Cognitive disorder patient screening and rehabilitation device, equipment, storage medium and system

Abstract

The invention relates to a cognitive disorder patient screening and rehabilitation device, equipment, a storage medium and a system, and the device comprises a first screening module which is used for carrying out screening according to the score of a target object AD8 scale; when the evaluation score is greater than or equal to a preset threshold value, stopping screening, and determining that the target object is a candidate AD patient; the second screening module is used for screening out candidate AD patients and candidate VaD patients according to the scores of the target objects in the related tests; the third screening module is used for obtaining the brain medical image for further screening; the training module is used for correspondingly outputting training programs which can be executed on the mobile terminal to the candidate AD patients and the candidate VaD patients respectively; and the adjusting module is used for acquiring the training performance of the target object and / or the physiological parameters of the target object, and adjusting the difficulty of the current item, changing the training item or terminating the training. According to the technical scheme, AD or VaD confirmation is fast, and cost is low.

Description

Technical Field

[0001] The present application relates to the field of smart medical technology, and in particular to a device, equipment, storage medium and system for screening and rehabilitation of patients with cognitive impairment. Background Art

[0002] Alzheimer's disease (AD) is a degenerative disorder of the central nervous system characterized by progressive cognitive impairment and behavioral impairments that affect memory, thinking, language, and daily functioning. Vascular dementia (VaD) is a syndrome of cognitive impairment caused by cerebrovascular disease, including brain damage caused by various cerebrovascular diseases such as cerebral infarction, cerebral hemorrhage, and cerebral vascular sclerosis. The main difference between the two is that AD is a neurodegenerative disease associated with β-amyloid deposition and neurofibrillary tangles in the brain, while VaD is caused by brain damage caused by cerebrovascular disease. Regarding the characteristics of cognitive impairment, AD is primarily characterized by recent memory impairment and progressive cognitive decline in its early stages, while VaD is primarily characterized by executive dysfunction, and cognitive impairment may develop suddenly or worsen in a step-by-step manner. Patients with AD may experience psychiatric symptoms such as personality changes and behavioral abnormalities, while patients with VaD often have focal neurological signs and gait abnormalities. In clinical differentiation, the distinction between AD and VaD requires a combination of clinical characteristics, imaging manifestations, biomarkers and disease course characteristics.

[0003] In the prior art, the confirmation of AD or VaD is time-consuming and costly. Summary of the Invention

[0004] In view of this, the present application provides a device, equipment, storage medium and system for screening and rehabilitation of patients with cognitive impairment in order to solve at least one problem existing in the background technology.

[0005] To achieve the above objectives, the technical solution of this application is implemented as follows: In a first aspect, embodiments of the present application provide a device for screening and rehabilitation of patients with cognitive impairment, which is applied to Alzheimer's disease (AD) and vascular dementia (VaD), and the device comprises: A first screening module is configured to perform screening based on an assessment score of the target subject on the AD8 scale; if the assessment score is greater than or equal to a preset assessment threshold, the screening is terminated to determine that the target subject is a candidate AD patient; otherwise, the screening is continued; a second screening module, configured to screen out candidate AD patients based on the target subject's test scores in a hippocampus-related memory ability test, and further configured to screen out candidate VaD patients based on the target subject's test scores in a non-memory cognitive test; The third screening module is used to obtain brain medical images of target subjects who are both candidate AD patients and candidate VaD patients for further screening; A training module is used to output training programs that can be executed on a mobile terminal for candidate AD patients and candidate VaD patients respectively; The adjustment module is used to obtain the training performance of the target object and / or the physiological parameters of the target object, and adjust the training program according to the training performance and / or physiological parameters to adjust the difficulty of the current project, change the training project or terminate the training.

[0006] In an optional embodiment, the first screening module is further configured to: Output an electronic version of the AD8 scale that can be executed on a mobile terminal; The input responses to the AD8 scale are obtained to obtain the assessment score.

[0007] In an optional embodiment, the second screening module is further configured to: outputting a first test program for testing the target subject's hippocampus-related memory ability and a second test program for testing the target subject's non-memory cognitive ability; The test scores of the first test program and the second test program are obtained; the first test program includes a similar picture recognition program; the second test program includes a connection program and a cerebrovascular risk questionnaire program.

[0008] In an optional embodiment, the second screening module is further configured to: For a target subject who is both a candidate AD patient and a candidate VaD patient, when the test score of the cerebrovascular risk questionnaire program is less than a preset score threshold, the screening weight of the connection program is increased.

[0009] In an optional embodiment, the brain medical image includes a brain magnetic resonance image and / or a brain CT image; The third screening module is further used for: The hippocampal volume or white matter lesion area is obtained by analyzing the acquired brain magnetic resonance images and / or brain CT images; The target subject is further screened according to the hippocampal volume or white matter lesion area.

[0010] In an optional embodiment, the training module includes: The first training module is configured to output at least one of the following first-type training programs for the candidate AD patient: Virtual scene memory training program; Similar face memory training program; similar animal difference identification training program; Family Album Reconstruction Training Program; The second training module is configured to output at least one of the following second-type training programs for the candidate VaD patient: gait correction training program; Virtual multi-task execution training program; Rapid Information Processing Training Program; Motor coordination and decision speed training program.

[0011] In an optional embodiment, the gait correction training program is used to: Obtaining gait data of the target object; identifying abnormal features based on the gait data; Based on the abnormal features, a gamified training task is output.

[0012] In an optional embodiment, obtaining gait data of the target object includes: Obtain walking videos of the target object through the mobile terminal camera; Identifying skeletal key points of a target object based on the walking video to obtain gait data of the target object; the gait data at least includes toe-off clearance and heel-strike angle; The identifying abnormal features according to the gait data includes: Abnormal features are identified based on the toe-off clearance and the heel-contact angle, and a fall risk assessment value of the target object is generated.

[0013] In an optional embodiment, outputting a gamified training task based on the abnormal characteristics includes: A virtual footprint sequence synchronized with the target object's real-time gait is superimposed and displayed on the screen of the mobile terminal; wherein the stride, occurrence timing and horizontal offset of the virtual footprint sequence are set after analyzing the abnormal characteristics to guide the target object to adjust its own gait pattern during walking.

[0014] In an optional embodiment, the training performance of the target object includes: the training record of the target object in the training program, and / or the facial expression of the target object.

[0015] In an optional implementation manner, the adjustment module is further configured to: Obtaining physiological parameter values ​​measured by a wearable device of the target object; According to the physiological parameter value, the difficulty of the current project is adjusted, the training project is changed, or the training is terminated.

[0016] In an optional implementation manner, the adjustment module is further configured to: Acquiring environmental information of the environment in which the target object is located; Adjust the difficulty of the current project, change the training project or terminate the training according to the environmental information.

[0017] In an optional implementation manner, the adjustment module is further configured to: Obtain training records of multiple target objects and input them into the preset reinforcement learning model for learning; When the reward function change in the reinforcement learning model is less than a convergence threshold, the iterative training of the reinforcement learning model is stopped; the reinforcement learning model is used to adjust the generation rules of the training items according to the input training records.

[0018] In a second aspect, an embodiment of the present application provides a computing device, comprising: a storage component, a communication bus, and a processing component, wherein: The storage component is used to store the operating program of the cognitive impairment patient screening and rehabilitation device; The communication bus is used to realize the connection and communication between the storage component and the processing component; The processing component is used to execute the operating program of the cognitive impairment patient screening and rehabilitation device to realize the work of each module in any one of the cognitive impairment patient screening and rehabilitation devices described above.

[0019] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having an executable program stored thereon. When the executable program is executed by the processor, the operations of the various modules in any one of the cognitive impairment patient screening and rehabilitation devices described above are realized.

[0020] In a fourth aspect, an embodiment of the present application provides a system for screening and rehabilitation of patients with cognitive impairment, comprising: the computing device described above; A first client, configured to collect various screening data of the target object and send the data to the computing device; The second client is used to export data from the computing device for offline treatment of the target object.

