Cognitive function intelligent evaluation system and method suitable for old people

Abstract

The invention provides a cognitive function intelligent evaluation system and method suitable for old people, the system comprises a data acquisition layer, a data processing layer, a model training layer, an evaluation analysis layer and a user interaction layer, the data acquisition layer is connected with the data processing layer, the data processing layer is connected with the model training layer, the model training layer is connected with the evaluation analysis layer, and the evaluation analysis layer is connected with the user interaction layer. The system is high in intelligent degree, can monitor cognitive function changes of old people in real time, timely discover potential cognitive impairment risks, provides possibility for early intervention, realizes comprehensive and accurate assessment of the cognitive functions of the old people, improves the objectivity and accuracy of assessment, and improves the user experience. In addition, the system is convenient for old people, family members and medical staff to use, and the practicability and operability of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical fields of medical health and artificial intelligence, and particularly relates to an intelligent cognitive function assessment system and method applicable to the elderly. Background Art

[0002] With the aggravation of the global population aging, the health problems of the elderly have received increasing attention. Cognitive impairment is one of the common health problems of the elderly, such as Alzheimer's disease, mild cognitive impairment, etc. These diseases not only seriously affect the quality of life of the elderly, but also bring heavy burdens to families and society. Early and accurate assessment of the cognitive function of the elderly is of great significance for disease prevention, diagnosis and treatment.

[0003] Traditional cognitive function assessment methods mainly rely on neuropsychological scales, such as the Mini-Mental State Examination (MMSE), Montreal Cognitive Assessment Scale (MoCA), etc. Although these methods have a certain degree of reliability, they have disadvantages such as strong subjectivity, long time consumption, high professional requirements for assessors, and the assessment results are easily affected by the emotions and environmental factors of the assessed. Moreover, traditional assessment methods often can only conduct stage-by-stage assessments and cannot achieve real-time and dynamic monitoring of the cognitive function of the elderly.

[0004] In recent years, with the rapid development of artificial intelligence technologies, such as machine learning, deep learning, etc., new ideas and methods have been provided for cognitive function assessment. By using intelligent devices to collect multi-source information such as physiological data and behavioral data of the elderly, through data analysis and model training, automatic and intelligent assessment of the cognitive function of the elderly can be realized. However, there are still some problems in the current related research and applications, such as insufficient comprehensiveness and accuracy of data collection, the generality and accuracy of assessment models need to be improved, and there is a lack of personalized analysis and intervention suggestions for assessment results. Therefore, it is necessary to design an intelligent cognitive function assessment system applicable to the elderly. Summary of the Invention

[0005] The present invention provides an intelligent cognitive function assessment system and method applicable to the elderly to solve the problems existing in the existing cognitive function assessment methods, realize comprehensive, accurate, real-time and dynamic assessment of the cognitive function of the elderly, and provide a personalized cognitive health management plan for the elderly.

[0006] The present invention provides an intelligent cognitive function assessment system applicable to the elderly, including a data collection layer, a data processing layer, a model training layer, an assessment and analysis layer, and a user interaction layer; The data collection layer is connected to the data processing layer, the data processing layer is connected to the model training layer, the model training layer is connected to the assessment and analysis layer, and the assessment and analysis layer is connected to the user interaction layer.

[0007] Preferably, a smartwatch, a smart bracelet, an EEG cap, smart home devices, a voice acquisition device, and a cognitive test data acquisition device are arranged in the data acquisition layer. The smartwatch and the smart bracelet are used to collect physiological data of the elderly, such as heart rate, blood pressure, and blood oxygen saturation. The EEG cap is used to collect the EEG signals of the elderly and record the electrical activity of the brain. The smart home devices are used to collect the daily activity trajectories of the elderly, including walking speed, number of steps, activity time, and sleep data. The voice acquisition device is used to record the daily voice communication of the elderly and analyze their language expression ability and thinking logic. The cognitive test data acquisition device is used to collect the reaction time, memory ability, and attention data of the elderly.

