Parkinson's motion symptom assessment method and device, electronic equipment and storage medium

Abstract

The invention is suitable for the technical field of physiological signal recognition, and provides a Parkinson's motion symptom evaluation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a motion symptom evaluation mode for evaluating the current Parkinson's motion symptom of a to-be-tested Parkinson's patient according to historical evaluation data of the to-be-tested Parkinson's patient, the exercise symptom assessment mode comprises at least one group of exercise assessment items, and acquiring exercise monitoring data corresponding to the exercise assessment items completed by the Parkinson's disease patient to be tested; the motion monitoring data is acquired by configuring at least one group of wearable sensors, and an evaluation feature combination for evaluating the current Parkinson's motion symptom of the Parkinson's patient to be detected is determined according to the motion monitoring data; the evaluation feature combination comprises a plurality of motion features acquired from the motion monitoring data, and inputting the evaluation feature combination into a trained multi-feature fusion classification model to obtain an evaluation result. According to the invention, the accuracy of Parkinson's motion symptom evaluation of the Parkinson's disease patient can be improved.

Description

Technical Field

[0001] The present application belongs to the technical field of physiological signal recognition, and in particular, relates to a method, device, electronic device and computer-readable storage medium for evaluating Parkinson's motor symptoms. Background Art

[0002] Parkinson's disease (PD) is currently the most common movement disorder and the second largest neurodegenerative disease. The main pathological feature of Parkinson's disease is the progressive and selective loss of cells in certain areas of the central nervous system. This degeneration mainly occurs in dopaminergic neurons in the substantia nigra pars compacta (SNpc) and leads to classic Parkinson-like motor manifestations: bradykinesia, muscle rigidity, resting tremor, and posture and gait disorders. Currently, drug treatment is mainly used for PD patients. The typical feature of Parkinson's disease is that it has a good response to dopaminergic drugs (mostly levodopa). The levodopa challenge test (LCT) is used clinically to evaluate the patient's responsiveness to levodopa drugs. The responsiveness to levodopa drugs provides an important basis for the clinical diagnosis of PD, the optimization of treatment effects, and the evaluation of the suitability of device-assisted treatments (such as deep brain stimulation (DBS)).

[0003] At present, the most important thing for the evaluation of Parkinson's motor symptoms is to conduct the Unified Parkinson's Disease Rating Scale (UPDRS) evaluation. However, it is difficult to give an accurate score in the Parkinson's motor symptom assessment scale of the third part of the Unified Parkinson's Rating Scale (UPDRS III), and the scale is too rough to record the slight differences in each score. For example, in the evaluation of hand tremor, hand tremor needs to be scored according to the tremor amplitude less than 1cm, 1-3cm, or more than 3cm. In fact, it is difficult to accurately measure the amplitude of tremor in clinical practice. When scoring, the evaluator generally estimates the amplitude of the patient's limb tremor based on the amplitude of the patient's limb tremor. For another example, the evaluation of bradykinesia is scored according to the slight, mild, moderate, and severe slowing of the movement. Obviously, there is a lack of objective measurable data support and it is affected by the subjective judgment of the evaluator. There are also slapping tests, standing tests, etc., which are all qualitative estimates. Moreover, the scale is not sensitive to slight changes within a scoring range, and it is difficult to quantify the evaluation. Summary of the invention

[0004] The embodiments of the present application provide a method, device, electronic device and computer-readable storage medium for evaluating Parkinson's motor symptoms, which can improve the accuracy of evaluating Parkinson's motor symptoms in Parkinson's patients.

[0005] In a first aspect, the present application provides a method for evaluating Parkinson's motor symptoms, comprising:

[0006] Acquiring historical assessment data of a Parkinson's patient to be tested, and obtaining a motor symptom assessment model for assessing current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the historical assessment data, wherein the motor symptom assessment model includes at least one group of motor assessment items;

[0007] Collecting the motion monitoring data corresponding to the motion assessment items completed by the Parkinson's patient to be tested; the motion monitoring data is collected by configuring at least one group of wearable sensors;

[0008] Determining an evaluation feature combination for evaluating the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the motion monitoring data; wherein the evaluation feature combination includes a plurality of motion features obtained from the motion monitoring data;

[0009] The evaluation feature combination is input into a trained multi-feature fusion classification model to obtain an evaluation result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested.

[0010] Optionally, obtaining a motor symptom assessment model for assessing current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the historical assessment data comprises the following steps:

[0011] A motor symptom assessment model was constructed based on the historical Parkinson's assessment data and UPDRS assessment form of different Parkinson's patients;

[0012] Inputting the historical assessment data into the data screening layer of the motor symptom assessment mode model to obtain a Parkinson's patient information vector;

[0013] Inputting the Parkinson's patient information vector into the feature extraction layer of the motor symptom assessment model to obtain the medical history characteristics of the Parkinson's patient;

[0014] The medical history features are input into the result output layer of the motor symptom assessment model to obtain the motor symptom assessment model.

[0015] Optionally, the motion assessment items include one or more of a hand assessment item, an upper limb assessment item, a lower limb assessment item, and a posture assessment item; the wearable sensor includes at least one of a pressure sensor, a strain sensor, an acceleration sensor, a gyroscope sensor, a geomagnetic sensor, a distance sensor, a contact sensor, a temperature sensor, a Hall element, and a microphone; and the collecting of the motion monitoring data corresponding to the motion assessment items completed by the Parkinson's patient to be tested includes the following steps:

[0016] selecting one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, distance sensor, contact sensor, temperature sensor, Hall element and microphone to collect the motion monitoring data according to the hand assessment items; and / or

[0017] Select one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, distance sensor, contact sensor, temperature sensor, Hall element and microphone to collect the motion monitoring data according to the upper limb assessment items; and / or

[0018] Select one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, distance sensor, contact sensor, temperature sensor, Hall element and microphone to collect the motion monitoring data according to the lower limb assessment items; and / or

[0019] According to the body posture assessment items, at least one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, distance sensor, contact sensor, temperature sensor, Hall element and microphone are selected to collect the motion monitoring data.

