Method and device for acquiring screening model training data of patients with mild cognitive impairment and electronic equipment

Abstract

The invention provides a mild cognitive impairment patient screening model training data acquisition method and device and electronic equipment, and relates to the technical field of training data acquisition, and the method comprises the steps: constructing a community natural population cognitive health queue, and obtaining related evaluation data of queue research sample cognition; on the basis of a literature review method, a professional domain knowledge injection method, a domain expert consultation method and a Shap interpretable machine learning method, characteristic variables related to the mild cognitive impairment are screened out from the evaluation data and serve as model training data. The degree of association between the model training data obtained through the method and the mild cognitive impairment is higher, the data source is more real, and the method has more practical application significance.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of training data acquisition, in particular to a mild cognitive impairment patient screening model training data acquisition method and device and electronic equipment. BACKGROUND

[0002] As the early stage of dementia, how to early detect MCI patients in the apparent healthy community is the top priority of early prevention and control of dementia. Although large-scale population screening for mild cognitive impairment cannot be carried out due to various restrictions, the development and application of new screening tools to achieve rapid, accurate and intelligent screening of mild cognitive impairment in the community has become the common goal of global scholars.

[0003] With the rapid development of artificial intelligence, using artificial intelligence models for mild cognitive impairment screening is one of the main development directions. The mild cognitive impairment screening function of the artificial intelligence model is obtained by training data related to mild cognitive impairment. However, the existing training data related to mild cognitive impairment has the problems of non-authentic data source, too much and complex data, and low correlation between data and mild cognitive impairment, which will lead to the problem of inaccurate screening of the mild cognitive impairment screening model obtained by training. SUMMARY Embodiments of the present application provide a mild cognitive impairment patient screening model training data acquisition method, device and electronic equipment to solve the technical problems existing in the prior art.

[0004] Other characteristics and advantages of the present application will become apparent from the following detailed description, or will be learned by practice of the present application.

[0005] According to a first aspect of the embodiments of the present application, a mild cognitive impairment patient screening model training data acquisition method is provided, comprising: constructing a community natural population cognitive health cohort, and acquiring cognitive related evaluation data of cohort study samples; screening feature variables related to mild cognitive impairment from the evaluation data based on a literature review method, a professional field knowledge injection method, a field expert consultation method and a Shap interpretable machine learning method, as model training data.

[0006] In some embodiments of the present application, based on the foregoing scheme, the construction of the community natural population cognitive health cohort and the acquisition of the cognitive related evaluation data of the cohort study samples comprise: Population samples were recruited from natural population communities. Using a cohort research strategy as the entry point, comprehensive cognitive health assessment / diabetes comprehensive assessment was conducted on all subjects. Basic demographic information, cognitive and influencing factor assessment data, physical examination and biological specimen testing information of the sample population were systematically collected.

[0007] In some embodiments of the present application, based on the aforementioned scheme, in the process of constructing a cognitive health cohort of a natural population in the community, a three-level quality control strategy is adopted to carry out quality control work at the three levels of preparation, execution, and maintenance.

[0008] In some embodiments of the present application, based on the aforementioned scheme, the method of screening characteristic variables related to mild cognitive impairment from the evaluation data based on the literature review method, the method of injecting professional domain knowledge, the method of consulting domain experts, and the Shap interpretable machine learning method as model training data includes: The literature review method was used to screen out characteristic variables closely related to the occurrence of mild cognitive impairment from the evaluation data; By using a professional domain knowledge injection method combined with clinical knowledge, irrelevant noise features are eliminated from the characteristic variables closely related to the occurrence of mild cognitive impairment, and a set of candidate characteristic variables related to mild cognitive impairment is preliminarily determined; The candidate feature variable set is consulted with the help of domain expert consultation method, and the candidate feature variable set is sorted again to finally determine the total candidate feature variable set; Using Shap interpretable machine learning method, reverse feature screening is performed on the feature subsets in the total candidate feature variable set, and the top N feature variables in feature importance ranking in each feature subset are selected; For the first N feature variables in each feature subset, they are combined in order of feature importance to obtain multiple feature combination variables as model training data, where N is an integer greater than or equal to 1.