[0021] The cognitive impairment patient screening and rehabilitation device, equipment, storage medium and system provided in the embodiment of the present application realize stratified screening through the first screening module and the second screening module, which is short in time and low in cost, and the first screening module can be terminated in advance to further reduce the screening time; through the third screening module, further screening is carried out on patients who are both candidate AD patients and candidate VaD patients to make the screening more accurate; through the training module, a closed loop of screening and rehabilitation is formed, so that the data generated by the screening can be used for rehabilitation training to improve the rehabilitation effect. By adjusting the module, more effective training effects or good user experience can be obtained. Therefore, the cognitive impairment patient screening and rehabilitation device, equipment, storage medium and system provided in the embodiment of the present application can solve the problem of long time and high cost of confirming AD or VaD.

[0022] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A schematic diagram of the structure of a device for screening and rehabilitation of patients with cognitive impairment provided in an embodiment of the present application; Figure 2 A schematic diagram of the process of brain medical image processing in the cognitive impairment patient screening and rehabilitation device provided in an embodiment of the present application; Figure 3 A schematic diagram of a learning process of a reinforcement learning model in a device for screening and rehabilitation of patients with cognitive impairment provided in an embodiment of the present application; Figure 4 A schematic diagram of the process of executing the device for screening and rehabilitation of patients with cognitive impairment provided in an embodiment of the present application; Figure 5 A detailed flowchart of the execution process of the device for screening and rehabilitation of patients with cognitive impairment provided in an embodiment of the present application; Figure 6 A schematic diagram of the structure of a computing device provided in an embodiment of the present application; Figure 7 Schematic diagram of a system for screening and rehabilitation of patients with cognitive impairment provided in an embodiment of the present application.

[0024] Description of reference numerals: 10. Screening and rehabilitation device; 11. First screening module; 12. Second screening module; 13. Third screening module; 14. Training module; 15. Adjustment module; 50. Computing device; 51. Storage component; 52. Communication bus; 53. Processing component; 54. Input device; 55. Output device; 56. External communication interface; 611. Screening module; 612. Rehabilitation module; 62. First client; 63. Second client. DETAILED DESCRIPTION

[0025] The exemplary embodiments disclosed herein will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the specific embodiments described herein. Rather, these embodiments are provided to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0026] In the following description, numerous specific details are provided to provide a more thorough understanding of the present application. However, it will be apparent to those skilled in the art that the present application may be practiced without one or more of these details. In other instances, certain technical features known in the art are not described to avoid confusion with the present application; that is, all features of actual embodiments are not described herein, nor are well-known functions and structures described in detail.

[0027] In order to fully understand the present application, detailed steps and detailed structures will be presented in the following description to illustrate the technical solution of the present application. The preferred embodiments of the present application are described in detail below. However, in addition to these detailed descriptions, the present application may also have other implementation methods.

[0028] During research and development, the inventors of this application discovered that the current screening and rehabilitation devices and methods for patients with cognitive impairment have the following problems: Time-consuming: Current testing solutions, such as the Mini-Mental State Examination (MMSE) and the Montreal Cognitive Assessment (MoCA), are highly professional, complex, and time-consuming, making large-scale screening difficult.

[0029] Inaccurate: A single solution (such as a questionnaire alone) can easily misdiagnose mixed dementia.

[0030] High costs: Professional imaging equipment, such as positron emission tomography (PET) and cerebrospinal fluid testing equipment, is difficult to disseminate to primary care settings. Blood markers require specialized laboratory support and may not be covered by primary care.

[0031] Therefore, the inventors of this application have conducted a lot of research and development and proposed the following technical solutions.

[0032] Example 1

[0033] The present application embodiment provides a device for screening and rehabilitation of patients with cognitive impairment (referred to as screening and rehabilitation device 10 or device), referring to Figure 1 , the device comprises: The first screening module 11 is configured to perform screening based on the target subject's assessment score on the AD8 scale; if the assessment score is greater than or equal to a preset assessment threshold, the screening is terminated to determine that the target subject is a candidate AD patient; otherwise, the screening is continued; A second screening module 12 is configured to screen out candidate AD patients based on the test scores of the target subject in a hippocampus-related memory ability test, and is further configured to screen out candidate VaD patients based on the test scores of the target subject in a non-memory cognitive test; The third screening module 13 is used to obtain brain medical images of target subjects who are both candidate AD patients and candidate VaD patients for further screening; The training module 14 is configured to output training programs executable on the mobile terminal for the candidate AD patients and the candidate VaD patients, respectively; The adjustment module 15 is used to obtain the training performance of the target object and / or the physiological parameters of the target object, and adjust the training program according to the training performance and / or physiological parameters to adjust the difficulty of the current project, change the training project or terminate the training.

[0034] Specifically, the target object may be a patient with cognitive impairment or a patient suspected of cognitive impairment. In the following description, the target object may be collectively referred to as a patient or a user, and those skilled in the art may distinguish them according to specific circumstances.

[0035] Specifically, cognitive impairment can include AD, VaD, and mixed dementia. It is understood that cognitive impairment can also be caused by other reasons, and the rehabilitation device of the embodiment of the present application can also have a certain rehabilitation effect on other cognitive impairments. For more precise expression, those screened by the screening and rehabilitation device 10 of the present application are referred to as candidate AD patients or candidate VaD patients, but for the sake of simplicity, they are referred to as AD patients or VaD patients.

[0036] In the first screening module 11, the AD8 scale is short for the Ascertain Dementia 8 (AD8) questionnaire. The AD8 scale has a high sensitivity, for example, up to 84%, which helps reduce false negatives.

[0037] Specifically, the AD8 scale has 8 questions about cognitive decline. The target subject only needs to choose yes or no. If the answer is yes, the assessment score will increase. The higher the score, the higher the risk. More specifically, AD8 covers cognitive areas such as memory, orientation, executive function, and language ability. The AD8 scale is simple and easy to use, suitable for non-professionals, especially for individuals with low cultural level or unable to cooperate with complex tests. However, the AD8 scale test also has the disadvantage of being time-consuming. For example, it may take more than half an hour.

[0038] In this embodiment, to improve efficiency and save time, the assessment threshold is preset to 2 points. That is, if the assessment score is ≥ 2 points, the AD high risk is directly determined and the current AD8 scale is terminated. If the score is less than 2 points, the current AD8 scale can be continued and subsequent screening can be carried out. Specifically, the AD8 scale can achieve rapid initial screening in less than 20 seconds.

[0039] In the second screening module 12, the hippocampus-related memory ability test is used to test the target subject's situational memory ability and pattern separation ability. This ability is related to the human hippocampus and can be used to screen AD patients.

[0040] Non-memory cognitive tests can be used to assess a subject's non-memory cognitive abilities, such as executive function. VaD patients often have relatively severe impairments in executive function, while memory impairment is relatively mild. Therefore, executive function tests can be used to screen for VaD patients.

[0041] Understandably, high-risk AD patients can be directly screened through the first screening module 11. Those with less high risk or suspected disease can be screened through both the first screening module 11 and the second screening module 12. The second screening module screens AD patients using hippocampal-related memory tests. Vascular dystrophy (VD) patients can be excluded in the first screening module 11 and then screened using the non-memory cognitive tests in the second screening module 12.

[0042] In the third screening module 13, there are relatively few target subjects who are both candidates for AD and VaD, and this can be easily misjudged. Therefore, further screening can be performed using brain medical images to make the screening more accurate. The third screening module 13 has three possible results: one is that the subject is an AD patient, indicating that the results of the previous screenings in the first and second screening modules were biased (this is possible due to test errors); the second is that the subject is a VaD patient, indicating that the results of the previous screening module were biased, which is also possible. The third is that the subject is both a candidate for AD and a candidate for VaD, meaning that the subject suffers from both diseases. This is also possible, although it is relatively rare in practice. This indicates that the results of the previous screenings in the first and second screening modules were correct.

[0043] Specifically, the brain medical image can be uploaded by the target subject or their relatives, or a website address for the brain medical image can be provided, and the third screening module 13 accesses the website to obtain the image. The third screening module 13 can also be used to perform image analysis on the acquired brain medical image to determine the pathological condition of the target subject's brain.

[0044] In training module 14, targeted rehabilitation training can be provided to AD patients and VaD patients respectively. Compared with the situation where no accurate screening is performed, that is, AD patients and VaD patients are treated with the same training method, the embodiment of the present application distinguishes AD patients and VaD patients after screening and uses different training programs for each, which has a better training effect.

