Patient screening method and device based on mild cognitive impairment patient model, storage medium and electronic equipment

Abstract

The invention provides a patient screening method and device based on a mild cognitive impairment patient model, a storage medium and electronic equipment, and relates to the technical field of mild cognitive impairment screening, and the method comprises the steps: collecting research sample data based on community natural population health data; extracting training data based on the research sample data; training an extreme gradient lifting algorithm model based on the training data to obtain a plurality of preliminary models; performing model performance evaluation on the plurality of preliminary models, and selecting the preliminary model meeting evaluation requirements as a rapid screening model for mild cognitive impairment; screening patients with mild cognitive impairment based on the rapid screening model for mild cognitive impairment. Through the method, patients with mild cognitive impairment can be accurately screened, and the screening efficiency is high.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mild cognitive impairment screening, in particular to a patient screening method and device based on a mild cognitive impairment patient model, a storage medium and an electronic device. BACKGROUND

[0002] Due to the community screening of MCI (mild cognitive impairment), professional personnel need to be face-to-face evaluated, although the electronic questionnaire evaluation system has been realized at the present stage, but its essence is still a questionnaire evaluation mode. Whether it is a paper questionnaire or an electronic questionnaire, it will bring necessary human, material, financial and professional technical barriers (such as repeated training and examination of evaluators) and other real challenges in the evaluation process, which to some extent limits the key node of early screening of cognitive impairment, and is an important restricting condition for carrying out cognitive function universal screening work in the current community of the elderly.

[0003] With the rapid development of artificial intelligence, using machine learning methods to predict cognitive impairment diseases is a more and more popular choice.

[0004] However, the existing technology generally has the following problems: 1. The training data source is too one-sided, and most of the training data is based on hospital patients, which has no practical application value; 2. The training data is not closely related to mild cognitive impairment, resulting in an unsatisfactory model effect; 3. The model performance has not been evaluated, and most of the model AUC (area under the ROC curve) is less than 0.75. SUMMARY

[0005] The embodiments of the present application provide a patient screening method, device, storage medium and electronic device based on a mild cognitive impairment patient model to solve the technical problems existing in the prior art.

[0006] 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.

[0007] According to a first aspect of the embodiments of the present application, a patient screening method based on a mild cognitive impairment patient model is provided, comprising: Collecting research sample data based on community natural population health data; Extracting training data based on the research sample data; Training an extreme gradient boosting algorithm model based on the training data to obtain a plurality of preliminary models; Model performance evaluation is performed on the plurality of preliminary models, and a preliminary model meeting the evaluation requirements is selected as a mild cognitive impairment rapid screening model; screening mild cognitive impairment patients based on the mild cognitive impairment rapid screening model.

[0008] In some embodiments of the present application, based on the foregoing scheme, the research sample data based on community natural population health data collection includes: Recruit population samples in the natural population community, and perform health evaluation on all population samples to collect health evaluation data as the research sample data.

[0009] In some embodiments of the present application, based on the foregoing scheme, the training data extracted based on the research sample data includes: Determine the first characteristic variable closely related to the occurrence of mild cognitive impairment from the research sample data by using literature review method; Determine the first characteristic variable set related to mild cognitive impairment from the first characteristic variable by means of professional field knowledge injection method combined with clinical knowledge; Consult and arrange the first characteristic variable set to obtain the second characteristic variable set by means of field expert consultation method; Perform reverse feature screening on the feature subsets in the second characteristic variable set by means of Shap interpretable machine learning method, and select the top N characteristic variables in each feature subset in terms of feature importance; Combine the top N characteristic variables in each feature subset in terms of the order of feature importance to obtain a plurality of characteristic combination variables as training data, wherein N is an integer greater than or equal to 1.

[0010] In some embodiments of the present application, based on the foregoing scheme, the training of the extreme gradient boosting algorithm model based on the training data includes: Train the extreme gradient boosting algorithm model based on the training data under the premise of training direction of optimal AUC to obtain a plurality of preliminary models.

[0011] In some embodiments of the present application, based on the foregoing scheme, the model performance evaluation of the plurality of preliminary models includes: Perform horizontal comparison on all preliminary models, and determine the inclusion criteria of the preferred screening model by using expert consultation method; According to the comparison result and the inclusion criteria, the preliminary model meeting the requirements is used as the mild cognitive impairment screening model.