[0009] In some embodiments of the present application, based on the aforementioned scheme, the literature review method is used to screen characteristic variables closely related to the occurrence of mild cognitive impairment from the evaluation data, including: Based on the literature review method, we collected the influencing factors related to mild cognitive impairment from the literature related to mild cognitive impairment and formed a review list of influencing factors of mild cognitive impairment; Based on the review list of influencing factors of mild cognitive impairment, characteristic variables closely related to the occurrence of cognitive impairment are screened from the evaluation data.

[0010] In some embodiments of the present application, based on the foregoing scheme, the professional knowledge injection method eliminates irrelevant noise features from the feature variables closely related to the occurrence of mild cognitive impairment in combination with clinical knowledge, and preliminarily determines a candidate feature variable set related to mild cognitive impairment, including: An evaluation model is developed around the mild cognitive impairment influencing factor review list, wherein the evaluation indicators of the evaluation model include blood collection indicators, lifestyle characteristics, scale evaluation characteristics, cognitive evaluation indicators, previous chronic disease characteristics, and physical dimension indicators; The evaluation model is pre-tested in combination with expert experience and evaluation scenarios; The feature variables closely related to the occurrence of cognitive impairment are evaluated by using the verified evaluation model, and the evaluation results are cleaned and arranged to obtain a candidate feature variable set related to mild cognitive impairment.

[0011] In some embodiments of the present application, based on the foregoing scheme, the field expert consultation method is used to consult the candidate feature variable set, and the candidate feature variable set is arranged again to finally determine a total candidate feature variable set, including: The candidate feature variable set is classified and processed to obtain a plurality of feature subsets; The field expert consultation method is used to screen the features in each feature subset; The screened plurality of feature subsets are sequentially combined in a single mode and a multi-mode to obtain the total candidate feature variable set.

[0012] In some embodiments of the present application, based on the foregoing scheme, the Shap interpretable machine learning method is used to perform reverse feature screening on the feature subsets in the total candidate feature variable set, and the feature variables with top N importance in each feature subset are selected, including: The Shap interpretable machine learning method is used to sort the importance of the features in each feature subset in the total candidate feature variable set in terms of their contribution to label prediction, and a plurality of feature importance sorted feature distribution results are obtained; Each feature importance sorted feature distribution result is arranged, and in combination with expert experience, the feature variables with top N importance in each feature subset are retained.

[0013] According to a second aspect of an embodiment of the present application, a mild cognitive impairment patient screening model training data acquisition device is provided, including: An acquisition unit is configured to construct a community natural population cognitive health cohort, and acquire cognitive related evaluation data of a cohort study sample; The screening unit is configured to screen feature variables related to mild cognitive impairment from the evaluation data based on a literature review method, a professional field knowledge injection method, a field expert consultation method, and a Shap interpretable machine learning method, as model training data.

[0014] According to a third aspect of the embodiments of the present application, an electronic device is provided, comprising a memory and a processor. The memory is configured to store computer instructions. The processor is configured to invoke the computer instructions stored in the memory, so that the electronic device performs the method according to the first aspect.

[0015] The technical solution of the present application has the following beneficial effects: The training data obtained by the method is based on a community of natural persons, which is more realistic and has higher application value than the training data obtained by the existing method based on hospital patients.

[0016] The training data is obtained based on the literature review method, the professional field knowledge injection method, the field expert consultation method, and the Shap interpretable machine learning method, so that the training data is more closely related to mild cognitive impairment, thereby ensuring that the model trained has more accurate screening performance.

