Method and device for evaluating parkinsonian motor symptoms, electronic device and storage medium

Abstract

The application is suitable for the field of physiological signal recognition, and provides a Parkinson motor symptom evaluation method and device, an electronic device and a storage medium. The method comprises the following steps: obtaining a motor symptom evaluation mode for evaluating the current Parkinson motor symptom of a to-be-evaluated Parkinson patient according to historical evaluation data of the to-be-evaluated Parkinson patient, the motor symptom evaluation mode comprising at least one group of motor evaluation items; collecting motor monitoring data corresponding to the motor evaluation items completed by the to-be-evaluated Parkinson patient; collecting the motor monitoring data through at least one group of wearable sensors; determining an evaluation feature combination for evaluating the current Parkinson motor symptom of the to-be-evaluated Parkinson patient according to the motor monitoring data; the evaluation feature combination comprises a plurality of motor features obtained from the motor monitoring data; inputting the evaluation feature combination into a trained multi-feature fusion classification model to obtain an evaluation result. The application can improve the accuracy of Parkinson motor symptom evaluation for Parkinson patients.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of physiological signal recognition, and particularly relates to a Parkinson motor symptom evaluation method and device, an electronic device, and a computer readable storage medium. BACKGROUND

[0002] Parkinson's Disease (PD) is the most common movement disorder and the second most common neurodegenerative disease. The main pathological feature of Parkinson's Disease is the progressive and selective loss of cells in certain regions of the central nervous system. This degeneration mainly occurs in dopaminergic neurons of the substantia nigra compacta (SNpc) and leads to classic Parkinson-like motor manifestations: bradykinesia, muscle rigidity, resting tremor, and postural and gait disorders. Currently, drug therapy is mainly used for PD patients. The typical feature of Parkinson's Disease is good responsiveness to dopaminergic drugs (most of which refer to levodopa). Levodopa challenge test (LCT) is used in clinical practice to evaluate the responsiveness of patients to levodopa drugs. Responsiveness to levodopa drugs provides an important basis for the clinical diagnosis of PD, the optimization of treatment effect, and the evaluation of the applicability of device-assisted treatment (such as deep brain stimulation (DBS)).

[0003] Currently, the most important thing for Parkinson motor symptom evaluation is to perform Unified Parkinson's Disease Rating Scale (UPDRS) evaluation. However, in the evaluation of the Parkinson motor symptom evaluation scale in Part III of the Unified Parkinson Rating Scale (UPDRS III), it is difficult to give an accurate score, and the scale is too rough to give a record of the subtle differences in each score. For example, in the evaluation of hand tremor, hand tremor needs to be scored according to the tremor amplitude of less than 1 cm, 1-3 cm, or more than 3 cm. In fact, it is difficult to accurately measure the amplitude of tremor in clinical practice, and when scoring, the evaluator generally estimates the score according to the amplitude of the patient's limb tremor. For example, in the evaluation of bradykinesia, the score is based on slight, mild, moderate, and severe slowing of movement, which obviously lacks objective measurable data support and is affected by the evaluator's subjective judgment. There are also qualitative estimates such as the patellar test and the standing test. Moreover, the scale is not sensitive to slight changes within a score range, making it difficult to quantitatively evaluate. SUMMARY

[0004] The Parkinson motor symptom evaluation method, device, electronic device, and computer readable storage medium provided by the embodiments of the present application can improve the accuracy of Parkinson motor symptom evaluation for Parkinson's Disease patients.

[0005] In a first aspect, the embodiments of the present application provide a Parkinson motor symptom evaluation method, comprising:

[0006] obtaining historical evaluation data of a Parkinson patient to be tested, and obtaining a motor symptom evaluation mode for evaluating the current Parkinson motor symptom of the Parkinson patient to be tested according to the historical evaluation data, wherein the motor symptom evaluation mode comprises at least one group of motor evaluation items;

[0007] collecting motor monitoring data corresponding to the motor evaluation items completed by the Parkinson patient to be tested, wherein the motor monitoring data is collected by configuring at least one group of wearable sensors;

[0008] determining an evaluation feature combination for evaluating the current Parkinson motor symptom of the Parkinson patient to be tested according to the motor monitoring data, wherein the evaluation feature combination comprises a plurality of motor features obtained from the motor monitoring data;

[0009] inputting the evaluation feature combination into a trained multi-feature fusion classification model to obtain an evaluation result of the current Parkinson motor symptom of the Parkinson patient to be tested.

[0010] Optionally, the obtaining of the motor symptom evaluation mode for evaluating the current Parkinson motor symptom of the Parkinson patient to be tested according to the historical evaluation data comprises the following steps:

[0011] constructing a motor symptom evaluation mode model according to historical Parkinson evaluation data and UPDRS evaluation tables of different Parkinson patients;

[0012] inputting the historical evaluation data into a data screening layer of the motor symptom evaluation mode model to obtain a Parkinson patient information vector;

[0013] inputting the Parkinson patient information vector into a feature extraction layer of the motor symptom evaluation mode model to obtain a medical history feature of the Parkinson patient;

[0014] inputting the medical history feature into a result output layer of the motor symptom evaluation mode model to obtain the motor symptom evaluation mode.

