Cognitive disorder level evaluation method and system based on TMT and storage medium

Abstract

The invention relates to the technical field of cognitive impairment detection, and discloses a TMT-based cognitive impairment level evaluation method and system and a storage medium, and the method comprises the following steps: S1, tiling a TMT paper quality table at a designated position on an electronic acquisition board; s2, the testee uses an electromagnetic pen to complete a TMT connection task according to written instructions; s3, obtaining track data of the testee; and S4, preprocessing the trajectory data through a data preprocessing module. According to the TMT-based cognitive impairment level evaluation method, automatic feature extraction and analysis are performed on the collected trajectory data, the cognitive impairment level evaluation result is output, and objective and reproducible automatic auxiliary diagnosis of the cognitive impairment level can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of cognitive impairment detection, and in particular to a method, system and storage medium for evaluating cognitive impairment level based on TMT. Background Art

[0002] With the development of society, the aging problem is a severe challenge facing all countries. Various neurodegenerative diseases such as Alzheimer's disease (AD) can cause memory impairment, language impairment, cognitive impairment, motor imbalance and other problems in the elderly, which is bringing heavy social and economic burdens to the country and families. Since degenerative diseases such as Alzheimer's disease develop gradually, if mild cognitive impairment (MCI) can be detected and intervened in time, medical care can be provided to delay the formation of Alzheimer's disease.

[0003] Cognitive assessment tests such as the Mini-Mental State Examination (MMSE) and the Montreal Cognitive Assessment (MoCA) are relatively simple and easy to obtain ways to quickly assess cognitive impairment. However, their assessment methods mainly rely on the subjective judgment of professional physicians, so the credibility of the assessment results is not high, the assessment effect is not good, and the time cost of manual assessment is also relatively high. Summary of the invention

[0004] 1. Technical issues to be resolved In view of the deficiencies of the prior art, the present invention provides a method, system and storage medium for assessing the level of cognitive impairment based on TMT, which have the advantage of being able to automatically and objectively assess the level of cognitive impairment of a subject.

[0005] (II) Technical solution In order to achieve the above-mentioned purpose of being able to automatically and objectively evaluate the cognitive impairment level of the subject, the present invention provides the following technical solution: a method for evaluating the cognitive impairment level based on TMT, comprising the following steps: S1. Lay the TMT paper mass table flat on the designated position on the electronic collection board; S2, the subjects followed the written instructions and used the electromagnetic pen to complete the TMT connection task; S3, obtaining the trajectory data of the subject; S4, preprocessing the trajectory data through a data preprocessing module; S5, clustering the trajectory data through the trajectory key point extraction module, and sorting the point sets in the cluster according to the average sampling timestamps to determine the order of the center points after clustering; S6. Through the feature processing module, query the statistical features of the subject in the medical record system according to the subject's ID number; calculate the relevant features of the TMT task; Concatenate statistical features and correlation features into a one-dimensional feature vector; S7. Input the one-dimensional feature vector into the classifier module to obtain the cognitive impairment level assessment result of the subject.

[0006] As a preferred technical solution of the present invention, the trajectory data is synchronously collected by the electronic collection board and the electromagnetic pen, and includes real-time data of the pen touch point and pressing pressure.

[0007] As a preferred technical solution of the present invention, the data preprocessing module preprocesses the trajectory data including: Smooth the trajectory data; Fill the length of trajectory data of different lengths; The trajectory data is downsampled equidistantly.

[0008] As a preferred technical solution of the present invention, the statistical characteristics include gender, age and education level.

[0009] As a preferred technical solution of the present invention, the relevant features of the TMT task include: The completion time of the TMT task, the preparation time of the TMT task, the execution time of the TMT task, the smoothness measure of the trajectory, the pressure characteristics during the task execution, the distance between the key points and the key points of the normal control group.

[0010] As a preferred technical solution of the present invention, the classifier module includes a random forest classifier, a bagging classifier, an AdaBoost classifier and an XGBoost classifier.

[0011] As a preferred technical solution of the present invention, the feature processing module performs dimensionality reduction processing on the one-dimensional feature vector through principal component analysis (PCA) or independent component analysis (ICA).