[0012] According to the second aspect of the embodiments of the present application, a patient screening device based on a mild cognitive impairment patient model is provided, which includes: The collection unit is configured to collect research sample data based on community natural person health data; The extraction unit is configured to extract training data based on the research sample data; The training unit is configured to train an extreme gradient boosting algorithm model based on the training data to obtain a plurality of preliminary models; The performance evaluation unit is configured to perform model performance evaluation on the plurality of preliminary models, and select a preliminary model meeting evaluation requirements as a mild cognitive impairment rapid screening model; The screening unit is configured to perform mild cognitive impairment patient screening based on the mild cognitive impairment rapid screening model.

[0013] According to a third aspect of the embodiments of the present application, a computer readable storage medium is provided, the storage medium stores computer instructions, and the computer instructions make the computer execute the method according to the first aspect when the computer instructions are executed on the computer.

[0014] According to a fourth aspect of the embodiments of the present application, an electronic device is provided, including 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 executes the method according to the first aspect.

[0015] The technical solution of the present application extracts features related to mild cognitive impairment based on community real person data, ensures the authenticity of the data source and the correlation degree of the features and mild cognitive impairment, uses the features as model training data to train a mild cognitive impairment screening model, and performs performance evaluation on the mild cognitive impairment screening model to ensure that the model performance meets the actual requirements and ensures the screening accuracy.

[0016] 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

[0017] The accompanying drawings incorporated in the specification and forming a part of the specification illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application. Obviously, 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 Fig. 1 shows a flowchart of a patient screening method based on a mild cognitive impairment patient model according to an embodiment of the present application; Figure 2A block diagram of a patient screening device based on a mild cognitive impairment patient model is shown in accordance with an embodiment of the present application; Figure 3 A block diagram of an electronic device is shown in accordance with an embodiment of the present application; Figure 4 A structural schematic of a computer system suitable for use in implementing the electronic device of the embodiments of the present application is shown. DETAILED DESCRIPTION

[0018] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations may, however, be implemented in many different forms and should not be construed as limited to the implementations set forth herein; rather, these implementations are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the example implementations to those skilled in the art. Like reference numerals may refer to like elements throughout the description of the figures.

[0019] 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

[0020] The block diagrams in the drawings show only the functionality of the embodiments and do not necessarily imply a particular arrangement of circuitry and / or software. For example, the functions could be provided in software, hardware, or a combination of both. In an embodiment, the functions can be provided as a machine-readable medium for execution by a processor. The block diagrams also illustrate a flow of control between software modules rather than the specific sequences of execution.

[0021] The flow diagrams shown in the figures, which show the functionality and operation of implementations, are not necessary to be executed in the order presented in the figures. In some implementations, the operations in one operational / flow block can be performed in a different order. Further, some operations can be performed simultaneously. Additionally, some operations can be omitted or combined. Also, the flow diagrams can be implemented using hardware, software, or a combination of both.

[0022] It should be noted that the terms "plurality" and "a plurality" as used herein mean two or more.

[0023] It should be noted that the terms "first", "second", and the like, as used herein do not necessarily have an ordinal meaning. Rather, such terms are used to distinguish different structures or steps from one another. Terms concerning descriptions of the drawings, such as "on", "under", "top", "bottom", "side", "front", "back", "left", "right", "rear", "back", "forward", "forwardly", "rearward", "rearwardly", and the like, are used with respect to the orientation of the figures and not with respect to an actual position of the structures or devices illustrated in the figures. Unless otherwise noted, the terms "coupled" and "connected", as used herein, are intended to mean either an indirect or a direct connection. Thus, the terms "coupled" and "connected", along with derivatives thereof are used synonymously with the term "communicative coupled" or "signal communicative coupled", unless otherwise stated. It should also be noted that the terms "coupled" or "connected" and variations thereof are intended to cover any implementation of a direct or indirect connection. Accordingly, the terms "coupled" and "connected", and variations thereof are used synonymously with the term "communicative coupled" or "signal communicative coupled", unless otherwise stated.