[0015] Optionally, the motor evaluation items comprise one or more of a hand evaluation item, an upper limb evaluation item, a lower limb evaluation item, and a body posture evaluation item; the wearable sensors comprise at least one of a pressure sensor, a strain sensor, an acceleration sensor, a gyroscope sensor, a geomagnetic sensor, a distance measuring sensor, a contact sensor, a temperature sensor, a Hall element, and a microphone; and the collecting of the motor monitoring data corresponding to the motor evaluation items completed by the Parkinson patient to be tested comprises the following steps:

[0016] According to the hand evaluation project, one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, ranging sensor, contact sensor, temperature sensor, Hall element, and microphone is selected to collect the motion monitoring data; and / or

[0017] According to the upper limb evaluation project, one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, ranging sensor, contact sensor, temperature sensor, Hall element, and microphone is selected to collect the motion monitoring data; and / or

[0018] According to the lower limb evaluation project, one or more of the pressure sensor, strain sensor, acceleration sensor, gyroscope sensor, geomagnetic sensor, ranging sensor, contact sensor, temperature sensor, Hall element, and microphone is selected to collect the motion monitoring data; and / or

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

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

[0021] A time window is set, the motion monitoring data is divided into time windows, and the statistical values of the data in the time window are analyzed 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 point, zero-crossing point, and maximum slope point;

[0022] The data in the time window is subjected to Fourier transform to obtain frequency domain distribution information in the time window, and the frequency domain features are obtained according to the frequency domain distribution information; wherein the frequency domain features include one or more of power spectrum extreme point and frequency range;

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

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

[0025] The historical Parkinson evaluation data and a preset feature ranking model are used to rank the time domain features and the frequency domain features, to obtain a first ranking result;

[0026] The time domain features and the frequency domain features are randomly combined to obtain a plurality of feature combinations;

[0027] The historical Parkinson evaluation data and the feature ranking model are used to rank the plurality of feature combinations, to obtain a second ranking result;

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

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

[0030] A Parkinson symptom training set is obtained, and the Parkinson symptom training set comprises historical motion data and historical Parkinson motor symptom evaluation results;

[0031] The historical motion data is processed to obtain normalized motion data;

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

[0033] Optionally, the evaluation feature combination is input into the trained multi-feature fusion classification model, to obtain the evaluation result of the current Parkinson motor symptom of the to-be-tested Parkinson patient, comprising the following steps:

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

[0035] The fusion feature value is clustered, and the evaluation result of the current Parkinson motor symptom of the to-be-tested Parkinson patient is determined according to the clustering result.

[0036] In a second aspect, the embodiments of the present application provide a Parkinson motor symptom evaluation device, comprising:

[0037] A motor symptom evaluation mode determination module is configured to obtain historical evaluation data of a to-be-tested Parkinson patient, and obtain a motor symptom evaluation mode for evaluating the current Parkinson motor symptom of the to-be-tested Parkinson patient according to the historical evaluation data, wherein the motor symptom evaluation mode comprises at least one set of motor evaluation items;

[0038] The motion data acquisition module is configured to collect motion monitoring data corresponding to the motion evaluation project completed by the Parkinson patient to be evaluated; the motion monitoring data is collected by configuring at least one set of wearable sensors;

[0039] The feature combination determination module is configured to determine an evaluation feature combination for evaluating the current Parkinson motion symptom of the Parkinson patient to be evaluated according to the motion monitoring data;

[0040] The motion symptom evaluation module is configured to input the evaluation feature combination into a trained multi-feature fusion classification model to obtain an evaluation result of the current Parkinson motion symptom of the Parkinson patient to be evaluated.

[0041] In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the Parkinson motion symptom evaluation method in the first aspect when executing the computer program.

[0042] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program implements the steps of the Parkinson motion symptom evaluation method in the first aspect when executed by a processor.

[0043] The present application collects the motion monitoring data corresponding to the motion evaluation project completed by the Parkinson patient to be evaluated, determines an evaluation feature combination for evaluating the current Parkinson motion symptom of the Parkinson patient to be evaluated according to the motion monitoring data, processes the evaluation feature combination by using a multi-feature fusion classification model, and obtains an evaluation result of the current Parkinson motion symptom of the Parkinson patient to be evaluated, thereby improving the accuracy of the Parkinson motion symptom evaluation of the Parkinson patient. Specifically, the motion symptom evaluation mode is determined according to the historical evaluation data of the Parkinson patient to be evaluated, that is, the motion symptom evaluation mode is constructed based on the real situation of the Parkinson patient to be evaluated, which can more specifically check the motion function of the Parkinson patient to be evaluated and improve the accuracy of the Parkinson motion symptom evaluation. Meanwhile, the evaluation feature combination for evaluating the current Parkinson motion symptom of the Parkinson patient to be evaluated is determined according to the motion monitoring data, the evaluation feature combination includes multiple motion features obtained from the motion monitoring data, which means that the evaluation feature combination can better reflect the motion ability of the Parkinson patient to be evaluated, and finally the evaluation result of the current Parkinson motion symptom of the Parkinson patient to be evaluated is obtained by using the multi-feature fusion classification model, which can avoid subjective judgment of evaluators, quantitatively evaluate the Parkinson patient to be evaluated according to the real motion monitoring data, and improve the accuracy of the Parkinson motion symptom evaluation. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only some of the embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

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

[0046] Figure 2 is a structural diagram of the assessment of Parkinson's motor symptoms provided by an embodiment of the present application;

[0047] Figure 3 is a structural diagram of the electronic device for the assessment of Parkinson's motor symptoms provided by an embodiment of the present application. DETAILED DESCRIPTION

[0048] In the following description, for the purpose of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0049] It should be understood that the term "comprising" as used in the specification and the appended claims indicates the presence of the recited features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0050] It should also be understood that the term "and / or" as used herein refers to any combination of one or more of the associated listed items, and all possible combinations, and includes these combinations.