[0017] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings, which are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application and, together with the specification, serve to explain the principles of the present application. It is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor. In the drawings: Figure 1 A flowchart of a method for obtaining training data of a mild cognitive impairment patient screening model is shown according to an embodiment of the present application; Figure 2 A block diagram of an apparatus for obtaining training data of a mild cognitive impairment patient screening model is shown according to an embodiment of the present application; Figure 3 A block diagram of an electronic device is shown according to an embodiment of the present application; Figure 4 A structural diagram of a computer system suitable for implementing the electronic device of the embodiments of the present application is shown. DETAILED DESCRIPTION

[0019] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations can be implemented in any

[0020] Moreover, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the

[0021] The block diagrams in the drawings show only the functionality and arrangement of physical blocks, these can not necessarily imply physical constitution in its implementation. That is, these can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0022] The flow diagrams shown in the drawings are only exemplary and not necessarily all inclusive of all content and operations / steps, nor are they necessarily performed in the order described. For example, some operations / steps can be broken down further, while some operations / steps can be combined or partially combined, and thus the actual order of execution can be changed according to actual conditions.

[0023] It should be noted that "a plurality of" as referred to herein means two or more.

[0024] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0025] Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The following embodiments and features in the embodiments can be combined with each other without conflict.

[0026] Referring to Figure 1 Fig. 1 shows a flow diagram of a method for acquiring training data of a mild cognitive impairment patient screening model according to an embodiment of the present application.

[0027] As Figure 1 shown, a mild cognitive impairment patient screening model training data acquisition method is shown, specifically including steps S100 to S200.

[0028] Referring Figure 1 to the drawings, in step S100, a community natural population cognitive health cohort is constructed, and cognitive-related evaluation data of cohort study samples are acquired.

[0029] In some possible embodiments, based on the foregoing scheme, the step S100 includes: In the community of natural population, population samples are recruited, and cognitive health comprehensive evaluation / diabetes comprehensive assessment is performed on all subjects as a breakthrough point of population research strategy. Basic demographic information, cognitive and influencing factor evaluation data, physical examination and biological specimen detection information of the sample population are systematically collected.

[0030] It should be noted that in the present embodiment, the acquired data are all from the real world natural population community, and this method has more practical application value compared with the traditional method of acquiring data from hospital patients.

[0031] In some possible embodiments, based on the foregoing scheme, in the process of constructing the community natural population cognitive health cohort, a three-level quality control strategy is adopted to carry out quality control work from three aspects of preparation, execution and maintenance.

[0032] It should be noted that in the present embodiment, the three-level quality control strategy is adopted in the process of constructing the community natural population cognitive health cohort, which can lay a solid foundation for accurate collection of real world data, development of cognitive-related scientific research and sustainable cohort development.

[0033] Continuing to refer to Figure 1 , in step S200, feature variables related to mild cognitive impairment are screened from the evaluation data based on the literature review method, professional field knowledge injection method, field expert consultation method and Shap interpretable machine learning method, and used as model training data.

[0034] In some possible embodiments, based on the foregoing scheme, the step S200 includes: In step S210, the literature review method is used to screen feature variables closely related to the occurrence of mild cognitive impairment from the evaluation data. In step S220, irrelevant noise features are removed from the feature variables closely related to the occurrence of mild cognitive impairment by means of the professional field knowledge injection method combined with clinical knowledge, and a set of candidate feature variables related to mild cognitive impairment is preliminarily determined. Step S230: Consult the candidate feature variable set with the help of a domain expert consultation method, sort the candidate feature variable set again, and finally determine the total candidate feature variable set; Step S240, using the Shap interpretable machine learning method to perform reverse feature screening on the feature subsets in the total candidate feature variable set, and select the top N feature variables in the feature importance ranking in each feature subset; In step S250 , the first N feature variables in each feature subset are combined in order of feature importance to obtain a plurality of feature combination variables as model training data, where N is an integer greater than or equal to 1.

[0035] In some feasible embodiments, based on the above solution, step S210 includes: Based on the literature review method, we collected the influencing factors related to mild cognitive impairment from the literature related to mild cognitive impairment and formed a review list of influencing factors of mild cognitive impairment; Based on the review list of influencing factors of mild cognitive impairment, characteristic variables closely related to the occurrence of cognitive impairment are screened from the evaluation data.