[0008] Preferably, a control module, a data cleaning unit, a data preprocessing unit, a data denoising unit, and a data feature extraction unit are arranged in the data processing layer. The data cleaning unit, the data preprocessing unit, the data denoising unit, and the data feature extraction unit are respectively connected to the control module. The data cleaning unit is used to clean the data. The data preprocessing unit is used to normalize the data. The data denoising unit is used to denoise the data. The data feature extraction unit is used to extract features related to cognitive functions from the preprocessed data, including frequency features of physiological signals, activity pattern features of behavioral data, reaction time of cognitive test data, and accuracy rate features.

[0009] Preferably, a dataset construction unit, a model selection and training unit, and a model evaluation and optimization unit are arranged in the model training layer. The dataset construction unit is used to collect multi-source data of a large number of elderly people, annotate them, and construct a training dataset and a test dataset. The annotation information includes the cognitive function status of the elderly. The model selection and training unit selects a suitable machine learning and deep learning model for training. During the training process, cross-validation and regularization methods are used to prevent the model from overfitting, adjust the model parameters, and improve the performance of the model. The model evaluation and optimization unit uses the test dataset to evaluate the trained model. The evaluation indicators include accuracy rate, recall rate, F1 value, and mean square error. According to the evaluation results, the model is optimized until the model performance reaches a satisfactory level.

[0010] Preferably, a cognitive function evaluation unit, a risk prediction unit, and an evaluation report generation unit are provided in the evaluation and analysis layer. The cognitive function evaluation unit is configured to input the preprocessed and feature-extracted data into a trained cognitive function evaluation model to obtain the cognitive function status score of the elderly, as well as the judgment result of the type and degree of cognitive impairment; the risk prediction unit uses a cognitive function prediction model, combines the historical data and current evaluation results of the elderly, predicts the risk probability of cognitive function decline in a future period of time, and divides the risk level; the evaluation report generation unit generates a detailed cognitive function evaluation report based on the evaluation results and risk prediction.

[0011] Preferably, a doctor-patient interaction unit is provided in the user interaction layer. The doctor-patient interaction unit provides a friendly interaction interface for the elderly, their families, and medical staff. The elderly can conduct cognitive tests and view their own cognitive health reports through this interface; family members can understand the cognitive status of the elderly in real time; medical staff can review, adjust the evaluation results, and formulate personalized intervention plans.

[0012] Preferably, a method for using a cognitive function intelligent evaluation system for the elderly includes the following steps: A. Regularly collect multi-source data of the elderly, including daily physiological and behavioral data, as well as cognitive test data collected regularly.

[0013] B. Perform preprocessing operations such as cleaning, denoising, and normalization on the collected data to ensure the quality and usability of the data.

[0014] C. Extract features related to cognitive function from the preprocessed data, such as frequency features of physiological signals, activity pattern features of behavioral data, response time and accuracy rate of cognitive test data, etc. D. Input the extracted features into a trained cognitive function evaluation model to obtain the cognitive function evaluation results, including the cognitive function status score, the type and degree of cognitive impairment. E. Use a cognitive function prediction model to predict the risk of future cognitive function decline of the elderly based on their current cognitive function status and historical data, and give the corresponding risk level. F. Finally, generate a detailed cognitive function evaluation report based on the evaluation results and risk prediction, providing a decision-making basis for the elderly, their families, and medical staff. Beneficial effects

[0015] The present invention has a high degree of intelligence, can monitor the changes in the cognitive function of the elderly in real time, timely detect the potential risks of cognitive dysfunction, provide the possibility for early intervention, realize a comprehensive and accurate assessment of the cognitive function of the elderly, improve the objectivity and accuracy of the assessment, and is also convenient for the elderly, their families and medical staff to use, improving the practicability and operability of the system.

[0016] (2) The present invention can monitor the changes in the cognitive function of the elderly in real time, timely detect the potential risks of cognitive dysfunction, and provide the possibility for early intervention. The above description is only an overview of the technical solution of the embodiment of the present invention. In order to be able to understand the technical means of the embodiment of the present invention more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the embodiment of the present invention more obvious and understandable, the following specifically gives the specific implementation manners of the present invention. Brief Description of the Drawings