[0051] As used in the specification and the appended claims, the term "if' can be interpreted as meaning "when" or "once" or "in response to a determination" or "in response to a detection" depending on the context. Similarly, the phrase "if determined" or "if detected [the described condition or event]" can be interpreted to mean "once determined" or "in response to a determination" or "once detected [the described condition or event]" or "in response to a detection [the described condition or event]" depending on the context.

[0052] Reference within the specification of this application to "one embodiment" or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrase "in one embodiment" or "in some embodiments" in various places within specifications are not necessarily all referring to the same embodiment, however, are meant to signify that "one or more, but not all embodiments" of the application so described are contemplated to develop the application. The terms "including," "comprising," "having," and variations thereof, are meant to encompass the items listed thereafter and equivalents thereof as well as additional items.

[0053] At present, when the Parkinson motor symptom is evaluated by the UPDRS-III scale, the evaluation result is subjective and individual bias is large, which affects the accuracy of the Parkinson motor symptom evaluation. With the gradual maturity of the application technology of wearable sensor technology and equipment in motion analysis, the Parkinson motor symptom evaluation of Parkinson patients can be quantified through wearable equipment, and automatic evaluation with higher sensitivity, better consistency and accuracy than traditional scales can be realized. However, due to the complexity and diversity of Parkinson patients' motor performance, the body parts involved are also different. At present, when wearable equipment is applied in the field of Parkinson's disease, it can only realize the evaluation of one or several typical motor symptoms, and the analysis of these motor symptoms is discrete, which leads to insufficient evaluation of Parkinson motor symptoms. At the same time, due to the great difference in physiological structure, muscle group and other aspects of different body parts, it means that different motor symptom evaluations of Parkinson's disease in different body parts often need different motor feature data, and the existing wearable equipment applied in the field of Parkinson's disease cannot analyze the motor symptoms of different body parts, which leads to inaccurate evaluation of Parkinson motor symptoms.

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

[0055] Figure 1 The flowchart of a Parkinson motor symptom evaluation method provided by the embodiment of the application is shown, and the details are as follows:

[0056] S1, obtain the historical evaluation data of the Parkinson patient to be tested, and obtain a motor symptom evaluation mode for evaluating the current Parkinson motor symptom of the Parkinson patient to be tested according to the historical evaluation data, wherein the motor symptom evaluation mode includes at least one group of motor evaluation items.

[0057] In the embodiments of the present application, the historical evaluation data refers to data of a Parkinson's disease patient to be tested for evaluation of Parkinson's symptoms 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, and legs), drug treatment evaluation data (such as drug use time and drug use amount), Parkinson's diagnosis data (such as tremor amplitude), and the like. The above-mentioned motor symptom evaluation mode is used to evaluate the Parkinson's motor symptoms of different body parts of the Parkinson's disease patient to be tested, wherein different body parts correspond to different motor evaluation items, so that by determining the different body parts of the Parkinson's disease patient to be tested that need to be evaluated, 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 disease patient to be tested; at the same time, since the historical evaluation data contains more Parkinson's symptom information, the different body parts of the Parkinson's disease patient to be tested that need to be evaluated can be more comprehensively and accurately determined, and thus a more accurate motor symptom evaluation mode can be obtained.

[0058] S2, collecting movement monitoring data corresponding to the motor evaluation items completed by the Parkinson's disease patient to be tested; the movement monitoring data is collected by at least one group of wearable sensors.

[0059] In the embodiments of the present application, different motor evaluation items correspond to different wearable sensors for collecting movement monitoring data of corresponding body parts. The movement monitoring data includes acceleration information, angular velocity information, and orientation information of different body parts of the Parkinson's disease patient to be tested. Therefore, by collecting the movement monitoring data corresponding to the motor evaluation items completed by the Parkinson's disease patient to be tested through at least one group of wearable sensors, the movement physiological data related to Parkinson's disease of different body parts of the Parkinson's disease patient to be tested can be collected in a targeted manner.

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

[0061] In the embodiments of the present application, the evaluation feature combination for evaluating the current Parkinson's motor symptoms of the Parkinson's disease patient to be tested is determined through the movement monitoring data, and since the evaluation feature combination includes a plurality of movement features obtained from the movement monitoring data, the Parkinson's motor symptoms can be evaluated through different movement features, and the accuracy of evaluating the Parkinson's motor symptoms can be improved.

[0062] S4, 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 disease patient to be tested.