[0020] Optionally, the motion features include time domain features and frequency domain features, and determining the evaluation feature combination for evaluating the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the motion monitoring data comprises the following steps:

[0021] Setting a time window, dividing the motion monitoring data into time windows, and analyzing the statistical values ​​of the data in the time window at the time domain level to obtain the time domain features; wherein the time domain features include: one or more of mean, variance, standard deviation, extreme value point, zero crossing point, and slope maximum point;

[0022] Performing Fourier transform on the data in the time window to obtain frequency domain distribution information in the time window, and obtaining the frequency domain features according to the frequency domain distribution information; wherein the frequency domain features include one or more of power spectrum extreme points and frequency ranges;

[0023] A combination of evaluation features of the current Parkinson's motor symptoms of the Parkinson's patient to be tested is determined according to the time domain features and the frequency domain features.

[0024] Optionally, determining the evaluation feature combination of the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the time domain features and the frequency domain features comprises the following steps:

[0025] Sorting the time domain features and the frequency domain features using the historical Parkinson's assessment data and a preset feature sorting model to obtain a first sorting result;

[0026] Randomly combining the time domain features and the frequency domain features to obtain multiple feature combinations;

[0027] sorting the plurality of feature combinations using the historical Parkinson's assessment data and the feature sorting model to obtain a second sorting result;

[0028] The evaluation feature combination is determined according to the second sorting result, and the feature weight of the time domain feature and / or the feature weight of the frequency domain feature in the evaluation feature combination is determined according to the first sorting result.

[0029] Optionally, the training process of the multi-feature fusion classification model includes the following steps:

[0030] Acquire a Parkinson's symptom training set, wherein the Parkinson's symptom training set includes historical movement data and historical Parkinson's movement symptom assessment results;

[0031] Processing the historical motion data to obtain normalized motion data;

[0032] The normalized motion data is input into a neural network for training. During the training process, the parameters of the neural network are optimized according to the historical Parkinson's motor symptom assessment results to obtain the trained multi-feature fusion classification model.

[0033] Optionally, the step of inputting the evaluation feature combination into a trained multi-feature fusion classification model to obtain an evaluation result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested comprises the following steps:

[0034] Using the multi-feature fusion classification model to perform feature fusion on the time domain features and / or frequency domain features in the evaluation feature combination to obtain a fused feature value;

[0035] The fused feature values ​​are clustered, and an assessment result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested is determined according to the clustering result.

[0036] In a second aspect, an embodiment of the present application provides a device for evaluating Parkinson's motor symptoms, comprising:

[0037] a motor symptom assessment mode determination module, used to obtain historical assessment data of a Parkinson's patient to be tested, and to obtain a motor symptom assessment mode for assessing the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the historical assessment data, wherein the motor symptom assessment mode includes at least one group of motor assessment items;

[0038] A motion data acquisition module, used to collect motion monitoring data corresponding to the motion assessment project completed by the Parkinson's patient to be tested; the motion monitoring data is collected by configuring at least one group of wearable sensors;

[0039] A feature combination determination module, used to determine an evaluation feature combination for evaluating the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the movement monitoring data;

[0040] The motor symptom assessment module is used to input the assessment feature combination into the trained multi-feature fusion classification model to obtain the assessment result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested.

[0041] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the Parkinson's motor symptom assessment method described in the first aspect when executing the computer program.

[0042] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the Parkinson's motor symptom assessment method described in the first aspect are implemented.

[0043] This application collects the motion monitoring data corresponding to the motion assessment items completed by the Parkinson's patient to be tested, determines the evaluation feature combination used to evaluate the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the motion monitoring data, and uses a multi-feature fusion classification model to process the above evaluation feature combination to obtain the evaluation result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested, which can improve the accuracy of Parkinson's motor symptom evaluation for Parkinson's patients. Specifically, since the above motor symptom evaluation mode is determined according to the historical evaluation data of the Parkinson's patient to be tested, that is, the above motor symptom evaluation mode is constructed based on the actual situation of the Parkinson's patient to be tested, the motor function of the Parkinson's patient to be tested can be more targeted to improve the accuracy of Parkinson's motor symptom evaluation. At the same time, an evaluation feature combination for evaluating the current Parkinson's motor symptoms of the Parkinson's patient to be tested is determined according to the above-mentioned motion monitoring data. Since the above-mentioned evaluation feature combination includes multiple motion features obtained from the motion monitoring data, it means that the above-mentioned evaluation feature combination can better reflect the motor ability of the above-mentioned Parkinson's patient to be tested. Finally, the evaluation result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested is obtained through the above-mentioned multi-feature fusion classification model, which can avoid the subjective judgment of the evaluator and perform quantitative evaluation based on the actual motion monitoring data of the Parkinson's patient to be tested, thereby improving the accuracy of the Parkinson's motor symptom evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 is a flow chart of Parkinson's motor symptom assessment provided by an embodiment of the present application;

[0046] Figure 2 It is a schematic diagram of the structure of the Parkinson's motor symptom assessment provided in the embodiment of the present application;