[0024] The technical solutions and advantages of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled 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 drawings. The following embodiments and features in the embodiments can be combined with each other without conflict.

[0026] Referring to Figure 1 , a flowchart of a patient screening method based on a mild cognitive impairment patient model is shown according to an embodiment of the present application.

[0027] As Figure 1 shown, a patient screening method based on a mild cognitive impairment patient model is shown, which specifically includes steps S100 to S500.

[0028] Referring to Figure 1 , in step S100, research sample data is collected based on community natural population health data.

[0029] In some feasible embodiments, based on the foregoing scheme, the step S100 includes: Recruit population samples in a natural population community, and collect health evaluation data of all population samples as the research sample data by taking a population research strategy as a breakthrough point.

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

[0031] Continuing to refer to Figure 1 , in step S200, training data is extracted based on the research sample data.

[0032] In some feasible embodiments, based on the foregoing scheme, the step S200 includes: In step S210, a literature review method is used to determine a first characteristic variable closely related to the occurrence of mild cognitive impairment from the research sample data; In step S220, a first characteristic variable set related to mild cognitive impairment is determined from the first characteristic variable by means of a professional field knowledge injection method combined with clinical knowledge; Step S230, the first characteristic variable set is consulted and arranged by means of a domain expert consultation method, to obtain a second characteristic variable set; Step S240, a feature subset in the second characteristic variable set is subjected to reverse feature screening by means of a Shap interpretable machine learning method, and the top N characteristic variables in each feature subset in terms of feature importance are selected; Step S250, for the top N characteristic variables in each feature subset, combination is performed in accordance with the order of feature importance, to obtain a plurality of characteristic combination variables as training data, wherein N is an integer greater than or equal to 1.

[0033] It can be understood that the association between the training data and the mild cognitive impairment can be improved by step S200, thereby guaranteeing the screening performance of the subsequent trained model from the root.

[0034] In some feasible embodiments, based on the foregoing scheme, the step S210 comprises: collecting factors related to mild cognitive impairment from literatures related to mild cognitive impairment based on a literature review method, to form a mild cognitive impairment factor review list; screening the first characteristic variables closely related to the occurrence of cognitive impairment from the evaluation data based on the mild cognitive impairment factor review list.

[0035] In some feasible embodiments, based on the foregoing scheme, the step S220 comprises: establishing an evaluation model around the mild cognitive impairment factor review list, wherein the evaluation indicators of the evaluation model include blood collection indicators, life behavior style characteristics, scale evaluation characteristics, cognitive evaluation indicators, previous chronic disease characteristics, and physical dimension indicators; pre-experiment verification is performed on the evaluation model in combination with expert experience and evaluation scenarios; the first characteristic variables are evaluated by using the verified evaluation model, and the evaluation results are cleaned and arranged, to obtain the first characteristic variable set related to mild cognitive impairment.

[0036] In some feasible embodiments, based on the foregoing scheme, the step S230 comprises: classifying the first characteristic variable set to obtain a plurality of feature subsets; screening the features in each feature subset by means of a domain expert consultation method; sequentially performing single-modal combination and multi-modal combination on the screened plurality of feature subsets, to obtain a second characteristic variable set.

[0037] In some feasible embodiments, based on the foregoing scheme, the step S240 comprises: The Shap interpretable machine learning method is used to label whether it is mild cognitive impairment, to sort the contribution of the features in each feature subset in the second feature variable set to the label prediction, and to obtain a plurality of feature distribution results of feature importance ranking. The feature distribution results of each feature importance ranking are sorted, and the top N features in each feature subset are retained in combination with expert experience.

[0038] With reference to Figure 1 , in step S300, an extreme gradient boosting algorithm model is trained based on the training data to obtain a plurality of preliminary models.

[0039] It can be understood that in the embodiment, a plurality of feature variables related to mild cognitive impairment can be obtained by step S200, each feature variable can be used as a training data to train the model, and therefore a plurality of preliminary models can be obtained. Moreover, since each feature variable is related to mild cognitive impairment, each preliminary model obtained also has better performance in identifying mild cognitive impairment.

[0040] In some possible embodiments, based on the foregoing scheme, step S300 includes: Based on the training data, an extreme gradient boosting algorithm model is trained under the premise of the best AUC as the training direction to obtain a plurality of preliminary models.