[0045] Furthermore, during the training of training module 14, the data obtained from the screening of the previous three screening modules can be directly utilized to form a more targeted and personalized training program, so that screening and rehabilitation form a closed loop and the rehabilitation effect is improved.

[0046] Furthermore, the training program can be run on a mobile device, such as a mobile phone or tablet, for easy user access. Specifically, the training program can be a mobile application (APP) or WeChat mini-program. Specifically, the training program server can be located in the cloud and can include an artificial intelligence (AI) engine.

[0047] In the adjustment module 15, the difficulty of the current item in the training program can be adjusted based on the target subject's training performance. That is, the training program can automatically adjust its difficulty based on the target subject's training performance, without the need for manual adjustment (e.g., by a doctor). For example, the difficulty can be relatively low at the beginning, and then gradually increased based on training performance. Of course, it should not be too easy at the beginning, otherwise the training effect will be poor. Therefore, a medium to low training difficulty can be used as the initial difficulty, rather than the lowest training difficulty. If a special patient encounters an initial difficulty that is too difficult and affects the training effect, the training difficulty can be automatically adjusted downward.

[0048] Specifically, for patients with some special conditions, the training program can be changed or the training can be terminated to obtain more effective training results or a good user experience.

[0049] The cognitive impairment screening and rehabilitation device provided in the embodiment of the present application implements stratified screening through a first screening module 11 and a second screening module 12, which is time-efficient and low-cost. The first screening module 11 can be terminated early, further reducing screening time. The third screening module 13 allows for further screening of both AD and VaD candidate patients, making the screening more accurate. The training module 14 forms a closed loop between screening and rehabilitation, allowing the data generated by the screening to be used for rehabilitation training and improving rehabilitation effectiveness. The adjustment module 15 can achieve more effective training results or a better user experience.

[0050] In some embodiments of the present application, the first screening module 11 is further configured to: Output an electronic version of the AD8 scale that can be executed on a mobile terminal; The input responses to the AD8 scale are obtained to obtain the assessment score.

[0051] In this way, the AD8 scale questionnaire can be conducted conveniently and quickly. It can be understood that the electronic version can adopt many more humane testing methods, such as touch screen, voice interaction, etc.

[0052] In some embodiments of the present application, the second screening module 12 is further configured to: outputting a first test program for testing the target subject's hippocampus-related memory ability and a second test program for testing the target subject's executive ability; The test scores of the first test program and the second test program are obtained; the first test program includes a similar picture recognition program; the second test program includes a connection program and a cerebrovascular risk questionnaire program.

[0053] It can be understood that the test program can also be called a test game, which can output a program or game that can test the cognitive ability of the target object as needed, and requires the target object to perform corresponding operations based on its cognitive ability. The test program includes a first test program and a second test program. Compared with the fixed questions output by the aforementioned AD8, the test program will adjust the difficulty level of the test according to the operating conditions of the target object to obtain more accurate test results, and the same is true for the training program in the following training module 14. Compared with traditional rehabilitation training, such as the mechanical repetition of paper and pencil tasks, patient compliance is poor (completion rate <50%). The completion rate of the embodiment of the present application is increased to 85%, and the training program in the following training module 14 is similar.

[0054] Specifically, similar pictures in the similar picture recognition program may include pictures with similar content, or pictures with the same content but different new and old versions, etc. Similar pictures may be 5 pictures of daily objects, and each picture may be displayed for 3 seconds.

[0055] More specifically, 10 pictures (3 old, 3 similar distractors, and 4 new) may be provided, and the target object's operation includes options for clicking to confirm, and the options may include "same," "similar," "new," and the like.

[0056] The test is scored as follows: correctly rejecting similar distractors (15 points each, out of 45 points) + correctly identifying old items (10 points each, out of 30 points). The higher the score, the lower the risk.

[0057] It should be noted that the similar image recognition program mainly tests the target subject's pattern separation ability, which is closely related to the function of the hippocampal dentate gyrus and is of great significance for the early diagnosis of AD. It is understandable that the similar image recognition program can also be used to identify patients with other cognitive impairments. Specifically, the AD risk assessment criteria can be referred to Table 1: Table 1

[0058] Specifically, the linking procedure and the cerebrovascular risk questionnaire procedure can be: Display numbers 1-5 randomly distributed, and connect the target objects in order of size (time limit 15 seconds).

[0059] Scoring: 30 points if the time is ≤ 8 seconds, 15 points if the time is between 8 and 15 seconds, and 0 points if the time is overtime.

[0060] It should be noted that the connection procedure mainly tests the executive function and information processing speed of the target subject, which is related to the function of the frontal lobe-subcortical pathway and has a high sensitivity for screening VaD.

[0061] Specifically, the connection procedure in the embodiment of the present application is further simplified based on the connection procedure of the prior art, making it more suitable for patients with cognitive impairment and speeding up the screening process. For example, the original connection procedure is a trail making test (TMT), which is divided into two parts, A and B. The specific content of TMT-A is as follows: Test Material: A piece of paper with the numbers 1 to 25 randomly distributed on it.

[0062] Test requirements: The subjects need to connect the numbers in sequence with a pen.

[0063] Record metrics: time required to complete the test and number of errors. Completion time reflects the subject's information processing speed, while the number of errors may reflect the subject's ability to sustain attention and accuracy. This embodiment of the application simplifies the TMT-A to numbers 1-5, speeding up the test.

[0064] It should be noted that due to the simplified design of the relevant procedures of this application, the test time of the first test program and the second test program can be less than 50 seconds. Combined with the rapid initial screening of the AD8 scale, the total test time of the two screening modules can be less than 90 seconds. In this way, it is adapted to large-scale screening scenarios at the grassroots level, such as community physical examinations. Compared with the shortcomings of the existing screening process that is too time-consuming (such as MMSE takes 10-15 minutes) and the difficulty of popularizing primary medical care, the embodiments of the present application have been greatly improved.

[0065] Furthermore, for more accurate screening, a cerebrovascular risk questionnaire can be administered. This questionnaire can include risk factors such as hypertension, diabetes, and a history of stroke. Each item is worth 10 points, with an initial maximum score of 30. Ten points will be deducted for each risk factor checked.

[0066] By implementing the linking procedure and the cerebrovascular risk questionnaire procedure, screening of VaD patients can achieve a specificity of >80%.

[0067] Specifically, the VaD risk determination criteria can refer to Table 2: Table 2

[0068] Specifically, the aforementioned line-connecting program can be replaced with a clock-drawing program. This program requires the subject to draw a clock on the screen and label it with a specific time, such as "0:10." This program comprehensively assesses the subject's visual-spatial ability, executive function, and abstract thinking skills, and is an internationally recognized screening tool for patients with cognitive impairment.

[0069] The risk levels of AD and VaD are determined separately, and the total scores are not added together.

[0070] In some embodiments of the present application, the second screening module 12 is further configured to: For a target subject who is both a candidate AD patient and a candidate VaD patient, when the test score of the cerebrovascular risk questionnaire program is less than a preset score threshold, the screening weight of the connection program is increased.

[0071] Being a candidate for both AD and Vascular Dementia (VD) suggests a mixed dementia diagnosis. However, this cannot be definitively determined, as mixed dementia can be easily misdiagnosed. Therefore, executive function tests, often referred to as the "connection procedure," can be weighted based on the patient's cerebrovascular risk factors. A preset score threshold of 10 is recommended.

[0072] For example, if a patient has a history of hypertension, diabetes, and stroke in the cerebrovascular risk questionnaire and all three are checked, their score is 0. Therefore, their cerebrovascular risk is very high, and the weighting of the executive function test is increased. The score from the online procedure is multiplied by a weight of 0.8. For example, if a patient takes 12 seconds to complete the test (which falls between 8 and 15 seconds), they should receive 15 points, but multiplying by the weighting gives them 12 points. This further increases their risk as a candidate for Vascular Dementia (VD). Dynamic weighting improves the accuracy and speed of identification. Weighting can be automatically increased by the device, eliminating the need for manual setting.