[0047] Figure 3 It is a schematic diagram of the structure of an electronic device for evaluating Parkinson's motor symptoms provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0049] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0050] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0051] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0052] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0053] At present, the evaluation of Parkinson's motor symptoms through the UPDRS-III scale relies on the personal judgment of the evaluator, which makes the evaluation results highly subjective and individual biased, affecting the accuracy of the evaluation of Parkinson's motor symptoms. With the gradual maturity of wearable sensor technology and equipment in motion analysis, the evaluation of motor symptoms of Parkinson's patients can be quantified through wearable devices, realizing automatic evaluation with higher sensitivity, better consistency and accuracy than traditional scales. However, due to the complex and diverse motor performance of Parkinson's patients and the different body parts involved, wearable devices can only be used in the field of Parkinson's disease to evaluate one or several typical motor symptoms, and the analysis of these motor symptoms is discrete, resulting in insufficient evaluation of Parkinson's motor symptoms; at the same time, due to the large differences in physiological structure, muscle groups and other aspects of different body parts, the evaluation of Parkinson's motor symptoms in different body parts often requires different motion feature data, and the existing wearable devices cannot be used in the field of Parkinson's disease to analyze motor symptoms in different body parts in a targeted manner, resulting in inaccurate evaluation of Parkinson's motor symptoms.

[0054] In order to improve the accuracy of Parkinson's motor symptom assessment, the present application provides a Parkinson's motor symptom assessment method based on feature combination.

[0055] Figure 1 A flow chart of a method for evaluating Parkinson's motor symptoms provided by an embodiment of the present application is shown, and is described in detail as follows:

[0056] S1. Acquire historical assessment data of a Parkinson's patient to be tested, and obtain a motor symptom assessment model for assessing current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the historical assessment data, wherein the motor symptom assessment model includes at least one group of motor assessment items.

[0057] In the embodiment of the present application, the above historical evaluation data refers to the data of Parkinson's symptom evaluation of the Parkinson's patient to be tested within a period of time and reflecting the history of Parkinson's disease, including motor function evaluation data (such as motor data of major parts such as hands, arms, thighs, calves, etc.), drug treatment evaluation data (such as medication time, medication dosage, etc.), Parkinson's diagnosis data (such as tremor amplitude, etc.), etc. The above motor symptom evaluation mode is used to evaluate the Parkinson's motor symptoms of different body parts of the above Parkinson's patient to be tested, wherein different body parts correspond to different motor evaluation items, so by determining the different body parts that need to be evaluated for the above Parkinson's patient to be tested, one or more groups of motor evaluation items can be correspondingly determined as the motor symptom evaluation mode for evaluating the current Parkinson's motor symptoms of the Parkinson's patient to be tested; at the same time, because the above historical evaluation data contains more abundant Parkinson's symptom information, it is possible to more comprehensively and accurately determine the different body parts that need to be evaluated for the Parkinson's patient to be tested, thereby obtaining a more accurate motor symptom evaluation mode.

[0058] S2. Collecting the motion monitoring data corresponding to the motion assessment items completed by the Parkinson's disease patient to be tested; the motion monitoring data is collected by configuring at least one group of wearable sensors.

[0059] In the embodiment of the present application, different motion assessment items correspond to different wearable sensors, which are used to collect motion monitoring data of corresponding body parts. The above motion monitoring data includes acceleration information, angular velocity information, orientation information, etc. of different body parts of the Parkinson's patient to be tested. Therefore, by collecting the motion monitoring data corresponding to the motion assessment items completed by the above-mentioned Parkinson's patient to be tested through at least one group of wearable sensors, the motion physiological data related to Parkinson's disease of different body parts of the Parkinson's patient to be tested can be collected in a targeted manner.

[0060] S3. Determine, based on the motion monitoring data, an evaluation feature combination for evaluating the current Parkinson's motor symptoms of the Parkinson's patient to be tested; wherein the evaluation feature combination includes a plurality of motion features obtained from the motion monitoring data.

[0061] In an embodiment of the present application, an evaluation feature combination for evaluating the current Parkinson's motor symptoms of the Parkinson's patient to be tested is determined by the above-mentioned motion monitoring data. Since the above-mentioned evaluation feature combination includes multiple motion features obtained from the above-mentioned motion monitoring data, it means that the Parkinson's motor symptoms can be evaluated through multiple different motion features, which can improve the accuracy of the evaluation of Parkinson's motor symptoms.

[0062] S4. Input the above-mentioned evaluation feature combination into the trained multi-feature fusion classification model to obtain the evaluation result of the current Parkinson's motor symptoms of the above-mentioned Parkinson's patient to be tested.

[0063] In an embodiment of the present application, the multi-feature fusion classification model is used to fuse and classify different motion features, and obtain the evaluation result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the classification result. For example, the multi-feature fusion classification model can assign different weights to different motion features according to the combination of wearable sensors and motion evaluation items, and fuse multiple motion features according to the weights, so as to accurately evaluate the Parkinson's motor symptoms of different body parts of the Parkinson's patient to be tested in a targeted manner. At the same time, by obtaining the evaluation result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested through the multi-feature fusion classification model, the subjectivity of manual analysis and evaluation can be avoided, and the objectivity of quantitative evaluation of Parkinson's motor symptoms can be improved.