[0017] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the drawings required to be used in the description of the embodiment will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0018] Figure 1 is the system architecture diagram of the present invention; Figure 2 is the control principle block diagram of the data processing layer of the present invention; Figure 3 is the working flow chart of the present invention; Description of the reference numerals: data acquisition layer 1, data processing layer 2, model training layer 3, evaluation and analysis layer 4, user interaction layer 5, smart watch 6, smart bracelet 7, EEG cap 8, smart home device 9, voice acquisition device 10, cognitive test data acquisition device 11, control module 12, data cleaning unit 13, data preprocessing unit 14, data denoising unit 15, data feature extraction unit 16, data set construction unit 17, model selection and training unit 18, model evaluation and optimization unit 19, cognitive function evaluation unit 20, risk prediction unit 21, evaluation report generation unit 22, doctor-patient interaction unit 23. Detailed Description of the Invention

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this invention belongs; the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the terms "comprising" and "having" and any variations thereof in the specification and claims of this invention and the drawings are intended to cover non-exclusive inclusion.

[0021] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in connection with the embodiments can be included in at least one embodiment of the present invention. The phrase "embodiments" appearing in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0022] In the description of the present invention, it should be noted that, unless otherwise clearly defined and limited, the terms "installed", "connected", and "coupled" should be construed in a broad sense. For example, the "connection" or "coupling" of mechanical structures can refer to a physical connection. For example, a physical connection can be a fixed connection, such as a fixed connection through a fixing member, such as a screw, bolt, or other fixing member; a physical connection can also be a detachable connection, such as a snap connection or a snap-fit connection; a physical connection can also be an integral connection, such as a connection formed by welding, bonding, or integral molding. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0023] To enable those skilled in the technical field to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0024] Please refer to Figures 1 - 3 , the present invention discloses an intelligent cognitive function evaluation system suitable for the elderly, including a data acquisition layer 1, a data processing layer 2, a model training layer 3, an evaluation and analysis layer 4, and a user interaction layer 5; The data acquisition layer 1 is connected to the data processing layer 2, the data processing layer 2 is connected to the model training layer 3, the model training layer 3 is connected to the evaluation and analysis layer 4, and the evaluation and analysis layer 4 is connected to the user interaction layer 5.

[0025] Among them, in the data acquisition layer 1, there are a smart watch 6, a smart bracelet 7, an electroencephalogram cap 8, smart home devices 9, a voice acquisition device 10, and a cognitive test data acquisition device 11. The smart watch and the smart bracelet are used to collect physiological data of the elderly, such as heart rate, blood pressure, and blood oxygen saturation; the electroencephalogram cap is used to collect the electroencephalogram signals of the elderly and record the electrical activity of the brain; the smart home devices are used to collect the daily activity trajectories of the elderly, including walking speed, number of steps, activity time, and sleep data; the voice acquisition device is used to record the daily voice communication of the elderly and analyze their language expression ability and thinking logic; the cognitive test data acquisition device is used to collect the reaction time, memory ability, and attention data of the elderly.

[0026] In the present invention, in the data processing layer 2, there are a control module 12, a data cleaning unit 13, a data preprocessing unit 14, a data denoising unit 15, and a data feature extraction unit 16. The data cleaning unit 13, the data preprocessing unit 14, the data denoising unit 15, and the data feature extraction unit 16 are respectively connected to the control module 12. The data cleaning unit is used to clean the data, the data preprocessing unit is used to perform normalization processing on the data; the data denoising unit is used to perform denoising processing on the data; the data feature extraction unit is used to extract features related to cognitive functions from the preprocessed data, including frequency features of physiological signals, activity pattern features of behavior data, reaction time of cognitive test data, and accuracy rate features.

[0027] In the present invention, in the model training layer 3, there are a dataset construction unit 17, a model selection and training unit 18, and a model evaluation and optimization unit 19. The dataset construction unit is used to collect multi-source data of a large number of elderly people, perform annotation, and construct a training dataset and a test dataset. The annotation information includes the cognitive function status of the elderly; the model selection and training unit selects a suitable machine learning and deep learning model for training. During the training process, cross-validation and regularization methods are used to prevent the model from overfitting, adjust the model parameters, and improve the performance of the model; the model evaluation and optimization unit uses the test dataset to evaluate the trained model. The evaluation indicators include accuracy rate, recall rate, F1 value, and mean square error. According to the evaluation results, the model is optimized, such as adjusting the model structure, replacing the algorithm, increasing the training data, etc., until the model performance reaches a satisfactory level.