[0012] (III) Beneficial effects Compared with the prior art, the present invention provides a method for assessing the level of cognitive impairment based on TMT, which has the following beneficial effects: 1. This TMT-based cognitive impairment level assessment method outputs cognitive impairment level assessment results by automatically extracting and analyzing the collected trajectory data, and can achieve objective and reproducible automated auxiliary diagnosis of cognitive impairment levels.

[0013] 2. This TMT-based cognitive impairment level assessment method combines traditional statistical features and highly interpretable electronic extraction features (such as time features, pressure features, smoothness features, and ordered key point distance features based on reference templates) in the feature extraction stage, which is more understandable and acceptable to clinicians and is of great help in auxiliary diagnosis.

[0014] 3. This TMT-based cognitive impairment level assessment method does not require professionally trained doctors to interpret and judge the TMT task results during the detection process. It only relies on computer computing power to achieve efficient and simple assessment, can realize large-scale diagnosis and is suitable for home telemedicine, which is of great significance for the early screening and treatment of Alzheimer's disease. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is an overall flow chart of the evaluation method of the present invention; Figure 2 Schematic diagram of reference template selection, key point extraction and key point distance feature extraction between the reference and the reference in the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Embodiment 1: See also Figure 1 and Figure 2 , a method for assessing the level of cognitive impairment based on TMT (threading test), comprising the following steps: S1. Lay the TMT paper quality sheet flat on the designated position on the electronic collection board. The TMT paper quality sheet is standardized to ensure the consistency of data collection.

[0018] S2. Subjects follow written instructions and use electromagnetic pens to complete the TMT connection task, which includes: Task 1: Alternately connect the numbers surrounded by circles and squares in order from small to large to test visual search ability and reaction time.

[0019] Task 2: Add some extra circles and squares as interference blocks with the same number to test cognitive flexibility and the ability to resist interference.

[0020] S3. Obtain the subject's trajectory data. The trajectory data is synchronously collected by the electronic collection board and the electromagnetic pen, including real-time data of the pen touch point and pressing pressure. The collected data is stored in the data preprocessing module.

[0021] S4. Preprocess the trajectory data through a data preprocessing module. The preprocessing specifically includes: a. Smoothing the trajectory data to reduce the interference of acquisition noise on the data; b. Pad the length of trajectory data of different lengths. The padding methods include padding with 0 at the end, padding with the value of the last sampling point at the end, and padding with the average value of the trajectory at the end; c. Perform equidistant downsampling on the trajectory data to remove redundant data and reduce computing resources.

[0022] S5. Cluster the trajectory data through the trajectory key point extraction module, and sort them according to the average sampling timestamp of the point set in the cluster to determine the order of the center points after clustering; specifically, Kmeans-VQ (vector quantization) is used to cluster the trajectory data.

[0023] S6. Through the feature processing module, query the statistical features of the subject in the medical record system according to the subject's ID number; calculate the relevant features of the TMT task; Among them, the statistical characteristics include gender, age, and education level; Relevant characteristics of TMT tasks include: The completion time of the TMT task, the preparation time of the TMT task (or thinking time, which can be counted according to the number of points where the recorded pressure is less than or equal to 0), the execution time of the TMT task (based on the number of points where the recorded pressure is greater than 0), the smoothness metric of the trajectory (the sum of the squares of the third-order acceleration), the pressure characteristics during the execution of the task (including the minimum pressure, maximum pressure, and average pressure), and the distance between the key points and the key points of the normal control group; Finally, the statistical features and correlation features are concatenated into a one-dimensional feature vector. During processing, the one-dimensional feature vector can be reduced in dimension through principal component analysis (PCA) or independent component analysis (ICA).

[0024] S7. Input the one-dimensional feature vector into the classifier module to obtain the cognitive impairment level assessment result of the subject. The classifier module includes random forest classifier, bagging classifier, AdaBoost and XGBoost classifier.

[0025] The distance calculation method between the key points and the normal control group key points can be referred to Figure 2:Here, it is assumed that each trajectory of the normal control group contains components similar to the standard answer of the TMT task. Therefore, a trajectory that is highly similar to other trajectories in the group is selected from the normal control group as the best template (or reference trajectory). Specifically, the template selection rule is to select the structure with the highest similarity to other trajectory sequences. First, we randomly select several trajectories from the normal control group of the training set to form a subset, and then calculate the dynamic time transform distance between the trajectories in the subset. Then, the trajectory with the smallest sum of dynamic time transform distances with other trajectories is selected as the reference. Finally, the reference trajectory is Gaussian smoothed. Optionally, the method of selecting the template also includes arbitrarily selecting or manually selecting a trajectory with a higher degree of completion from the normal control group. Optionally, the smoothing method of the reference trajectory also includes convolution smoothing, sliding average smoothing, and B-spline smoothing.