[0073] In some embodiments of the present application, the brain medical image includes a brain magnetic resonance image and / or a brain CT image; The third screening module 13 is further used for: The hippocampal volume or white matter lesion area is obtained by analyzing the acquired brain magnetic resonance images and / or brain CT images; The target subject is further screened according to the hippocampal volume or white matter lesion area.

[0074] Magnetic resonance imaging or CT images can show the brain structure more clearly and comprehensively to confirm brain health.

[0075] Specifically, AI can be used to analyze MRI or CT images to determine hippocampal volume or white matter lesion area. For example, the mobile lightweight third-generation neural network (Mobile Neural Network Version 3, MobileNetV3) can be used to analyze and segment images.

[0076] Specifically, the magnetic resonance images or CT images can be in Digital Imaging and Communications in Medicine (DICOM) format with a resolution ≥1 mm³. Preprocessing includes denoising (non-local means filtering) and normalization, where standard score (Z-score) normalization is used.

[0077] The third screening module 13 can be used for segmenting magnetic resonance images or CT images. The segmentation process includes: A lightweight MobileNetV3 model was used, with an input layer size of 224×224×3 (RGB channels), and the output was a binary mask of the hippocampus. The binary mask of the hippocampus is a three-dimensional matrix (or stacked two-dimensional slices), with each voxel having a value of 0 (background) or 1 (hippocampus). Understandably, before obtaining the binary mask of the hippocampus, it is necessary to obtain the hippocampus ROI (Region of Interest). Then, a segmentation algorithm (such as thresholding or deep learning) is used to extract the hippocampus boundary from the ROI, accurately separating the hippocampus from adjacent structures to obtain the binary mask of the hippocampus.

[0078] Hippocampal volume calculation: mask voxel number × voxel volume (e.g., 1 mm³). The result is displayed as a percentage (compared to a database of healthy individuals of the same age). The mask voxel number is the total number of voxels with a median value of 1 in the statistical mask, that is, the number of voxels occupied by the hippocampus in the image. The actual size of each voxel in physical space is determined by the image resolution. For example, if the image resolution is 1 mm × 1 mm × 1 mm (isotropic), the volume of each voxel is 1 mm³. If the resolution is 0.5 mm × 0.5 mm × 2 mm, the voxel volume is 0.5 × 0.5 × 2 = 0.5 mm³.

[0079] refer to Figure 2 ,The specific process of brain medical image processing can include : image input, ,preprocessing, hippocampal ROI extraction, hippocampal volume calculation and ,result output.

[0080] Understandably, AD patients can be identified by hippocampal volume, and VaD patients by white matter lesion area. Therefore, obtaining hippocampal volume or white matter lesion area significantly improves confirmation accuracy. By quantifying key indicators such as hippocampal volume and white matter lesions, the accuracy of AD / VaD differentiation has increased from 78% to 89%. AI-automated interpretation compensates for the shortage of specialized physicians, generating reports within 5 minutes and providing imaging evidence for rehabilitation outcome assessment.

[0081] The lightweight MobileNetV3 model reduces image analysis costs by 90%, enabling primary care physicians to independently perform initial AD / VaD screening. This allows for better understanding and the acquisition of other structural features of the brain that can help confirm AD or VaD. Disease progression monitoring sensitivity is enhanced (e.g., a ±2% warning threshold for hippocampal atrophy), allowing for dynamic optimization of intervention plans.

[0082] In addition, when obtaining MRIs is difficult, fundus photographs can be used instead of brain MRIs. Because retinal vascular changes are significantly associated with VaD, fundus photographs can be used instead of brain MRIs.

[0083] Finally, after obtaining the test scores of the first test program and the second test program, a comprehensive judgment is made. When making a comprehensive judgment, the scores need to be corrected according to age / education level: ≥70 years old: The total AD score threshold is reduced by 5 points.

[0084] For those with primary school education or below: the time threshold for the online test is relaxed by 20%.

[0085] Next, the cognitive impairment patient screening and rehabilitation device provided in the embodiments of the present application will be further described in conjunction with specific embodiments.

[0086] Case A (suspected AD): AD module: 15 points for similar distractors + 20 points for old items = 35 points (high risk).

[0087] VaD module: 30 points for connection test + 30 points for risk factors = 60 points (low risk).

[0088] Determination: High risk for Alzheimer's disease (AD). Aβ-PET is recommended. (Aβ-PET uses positron emission tomography (PET) technology, using radionuclide-labeled specific imaging agents, to noninvasively and visually detect β-amyloid (Aβ) deposits in the brain. It is the gold standard for early diagnosis of Alzheimer's disease (AD). Case B (suspected VaD): AD module: 45 points for similar distractors + 20 points for old items = 65 points (low risk).

[0089] VaD module: 15 points for connection test + 10 points for risk factors = 25 points (high risk).

[0090] Judgment: High risk of VaD, cerebrovascular evaluation is recommended.

[0091] Case C (hybrid): AD module: 30 points for similar interference items + 20 points for old items = 50 points (medium risk).

[0092] VaD module: 0 points for connection test + 10 points for risk factors = 10 points (high risk).

[0093] Judgment: High risk of VaD with moderate risk of AD, comprehensive evaluation is recommended.

[0094] Case D (mixed): AD module: 45 points for similar interference items + 10 points for old items = 55 points (medium risk).

[0095] VaD module: 15 points for connection test + 20 points for risk factors = 35 points (medium risk).

[0096] MRI images showed hippocampal atrophy without obvious cerebrovascular lesions.

[0097] Judgment: Intermediate risk of VaD and high risk of AD, comprehensive evaluation is recommended.

[0098] Case E (boundary conditions): AD module: Episodic memory 50 points (medium risk).

[0099] VaD module: 25 points for the dot-connection test (high risk) + 20 points for risk factors (1 history of stroke).

[0100] Imaging tips: MRI showed lacunar lesions in the right basal ganglia and normal hippocampal volume.

[0101] Judgment: High risk of VaD, cerebrovascular evaluation is recommended.

[0102] In some embodiments of the present application, the training module includes: The first training module is configured to output at least one of the following first-type training programs for the candidate AD patient: Virtual scene memory training program; Similar face memory training program; similar animal difference identification training program; Family album reconstruction training program.

[0103] Here, the first type of cognitive impairment patient may be AD. Compared to VaD, AD has more severe impairments in memory, language, etc., so the training program is more focused on memory and other aspects.

[0104] Specifically, the parameters of the first type of training program, such as difficulty or training intensity, can be determined by referring to the measurement results of the AD8 scale in the first screening module 11. This is determined by the program and does not require manual determination. Of course, it can also be generated based on the learning results of the subsequent reinforcement learning model.

[0105] Understandably, the virtual scene can be virtual reality (VR) or augmented reality (AR). Understandably, the virtual scene memory program primarily activates the hippocampus. For example, the virtual scene could be a supermarket, where the subject is required to memorize the locations of 10 items (e.g., apples in the fruit and vegetable section, milk in the refrigerator), then reproduce them and complete the checkout process after 5 minutes. The difficulty level can be adjusted based on performance by increasing or decreasing the number of items (±3 items) or shortening the memorization time (±1 minute).

[0106] The similar face memory program is a form of pattern separation training. Specifically, it presents highly similar faces, forcing the subject to memorize them and then determine whether the new face has appeared before. Difficulty can be adjusted by increasing or decreasing the number of images presented or by increasing or decreasing the number of images presented.

[0107] Similarly, the similar-animal difference recognition program is also a form of pattern separation training. Specifically, this program displays images of highly similar animals (e.g., different dog breeds). The subject is asked to click on the different details (e.g., ear shape, fur color) and recall the category. Difficulty can be adjusted by increasing the number of similar items (e.g., from 3 to 5) or shortening the display time (from 5 seconds to 3 seconds).

[0108] The family album reconstruction program is used to activate autobiographical memories. Specifically, the program uploads old family photos of the target subject, and AI generates a timeline, arranging them in chronological order and describing the details (e.g., "This is from my son's wedding, and you wore a red cheongsam"). Autobiographical memory training can delay the degeneration of the default mode network (DMN).

[0109] In some embodiments of the present application, the training module 14 further includes: The second training module is configured to output at least one of the following second-type training programs for the candidate VaD patient: gait correction training program; Virtual multi-task execution training program; Rapid Information Processing Training Program; Motor coordination and decision speed training program.