[0063] In the embodiments of the present application, the multi-feature fusion classification model is used for feature fusion and classification of different motion features, and the evaluation result of the current Parkinson's motion symptom of the to-be-tested Parkinson's patient is obtained 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 the motion evaluation project, and fuse multiple motion features according to the weight, so as to accurately evaluate the Parkinson's motion symptom of different body parts of the to-be-tested Parkinson's patient. At the same time, the evaluation result of the current Parkinson's motion symptom of the to-be-tested Parkinson's patient obtained by the multi-feature fusion classification model can avoid the subjectivity of artificial analysis and evaluation, and improve the objectivity of quantitative evaluation of Parkinson's motion symptom.

[0064] In the embodiments of the present application, the motion monitoring data corresponding to the motion evaluation project completed by the to-be-tested Parkinson's patient is collected, the evaluation feature combination for evaluating the current Parkinson's motion symptom of the to-be-tested Parkinson's patient is determined according to the motion monitoring data, the multi-feature fusion classification model is used to process the evaluation feature combination, and the evaluation result of the current Parkinson's motion symptom of the to-be-tested Parkinson's patient is obtained, which can improve the accuracy of Parkinson's motion symptom evaluation of Parkinson's patients. Specifically, since the motion symptom evaluation mode is determined according to the historical evaluation data of the to-be-tested Parkinson's patient, that is, the motion symptom evaluation mode is constructed based on the real situation of the to-be-tested Parkinson's patient, the motion function of the to-be-tested Parkinson's patient can be more accurately checked, and the accuracy of Parkinson's motion symptom evaluation is improved. At the same time, the evaluation feature combination for evaluating the current Parkinson's motion symptom of the to-be-tested Parkinson's patient is determined according to the motion monitoring data, and since the evaluation feature combination includes multiple motion features obtained from the motion monitoring data, it means that the evaluation feature combination can better reflect the motion ability of the to-be-tested Parkinson's patient, and finally the evaluation result of the current Parkinson's motion symptom of the to-be-tested Parkinson's patient is obtained through the multi-feature fusion classification model, which can avoid subjective judgment of the evaluator, and the quantitative evaluation is performed according to the real motion monitoring data of the to-be-tested Parkinson's patient, thereby improving the accuracy of Parkinson's motion symptom evaluation.

[0065] In the embodiments of the present application, the motion symptom evaluation mode for evaluating the current Parkinson's motion symptom of the to-be-tested Parkinson's patient obtained according to the historical evaluation data includes:

[0066] constructing a motion symptom evaluation mode model according to the historical Parkinson's evaluation data and the UPDRS evaluation table of different Parkinson's patients;

[0067] inputting the historical evaluation data into the data screening layer of the motion symptom evaluation mode model to obtain a Parkinson's patient information vector;

[0068] inputting the Parkinson's patient information vector into a feature extraction layer of a motor symptom evaluation mode model to obtain a medical history feature of the Parkinson's patient;

[0069] inputting the medical history feature into a result output layer of the motor symptom evaluation mode model to obtain the motor symptom evaluation mode.

[0070] In some embodiments, the historical Parkinson's evaluation data refers to data of Parkinson's symptom evaluation of different Parkinson's patients in a historical period, and at least includes motor function evaluation data, drug treatment evaluation data, Parkinson's diagnosis data, etc. The UPDRS evaluation table refers to a scoring table used for classifying / hierarchizing the symptoms of the Parkinson's patient. The motor symptom evaluation mode model can be a neural network model, a linear model, etc. The data screening layer of the motor symptom evaluation mode model is used to screen out important information of the Parkinson's patient to be tested and perform vectorization processing, wherein the important information includes the onset time of the patient, the medication condition, the motor diagnosis, etc. The feature extraction layer of the motor symptom evaluation mode model is used to extract important features of the Parkinson's patient to be tested as the medical history feature, including the medication time feature, the motor feature, etc. The result output layer of the motor symptom evaluation mode model is used to determine the motor symptom of the Parkinson's patient to be tested according to the medical history feature and perform corresponding mode evaluation, for example, according to the medical history feature, it is determined that the motor symptom of the Parkinson's patient A to be tested is upper limb-tremor, and then the upper limb evaluation item is generated as the motor symptom evaluation mode. Through the motor symptom evaluation mode model, the motor symptom evaluation mode of the Parkinson's patient to be tested can be obtained, and the motor symptom of the Parkinson's patient to be tested can be more comprehensively evaluated, and a more accurate motor symptom evaluation mode can be obtained.

[0071] In optional embodiments of the present application, the motor evaluation item includes one or more of a hand evaluation item, an upper limb evaluation item, a lower limb evaluation item, and a body posture evaluation 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 measuring sensor, a contact sensor, a temperature sensor, a Hall element, and a microphone, and the motor monitoring data corresponding to the motor evaluation item completed by the Parkinson's patient to be tested is collected by the following steps:

[0072] one or more of the pressure sensor, the strain sensor, the acceleration sensor, the gyroscope sensor, the geomagnetic sensor, the distance measuring sensor, the contact sensor, the temperature sensor, the Hall element, and the microphone are selected according to the hand evaluation item to collect the motor monitoring data; and / or

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

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

[0075] According to the body posture evaluation project, one or more of the pressure sensor, the strain sensor, the acceleration sensor, the gyroscope sensor, the geomagnetic sensor, the distance sensor, the contact sensor, the temperature sensor, the Hall element, and the microphone are selected to collect the motion monitoring data.