[0064] This application collects the motion monitoring data corresponding to the motion assessment items completed by the Parkinson's patient to be tested, determines the evaluation feature combination used to evaluate the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the motion monitoring data, and uses a multi-feature fusion classification model to process the above evaluation feature combination to obtain the evaluation result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested, which can improve the accuracy of Parkinson's motor symptom evaluation for Parkinson's patients. Specifically, since the above motor symptom evaluation mode is determined according to the historical evaluation data of the Parkinson's patient to be tested, that is, the above motor symptom evaluation mode is constructed based on the actual situation of the Parkinson's patient to be tested, the motor function of the Parkinson's patient to be tested can be more targeted to improve the accuracy of Parkinson's motor symptom evaluation. At the same time, an evaluation feature combination for evaluating the current Parkinson's motor symptoms of the Parkinson's patient to be tested is determined according to the above-mentioned motion monitoring data. Since the above-mentioned evaluation feature combination includes multiple motion features obtained from the motion monitoring data, it means that the above-mentioned evaluation feature combination can better reflect the motor ability of the above-mentioned Parkinson's patient to be tested. Finally, the evaluation result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested is obtained through the above-mentioned multi-feature fusion classification model, which can avoid the subjective judgment of the evaluator and perform quantitative evaluation based on the actual motion monitoring data of the Parkinson's patient to be tested, thereby improving the accuracy of the Parkinson's motor symptom evaluation.

[0065] In the embodiment of the present application, the motor symptom assessment model for assessing the current Parkinson's motor symptoms of the Parkinson's patient to be tested obtained according to the historical assessment data includes:

[0066] A motor symptom assessment model was constructed based on the historical Parkinson's assessment data and UPDRS assessment form of different Parkinson's patients;

[0067] Inputting the above historical assessment data into the data screening layer of the above motor symptom assessment model to obtain a Parkinson's patient information vector;

[0068] The above Parkinson's patient information vector is input into the feature extraction layer of the motor symptom assessment model to obtain the medical history characteristics of the Parkinson's patient;

[0069] The above-mentioned medical history features are input into the result output layer of the above-mentioned motor symptom assessment model to obtain the above-mentioned motor symptom assessment model.

[0070] In some embodiments, the above-mentioned historical Parkinson's evaluation data refers to the data of Parkinson's symptom evaluation of different Parkinson's patients within a period of history, including at least motor function evaluation data, drug treatment evaluation data, Parkinson's diagnosis data, etc. The above-mentioned UPDRS evaluation table refers to a rating scale used to classify / grade symptoms of Parkinson's patients. The above-mentioned motor symptom evaluation pattern model can be a neural network model, a linear model, etc. The data screening layer of the above-mentioned motor symptom evaluation pattern model is used to filter out important information of the Parkinson's patient to be tested and perform vector processing, wherein the above-mentioned important information includes the patient's onset time, medication situation, motor diagnosis, etc. The feature extraction layer of the above-mentioned motor symptom evaluation pattern model is used to extract important features of the Parkinson's patient to be tested as medical history features, including medication time features, motor features, etc. The result output layer of the above-mentioned motor symptom evaluation pattern model is used to determine the motor symptoms of the Parkinson's patient to be tested according to the medical history features and perform corresponding pattern evaluation. For example, according to the medical history features, the motor symptoms of the Parkinson's patient A to be tested are determined to be upper limb-tremor, and the upper limb evaluation items are correspondingly generated as the motor symptom evaluation pattern. By obtaining the motor symptom assessment pattern of the Parkinson's disease patient to be tested through the motor symptom assessment pattern model, a more comprehensive motor symptom assessment of the Parkinson's disease patient to be tested can be performed, and a more accurate motor symptom assessment pattern can be obtained.

[0071] In an optional embodiment of the present application, the above-mentioned motion assessment items include one or more of a hand assessment item, an upper limb assessment item, a lower limb assessment item, and a posture assessment item; the above-mentioned wearable sensor includes at least one of a pressure sensor, a strain sensor, an acceleration sensor, a gyroscope sensor, a geomagnetic sensor, a distance sensor, a contact sensor, a temperature sensor, a Hall element, and a microphone, and the above-mentioned acquisition of the motion monitoring data corresponding to the above-mentioned motion assessment items completed by the above-mentioned Parkinson's patient to be tested includes the following steps:

[0072] Selecting one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, distance sensor, contact sensor, temperature sensor, Hall element and microphone to collect the motion monitoring data according to the hand assessment items; and / or

[0073] According to the upper limb assessment items, one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, distance sensor, contact sensor, temperature sensor, Hall element and microphone are selected to collect the motion monitoring data; and / or

[0074] According to the above-mentioned lower limb assessment items, one or more of the above-mentioned pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, distance sensor, contact sensor, temperature sensor, Hall element and microphone are selected to collect the above-mentioned motion monitoring data; and / or

[0075] According to the above-mentioned body posture assessment items, at least one or more of the above-mentioned pressure sensors, strain sensors, acceleration sensors, gyroscope sensors, geomagnetic sensors, distance measuring sensors, contact sensors, temperature sensors, Hall elements and microphones are selected to collect the above-mentioned motion monitoring data.

[0076] In some embodiments, the hand assessment items may include: finger-pointing test (such as tapping the thumb with the index finger 10 times at the largest amplitude and fastest speed), fist test (such as fully opening the palm and repeatedly stretching and clenching the fist 10 times at the fastest speed), etc.; the upper limb assessment items may include: alternating test (such as extending the arm forward, palm facing down, and flipping the palm up and down alternately 10 times at the fastest speed and largest amplitude), postural tremor test (such as extending the arm forward with the palm facing down, wrist straight, fingers separated and not touching each other for 10 seconds), action tremor test (such as extending the arm straight, touching the assessor's fingers as far as possible , and then point to the tip of the nose, repeat three times), static tremor test (such as sitting naturally, with arms relaxed and placed on the armrests on both sides, maintaining this state for 10 seconds), etc.; the above-mentioned lower limb assessment items may include: toe tapping test (such as putting the heel on the ground, tapping the ground with the toes 10 times with the largest amplitude and fastest speed), leg flexibility test (such as putting both feet on the ground, raising the feet and stepping on the ground 10 times with the largest amplitude and fastest speed), etc.; the above-mentioned posture assessment items may include: standing balance test (such as whether the process from sitting to standing can be completed), gait test (such as walking at least 10 meters, then turning around and walking back to the starting point), etc. Since the above-mentioned motion assessment items can be combined according to the historical assessment data of the Parkinson's patient to be tested, and different sensors can be selected for different motion assessment items, the motion assessment of the Parkinson's patient to be tested can be more accurate.