[0110] Here, the second type of cognitive impairment patient may be VaD. Compared with AD, VaD has more severe impairment in executive function and other aspects, so the training program is more focused on executive function and other aspects.

[0111] Similarly, the parameters of the second type of training program, such as difficulty or training intensity, can also be determined by referring to the data in the previous screening module and will not be described in detail.

[0112] In some embodiments of the present application, the gait correction training program is used to: Obtaining gait data of the target object; identifying abnormal features based on the gait data; Based on the abnormal features, a gamified training task is output.

[0113] Specifically, obtaining the gait data of the target object may include: Use the mobile terminal camera to obtain the current walking video of the target object.

[0114] In some embodiments of the present application, obtaining gait data of the target object includes: Obtain walking videos of the target object through the mobile terminal camera; Identifying skeletal key points of a target object based on the walking video to obtain gait data of the target object; the gait data at least includes toe-off clearance and heel-strike angle; The identifying abnormal features according to the gait data includes: Abnormal features are identified based on the toe-off clearance and the heel-contact angle, and a fall risk assessment value of the target object is generated.

[0115] The target subject's current walking video includes capturing a video of the target subject walking in a straight line (naturally swinging their arms) for 3-5 meters (round trip). This process can be repeated three times for more accurate acquisition. The acquisition method includes setting a camera aligned at a height relative to the target subject's waist to capture the target subject's gait data. The camera can be a mobile phone or tablet camera.

[0116] After acquiring the gait data of the target object, it is compared with the normal gait data to obtain abnormal features. For the gait data including the toe clearance and heel contact angle, a fall risk assessment value of the target object can also be generated. For example, if the toe clearance is too small or the heel contact angle is too abnormal, it indicates a high risk of falling. For example, due to the decreased contraction strength of the gastrocnemius muscle on the back of the calf and abnormal nerve control in VaD patients, this gap will be significantly reduced, which is a key risk indicator for tripping. In addition, VaD patients often "slap their feet" to the ground (reduced heel contact angle) or land flat on the ground, which can also easily lead to unstable walking.

[0117] Compared to traditional clinical observations or wearable devices, which cannot conveniently measure these subtle yet crucial biomechanical parameters, this method enables automated, marker-free, contactless at-home monitoring of these parameters for the first time, providing unprecedented insights into fall risk. It can also inform more targeted training programs.

[0118] Specifically, the gait data may further include at least one of the following: Stride length, stride width, stride frequency, proportion of double support time, gait cycle, knee flexion angle and trunk lateral tilt angle.

[0119] The following examples illustrate gait data such as stride length, stride width, and proportion of bipedal support time. Please refer to Table 3 for details.

[0120] Table 3

[0121] Specifically, the gait data of the target object can be obtained through a human posture estimation model, that is, the recorded video is analyzed through the model to output the 2D coordinates of the hip, knee, and ankle joints; the stride length, step width, step frequency, proportion of double-foot support time, toe-off clearance, and heel contact angle are calculated; the gait cycle (contact period, swing period) is identified through the hip joint motion trajectory, and abnormal data in the above gait data is extracted to obtain abnormal features.

[0122] Additionally, gait correction training programs are used to: A lower limb kinetic chain model was constructed, and the knee flexion angle was calculated (normal walking: 60°±5°).

[0123] Detect trunk lateral tilt angle (abnormal threshold: >5° and lasting for more than 3 steps).

[0124] The AR display is superimposed on the camera image to mark abnormal parts (such as a leg that is not swinging enough with a red highlight).

[0125] It can be understood that these steps can also be performed by a human posture estimation model.

[0126] Furthermore, voice prompts can be given for abnormalities during training, such as: "The left leg swing is insufficient, try raising your knee", "The stride is less than 50cm, please increase your pace", etc.

[0127] Specifically, the above-mentioned human posture estimation model can be a MobileNetV3 lightweight model.

[0128] In some embodiments of the present application, outputting a gamified training task based on the abnormal features includes: A virtual footprint sequence synchronized with the target object's real-time gait is superimposed and displayed on the screen of the mobile terminal; wherein the stride, occurrence timing and horizontal offset of the virtual footprint sequence are set after analyzing the abnormal characteristics to guide the target object to adjust its own gait pattern during walking.

[0129] Therefore, the feedback provided by training module 14 is not simply a voice command of "faster, slower." Instead, it uses AR technology to overlay a dynamic sequence of virtual footprints onto the camera's real-time image. This sequence has the following features: adjustable spatiotemporal parameters, including the position (controlling stride length), timing (controlling cadence), and horizontal offset of each footprint.

[0130] The virtual footprint sequence can be adaptively offset: when asymmetry is detected in the user (such as a smaller left stride), the virtual footprint sequence will automatically shift to the left, leveraging the user's visual-motor coordination instinct to induce them to actively take a larger left step to center the footprint, thereby achieving active correction.

[0131] Therefore, this is a "guided" rather than "instructive" rehabilitation intervention. It utilizes the inherent "visual pursuit" and "gait adaptability" instincts of the human nervous system, and the training effect is more natural and profound. It is a brand-new interactive paradigm for digital therapy.

[0132] Furthermore, based on the abnormal characteristics, outputting the gamified training task may also include: Virtual obstacles randomly appear on the screen, with a height of 10cm-20cm. The target object needs to lift its legs to cross them and maintain balance.

[0133] Difficulty Adjustment: After three consecutive correct attempts, the difficulty level increases, such as increasing stride length by 5 cm or raising the obstacle height by 2 cm. After two consecutive failures, the difficulty level decreases, such as reducing stride length by 5 cm.

[0134] It can be understood that the virtual multi-tasking execution training program is a type of executive function training, which may specifically include: In a simulated kitchen scenario, the target player must simultaneously operate a cooking timer (which rings every 30 seconds), answer a virtual phone call, record a shopping list, and avoid burning the pot. The difficulty can be adjusted by increasing the number of concurrent tasks, such as adding a "turn off the heat and prepare the dish" step or shortening the interval between tasks.

[0135] Specifically, the rapid information processing training program may include: Output randomly flashing symbol-number combinations to the screen and output training rules. For example, the target object is required to be classified according to the rules within 1 second. Classification can be achieved by pressing different buttons, such as "click the left button for red symbols and the right button for odd numbers." The symbol-number combinations can include colored shapes, such as ▲-3, ●-5, etc.

[0136] Specifically, a motor coordination and decision-making speed training program may include: A virtual scene is created where a virtual character navigates a maze. The target subject is required to control the virtual character to avoid moving obstacles and quickly choose the correct path to reach the destination. The target subject can control the virtual character by leaning or moving their body. The motor coordination and decision-making speed training program can capture the target subject's body movements using a camera, such as a mobile phone camera, to control the virtual character. The difficulty can be adjusted by increasing the speed of obstacles or increasing the complexity of the maze (e.g., multiple floors).

[0137] The following is a list of the defects of the target objects corresponding to various training programs. Please refer to Table 4 for details.

[0138] Table 4

[0139] In some embodiments of the present application, the target subject's training performance includes: the target subject's training record during the training program, and / or the target subject's facial expressions. In this way, the difficulty of the current exercise can be adjusted in a timely manner based on the target subject's training record to achieve better training results. The training record can include the patient's test accuracy, reaction time, etc.

[0140] For some patients with special circumstances, such as those whose training remains suboptimal after adjusting the difficulty, it's necessary to consider the patient's emotions and modify the training program. This is because, based on the neuropsychological theory of "learned helplessness," patients with cognitive impairment are prone to giving up and becoming passive in training due to failure. The core innovation of this solution lies in elevating "user experience" and "emotion management" to the same level of importance as "cognitive training." By adjusting the difficulty level, users are proactively prevented from feeling frustrated, something not considered in conventional rehabilitation software.

[0141] Specifically, traditional rehabilitation training only prompts "error" when the user fails. This system has designed a composite response mechanism: First failure: Systematically reduce the difficulty of the item (e.g., reduce the number of distractors).

[0142] Second consecutive failure: The system will not let the user frustrate again on the same task. Instead, it will intelligently switch to a task type that the user has performed well in the past (for example, switching from a memory task to a visual-spatial task), allowing the user to gain a sense of success and control, and maintain training motivation.