[0026] Embodiment 2: Based on the first embodiment, this embodiment provides a cognitive impairment level assessment system based on TMT, which specifically includes: Electronic collection equipment, including an electronic collection board and a matching electromagnetic pen, used to collect the pen touch point and pressing pressure data of the subjects in the TMT task; A data storage module, used to receive and store trajectory data collected by the electronic collection device; A data preprocessing module, used to preprocess trajectory data; Trajectory key point extraction module, used to cluster trajectory data and sort them according to the average sampling timestamp to determine the order of key points; The feature processing module is used to combine statistical features with TMT task-related features to generate a one-dimensional feature vector; The classifier module is used to output the cognitive impairment level assessment result through a classifier based on the one-dimensional feature vector.

[0027] Embodiment three: Based on the first embodiment, this embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the TMT-based cognitive impairment level assessment method in the first embodiment can be implemented.

[0028] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for assessing cognitive impairment level based on TMT, characterized in that: The following steps are involved: S1. Lay the TMT paper mass table flat on the designated position on the electronic collection board; S2, the subjects followed the written instructions and used the electromagnetic pen to complete the TMT connection task; S3, obtaining the trajectory data of the subject; S4, preprocessing the trajectory data through a data preprocessing module; S5, clustering the trajectory data through the trajectory key point extraction module, and sorting the point sets in the cluster according to the average sampling timestamps to determine the order of the center points after clustering; S6. Through the feature processing module, query the statistical features of the subject in the medical record system according to the subject's ID number; calculate the relevant features of the TMT task; Concatenate statistical features and correlation features into a one-dimensional feature vector; S7. Input the one-dimensional feature vector into the classifier module to obtain the cognitive impairment level assessment result of the subject.

2. A method for assessing cognitive impairment level based on TMT according to claim 1, characterized in that: The trajectory data is synchronously collected by the electronic collection board and the electromagnetic pen, and includes real-time data of the pen touch point and pressing pressure.

3. The method for assessing cognitive impairment level based on TMT according to claim 1, characterized in that: The data preprocessing module preprocesses the trajectory data including: Smooth the trajectory data; Fill the length of trajectory data of different lengths; The trajectory data is downsampled equidistantly.

4. The method for assessing cognitive impairment level based on TMT according to claim 1, characterized in that: The statistical characteristics include gender, age and education level.

5. The method for assessing cognitive impairment level based on TMT according to claim 1, characterized in that: The relevant features of the TMT task include: The completion time of the TMT task, the preparation time of the TMT task, the execution time of the TMT task, the smoothness measure of the trajectory, the pressure characteristics during the task execution, the distance between the key points and the key points of the normal control group.

6. The method for assessing cognitive impairment level based on TMT according to claim 1, characterized in that: The classifier modules include random forest classifier, bagging classifier, AdaBoost and XGBoost classifier.

7. The method for assessing cognitive impairment level based on TMT according to claim 1, characterized in that: The feature processing module performs dimensionality reduction processing on the one-dimensional feature vector through principal component analysis (PCA) or independent component analysis (ICA).

8. A TMT-based cognitive impairment level assessment system, characterized in that: include: Electronic collection equipment, including an electronic collection board and a matching electromagnetic pen, used to collect the pen touch point and pressing pressure data of the subjects in the TMT task; A data storage module, used to receive and store trajectory data collected by the electronic collection device; A data preprocessing module, used to preprocess trajectory data; Trajectory key point extraction module, used to cluster trajectory data and sort them according to the average sampling timestamp to determine the order of key points; The feature processing module is used to combine statistical features with TMT task-related features to generate a one-dimensional feature vector; The classifier module is used to output the cognitive impairment level assessment result through a classifier based on the one-dimensional feature vector.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method for assessing the level of cognitive impairment based on TMT as described in any one of claims 1 to 7 is implemented.

Images