[0076] In some embodiments, the hand evaluation project can include a finger tapping test (e.g., tapping the thumb with the index finger 10 times at the maximum amplitude and the fastest speed), a fist clenching test (e.g., fully opening the palm and repeatedly clenching the palm 10 times at the fastest speed), etc.; the upper limb evaluation project can include a alternating test (e.g., extending the arm, with the palm facing down, and alternating the palm up and down 10 times at the fastest speed and the maximum amplitude), a postural tremor test (e.g., extending the arm with the palm facing down, straightening the wrist, and keeping the fingers apart without touching each other for 10 seconds), a kinetic tremor test (e.g., extending the arm as far as possible to touch the evaluator's finger, and then pointing to the nose tip, repeating three times), a static tremor test (e.g., sitting naturally, with the arms relaxed and placed on the double-sided handrails, maintaining this state for 10 seconds), etc.; the lower limb evaluation project can include a toe tapping test (e.g., placing the heel on the ground, and tapping the ground with the toes 10 times at the maximum amplitude and the fastest speed), a leg flexibility test (e.g., placing both feet on the ground, and lifting the feet to the ground 10 times at the maximum amplitude and the fastest speed), etc.; the body posture evaluation project can include a standing balance test (e.g., whether the process from sitting to standing can be completed), a gait test (e.g., walking at least 10 meters, and then turning around to walk back to the starting point), etc. Since the motion evaluation project can be combined according to the historical evaluation data of the Parkinson's patient to be tested, and different sensors can be selected for different motion evaluation projects, the motion evaluation of the Parkinson's patient to be tested can be more accurate.

[0077] In the embodiments of the present application, the motion features include time domain features and frequency domain features, and the evaluation feature combination for evaluating the current Parkinson's motion symptoms of the Parkinson's patient to be tested is determined according to the motion monitoring data, including the following steps:

[0078] The motion monitoring data is divided into time windows, and statistical values of data in the time windows are analyzed in the time domain to obtain the time domain features; wherein the time domain features include one or more of mean, variance, standard deviation, extreme point, zero-crossing point, and maximum slope point;

[0079] The data in the time windows is subjected to Fourier transform to obtain frequency domain distribution information in the time windows, and the frequency domain features are obtained according to the frequency domain distribution information; wherein the frequency domain features include one or more of power spectrum extreme point and frequency range;

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

[0081] In some embodiments, the motion features are determined by motion signals (i.e. motion monitoring data) collected by wearable sensors. Since the motion signals change with time and are also related to frequency information, by setting a time window (for example, a time window of 2S), the motion monitoring data is divided into time windows, the statistical values of data in each time window are analyzed in the time domain to obtain time domain features, and by Fourier transform, the frequency domain distribution information in different time windows is obtained, and the frequency domain features 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 disease motor symptom of the to-be-tested Parkinson's disease patient is evaluated based on features from different angles (time domain features and frequency domain features), thereby improving the accuracy of Parkinson's disease motor symptom evaluation.

[0082] Optionally, the evaluation feature combination of the current Parkinson's disease motor symptom of the to-be-tested Parkinson's disease patient is determined according to the time domain features and the frequency domain features, including the following steps:

[0083] The time domain features and the frequency domain features are sorted using the historical Parkinson's disease evaluation data and a preset feature sorting model to obtain a first sorting result;

[0084] The time domain features and the frequency domain features are randomly combined to obtain a plurality of feature combinations;

[0085] The plurality of feature combinations are sorted using the historical Parkinson's disease evaluation 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 features and / or the feature weight of the frequency domain features in the evaluation feature combination are determined according to the first sorting result.

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

[0088] In an optional embodiment of the present application, it is assumed that the preset feature ranking model is an XGBoost model. The XGBoost model is trained by historical Parkinson's evaluation data, so that the XGBoost model can learn important features that affect the historical Parkinson's evaluation data, and the trained XGBoost model is used to rank a plurality of motion features to obtain a first ranking 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 a plurality of feature combinations, and the trained XGBoost model is also used to rank a plurality of feature combinations to obtain a second ranking 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)), and feature combination 3 (motion feature 1 (100), motion feature 3 (60)), and an evaluation feature combination is selected from the second ranking result.

[0089] In another optional embodiment of the present application, motion features with lower weights can be filtered from the first ranking result and the second ranking 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 an embodiment of the present application, the training process of the multi-feature fusion classification model includes the following steps:

[0091] Obtain a Parkinson's symptom training set, which includes historical motion data and historical Parkinson's motor symptom evaluation results;

[0092] The historical motion data is processed to obtain normalized motion data.

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

[0094] In some embodiments, the normalized motion data is obtained by processing the historical motion data to ensure the uniformity and comparability of the data. Training the neural network using the normalized motion data enables the neural network to learn the ability to fuse different motion features. The 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 motion symptom evaluation results using cross-entropy loss function and gradient descent optimization algorithm. Finally, through repeated iterative training, the multi-feature fusion classification model can learn the best combination of different feature weights, thereby achieving the goal of multi-feature fusion classification and improving the accuracy of Parkinson's motion symptom evaluation.