[0028] In the present invention, a cognitive function evaluation unit 20, a risk prediction unit 21, and an evaluation report generation unit 22 are provided in the evaluation and analysis layer 4. The cognitive function evaluation unit is configured to input the preprocessed and feature-extracted data into a trained cognitive function evaluation model to obtain the cognitive function status score of the elderly and the judgment result of the type and degree of cognitive impairment; the risk prediction unit uses a cognitive function prediction model, combines the historical data and current evaluation results of the elderly, predicts the risk probability of cognitive function decline in a future period of time, and divides the risk level; the evaluation report generation unit generates a detailed cognitive function evaluation report according to the evaluation results and risk prediction. The report content includes the basic information of the elderly, the cognitive function evaluation results, the analysis of cognitive function shortboards, risk warning information, and personalized intervention suggestions (such as cognitive training programs, lifestyle adjustment suggestions, regular review reminders, etc.). The evaluation report is presented in a visual way, which is convenient for the elderly, their families, and medical staff to view and understand.

[0029] In addition, in the present invention, a doctor-patient interaction unit 23 is provided in the user interaction layer 5. The doctor-patient interaction unit provides a friendly interaction interface for the elderly, their families, and medical staff. The elderly can conduct cognitive tests and view their own cognitive health reports through this interface; family members can understand the cognitive status of the elderly in real time; medical staff can review, adjust the evaluation results, and formulate personalized intervention plans.

[0030] The present invention can be applied to scenarios such as families, community elderly care service centers, and medical institutions. In the family, the elderly can independently collect data and conduct cognitive tests through intelligent terminal devices, and family members can understand the cognitive status of the elderly in real time; in the community elderly care service center, staff can use the system to conduct regular cognitive function evaluations and health management for the elderly in the jurisdiction; in medical institutions, doctors can use the system as an auxiliary diagnosis tool to provide a basis for the diagnosis and treatment of cognitive impairment of the elderly.

[0031] Working principle: A method for using a cognitive function intelligent evaluation system suitable for the elderly includes the following steps: A. Regularly collect multi-source data of the elderly, including daily physiological and behavioral data, and regularly conducted cognitive test data.

[0032] B. Perform preprocessing operations such as cleaning, denoising, and normalization on the collected data to ensure the quality and usability of the data.

[0033] C. Extract features related to cognitive function from the preprocessed data, such as frequency features of physiological signals, activity pattern features of behavioral data, response time and correct rate of cognitive test data, etc. D. Input the extracted features into the trained cognitive function assessment model to obtain the cognitive function assessment results, including the cognitive function status score, the type and degree of cognitive impairment; E. Use the cognitive function prediction model to predict the risk of future cognitive function decline of the elderly based on their current cognitive function status and historical data, and give the corresponding risk level; F. Finally, generate a detailed cognitive function assessment report based on the assessment results and risk prediction to provide a decision-making basis for the elderly, their families and medical staff.

[0034] The present invention can monitor the changes in the cognitive function of the elderly in real time, timely detect potential risks of cognitive impairment, and provide the possibility for early intervention.

[0035] In summary, the present invention has a high degree of intelligence, can monitor the changes in the cognitive function of the elderly in real time, timely detect potential risks of cognitive impairment, provides the possibility for early intervention, realizes a comprehensive and accurate assessment of the cognitive function of the elderly, improves the objectivity and accuracy of the assessment, and is also convenient for the elderly, their families and medical staff to use, improving the practicability and operability of the system.

[0036] As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent cognitive function assessment system suitable for the elderly, characterized in that, It includes a data acquisition layer (1), a data processing layer (2), a model training layer (3), an evaluation and analysis layer (4), and a user interaction layer (5); The data acquisition layer (1) is connected to the data processing layer (2), the data processing layer (2) is connected to the model training layer (3), the model training layer (3) is connected to the evaluation and analysis layer (4), and the evaluation and analysis layer (4) is connected to the user interaction layer (5).