[0143] Specifically, the patient's facial expression can be captured by the mobile terminal's camera, and the patient's mood can be judged based on the patient's facial expression. If the patient's mood is relatively depressed or irritable, the training program can be changed or the test can be terminated.

[0144] Specifically, the training items in the device are not a pre-set fixed question bank, but are generated in real time based on user errors. This is a self-evolving, highly personalized training system. It is no longer a static "trainer," but an "intelligent coach" capable of identifying users' unique cognitive deficiencies and generating targeted "antidotes," thanks to powerful backend algorithms and content generation capabilities. For example, the device incorporates many foundational elements, such as basic images, which have only a single shape feature and no other features. These basic images can be configured with a variety of freely addable features, such as color, brightness, background, atmosphere, and so on. Based on the patient's condition, corresponding features can be added to generate test items for the corresponding patient, making the test items more personalized for the patient. Direct effects: training completion rate increased to 85% (enhanced user stickiness), and cognitive function improvement rate increased by 30% (such as improved episodic memory scores).

[0145] In some embodiments of the present application, the adjustment module 15 is further configured to: Obtaining physiological parameter values ​​measured by a wearable device of the target object; According to the physiological parameter value, the difficulty of the current project is adjusted, the training project is changed, or the training is terminated.

[0146] It is understandable that since the training items in the training module 14 require the patient's full commitment, it is also necessary to pay attention to the patient's physiological parameter values, such as heart rate, blood oxygen, etc., while obtaining the training records. These can be obtained through the patient's wearable device, such as a bracelet. If the patient's physiological parameter values ​​are found to be abnormal, such as a heart rate exceeding 120 and blood oxygen below 90%, the training can be terminated in time. On the one hand, considering the abnormality of the patient's physiological parameter values, the effect of continuing training may not be good. On the other hand, continuing training may cause harm to the patient's body.

[0147] Specifically, the patient's safe heart rate can be determined by calculating (220 - age) * 70%. For example, if a 50-year-old patient has a safe heart rate of 119, then training should be terminated immediately if the heart rate exceeds 119.

[0148] Furthermore, through wearable devices, wearable devices (heart rate, blood oxygen, etc.), rehabilitation training logs and imaging data can be integrated to build a full-cycle health portrait of the patient.

[0149] In some embodiments of the present application, the adjustment module 15 is further configured to: Acquiring environmental information of the environment in which the target object is located; Adjust the difficulty of the current project, change the training project or terminate the training according to the environmental information.

[0150] It is understood that the adjustment module 15 can also include environmental awareness capabilities. For example, by interacting with a training mobile terminal (e.g., a mobile phone) or a wearable device (e.g., a smart bracelet) to obtain information about the target subject's environment (e.g., ambient noise, light intensity, social interaction, etc.). The training program can be adjusted based on this environmental information. For example, if excessive ambient noise affects the patient's attention, the difficulty of the training program can be automatically reduced or the training can be paused and resumed when the environment improves.

[0151] Furthermore, the training program can be adjusted comprehensively based on various information such as environmental information, patient training performance, physiological parameter values, etc. These various parameters are not necessarily all required. If they are present, they can be used as a reference for adjustment. If they are not present, adjustments can also be made based on other information.

[0152] In some embodiments of the present application, the adjustment module 15 is further configured to: Obtain training records of multiple target objects and input them into the preset reinforcement learning model for learning; When the reward function change in the reinforcement learning model is less than a convergence threshold, the iterative training of the reinforcement learning model is stopped; the reinforcement learning model is used to adjust the generation rules of the training items according to the input training records.

[0153] In order to make the training program generation rules more scientific and improve the rehabilitation effect, a dynamic algorithm and reinforcement learning framework are introduced to establish an adaptive difficulty system.

[0154] The reinforcement learning framework, that is, the reinforcement learning model of this embodiment, can adjust the generation rules of the training items according to the real-time performance of the target object (such as accuracy and reaction time).

[0155] Specifically, the reinforcement learning framework's state space for each learning session encompasses the target subject's accuracy, average reaction time, and task type from the last five training sessions. The action space allows for adjustment of the number of distractors (±1 to 3) and the task duration (±2 seconds). The reward function comprehensively considers the difference between the current accuracy and the baseline accuracy, as well as the inverse of the reaction time. Based on a large number of historical patient training logs, the system utilizes an iterative optimization algorithm (PPO). Iterations are terminated when the reward function changes below a convergence threshold, enabling intelligent adaptive adjustment of task difficulty.

[0156] Specifically, the reward function can refer to the following expression (1): reward=0.7×(current_accuracy-baseline_accuracy)+0.3×(1 / reaction_time) (1) Where reward is the reward function, current_accuracy is the current accuracy, baseline_accuracy is the baseline accuracy, and reaction_time is the reaction time in seconds. The baseline accuracy can be set based on different target objects and is not limited. The calculation result of the expression ignores the unit and only the value is used as the iteration basis.

[0157] Training data: Based on the historical training logs of 1000 patients, the PPO algorithm was iterated 1000 times, and the convergence threshold Δreward < 0.01.

[0158] Example: If the accuracy rate on the episodic memory task is >90% for three consecutive times, increase the number of distractors (e.g., from 10 items to 15 items).

[0159] Specifically, refer to Figure 3 , the learning process of the reinforcement learning model can include: Obtain training records, PPO algorithm decisions, model parameter updates and feedback to the user end.

[0160] Among them, the PPO algorithm decision is to input the reinforcement learning framework, and the model parameter update includes the update of the item generation rule.

[0161] Specifically, the device can generate phase targets: Generate personalized goals each week (e.g., “Focus on improving connection test speed to under 12 seconds this week”).

[0162] Specifically, the adjustment module 15 may also set data-driven training optimization.

[0163] A. Multidimensional data dashboard, refer to Table 5.

[0164] Table 5

[0165] B. Family doctor collaboration Family APP: View training reports and receive suggestions (e.g., "Grandma Wang's memory has improved recently, so the complexity of her kitchen tasks can be increased").

[0166] Doctor-side platform: Export structured data as comma-separated values ​​(CSV) and PDF, supporting comparative analysis with clinical scales such as MoCA.

[0167] Furthermore, the training module 14 can introduce human-computer dialogue in the form of voice and set up a virtual AI coach. The following is a simple example of the common words of the AI ​​coach: For example, in a virtual scene memory program, the AI ​​coach: "Auntie Zhang, let's play a supermarket shopping game today. Remember the location of apples and milk on the shelves!"

[0168] "Great! You've memorized 6 items, 2 more than last week! How about trying the 8-item challenge tomorrow?"

[0169] In addition to task introductions and feedback, AI coaches can also provide emotional feedback: For example, based on the patient's performance, encouraging voice messages can be triggered (such as "Significant progress!") or prompts to adjust the difficulty level can be provided (such as "Shall we slow down and try again?").

[0170] Furthermore, the patient's facial expressions can be obtained and combined with facial expression recognition to automatically switch tasks when the patient's frustration is detected.

[0171] In order to more clearly understand the screening and rehabilitation device 10 provided in the embodiment of the present application, the execution process of the screening and rehabilitation device 10 provided in the embodiment of the present application will be introduced below. Figure 4 This is a flow chart of the execution process of the cognitive impairment patient screening and rehabilitation device provided in the embodiment of the present application, refer to Figure 4 As shown, the execution process may include: Step 201: Screening is performed based on the target subject's assessment score on the AD8 scale; if the assessment score is greater than or equal to a preset assessment threshold, the screening is terminated and the target subject is determined to be a candidate AD patient; otherwise, the screening is continued.

[0172] Step 202: Screening out candidate AD patients based on the target subject's test scores in the hippocampus-related memory ability test, and also screening out candidate VaD patients based on the target subject's test scores in the non-memory cognitive test.

[0173] Step 203: For the target subject who is both a candidate AD patient and a candidate VaD patient, obtain a brain medical image for further screening.

[0174] Step 204: Outputting training programs that can be executed on the mobile terminal for the candidate AD patients and the candidate VaD patients respectively.

