash dosage prediction technique and device |
| CN111755120A (en) * | 2020-06-29 | 2020-10-09 | 西南民族大学 | Cognitive impairment prediction method based on edge intelligence and multimode perception |
| CN112086108A (en) * | 2020-08-04 | 2020-12-15 | 科大讯飞股份有限公司 | Cognitive disorder prediction method, electronic device and storage device |
-
2021
- 2021-05-30 CN CN202110596294.9A patent/CN113380407A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105653833A (en) * | 2014-11-12 | 2016-06-08 | 腾讯科技（深圳）有限公司 | Method and device for recommending game community |
| CN104834983A (en) * | 2014-12-25 | 2015-08-12 | 平安科技（深圳）有限公司 | Business data processing method and device |
| CN104881591A (en) * | 2015-06-25 | 2015-09-02 | 贾建平 | Cognitive disorder data processing method and system |
| CN107909453A (en) * | 2017-12-18 | 2018-04-13 | 南京理工大学 | One kind, which is paid in advance, supplements intelligent analysis system and method with money |
| CN110085314A (en) * | 2019-04-11 | 2019-08-02 | 上海翼依信息技术有限公司 | Intelligent analysis method, system and the equipment of medical test data |
| CN110400022A (en) * | 2019-07-31 | 2019-11-01 | 中国工商银行股份有限公司 | Self-help teller machine cash dosage prediction technique and device |
| CN111755120A (en) * | 2020-06-29 | 2020-10-09 | 西南民族大学 | Cognitive impairment prediction method based on edge intelligence and multimode perception |
| CN112086108A (en) * | 2020-08-04 | 2020-12-15 | 科大讯飞股份有限公司 | Cognitive disorder prediction method, electronic device and storage device |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114023452A (en) * | 2021-11-10 | 2022-02-08 | 中国科学院心理研究所 | Multi-dimensional early warning model construction method for screening high risk of cognitive impairment and evaluation system thereof |
| CN114068012A (en) * | 2021-11-15 | 2022-02-18 | 北京智精灵科技有限公司 | Cognitive decision-oriented multi-dimensional hierarchical drift diffusion model modeling method |
| CN114068012B (en) * | 2021-11-15 | 2022-05-10 | 北京智精灵科技有限公司 | Cognitive decision-oriented multi-dimensional hierarchical drift diffusion model modeling method |
| WO2023087917A1 (en) * | 2021-11-17 | 2023-05-25 | 北京智精灵科技有限公司 | Cognitive decision-making evaluation method and system based on multi-dimensional hierarchical drift diffusion model |
| CN114420300A (en) * | 2022-01-20 | 2022-04-29 | 北京大学第六医院 | Chinese old cognitive impairment prediction model |
| CN114420300B (en) * | 2022-01-20 | 2023-08-04 | 北京大学第六医院 | Chinese senile cognitive impairment prediction model |
| CN114550918A (en) * | 2022-02-23 | 2022-05-27 | 中国科学院心理研究所 | Mental disorder evaluation method and system based on drawing characteristic data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chakraborty et al. | Novel Enhanced-Grey Wolf Optimization hybrid machine learning technique for biomedical data computation | |
| CN113380407A (en) | Method for constructing intelligent prediction of cognitive impairment | |
| Kundu et al. | AltWOA: Altruistic Whale Optimization Algorithm for feature selection on microarray datasets | |
| Maraziotis | A semi-supervised fuzzy clustering algorithm applied to gene expression data | |
| Turner et al. | Hierarchical approximate Bayesian computation | |
| Sachan et al. | Evidential reasoning for preprocessing uncertain categorical data for trustworthy decisions: An application on healthcare and finance | |
| Polat et al. | Principles component analysis, fuzzy weighting pre-processing and artificial immune recognition system based diagnostic system for diagnosis of lung cancer | |
| Klami et al. | Probabilistic approach to detecting dependencies between data sets | |
| Khanmohammadi et al. | AHP based classification algorithm selection for clinical decision support system development | |
| Paredes et al. | Long term cardiovascular risk models’ combination | |
| Prasetio | Genetic Algorithm to Optimize k-Nearest Neighbor Parameter for Benchmarked Medical Datasets Classification | |
| Kamel et al. | Feature selection using grasshopper optimization algorithm in diagnosis of diabetes disease | |
| Pena et al. | Learning dynamic Bayesian network models via cross-validation | |
| Chamlal et al. | A hybrid feature selection approach for Microarray datasets using graph theoretic-based method | |
| Shi et al. | Bayesian model selection for generalized linear models using non-local priors | |
| Li et al. | Causal-aware generative imputation for automated underwriting | |
| Prasetio et al. | Features Selection and k-NN Parameters Optimization based on Genetic Algorithm for Medical Datasets Classification | |
| Angayarkanni | Predictive analytics of chronic kidney disease using machine learning algorithm | |
| Shujaaddeen et al. | A New Machine Learning Model for Detecting levels of Tax Evasion Based on Hybrid Neural Network | |
| Yin et al. | Stroke risk prediction: Comparing different sampling algorithms | |
| Lou et al. | Analysis of temporal high-dimensional gene expression data for identifying informative biomarker candidates | |
| Sabouri et al. | Prediction of Depression via Supervised Learning Models: Performance Comparison and Analysis. | |
| De Silva et al. | Performance Analysis of Machine Learning Classification Algorithms in the Case of Heart Failure Prediction | |
| Khaire et al. | Optimizing feature selection parameters using statistically equivalent signature (SES) algorithm | |
| Chezhiyan et al. | An Efficient Pre-Processing Method Using Optimization Techniques For Heart Disease Prediction |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231207 Address after: Floor 16, No. 192 Yuzhou Road, Yuzhong District, Chongqing, 400042 Applicant after: Chongqing Zhiyixing Technology Development Co.,Ltd. Address before: 400016 No. 1, Medical College Road, Yuzhong District, Chongqing Applicant before: Chongqing Medical University |
|
| TA01 | Transfer of patent application right |