[0077] In the embodiment of the present application, the above-mentioned motion features include time domain features and frequency domain features. The above-mentioned determination of the evaluation feature combination for evaluating the current Parkinson's motor symptoms of the above-mentioned Parkinson's patient to be tested according to the above-mentioned motion monitoring data includes the following steps:

[0078] Setting a time window, dividing the above-mentioned motion monitoring data into time windows, and analyzing the statistical values ​​of the data in the above-mentioned time window at the time domain level to obtain the above-mentioned time domain characteristics; wherein the above-mentioned time domain characteristics include: one or more of mean, variance, standard deviation, extreme value point, zero crossing point, and slope maximum point;

[0079] Performing Fourier transform on the data in the time window to obtain frequency domain distribution information in the time window, and obtaining the frequency domain features according to the frequency domain distribution information; wherein the frequency domain features include one or more of power spectrum extreme points and frequency ranges;

[0080] The evaluation feature combination of the current Parkinson's motor symptoms of the Parkinson's patient to be tested is determined according to the time domain features and the frequency domain features.

[0081] In some embodiments, the above-mentioned motion characteristics are determined by motion signals (i.e., motion monitoring data) collected by wearable sensors. Since the motion signal not only changes with time but is also related to information such as frequency, the motion monitoring data is divided into time windows by setting a time window (for example, a 2S time window is set), and the statistical values ​​of the data in each time window are analyzed at the time domain level to obtain the time domain characteristics, and the frequency domain distribution information in different time windows is obtained through Fourier transform. The frequency domain characteristics of the corresponding time window are obtained according to the frequency domain distribution information. The number of motion features can be enriched, and the Parkinson's motor symptoms of the Parkinson's patient to be tested can be evaluated based on features from different angles (time domain features and frequency domain features), thereby improving the accuracy of the Parkinson's motor symptom evaluation.

[0082] Optionally, the determining of the evaluation feature combination of the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the time domain features and the frequency domain features comprises the following steps:

[0083] Sorting the time domain features and the frequency domain features using the historical Parkinson's assessment data and a preset feature sorting model to obtain a first sorting result;

[0084] Randomly combining the time domain features and the frequency domain features to obtain multiple feature combinations;

[0085] Sorting the plurality of feature combinations using the historical Parkinson's assessment data and the feature sorting model to obtain a second sorting result;

[0086] The evaluation feature combination is determined according to the second sorting result, and the feature weight of the time domain feature and / or the feature weight of the frequency domain feature in the evaluation feature combination is determined according to the first sorting result.

[0087] In some embodiments, the preset feature ranking model can be one of a logistic regression model (LR), a support vector machine model (SVM), a random forest model (RF) and an extreme gradient boosting model (XGBoost). Since there are many motion features, and the motion features required for evaluating Parkinson's motor symptoms in different parts of the body are also different, in order to further improve the accuracy and pertinence of Parkinson's motor symptom evaluation, different motion features are ranked by the feature ranking model, and different feature weights are assigned according to the ranking results; different feature combinations are constructed by random combination, and different feature combinations are ranked by the feature ranking model, so as to find a more accurate and appropriate feature combination.

[0088] In an optional embodiment of the present application, it is assumed that the above-mentioned preset feature sorting model is an XGBoost model, and the XGBoost model is trained by using historical Parkinson's assessment data so that the XGBoost model can learn important features that affect the above-mentioned historical Parkinson's assessment data, and the trained XGBoost model is used to sort multiple motion features to obtain a first sorting result, including: motion feature 1 (100), motion feature 2 (80), motion feature 3 (60) and motion feature 4 (40), wherein X in (X) is the corresponding feature weight; different motion features are randomly combined to obtain multiple feature combinations, and the trained XGBoost model is also used to sort the multiple feature combinations to obtain a second sorting result including: feature combination 1 (motion feature 1 (100), motion feature 2 (80), motion feature 3 (60)), feature combination 2 (motion feature 1 (100), motion feature 2 (80)), feature combination 3 (motion feature 1 (100), motion feature 3 (60)), and an evaluation feature combination is selected from the second sorting result.

[0089] In another optional embodiment of the present application, motion features with lower weights can be filtered out from the first sorting result and the second sorting result according to a preset feature weight threshold, so as to reduce the number of features and improve the evaluation efficiency of Parkinson's motor symptoms.

[0090] In the embodiment of the present application, the training process of the multi-feature fusion classification model includes the following steps:

[0091] Obtaining a Parkinson's symptom training set, wherein the Parkinson's symptom training set includes historical movement data and historical Parkinson's movement symptom assessment results;

[0092] Processing the above historical motion data to obtain normalized motion data;

[0093] The normalized motion data is input into a neural network for training. During the training process, the parameters of the neural network are optimized according to the historical Parkinson's motor symptom assessment results to obtain the trained multi-feature fusion classification model.