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

[0096] The time domain features and / or frequency domain features in the evaluation feature combination are fused using the multi-feature fusion classification model to obtain a fusion feature value.

[0097] The fusion feature value is clustered, and the evaluation result of the current Parkinson's motion symptom of the Parkinson's patient to be tested is determined according to the clustering result.

[0098] In some embodiments, the multi-feature fusion classification model can fuse the time domain features and / or frequency domain features in the evaluation feature combination according to the feature weights, and since the evaluation feature combination includes different time domain features and / or frequency domain features, the evaluation feature combination can be fused by the multi-feature fusion classification model to obtain a fusion feature value. Therefore, clustering the fusion feature value can reduce the calculation amount and improve the evaluation efficiency of Parkinson's motion symptoms.

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

[0100] Step 1, taking each fusion feature value as a sample, randomly selecting k samples as initial cluster centers, denoted as u1, u2,..., uk. k ;

[0101] Step 2, for each sample x, calculate the distance to the k initial cluster centers, select the cluster where the nearest cluster center is located, and assign the sample to the cluster;

[0102] Step 3, for each cluster, calculate the average value of the samples therein as a new cluster center;

[0103] Repeat steps 2-3 until the cluster centers no longer change or a preset number of iterations is reached, and obtain different clustering results according to different clusters.

[0104] Wherein, whether the cluster center changes or not can be determined by the following formula:

[0105]

[0106] Wherein, J represents the overall sum of squares, when the overall sum of squares is minimum, the cluster center no longer changes; k represents the number of clusters; C i represents the i-th cluster, u i represents the cluster center of the i-th cluster, ‖x-u i ‖ 2 represents the Euclidean distance of the sample x to the cluster center.

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

[0108] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to 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 motor symptom assessment method described in the above embodiment, Figure 2 Fig. 1 shows a structural schematic diagram of a Parkinson motor symptom assessment device provided by an embodiment of the present application. For ease of illustration, only the parts related to the embodiments of the present application are shown.

[0110] Referring to Figure 2The device can be a Parkinson motor symptom evaluation device 21, which can include a motor symptom evaluation mode determination module 211, a motor data acquisition module 212, a feature combination determination module 213, and a motor symptom evaluation module 214.

[0111] Referring to Figure 2 The Parkinson motor symptom evaluation device 21 includes:

[0112] The motor symptom evaluation mode determination module 211 is configured to acquire historical evaluation data of a Parkinson patient to be evaluated, and determine a motor symptom evaluation mode for evaluating the current Parkinson motor symptom of the Parkinson patient to be evaluated according to the historical evaluation data, wherein the motor symptom evaluation mode includes at least one set of motor evaluation items.

[0113] The motor data acquisition module 212 is configured to acquire motor monitoring data corresponding to the motor evaluation items completed by the Parkinson patient to be evaluated, wherein the motor monitoring data is acquired by configuring at least one set of wearable sensors.

[0114] The feature combination determination module 213 is configured to determine an evaluation feature combination for evaluating the current Parkinson motor symptom of the Parkinson patient to be evaluated according to the motor monitoring data.

[0115] The motor symptom evaluation module 214 is configured to input the evaluation feature combination into a trained multi-feature fusion classification model to obtain an evaluation result of the current Parkinson motor symptom of the Parkinson patient to be evaluated.

[0116] In some embodiments, the motor symptom evaluation mode determination module 211 determines the motor symptom evaluation mode for evaluating the current Parkinson motor symptom of the Parkinson patient to be evaluated according to the historical evaluation data by the following steps, including:

[0117] Constructing a motor symptom evaluation mode model according to historical Parkinson evaluation data and UPDRS evaluation tables of different Parkinson patients;

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

[0119] Inputting the Parkinson patient information vector into a feature extraction layer of the motor symptom evaluation mode model to obtain a medical history feature of the Parkinson patient;

[0120] Inputting the medical history feature into a result output layer of the motor symptom evaluation mode model to obtain the motor symptom evaluation mode.

[0121] In some embodiments, the movement assessment item comprises 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 comprises at least one of a pressure sensor, a strain sensor, an acceleration sensor, a gyroscope sensor, a geomagnetic sensor, a ranging sensor, a contact sensor, a temperature sensor, a Hall element, and a microphone; and the movement data acquisition module 212 acquires the movement monitoring data corresponding to the movement assessment item completed by the Parkinson patient to be tested by the following steps, comprising:

[0122] selecting one or more of the pressure sensor, the strain sensor, the acceleration sensor, the gyroscope sensor, the geomagnetic sensor, the ranging sensor, the contact sensor, the temperature sensor, the Hall element, and the microphone according to the hand assessment item to acquire the movement monitoring data; and / or

[0123] selecting one or more of the pressure sensor, the strain sensor, the acceleration sensor, the gyroscope sensor, the geomagnetic sensor, the ranging sensor, the contact sensor, the temperature sensor, the Hall element, and the microphone according to the upper limb assessment item to acquire the movement monitoring data; and / or

[0124] selecting one or more of the pressure sensor, the strain sensor, the acceleration sensor, the gyroscope sensor, the geomagnetic sensor, the ranging sensor, the contact sensor, the temperature sensor, the Hall element, and the microphone according to the lower limb assessment item to acquire the movement monitoring data; and / or

[0125] selecting one or more of the pressure sensor, the strain sensor, the acceleration sensor, the gyroscope sensor, the geomagnetic sensor, the ranging sensor, the contact sensor, the temperature sensor, the Hall element, and the microphone according to the posture assessment item to acquire the movement monitoring data.