[0041] The logic of this step is that after determining the target of the best AUC as the training direction, the parameter combination condition under which the model can output the optimal AUC value is searched.

[0042] According to expert experience and under the premise of 5-fold cross-validation, the optimal parameter combination is searched in the hyperparameter space of seed (1-1000), CB (0.5, 0.8, 1.0), LR (0.001, 0.01, 0.1, 0.2), and MD (3, 6, 9), and the sensitivity, specificity, accuracy, AUC value and ROC curve of each model corresponding to each training direction under “each combination” are recorded.

[0043] Wherein, seed refers to random seed, CB refers to class balance, LR refers to learning rate, and MD refers to maximum depth.

[0044] It should be noted that the AUC in the present application refers to Area Under the Curve, that is, the area under the ROC curve, which is a commonly used performance evaluation index for measuring the overall classification ability of the model.

[0045] With reference to Figure 1, step S400, the model performance evaluation is performed on the plurality of preliminary models, and a preliminary model meeting the evaluation requirement is selected as a mild cognitive impairment rapid screening model.

[0046] It can be understood that the performance of the plurality of models is evaluated in this step, and the model meeting the requirement is further selected, thereby ensuring the performance of the finally obtained model.

[0047] In some possible embodiments, based on the foregoing scheme, step S400 includes: The preliminary models are compared horizontally, and an expert consultation method is used to determine the inclusion criteria of the preferred screening model; According to the comparison result and the inclusion criteria, a preliminary model meeting the requirement is selected as a mild cognitive impairment screening model.

[0048] For example, the model inclusion criteria determined by the expert consultation method are: AUC≥0.8 and F1≥0.8.

[0049] Wherein, F1 refers to F1 value (F1 - Score), which is a measure index of a classification problem, and is a harmonic mean of precision (Precision) and recall (Recall), used to comprehensively evaluate the performance of the model.

[0050] With reference to Figure 1 , step S500, a mild cognitive impairment patient is screened based on the mild cognitive impairment rapid screening model.

[0051] To sum up, the method first collects data based on a community population, thereby ensuring that the trained model is closer to the real situation, then extracts features related to mild cognitive impairment as training data, thereby ensuring the correlation between the training data and mild cognitive impairment, then trains the model with AUC as the training target, thereby ensuring the performance of the model, and finally, the model is screened according to the model performance, thereby leaving the model with better performance for patient screening, thereby ensuring the screening accuracy.

[0052] The device embodiment of the present application is described below, which can be used to execute the patient screening method based on the mild cognitive impairment patient model in 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.

[0053] With reference to Figure 2 According to the patient screening device 200 based on the mild cognitive impairment patient model according to one embodiment of the present application, as shown in the figure, the device includes: The acquisition unit 201 is configured to collect research sample data based on community natural population health data; The extraction unit 202 is configured to extract training data based on the research sample data. The training unit 203 is configured to train an extreme gradient boosting algorithm model based on the training data to obtain a plurality of preliminary models. The performance evaluation unit 204 is configured to perform model performance evaluation on the plurality of preliminary models, and select a preliminary model meeting the evaluation requirement as a mild cognitive impairment rapid screening model. The screening unit 205 is configured to perform mild cognitive impairment patient screening based on the mild cognitive impairment rapid screening model.

[0054] As Figure 3 shown, the embodiment of the present application further provides an electronic device 300, which comprises a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and capable of running on the processor, and the processor 320 implements the steps of the above-mentioned patient screening method based on a mild cognitive impairment patient model when executing the computer program 311.

[0055] Since the electronic device introduced in the embodiment is the device used to implement the patient screening device based on a mild cognitive impairment patient model in the embodiment of the present application, the specific implementation mode of the electronic device of the embodiment and its various forms of changes can be understood by those skilled in the art based on the method introduced in the embodiment of the present application, so the way how the electronic device implements the method in the embodiment of the present application will not be introduced in detail here, and as long as the device used by those skilled in the art to implement the method in the embodiment of the present application belongs to the range intended to be protected by the present application.