[0036] Exemplarily, the specific process of step S210 is as follows: Conduct a systematic literature search, summary, and review of previous research literature on mild cognitive impairment, collect information on independent influencing factors, assessment scales, biomarkers, and other factors related to mild cognitive impairment, and develop a review list of influencing factors of mild cognitive impairment. The retrospective checklist of factors affecting mild cognitive impairment was used to screen out characteristic variables closely related to the occurrence of cognitive impairment from the evaluation data.

[0037] In some feasible embodiments, based on the above solution, step S220 includes: An evaluation model is developed based on the review list of influencing factors of mild cognitive impairment, wherein the evaluation indicators of the evaluation model include: blood collection indicators, lifestyle characteristics, scale assessment characteristics, cognitive assessment indicators, previous chronic disease characteristics, and physical dimension indicators; Conducting pre-experimental verification of the evaluation model based on expert experience and evaluation scenarios; The validated assessment model was used to evaluate the characteristic variables closely related to the occurrence of cognitive impairment, and the assessment results were cleaned and sorted to obtain a set of alternative characteristic variables related to mild cognitive impairment.

[0038] For example, based on the above example, the specific process of step S220 is as follows: An evaluation tool is developed based on the review list of mild cognitive impairment influencing factors. The evaluation indicators of the evaluation tool include blood collection indicators, lifestyle characteristics, scale evaluation characteristics, cognitive evaluation indicators, previous chronic disease characteristics, and physical dimension indicators. After expert consultation and discussion, the "evaluation tool v1.0" is formed.

[0039] In combination with the use scenario of the evaluation tool, a small-scale population pre-test is carried out to objectively evaluate the scientificity and feasibility of the "evaluation tool v1.0". Meanwhile, feedbacks of the "evaluation tool v1.0" are collected during the small-scale population pre-test. After expert consultation and discussion, the "evaluation tool v2.0" is formed for formal data collection and use.

[0040] The characteristic variables closely related to cognitive impairment are evaluated by using the "evaluation tool v2.0", and all the data obtained after evaluation are systematically arranged and cleaned to obtain a set of alternative characteristic variables.

[0041] In some feasible embodiments, based on the foregoing scheme, step S230 includes: The alternative characteristic variable set is subjected to category classification processing to obtain a plurality of characteristic subsets; Each characteristic in each characteristic subset is screened by using a domain expert consultation method; The screened plurality of characteristic subsets are sequentially combined in a single mode and a multi-mode to obtain a total set of alternative characteristic variables.

[0042] For example, based on the foregoing example, the specific process of step S230 is as follows: On the basis of data cleaning, the data categories in the alternative characteristic variable set are uniformly classified, i.e., the characteristics in the alternative characteristic variable set are divided into an A characteristic subset (interrogation and physical examination), a B characteristic subset (biological sample detection indicators), and a C characteristic subset (innovative characteristic engineering). The A characteristic subset includes 1281 characteristics. Under the premise of using expert consultation and based on previous professional medical knowledge and experience, 40 characteristics are screened and used from the 1281 characteristics. The B characteristic subset includes 54 characteristics. After comprehensive consideration by the expert group, it is decided to use all of them. The C characteristic subset includes 6 innovative characteristic engineering variables. This type of variable is mainly based on the experience of electroencephalogram preprocessing methods to convert existing characteristics into innovative indicators.

[0043] The A, B, and C characteristic subsets are sequentially combined, and finally expanded into 7 data characteristic subsets composed of single mode and multi-mode, i.e., A, B, C, AB, AC, BC, and ABC characteristic subsets.

[0044] In some feasible embodiments, based on the foregoing scheme, step S240 includes: The Shap interpretable machine learning method is used to label whether it is mild cognitive impairment, the contribution of the features in each feature subset in the total candidate feature variable set to the label prediction is ranked in importance, and a plurality of feature importance ranking feature distribution results are obtained. The feature distribution results of each feature importance ranking are sorted, and the top N features in each feature subset are retained based on expert experience.