[0175] Step 205: Obtain the training performance of the target object and / or the physiological parameters of the target object, and adjust the training program according to the training performance and / or physiological parameters to adjust the difficulty of the current item, change the training item, or terminate the training.

[0176] Figure 5 A detailed flowchart of the execution process of the cognitive impairment patient screening and rehabilitation device provided in the embodiment of the present application is provided in FIG. Figure 5As shown, the execution process may include: Step 301: Obtain the AD8 scale.

[0177] Step 302: Is the score ≥ 2? If yes, go to step 307; if no, go to step 303.

[0178] Step 303: Obtain the image recognition test result, that is, the test result of the similar image recognition program.

[0179] Step 304: Obtain the test results of the connection program, that is, the test results of the program that recognizes patterns of different objects and connects them.

[0180] Step 305: Obtain a medical history questionnaire. This is the cerebrovascular risk questionnaire process. Sometimes, this step can precede step 304. It should be noted that step 306 is optional, meaning it is only performed for the target subject who is a candidate for both AD and Vascular Dementia (VD). Therefore, this step can proceed directly to step 307 without going through step 306. The wiring program can be replaced by a clock drawing program.

[0181] Step 306: Acquire a brain medical image.

[0182] Step 307: Determine the patient type. Based on steps 302, 303, 304, and 305, the type of the patient with cognitive impairment can be preliminarily determined. Further determination is then performed in step 306 to obtain a more accurate result.

[0183] Step 308: Output the first type of training program. That is, for the AD diagnosis, the first type of training program is output.

[0184] Step 309: Output the second type of training program. That is, for the patient determined to be VaD, output the second type of training program.

[0185] Each module included in this embodiment can be implemented by a processor in a computer; of course, it can also be implemented by a logic circuit in the computer. The processor can be a general-purpose processor, a digital signal processor (DSP), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a central processing unit (CPU), a microprocessor (MPU), or any other conventional processor.

[0186] Example 2

[0187] The present application embodiment provides a computing device 50, referring to Figure 6 The computing device 50 includes a storage component 51, a communication bus 52, and a processing component 53, wherein: The storage component 51 is used to store the operating program of the cognitive impairment patient screening and rehabilitation device; The communication bus 52 is used to realize the connection and communication between the storage component 51 and the processing component 53; The processing component 53 is used to execute the operating program of the cognitive impairment patient screening and rehabilitation device to realize the operation of each module in the cognitive impairment patient screening and rehabilitation device.

[0188] Specifically, the work of each module in the cognitive impairment patient screening and rehabilitation device may include: Figure 4 Steps shown.

[0189] It is understandable that the computing device 50 can be a dedicated intelligent device, such as a medical device, or a general-purpose intelligent terminal, such as a mobile phone, a tablet, and a laptop computer, or a server in the cloud. It is understandable that it can also be other devices that can achieve the above functions. In actual use, the computing device 50 can be a server in the cloud. On the one hand, it can have stronger computing power. On the other hand, because the existing public mobile communication network, such as the 5G network, can also provide sufficient data transmission capacity and a shorter response time, it provides a guarantee for the deployment of cloud servers. In the case where the computing device 50 is a cloud server, the user also needs to use a smart terminal such as a mobile phone to collect relevant information of the target object through the camera built into the smart terminal such as the mobile phone, and send the information to the cloud server through the communication device built into the smart terminal such as the mobile phone.

[0190] The type or structure of the storage component 51 can be found in the storage medium below and will not be described in detail here.

[0191] The processing unit 53 may be a general-purpose processor, a digital signal processor (DSP), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a central processing unit (CPU), a microprocessor (MPU), or any other conventional processor.

[0192] In some embodiments, the computing device 50 may further include an input device 54 , an output device 55 , and an external communication interface 56 . These components are interconnected via a bus system and / or other connection mechanisms (not shown).

[0193] In some embodiments, the input device 54 may include, for example, a keyboard, a mouse, a microphone, etc. If the computing device 50 is a smart terminal such as a mobile phone, a tablet, or a laptop computer, the input device 54 may also include a camera, etc.

[0194] The output device 55 can output various information to the outside, and may include a display, a speaker, a printer, a projector, a communication network and its connected remote output devices, etc.

[0195] External communication interface 56 can be wired, such as a standard serial port (RS232), a general-purpose interface bus (GPIB) interface, an Ethernet interface, or a universal serial bus (USB) interface, or wireless, such as wireless network communication technology (WiFi) or Bluetooth. If computing device 50 is a smart terminal such as a mobile phone, tablet, or laptop computer, external communication can be carried out through a public mobile communication network, i.e., a 4G or 5G network.

[0196] The description of the above device embodiment is similar to the description of the above apparatus embodiment and has similar beneficial effects as the apparatus embodiment. For technical details not disclosed in the embodiments of this application, please refer to the description of the apparatus embodiment in this application for understanding.

[0197] Example 3

[0198] An embodiment of the present application provides a computer-readable storage medium having an executable program stored thereon. When the executable program is executed by a processor, the operations of various modules in a device for screening and rehabilitation of patients with cognitive impairment are implemented.

[0199] Specifically, the work of each module in the cognitive impairment patient screening and rehabilitation device may include: Figure 4 Steps shown.

[0200] Exemplarily, the computer-readable storage medium may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A computer-readable storage medium is a tangible device that can hold and store instructions used by an instruction execution device. The readable storage medium may include, for example, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), a flash memory, a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the above. Among them: The RAM includes: static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM).

[0201] The ROM includes: Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), and Electrically Erasable Programmable Read-Only Memory (EEPROM).

[0202] The description of the above computer-readable storage medium embodiment is similar to the description of the above device embodiment and has similar beneficial effects as the device embodiment. For technical details not disclosed in the embodiments of this application, please refer to the description of the device embodiment in this application for understanding.

[0203] Example 4

[0204] The present invention provides a system for screening and rehabilitation of patients with cognitive impairment. Figure 7 , the rehabilitation system comprises: The computing device 50 described in the second embodiment; A first client 62 is used to collect various screening data of the target object and send it to the computing device; The second client 63 is used to export data from the computing device for offline treatment of the target object.

[0205] Specifically, the computing device 50 may include a screening module 611 and a rehabilitation module 612. The screening module 611 may include the first screening module 11, the second screening module 12, and the third screening module 13 described in Example 1, and the rehabilitation module 612 may include the training module 14 and the adjustment module 15 described in Example 1. Various data collected by the first client 62 may be sent to the screening module 611. The training program of the rehabilitation module 612 may be sent to the first client 62.

[0206] Specifically, the first client 62 can be a client of the target object, such as a mobile phone, a tablet computer, or a laptop computer. In addition to being used by the patient himself, the first client 62 can also be used by family members.

[0207] Specifically, the second client 63 can be a client used by the target patient's doctor, such as an office computer or a mobile phone. The doctor can use the second client 63 to provide feedback on the results of the doctor's examination of the patient or professional judgment, etc., to further improve the data collection.

[0208] Furthermore, the second client 63 may also be used to obtain the execution status of the screening module 611 and / or the rehabilitation module 612 to provide professional suggestions and improve the training program of the rehabilitation module 612 .

[0209] Furthermore, the second client 63 can also be used to export data from the screening module 611 and / or the rehabilitation module 612 for offline treatment of the target subject. For example, the data can be exported in structured formats such as CSV and PDF to support comparative analysis with clinical scales (such as MoCA).

[0210] Furthermore, for some high-risk patients that appear during screening and training, the information can be sent to the second client 63 simultaneously so that professional doctors can intervene in time.

[0211] The description of the above system embodiment is similar to the description of the above device embodiment and has similar beneficial effects as the device embodiment. For technical details not disclosed in the embodiments of this application, please refer to the description of the device embodiment in this application for understanding.

[0212] It should be noted that the various embodiments provided in the embodiments of the present application belong to the same concept; the various technical features in the technical solutions recorded in the various embodiments can be arbitrarily combined to form new embodiments without conflict.

[0213] Embodiments of the present application may be systems, methods, and / or computer program products. A computer program product may include a computer-readable storage medium on which are loaded computer-readable program instructions for causing a processor to implement various aspects of the present application. The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on a user computer, partially on a user device, as a standalone software package, partially on a user computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, by utilizing state information of computer-readable program instructions to personalize and customize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer-readable program instructions, thereby implementing various aspects of the present application.