2. The intelligent cognitive function evaluation system for the elderly according to claim 1, wherein An intelligent watch (6), an intelligent bracelet (7), an EEG cap (8), smart home devices (9), a voice acquisition device (10), and a cognitive test data acquisition device (11) are arranged in the data acquisition layer (1). The intelligent watch and the intelligent bracelet are used to collect physiological data of the elderly, such as heart rate, blood pressure, and blood oxygen saturation; the EEG cap is used to collect the EEG signals of the elderly and record the electrical activity of the brain; the smart home devices are used to collect the daily activity trajectories of the elderly, including walking speed, number of steps, activity time, and sleep data; the voice acquisition device is used to record the daily voice communication of the elderly and analyze their language expression ability and thinking logic; the cognitive test data acquisition device is used to collect the reaction time, memory ability, and attention data of the elderly.

3. The intelligent cognitive function evaluation system for the elderly according to claim 1, characterized in that, A control module (12), a data cleaning unit (13), a data preprocessing unit (14), a data denoising unit (15), and a data feature extraction unit (16) are arranged in the data processing layer (2). The data cleaning unit (13), the data preprocessing unit (14), the data denoising unit (15), and the data feature extraction unit (16) are respectively connected to the control module (12). The data cleaning unit is used to clean the data, the data preprocessing unit is used to normalize the data; the data denoising unit is used to denoise the data; the data feature extraction unit is used to extract features related to cognitive function from the preprocessed data, including frequency features of physiological signals, activity pattern features of behavior data, reaction time of cognitive test data, and accuracy rate features.

4. The intelligent cognitive function evaluation system for the elderly according to claim 1, characterized in that, A dataset construction unit (17), a model selection and training unit (18), and a model evaluation and optimization unit (19) are arranged in the model training layer (3). The dataset construction unit is used to collect multi-source data of a large number of elderly people, and perform annotation to construct a training dataset and a test dataset. The annotation information includes the cognitive function status of the elderly; the model selection and training unit selects appropriate machine learning and deep learning models for training. During the training process, cross-validation and regularization methods are used to prevent the model from overfitting, adjust the model parameters, and improve the performance of the model; the model evaluation and optimization unit uses the test dataset to evaluate the trained model. The evaluation indicators include accuracy rate, recall rate, F1 value, and mean square error. According to the evaluation results, the model is optimized until the model performance reaches a satisfactory level.

5. The intelligent cognitive function assessment system for the elderly according to claim 1, characterized in that The evaluation and analysis layer (4) is provided with a cognitive function evaluation unit (20), a risk prediction unit (21) and an evaluation report generation unit (22). The cognitive function evaluation unit is used to input the preprocessed and feature-extracted data into the trained cognitive function evaluation model to obtain the cognitive function status score of the elderly and the judgment results of the type and degree of cognitive impairment; the risk prediction unit uses the cognitive function prediction model, combines the historical data and the current evaluation results of the elderly to predict the risk probability of cognitive function decline in a future period of time and divides the risk level; the evaluation report generation unit generates a detailed cognitive function evaluation report according to the evaluation results and risk prediction.

6. The intelligent cognitive function assessment system for the elderly according to claim 1, characterized in that, The user interaction layer (5) is provided with a doctor-patient interaction unit (23). The doctor-patient interaction unit provides a friendly interaction interface for the elderly, their families and medical staff. The elderly can conduct cognitive tests and view their own cognitive health reports through this interface; family members can understand the cognitive status of the elderly in real time; medical staff can review, adjust the evaluation results and formulate personalized intervention plans.

7. A method for using an intelligent cognitive function evaluation system for the elderly as described in claim 1, characterized in that, Its usage method includes the following steps: A. Regularly collect multi-source data of the elderly, including daily physiological and behavioral data, and regularly conducted cognitive test data. 8.B. Perform preprocessing operations such as data cleaning, denoising, and normalization on the collected data to ensure the quality and usability of the data. 9.C. Extract features related to cognitive function from the preprocessed data, such as frequency features of physiological signals, activity pattern features of behavioral data, reaction time and correct rate of cognitive test data, etc. D. Input the extracted features into the trained cognitive function evaluation model to obtain the cognitive function evaluation results, including cognitive function status score, type and degree of cognitive impairment. E. Use the cognitive function prediction model to predict the risk of future cognitive function decline of the elderly according to their current cognitive function status and historical data, and give the corresponding risk level. F. Finally, generate a detailed cognitive function evaluation report according to the evaluation results and risk prediction, providing a decision-making basis for the elderly, their families and medical staff.

Images