[0045] For example, based on the foregoing example, the specific process of step S240 is as follows: Based on the data of the A feature subset, the B feature subset, the C feature subset, the AB feature subset, the AC feature subset, the BC feature subset, and the ABC feature subset, the SHAP interpretable machine learning technology is used to label whether it is mild cognitive impairment, and the contribution of the features in each subset to the label prediction is ranked in importance, i.e. 7 groups of feature importance ranking feature distribution results are obtained.

[0046] The feature importance ranking feature distribution results of each feature subset are sorted, and the top 20 features in the feature importance ranking are retained as the feature pool for model training after expert consultation, in order to prepare for the subsequent model of different feature combinations.

[0047] For example, based on the foregoing example, the specific process of step S250 is as follows: Based on the above steps, 7 groups of feature importance ranking feature distribution results of the A feature subset, the B feature subset, the C feature subset, the AB feature subset, the AC feature subset, the BC feature subset, and the ABC feature subset are obtained for label prediction (whether it is mild cognitive impairment).

[0048] Taking the top 20 features extracted from the A feature subset as an example, the features in this group are systematically combined, i.e. “top 3 feature combination”, “top 4 feature combination”, “top 5 feature combination”, “top 6 feature combination”, “top 7 feature combination”, “top 8 feature combination”, “top 9 feature combination”, “top 10 feature combination”, “top 11 feature combination”, “top 12 feature combination”, “top 13 feature combination”, “top 14 feature combination”, “top 15 feature combination”, “top 16 feature combination”, “top 17 feature combination”, “top 18 feature combination”, “top 19 feature combination”, “top 20 feature combination”, so that 18 combinations of features are obtained in this group.

[0049] It should be noted that the “top x feature combination” in the present embodiment refers to the combination of the top x features, and x is a positive integer.

[0050] For example, the "top 3 feature combinations" refers to the combination of the features ranked first, second and third.

[0051] Similarly, after combining all feature subsets, 7 groups of 18 feature combinations per group = 126 feature combinations are obtained.

[0052] Then, after training the 126 feature combinations as model training data on the model, 126 mild cognitive impairment patient screening models independent of each other are obtained.

[0053] The device embodiment of the present application is described below, which can be used to execute the mild cognitive impairment patient screening model training data acquisition method in any of the embodiments of the present application. For details not disclosed in the device embodiment of the present application, please refer to the embodiments of the method of the present application.

[0054] Referring to Figure 2 According to the mild cognitive impairment patient screening model training data acquisition device 200 of one embodiment of the present application, as shown in the figure, it comprises: The acquisition unit 201 is configured to construct a community natural population cognitive health cohort and acquire cognitive-related evaluation data of cohort study samples. The screening unit 202 is configured to screen feature variables related to mild cognitive impairment from the evaluation data based on the literature review method, the professional field knowledge injection method, the field expert consultation method and the Shap interpretable machine learning method, as model training data.

[0055] As Figure 3 shown, the present application also provides an electronic device 300, which comprises a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, it implements the steps of the above-mentioned mild cognitive impairment patient screening model training data acquisition method.

[0056] Since the electronic device introduced in the present embodiment is the device used to implement the mild cognitive impairment patient screening model training data acquisition device in the embodiments of the present application, based on the method introduced in the embodiments of the present application, those skilled in the art can understand the specific implementation of the electronic device of the present embodiment and its various forms of variation, so here the electronic device how to implement the method in the embodiments of the present application will not be introduced in detail, as long as the device used by those skilled in the art to implement the method in the embodiments of the present application belongs to the scope of the present application.

[0057] In the specific implementation process, the computer program 311 can implement any of the embodiments of the corresponding embodiments of the first aspect when executed by the processor.

[0058] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown.