[0214] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0215] Various aspects of the present application are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0216] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0217] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0218] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or modules can be electrical, mechanical or other forms.

[0219] The modules described above as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules; they may be located in one place or distributed on multiple network modules; some or all of the modules may be selected according to actual needs to achieve the purpose of this embodiment.

[0220] In addition, all functional modules in the embodiments of the present application can be integrated into one processing module, or each functional module can be a separate module, or two or more functional modules can be integrated into one module; the above-mentioned integrated modules can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0221] Those skilled in the art will understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments.

[0222] Alternatively, if the above-mentioned integrated modules of the present application are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling an electronic device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of the present application. Thus, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0223] In the above description, the terms "first\second\..." are only used to distinguish similar objects and do not represent a specific order of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence when permitted.

[0224] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0225] In the embodiments of this application, unless otherwise specified and limited, the term "connection" should be understood in a broad sense. For example, it can be an electrical connection, or it can be a connection between two components. It can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meaning of the above terms can be understood according to the specific circumstances.

[0226] The terminology used herein is intended solely to describe specific embodiments and is not intended to limit the present application. When used herein, the singular forms "a," "an," and "said / the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "comprising" and / or "including," when used in this specification, identify the presence of the described features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items. It should be understood that references to "one embodiment" or "some embodiments" throughout this specification mean that specific features, structures, or characteristics associated with the embodiment are included in at least one embodiment of the present application. Therefore, the appearance of "in one embodiment" or "in some embodiments" throughout this specification does not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of the present application, the embodiment numbers are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0227] It should be understood that the size of the serial numbers of the above processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0228] It should be understood that the above embodiments are exemplary and are not intended to encompass all possible implementations of the technical solutions of the present application. Various modifications and variations may be made based on the above embodiments without departing from the scope disclosed herein. Similarly, the various technical features of the above embodiments may be arbitrarily combined to form additional embodiments of the present application that may not be explicitly described. Therefore, the above embodiments merely illustrate several implementations of the present application and do not limit the scope of protection of the patent application.

Claims

1. A device for screening and rehabilitation of patients with cognitive impairment, applied to Alzheimer's disease (AD) and vascular dementia (VaD), characterized in that: The device comprises: A first screening module is configured to perform screening based on an assessment score of the target subject on the AD8 scale; if the assessment score is greater than or equal to a preset assessment threshold, the screening is terminated to determine that the target subject is a candidate AD patient; otherwise, the screening is continued; a second screening module, configured to screen out candidate AD patients based on the target subject's test scores in a hippocampus-related memory ability test, and further configured to screen out candidate VaD patients based on the target subject's test scores in a non-memory cognitive test; The third screening module is used to obtain brain medical images of target subjects who are both candidate AD patients and candidate VaD patients for further screening; A training module is used to output training programs that can be executed on a mobile terminal for candidate AD patients and candidate VaD patients respectively; The adjustment module is used to obtain the training performance of the target object and / or the physiological parameters of the target object, and adjust the training program according to the training performance and / or physiological parameters to adjust the difficulty of the current project, change the training project or terminate the training.

2. The device for screening and rehabilitation of patients with cognitive impairment according to claim 1, characterized in that: The first screening module is further configured to: Output an electronic version of the AD8 scale that can be executed on a mobile terminal; The input responses to the AD8 scale are obtained to obtain the assessment score.

3. The device for screening and rehabilitation of patients with cognitive impairment according to claim 1, characterized in that: The second screening module is further used to: outputting a first test program for testing the target subject's hippocampus-related memory ability and a second test program for testing the target subject's non-memory cognitive ability; The test scores of the first test program and the second test program are obtained; the first test program includes a similar picture recognition program; the second test program includes a connection program and a cerebrovascular risk questionnaire program.

4. The device for screening and rehabilitation of patients with cognitive impairment according to claim 3, characterized in that: The second screening module is further used to: For a target subject who is both a candidate AD patient and a candidate VaD patient, when the test score of the cerebrovascular risk questionnaire program is less than a preset score threshold, the screening weight of the connection program is increased.

5. The device for screening and rehabilitation of patients with cognitive impairment according to claim 1, characterized in that: The brain medical image includes a brain magnetic resonance image and / or a brain CT image; The third screening module is further used for: The hippocampal volume or white matter lesion area is obtained by analyzing the acquired brain magnetic resonance images and / or brain CT images; The target subject is further screened according to the hippocampal volume or white matter lesion area.

6. The device for screening and rehabilitation of patients with cognitive impairment according to claim 1, characterized in that: The training module includes: The first training module is configured to output at least one of the following first-type training programs for the candidate AD patient: Virtual scene memory training program; Similar face memory training program; similar animal difference identification training program; Family Album Reconstruction Training Program; The second training module is configured to output at least one of the following second-type training programs for the candidate VaD patient: gait correction training program; Virtual multi-task execution training program; Rapid Information Processing Training Program; Motor coordination and decision speed training program.

7. The device for screening and rehabilitation of patients with cognitive impairment according to claim 6, characterized in that: The gait correction training program is used to: Obtaining gait data of the target object; identifying abnormal features based on the gait data; Based on the abnormal features, a gamified training task is output.

8. The device for screening and rehabilitation of patients with cognitive impairment according to claim 7, characterized in that: The acquiring of gait data of the target object includes: Obtain walking videos of the target object through the mobile terminal camera; Identifying skeletal key points of a target object based on the walking video to obtain gait data of the target object; the gait data at least includes toe-off clearance and heel-strike angle; The identifying abnormal features according to the gait data includes: Abnormal features are identified based on the toe-off clearance and the heel-contact angle, and a fall risk assessment value of the target object is generated.

9. The device for screening and rehabilitation of patients with cognitive impairment according to claim 7, characterized in that: Outputting a gamified training task according to the abnormal features includes: A virtual footprint sequence synchronized with the target object's real-time gait is superimposed and displayed on the screen of the mobile terminal; wherein the stride, occurrence timing and horizontal offset of the virtual footprint sequence are set after analyzing the abnormal characteristics to guide the target object to adjust its own gait pattern during walking.

10. The device for screening and rehabilitation of patients with cognitive impairment according to claim 1, characterized in that: The training performance of the target object includes: the training record of the target object in the training program, and / or the facial expression of the target object.

11. The device for screening and rehabilitation of patients with cognitive impairment according to claim 1, characterized in that: The adjustment module is further configured to: Obtaining physiological parameter values ​​measured by a wearable device of the target object; According to the physiological parameter value, the difficulty of the current project is adjusted, the training project is changed, or the training is terminated.

12. The device for screening and rehabilitation of patients with cognitive impairment according to claim 1, characterized in that: The adjustment module is further configured to: Acquiring environmental information of the environment in which the target object is located; Adjust the difficulty of the current project, change the training project or terminate the training according to the environmental information.

13. The device for screening and rehabilitation of patients with cognitive impairment according to claim 7, characterized in that: The adjustment module is further configured to: Obtain training records of multiple target objects and input them into the preset reinforcement learning model for learning; When a change in a reward function in the reinforcement learning model is less than a convergence threshold, stopping the iterative training of the reinforcement learning model; The reinforcement learning model is used to adjust the generation rules of the training items according to the input training records.

14. A computing device, characterized in that The computing device comprises: a storage component, a communication bus, and a processing component, wherein: The storage component is used to store the operating program of the cognitive impairment patient screening and rehabilitation device; The communication bus is used to realize the connection and communication between the storage component and the processing component; The processing component is used to execute the operating program of the cognitive impairment patient screening and rehabilitation device to realize the operation of each module in the cognitive impairment patient screening and rehabilitation device according to any one of claims 1 to 13.

15. A computer-readable storage medium, characterized in that The computer-readable storage medium stores an executable program. When the executable program is executed by the processor, the operation of each module in the cognitive impairment patient screening and rehabilitation device according to any one of claims 1 to 13 is realized.

16. A system for screening and rehabilitation of patients with cognitive impairment, characterized in that: include: The computing device of claim 14; A first client, configured to collect various screening data of the target object and send the data to the computing device; The second client is used to export data from the computing device for offline treatment of the target object.

Images