[0056] In the specific implementation process, the computer program 311 can implement any implementation manner of the corresponding embodiment of the first aspect when executed by the processor.

[0057] Figure 4 The structure schematic diagram of the computer system of the electronic device suitable for implementing the embodiment of the present application is shown.

[0058] 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 use range of the embodiment of the present application.

[0059] As Figure 4As shown, the computer system 400 includes a central processing unit 401, which can perform various suitable actions and processes in accordance with programs stored in a read-only memory 402 or loaded from the storage section 408 into a random access memory 403, such as performing the methods described in the above embodiments. Various programs and data required for operation of the system are also stored in the random access memory 403. The central processing unit 401, the read-only memory 402, and the random access memory 403 are connected to each other through a bus 404. An input / output interface 405 is also connected to the bus 404.

[0060] Connected to the input / output interface 405 are an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. 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 necessary. A removable media 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 410 as necessary, so that a computer program read therefrom is installed in the storage section 408 as necessary.

[0061] In particular, in accordance with embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for performing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 409, and / or installed from the removable media 411. When the computer program is executed by the central processing unit 401, various functions defined in the system of the present application are performed.

[0062] 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.

[0063] 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.

[0064] 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.

[0065] 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 patient screening method based on a mild cognitive impairment patient model described in the above embodiments.

[0066] 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 patient screening method based on a mild cognitive impairment patient model described in the above embodiments.

[0067] 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.

[0068] 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.

[0069] 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 patient screening method based on a mild cognitive impairment patient model, characterized in that: include: Collect research sample data based on health data of natural population in the community; Extracting training data based on the research sample data; Training an extreme gradient boosting algorithm model based on the training data to obtain multiple preliminary models; Conduct model performance evaluation on multiple preliminary models and select preliminary models that meet the evaluation requirements as rapid screening models for mild cognitive impairment; Screening of patients with mild cognitive impairment is performed based on the rapid screening model for mild cognitive impairment.

2. The method according to claim 1, characterized in that The research sample data based on the community natural population health data collection includes: Recruit population samples from natural population communities, use a cohort research strategy as an entry point, conduct health assessments on all population samples, and collect health assessment data as the research sample data.

3. The method according to claim 1, characterized in that The step of extracting training data based on the research sample data includes: Literature review was used to identify the first characteristic variable closely related to the occurrence of mild cognitive impairment from the research sample data; Determining a first feature variable set related to mild cognitive impairment from the first feature variables by using a professional domain knowledge injection method combined with clinical knowledge; The first feature variable set is consulted and sorted by a domain expert consultation method to obtain a second feature variable set; Perform reverse feature screening on the feature subsets in the second feature variable set using the Shap interpretable machine learning method, and select the top N feature variables in the feature importance ranking in each feature subset; 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 training data, where N is an integer greater than or equal to 1.

4. The method according to claim 1, wherein The extreme gradient boosting algorithm model is trained based on the training data to obtain multiple preliminary models, including: Based on the training data, an extreme gradient boosting algorithm model is trained with the optimal AUC as the training direction to obtain multiple preliminary models.

5. The method according to claim 1, wherein The model performance evaluation of multiple preliminary models is performed, and preliminary models that meet the evaluation requirements are selected as rapid screening models for mild cognitive impairment, including: All preliminary models were compared horizontally, and the inclusion criteria for the preferred screening model were determined using expert consultation. According to the comparison results and inclusion criteria, the preliminary models that met the requirements were used as screening models for mild cognitive impairment.

6. A patient screening device based on a mild cognitive impairment patient model, characterized in that: include: Collection unit, used to collect research sample data based on health data of natural population in the community; An extraction unit, configured to extract training data based on the research sample data; A training unit, configured to train an extreme gradient boosting algorithm model based on the training data to obtain a plurality of preliminary models; A performance evaluation unit is used to evaluate the performance of multiple preliminary models and select preliminary models that meet the evaluation requirements as rapid screening models for mild cognitive impairment; A screening unit is used to screen patients with mild cognitive impairment based on the mild cognitive impairment rapid screening model.

7. A computer-readable storage medium, characterized in that The storage medium stores computer instructions, which, when executed on a computer, enable the computer to execute the method according to any one of claims 1 to 5.

8. 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 5.

Images