[0059] It should be noted that Figure 4 The computer system 400 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0060] like Figure 4 As shown, computer system 400 includes a central processing unit 401, which can perform various appropriate actions and processes according to programs stored in read-only memory 402 or programs loaded from storage unit 408 into random access memory 403, such as executing the methods described in the above embodiments. Random access memory 403 also stores various programs and data required for system operation. Central processing unit 401, read-only memory 402, and random access memory 403 are connected to each other via bus 404. Input / output interface 405 is also connected to bus 404.

[0061] The following components are connected to the input / output interface 405: an input section 406 including a keyboard, mouse, and the like; an output section 407 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and speakers; a storage section 408 including devices such as a hard disk; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output interface 405 as needed. Removable media 411, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 410 as needed, so that computer programs read from the removable media can be installed in the storage section 408 as needed.

[0062] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 409 and / or installed from a removable medium 411. When the computer program is executed by the central processing unit 401, the various functions defined in the system of the present application are performed.

[0063] It should be noted that the computer-readable medium in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present application, the computer-readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, transmit, propagate or transport a program for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, or the like, or any suitable combination thereof.

[0064] The flowcharts and block diagrams in the drawings illustrate the possible implementation architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In the flowcharts or block diagrams, each block can represent a module, a program segment or a part of code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different orders than that shown in the drawings. For example, two blocks that are shown in succession can actually be executed substantially in parallel, and sometimes in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams or flowcharts, and the combination of blocks in the block diagrams or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0065] The units described in the embodiments of the present application can be implemented in the form of software, or can be implemented in the form of hardware, and the described units can also be arranged in a processor. In some cases, the names of the units do not constitute a limitation on the units themselves.

[0066] As another aspect, the present application also provides a computer program product or computer program, which includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to enable the computer device to perform the method for acquiring training data of a mild cognitive impairment patient screening model described in the above embodiments.

[0067] As another aspect, the present application also provides a computer readable medium, which can be included in the electronic device described in the above embodiments, or can exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs, which, when executed by the electronic device, enable the electronic device to implement the method for acquiring training data of a mild cognitive impairment patient screening model described in the above embodiments.

[0068] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, such division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into several modules or units.

[0069] From the above description of the embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.) or network, and includes several instructions to enable a computing device (which can be a personal computer, server, touch terminal, or network device, etc.) to perform the methods according to the embodiments of the present application.

[0070] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. It is intended that the application embrace any and all variations of the application that fall within the scope of the general description herein. It is to be understood that the application is not to be limited to the specific examples, methods, and procedures described herein, and that specific examples are to be considered as illustrative only. It is further understood that the application can encompass all such variations as fall within the scope of the application. It is intended that the scope of the application encompass all techniques capable of approximating the teachings provided herein.

Claims

1. A method for obtaining training data for a screening model for patients with mild cognitive impairment, characterized in that: include: Construct a cognitive health cohort of natural populations in the community and obtain cognitive-related assessment data of cohort study samples; Based on the literature review method, professional domain knowledge injection method, domain expert consultation method and Shap interpretable machine learning method, characteristic variables related to mild cognitive impairment were screened out from the evaluation data as model training data.

2. The method according to claim 1, characterized in that The construction of a community natural population cognitive health cohort and the acquisition of cognition-related assessment data of cohort study samples include: Population samples were recruited from natural population communities. Using a cohort research strategy as the entry point, comprehensive cognitive health assessment / diabetes comprehensive assessment was conducted on all subjects. Basic demographic information, cognitive and influencing factor assessment data, physical examination and biological specimen testing information of the sample population were systematically collected.

3. The method according to claim 1, characterized in that In the process of constructing a cognitive health cohort of the natural population in the community, a three-level quality control strategy was adopted, and quality control work was carried out at the three levels of preparation, execution, and maintenance.