[0126] In some embodiments, the movement features comprise time domain features and frequency domain features, and the feature combination determination module 213 determines the assessment feature combination for evaluating the current Parkinson movement symptoms of the Parkinson patient to be tested according to the movement monitoring data by the following steps, comprising:

[0127] setting a time window, dividing the movement monitoring data by the time window, 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 comprise one or more of mean, variance, standard deviation, extreme point, zero-crossing point, and maximum slope 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 feature according to the frequency domain distribution information; wherein the frequency domain feature comprises one or more of a power spectrum extreme point and a frequency range;

[0129] determining the evaluation feature combination of the current Parkinson motor symptom of the to-be-tested Parkinson patient according to the time domain feature and the frequency domain feature.

[0130] In some embodiments, the feature combination determination module 213 determines the evaluation feature combination of the current Parkinson motor symptom of the to-be-tested Parkinson patient according to the time domain feature and the frequency domain feature by the following steps, comprising:

[0131] performing sorting on the time domain feature and the frequency domain feature by using the historical Parkinson evaluation data and a preset feature sorting model to obtain a first sorting result;

[0132] randomly combining the time domain feature and the frequency domain feature to obtain a plurality of feature combinations;

[0133] performing sorting on the plurality of feature combinations by using the historical Parkinson evaluation data and the feature sorting model to obtain a second sorting result;

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

[0135] In other embodiments, the Parkinson motor symptom evaluation device 21 further comprises a model training module, which comprises the following steps:

[0136] obtaining a Parkinson symptom training set, wherein the Parkinson symptom training set comprises historical motor data and historical Parkinson motor symptom evaluation results;

[0137] processing the historical motor data to obtain normalized motor data;

[0138] inputting the normalized motor data into a neural network for training, and optimizing parameters of the neural network according to the historical Parkinson motor symptom evaluation results in the training process to obtain the trained multi-feature fusion classification model.

[0139] In some embodiments, the motor symptom evaluation module 214 inputs the evaluation feature combination into the trained multi-feature fusion classification model by the following steps to obtain the evaluation result of the current Parkinson motor symptom of the to-be-tested Parkinson patient, comprising:

[0140] The time domain features and / or the frequency domain features in the evaluation feature combination are fused by using the multi-feature fusion classification model to obtain a fusion feature value;

[0141] The fusion feature value is clustered, and an evaluation result of a current Parkinson motor symptom of the Parkinson patient to be tested is determined according to a clustering result.

[0142] It should be noted that the information interaction, execution process and the like among the apparatuses / units are based on the same concept as the method embodiments of the present application, and specific functions and brought technical effects can be referred to the method embodiments part, which will not be repeated here.

[0143] Figure 3 A structural schematic diagram of an electronic device according to an embodiment of the present application is provided. As shown in the figure, the electronic device 3 of this embodiment includes at least one processor 30 (only one is shown in the figure), a memory 31, and a computer program 32 stored in the memory 31 and executable on the at least one processor 30. The processor 30 implements the steps in the Parkinson motor symptom evaluation method described in the above embodiments when executing the computer program 32. Figure 3 Figure 3 The processor 30 implements the steps in the Parkinson motor symptom evaluation method described in the above embodiments when executing the computer program 32.

[0144] The electronic device 3 can be a desktop computer, a notebook computer, a palm computer, a cloud server and the like computing device. The electronic device can include, but is not limited to, the processor 30, the memory 31. Those skilled in the art can understand that, Figure 3 The electronic device 3 is only an example and does not constitute a limitation on the electronic device 3, and can include more or fewer components than those shown, or combine certain components, or different components, for example, the electronic device can also include an input sending device, a network access device, a bus and the like.

[0145] The processor 30 can be a central processing unit (CPU), and can also be 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. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

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

[0147] It can be clearly understood by those skilled in the art that, for the convenience and brevity of description, only the division of the functional units and modules is taken as an example, and in actual application, the functions can be completed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit, and the integrated unit can be realized in the form of hardware or in the form of a software functional unit. In addition, the specific names of the functional units and modules are only for the convenience of mutual distinction, and are not used to limit the protection scope of the present application. The specific working process of the units and modules in the system can refer to the corresponding process in the Parkinson motor symptom evaluation method described in the above embodiments, which will not be repeated here.

[0148] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps in the Parkinson motor symptom evaluation method described in the above embodiments.

[0149] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the present application can implement all or part of the processes of the Parkinson motor symptom evaluation method described in the above embodiments through a computer program to instruct the relevant hardware, and the computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps of the Parkinson motor symptom evaluation method described in the above embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer readable medium can at least include any entity or device capable of carrying the computer program code to the photographing device / electronic device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, according to legislation and patent practice, the computer readable medium can not be an electrical carrier signal and a telecommunication signal.

[0150] In the embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0151] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0152] In the embodiments provided in the present application, it should be understood that the disclosed apparatus / network device and method can be implemented in other ways. For example, the apparatus / network device embodiments described above are only schematic. The division of the modules or units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0153] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may also be distributed to multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiment scheme according to actual needs.