[0094] In some embodiments, normalized motion data is obtained by processing historical motion data to ensure the uniformity and comparability of the data; the above-mentioned normalized motion data is used to train the above-mentioned neural network, so that the above-mentioned neural network can learn the ability to fuse different motion features. The above-mentioned neural network can be a multi-layer perceptron (MLP) or a convolutional neural network (CNN). During the training process, the model parameters can be optimized based on the historical Parkinson's motor symptom assessment results using optimization algorithms such as cross entropy loss function and gradient descent. Ultimately, through repeated iterative training, the above-mentioned multi-feature fusion classification model can learn the optimal combination of different feature weights, thereby achieving the goal of multi-feature fusion classification and improving the accuracy of Parkinson's motor symptom assessment.

[0095] In the embodiment of the present application, the above-mentioned evaluation feature combination is input into the trained multi-feature fusion classification model to obtain the evaluation result of the current Parkinson's motor symptoms of the above-mentioned Parkinson's patient to be tested, including the following steps:

[0096] Using the multi-feature fusion classification model, the time domain features and / or frequency domain features in the evaluation feature combination are fused to obtain fused feature values;

[0097] The fused feature values ​​are clustered, and the evaluation result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested is determined according to the clustering result.

[0098] In some embodiments, the above-mentioned multi-feature fusion classification model can perform feature fusion according to the feature weights of the time domain features and / or frequency domain features in the evaluation feature combination. At the same time, since the evaluation feature combination includes different time domain features and / or frequency domain features, it means that by performing feature fusion on the evaluation feature combination through the multi-feature fusion classification model, multiple motion features can be fused into a fused feature value. Therefore, clustering the fused feature values ​​can reduce the amount of calculation and improve the evaluation efficiency of Parkinson's motor symptoms.

[0099] In an optional embodiment of the present application, it is assumed that the k-means algorithm is used for clustering. Clustering is performed by the following steps:

[0100] Step 1: Take each of the above fusion feature values ​​as a sample, randomly select k samples as the initial clustering center, set as u 1 ,u 2 , ..., uk ;

[0101] Step 2: For each sample x, calculate its distance to the k initial cluster centers, select the cluster with the closest cluster center, and assign the sample to that cluster;

[0102] Step 3: For each cluster, calculate the average value of the samples in it as the new cluster center;

[0103] Repeat steps 2-3 until the cluster center no longer changes or the preset number of iterations is reached, and different clustering results are obtained according to different clusters.

[0104] Among them, the following formula can be used to determine whether the cluster center no longer changes:

[0105]

[0106] Among them, J represents the overall sum of squares. When the overall sum of squares is the smallest, the cluster center will no longer change; k represents the number of clusters; C i represents the i-th cluster, u i represents the cluster center of the i-th cluster, ‖xu i ‖ 2 Represents the Euclidean distance from sample x to the cluster center.

[0107] In an optional embodiment of the present application, for example, for a resting tremor test, the above clustering results may include 0: normal: no tremor; 1: mild: the maximum tremor amplitude is less than 1 cm; 2: mild: the maximum tremor amplitude is greater than or equal to 1 cm, but less than 3 cm; 3: moderate: the maximum tremor amplitude is greater than or equal to 3 cm, but less than 10 cm; 4: severe: the maximum tremor amplitude is greater than or equal to 10 cm. Assuming that the motor symptom assessment model includes motion assessment items of a resting tremor test and a gait test, after clustering, if the clustering result of the resting tremor test is 1: mild, and the clustering result of the gait test is 2: mild, then the output assessment result is: two motor assessments of tremor and gait have been performed, the assessment score is 3 points, and the patient exhibits mild tremor and mild gait impairment.

[0108] It should be understood that the size of the serial numbers of the steps in the above embodiments 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.

[0109] Corresponding to the Parkinson's motor symptom assessment method described in the above embodiment, Figure 2 A schematic diagram of the structure of a Parkinson's motor symptom assessment device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0110] Reference Figure 2 The device may be a Parkinson's motor symptom assessment device 21, and the Parkinson's motor symptom assessment device 21 may include a motor symptom assessment mode determination module 211, a motion data acquisition module 212, a feature combination determination module 213 and a motor symptom assessment module 214.

[0111] Reference Figure 2 , the Parkinson's movement symptom assessment device 21 comprises:

[0112] The motor symptom assessment mode determination module 211 is used to obtain historical assessment data of the Parkinson's patient to be tested, and obtain a motor symptom assessment mode for assessing the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the historical assessment data, wherein the motor symptom assessment mode includes at least one group of motor assessment items;

[0113] The motion data acquisition module 212 is used to collect the motion monitoring data corresponding to the motion assessment project completed by the Parkinson's patient to be tested; the motion monitoring data is collected by configuring at least one group of wearable sensors;

[0114] The feature combination determination module 213 is used to determine, according to the motion monitoring data, an evaluation feature combination for evaluating the current Parkinson's motor symptoms of the Parkinson's patient to be tested;

[0115] The motor symptom assessment module 214 is used to input the assessment feature combination into the trained multi-feature fusion classification model to obtain the assessment result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested.

[0116] In some embodiments, the motor symptom assessment mode determination module 211 obtains a motor symptom assessment mode for assessing the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the historical assessment data through the following steps, including:

[0117] A motor symptom assessment model was constructed based on the historical Parkinson's assessment data and UPDRS assessment form of different Parkinson's patients;

[0118] Inputting the historical assessment data into the data screening layer of the motor symptom assessment mode model to obtain a Parkinson's patient information vector;

[0119] Inputting the Parkinson's patient information vector into the feature extraction layer of the motor symptom assessment model to obtain the medical history characteristics of the Parkinson's patient;

[0120] The medical history features are input into the result output layer of the motor symptom assessment model to obtain the motor symptom assessment model.