4. The method according to any one of claims 1 to 3, characterized in that The method based on literature review, professional domain knowledge injection, domain expert consultation and Shap interpretable machine learning is used to screen out characteristic variables related to mild cognitive impairment from the evaluation data as model training data, including: The literature review method was used to screen out characteristic variables closely related to the occurrence of mild cognitive impairment from the evaluation data; By using a professional domain knowledge injection method combined with clinical knowledge, irrelevant noise features are eliminated from the characteristic variables closely related to the occurrence of mild cognitive impairment, and a set of candidate characteristic variables related to mild cognitive impairment is preliminarily determined; The candidate feature variable set is consulted with the help of domain expert consultation method, and the candidate feature variable set is sorted again to finally determine the total candidate feature variable set; Using Shap interpretable machine learning method, reverse feature screening is performed on the feature subsets in the total candidate feature variable set, and the top N feature variables in feature importance ranking in each feature subset are selected; For the first N feature variables in each feature subset, they are combined in order of feature importance to obtain multiple feature combination variables as model training data, where N is an integer greater than or equal to 1.

5. The method according to claim 4, characterized in that The literature review method was used to screen out characteristic variables closely related to the occurrence of mild cognitive impairment from the evaluation data, including: Based on the literature review method, we collected the influencing factors related to mild cognitive impairment from the literature related to mild cognitive impairment and formed a review list of influencing factors of mild cognitive impairment; Based on the review list of influencing factors of mild cognitive impairment, characteristic variables closely related to the occurrence of cognitive impairment are screened from the evaluation data.

6. The method according to claim 5, characterized in that The method of injecting professional domain knowledge combined with clinical knowledge is used to eliminate irrelevant noise features from the characteristic variables closely related to the occurrence of mild cognitive impairment, and preliminarily determine a set of candidate characteristic variables related to mild cognitive impairment, including: An evaluation model is developed based on the review list of influencing factors of mild cognitive impairment, wherein the evaluation indicators of the evaluation model include: blood collection indicators, lifestyle characteristics, scale assessment characteristics, cognitive assessment indicators, previous chronic disease characteristics, and physical dimension indicators; Conducting pre-experimental verification of the evaluation model based on expert experience and evaluation scenarios; The validated assessment model was used to evaluate the characteristic variables closely related to the occurrence of cognitive impairment, and the assessment results were cleaned and sorted to obtain a set of alternative characteristic variables related to mild cognitive impairment.

7. The method according to claim 6, characterized in that The candidate feature variable set is consulted with the domain expert consultation method, and the candidate feature variable set is sorted again to finally determine the total candidate feature variable set, including: Perform category classification processing on the candidate feature variable set to obtain multiple feature subsets; The features in each feature subset are screened using domain expert consultation method; The multiple feature subsets that have been screened are sequentially combined into single-mode and multi-mode combinations to obtain a total set of candidate feature variables.

8. The method according to claim 7, characterized in that The Shap interpretable machine learning method is used to perform reverse feature screening on the feature subsets in the total candidate feature variable set, and the top N feature variables in the feature importance ranking in each feature subset are selected, including: Using the Shap interpretable machine learning method, with mild cognitive impairment as the label, the features in each feature subset in the total candidate feature variable set are ranked by their importance in terms of their contribution to label prediction, and the feature distribution results of multiple groups of feature importance rankings are obtained; The feature distribution results of each group of feature importance rankings are sorted out, and combined with expert experience, the top N feature variables in each feature subset are retained.

9. A device for acquiring training data of a screening model for patients with mild cognitive impairment, characterized in that: include: Acquisition unit, used to build a cognitive health cohort of natural population in the community and obtain cognitive-related assessment data of cohort study samples; A screening unit is used to screen out characteristic variables related to mild cognitive impairment from the evaluation data based on a literature review method, a professional domain knowledge injection method, a domain expert consultation method, and a Shap interpretable machine learning method as model training data.

10. An electronic device, characterized in that: include: memory and processor; The memory is used to store computer instructions; The processor is configured to call the computer instructions stored in the memory so that the electronic device executes the method according to any one of claims 1 to 8.

Images