[0121] In some embodiments, the motion assessment items include one or more of a hand assessment item, an upper limb assessment item, a lower limb assessment item, and a posture assessment item; the wearable sensor includes at least one of a pressure sensor, a strain sensor, an acceleration sensor, a gyroscope sensor, a geomagnetic sensor, a distance sensor, a contact sensor, a temperature sensor, a Hall element, and a microphone. The motion data acquisition module 212 collects the motion monitoring data corresponding to the motion assessment items completed by the Parkinson's patient to be tested through the following steps, including:

[0122] selecting one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, distance sensor, contact sensor, temperature sensor, Hall element and microphone to collect the motion monitoring data according to the hand assessment items; and / or

[0123] Select one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, distance sensor, contact sensor, temperature sensor, Hall element and microphone to collect the motion monitoring data according to the upper limb assessment items; and / or

[0124] Select one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, distance sensor, contact sensor, temperature sensor, Hall element and microphone to collect the motion monitoring data according to the lower limb assessment items; and / or

[0125] According to the body posture assessment items, at least one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, distance sensor, contact sensor, temperature sensor, Hall element and microphone are selected to collect the motion monitoring data.

[0126] In some embodiments, the motion features include time domain features and frequency domain features, and the feature combination determination module 213 determines the evaluation feature combination for evaluating the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the motion monitoring data through the following steps, including:

[0127] Setting a time window, dividing the motion monitoring data into time windows, and analyzing the statistical values ​​of the data in the time window at the time domain level to obtain the time domain features; wherein the time domain features include: one or more of mean, variance, standard deviation, extreme value point, zero crossing point, and slope maximum point;

[0128] Performing Fourier transform on the data in the time window to obtain frequency domain distribution information in the time window, and obtaining the frequency domain features according to the frequency domain distribution information; wherein the frequency domain features include one or more of power spectrum extreme points and frequency ranges;

[0129] A combination of evaluation features of the current Parkinson's motor symptoms of the Parkinson's patient to be tested is determined according to the time domain features and the frequency domain features.

[0130] In some embodiments, the feature combination determination module 213 determines the assessment feature combination of the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the time domain features and the frequency domain features through the following steps, including:

[0131] Sorting the time domain features and the frequency domain features using the historical Parkinson's assessment data and a preset feature sorting model to obtain a first sorting result;

[0132] Randomly combining the time domain features and the frequency domain features to obtain multiple feature combinations;

[0133] sorting the plurality of feature combinations using the historical Parkinson's assessment data and the feature sorting model to obtain a second sorting result;

[0134] The evaluation feature combination is determined according to the second sorting result, and the feature weight of the time domain feature and / or the feature weight of the frequency domain feature in the evaluation feature combination is determined according to the first sorting result.

[0135] In some other embodiments, the Parkinson's movement symptom assessment device 21 further includes a model training module, and the model training module includes the following steps:

[0136] Acquire a Parkinson's symptom training set, wherein the Parkinson's symptom training set includes historical movement data and historical Parkinson's movement symptom assessment results;

[0137] Processing the historical motion data to obtain normalized motion data;

[0138] The normalized motion data is input into a neural network for training. During the training process, the parameters of the neural network are optimized according to the historical Parkinson's motor symptom assessment results to obtain the trained multi-feature fusion classification model.

[0139] In some embodiments, the motor symptom assessment module 214 inputs the assessment feature combination into the trained multi-feature fusion classification model through the following steps to obtain the assessment result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested, including:

[0140] Using the multi-feature fusion classification model to perform feature fusion on the time domain features and / or frequency domain features in the evaluation feature combination to obtain a fused feature value;

[0141] The fused feature values ​​are clustered, and an assessment result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested is determined according to the clustering result.

[0142] It should be noted that the information interaction, execution process, etc. between the devices / units are based on the same concept as the method embodiments of the present application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0143] Figure 3 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3 As shown, the electronic device 3 of this embodiment includes: at least one processor 30 ( Figure 3 The at least one processor 30 includes a memory 31 and a computer program 32 stored in the memory 31 and executable on the at least one processor 30. When the processor 30 executes the computer program 32, the steps of the method for evaluating Parkinson's motor symptoms described in the above embodiment are implemented.

[0144] The electronic device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will appreciate that Figure 3 It is only an example of the electronic device 3 and does not constitute a limitation of the electronic device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include an input sending device, a network access device, a bus, etc.

[0145] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0146] In some embodiments, the memory 31 may be an internal storage unit of the electronic device 3, such as a hard disk or memory of the electronic device 3. The memory 31 may also be an external storage device of the electronic device 3, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 3. Further, the memory 31 may also include both an internal storage unit of the electronic device 3 and an external storage device. The memory 31 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 31 may also be used to temporarily store data that has been sent or is to be sent.

[0147] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the functional units and modules is used as an example for illustration. In practical applications, the functional distribution can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit, and the integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the system can refer to the corresponding process in the Parkinson's motor symptom assessment method described in the above embodiment, which will not be repeated here.

[0148] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the Parkinson's motor symptom assessment method described in the above embodiment can be implemented.

[0149] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process in the Parkinson's motor symptom assessment method described in the above embodiment, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the Parkinson's motor symptom assessment method described in the above embodiment can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / electronic device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0150] In the embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0151] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0152] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0153] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0154] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for evaluating Parkinson's motor symptoms, It is characterized in that The method comprises the following steps: Acquiring historical assessment data of a Parkinson's patient to be tested, and obtaining a motor symptom assessment model for assessing current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the historical assessment data, wherein the motor symptom assessment model includes at least one group of motor assessment items; Collecting the motion monitoring data corresponding to the motion assessment items completed by the Parkinson's patient to be tested; the motion monitoring data is collected by configuring at least one group of wearable sensors; Determining an evaluation feature combination for evaluating the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the motion monitoring data; wherein the evaluation feature combination includes a plurality of motion features obtained from the motion monitoring data; The evaluation feature combination is input into a trained multi-feature fusion classification model to obtain an evaluation result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested.

2. The method for evaluating Parkinson's motor symptoms according to claim 1, It is characterized in that The step of obtaining a motor symptom assessment model for assessing the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the historical assessment data comprises the following steps: A motor symptom assessment model was constructed based on the historical Parkinson's assessment data and UPDRS assessment form of different Parkinson's patients; Inputting the historical assessment data into the data screening layer of the motor symptom assessment mode model to obtain a Parkinson's patient information vector; Inputting the Parkinson's patient information vector into the feature extraction layer of the motor symptom assessment model to obtain the medical history characteristics of the Parkinson's patient; The medical history features are input into the result output layer of the motor symptom assessment model to obtain the motor symptom assessment model.

3. The method for evaluating Parkinson's motor symptoms according to claim 1, It is characterized in that The motion assessment items include one or more of a hand assessment item, an upper limb assessment item, a lower limb assessment item, and a posture assessment item; the wearable sensor includes at least one of a pressure sensor, a strain sensor, an acceleration sensor, a gyroscope sensor, a geomagnetic sensor, a distance sensor, a contact sensor, a temperature sensor, a Hall element, and a microphone; and the acquisition of the motion monitoring data corresponding to the motion assessment items completed by the Parkinson's patient to be tested includes the following steps: selecting one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, distance sensor, contact sensor, temperature sensor, Hall element and microphone to collect the motion monitoring data according to the hand assessment items; and / or Select one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, distance sensor, contact sensor, temperature sensor, Hall element and microphone to collect the motion monitoring data according to the upper limb assessment items; and / or Select one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, distance sensor, contact sensor, temperature sensor, Hall element and microphone to collect the motion monitoring data according to the lower limb assessment items; and / or According to the body posture assessment items, at least one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, distance sensor, contact sensor, temperature sensor, Hall element and microphone are selected to collect the motion monitoring data.

4. The method for evaluating Parkinson's motor symptoms according to claim 2, It is characterized in that The motion features include time domain features and frequency domain features. The step of determining the evaluation feature combination for evaluating the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the motion monitoring data includes the following steps: Setting a time window, dividing the motion monitoring data into time windows, and analyzing the statistical values ​​of the data in the time window at the time domain level to obtain the time domain features; wherein the time domain features include: one or more of mean, variance, standard deviation, extreme value point, zero crossing point, and slope maximum point; Performing Fourier transform on the data in the time window to obtain frequency domain distribution information in the time window, and obtaining the frequency domain features according to the frequency domain distribution information; wherein the frequency domain features include one or more of power spectrum extreme points and frequency ranges; A combination of evaluation features of the current Parkinson's motor symptoms of the Parkinson's patient to be tested is determined according to the time domain features and the frequency domain features.

5. The method for evaluating Parkinson's motor symptoms according to claim 4, It is characterized in that The step of determining the evaluation feature combination of the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the time domain features and the frequency domain features comprises the following steps: Sorting the time domain features and the frequency domain features using the historical Parkinson's assessment data and a preset feature sorting model to obtain a first sorting result; Randomly combining the time domain features and the frequency domain features to obtain multiple feature combinations; sorting the plurality of feature combinations using the historical Parkinson's assessment data and the feature sorting model to obtain a second sorting result; The evaluation feature combination is determined according to the second sorting result, and the feature weight of the time domain feature and / or the feature weight of the frequency domain feature in the evaluation feature combination is determined according to the first sorting result.

6. The method for evaluating Parkinson's motor symptoms according to claim 1, It is characterized in that The training process of the multi-feature fusion classification model includes the following steps: Acquire a Parkinson's symptom training set, wherein the Parkinson's symptom training set includes historical movement data and historical Parkinson's movement symptom assessment results; Processing the historical motion data to obtain normalized motion data; The normalized motion data is input into a neural network for training. During the training process, the parameters of the neural network are optimized according to the historical Parkinson's motor symptom assessment results to obtain the trained multi-feature fusion classification model.

7. The method for evaluating Parkinson's motor symptoms according to any one of claims 1 to 6, It is characterized in that The step of inputting the evaluation feature combination into a trained multi-feature fusion classification model to obtain an evaluation result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested comprises the following steps: Using the multi-feature fusion classification model to perform feature fusion on the time domain features and / or frequency domain features in the evaluation feature combination to obtain a fused feature value; The fused feature values ​​are clustered, and an assessment result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested is determined according to the clustering result.

8. A device for evaluating Parkinson's motor symptoms, It is characterized in that include: a motor symptom assessment mode determination module, used to obtain historical assessment data of a Parkinson's patient to be tested, and to obtain a motor symptom assessment mode for assessing the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the historical assessment data, wherein the motor symptom assessment mode includes at least one group of motor assessment items; A motion data acquisition module, used to collect motion monitoring data corresponding to the motion assessment project completed by the Parkinson's patient to be tested; the motion monitoring data is collected by configuring at least one group of wearable sensors; A feature combination determination module, used to determine an evaluation feature combination for evaluating the current Parkinson's motor symptoms of the Parkinson's patient to be tested according to the movement monitoring data; The motor symptom assessment module is used to input the assessment feature combination into the trained multi-feature fusion classification model to obtain the assessment result of the current Parkinson's motor symptoms of the Parkinson's patient to be tested.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images