[0154] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method of assessing Parkinsonian motor symptoms, characterized by, The method comprises the following steps: Obtaining historical evaluation data of a to-be-tested Parkinson's patient, and obtaining a motor symptom evaluation mode for evaluating the current Parkinson's motor symptoms of the to-be-tested Parkinson's patient according to the historical evaluation data, wherein the motor symptom evaluation mode comprises at least one group of motor evaluation items; Collecting motor monitoring data corresponding to the motor evaluation items completed by the to-be-tested Parkinson's patient, wherein the motor 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 to-be-tested Parkinson's patient according to the motor monitoring data, wherein the evaluation feature combination comprises a plurality of motor features obtained from the motor monitoring data; 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 to-be-tested Parkinson's patient; The method comprises the following steps: Constructing a motor symptom evaluation mode model according to historical Parkinson's evaluation data and UPDRS evaluation tables of different Parkinson's patients; Inputting the historical evaluation data into a data screening layer of the motor symptom evaluation mode model to obtain a Parkinson's patient information vector; Inputting the Parkinson's patient information vector into a feature extraction layer of the motor symptom evaluation mode model to obtain a medical history feature of the Parkinson's patient; Inputting the medical history feature into a result output layer of the motor symptom evaluation mode model to obtain the motor symptom evaluation mode.

2. The method of assessing Parkinsonian motor symptoms according to claim 1, wherein, The motor evaluation items comprise one or more of a hand evaluation item, an upper limb evaluation item, a lower limb evaluation item, and a body posture evaluation item; the wearable sensors comprise at least one of a pressure sensor, a strain sensor, an acceleration sensor, a gyroscope sensor, a geomagnetic sensor, a distance measuring sensor, a contact sensor, a temperature sensor, a Hall element, and a microphone; and the method comprises the following steps: According to the hand evaluation item, one or more of the pressure sensor, the strain sensor, the acceleration sensor, the gyroscope sensor, the geomagnetic sensor, the distance measuring sensor, the contact sensor, the temperature sensor, the Hall element, and the microphone are selected to collect the motor monitoring data; and / or According to the upper limb evaluation item, one or more of the pressure sensor, the strain sensor, the acceleration sensor, the gyroscope sensor, the geomagnetic sensor, the distance measuring sensor, the contact sensor, the temperature sensor, the Hall element, and the microphone are selected to collect the motor monitoring data; and / or According to the lower limb evaluation item, one or more of the pressure sensor, the strain sensor, the acceleration sensor, the gyroscope sensor, the geomagnetic sensor, the distance measuring sensor, the contact sensor, the temperature sensor, the Hall element, and the microphone are selected to collect the motor monitoring data; and / or According to the body posture assessment project, at least one or more of the pressure sensor, the strain sensor, the acceleration sensor, the gyroscope sensor, the geomagnetic sensor, the distance measuring sensor, the contact sensor, the temperature sensor, the Hall element, and the microphone are selected to collect the motion monitoring data.

3. The method of assessing Parkinsonian motor symptoms according to claim 1, wherein, The motion features include time domain features and frequency domain features, and the evaluation feature combination for evaluating the current Parkinson's motor symptoms of the to-be-tested Parkinson's patient is determined according to the motion monitoring data, including the following steps: A time window is set, the motion monitoring data is divided into time windows, and the statistical values of the data in the time window are analyzed at the time domain level to obtain the time domain features; wherein the time domain features include one or more of mean value, variance, standard deviation, extreme value point, zero-crossing point, and maximum slope point; The data in the time window is subjected to Fourier transform to obtain the frequency domain distribution information in the time window, and the frequency domain features are obtained according to the frequency domain distribution information; wherein the frequency domain features include one or more of power spectrum extreme value point and frequency range; The evaluation feature combination of the current Parkinson's motor symptoms of the to-be-tested Parkinson's patient is determined according to the time domain features and the frequency domain features.

4. The method of assessing Parkinsonian motor symptoms according to claim 3, wherein, The evaluation feature combination of the current Parkinson's motor symptoms of the to-be-tested Parkinson's patient is determined according to the time domain features and the frequency domain features, including the following steps: The time domain features and the frequency domain features are sorted using the historical Parkinson's evaluation data and a preset feature sorting model to obtain a first sorting result; The time domain features and the frequency domain features are randomly combined to obtain a plurality of feature combinations; The plurality of feature combinations are sorted using the historical Parkinson's evaluation 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 are determined according to the first sorting result.

5. The method of assessing Parkinsonian motor symptoms according to claim 1, wherein, The training process of the multi-feature fusion classification model includes the following steps: Obtain a Parkinson's symptom training set, which includes historical motion data and historical Parkinson's motor symptom evaluation results; Process the historical motion data to obtain normalized motion data; Input the normalized motion data into a neural network for training, and optimize the parameters of the neural network according to the historical Parkinson's motor symptom evaluation results during the training process to obtain the trained multi-feature fusion classification model.

6. The method of assessing Parkinsonian motor symptoms according to any one of claims 1 to 5, wherein, The 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 to-be-tested Parkinson's patient, including the following steps: The time domain features and / or the frequency domain features in the evaluation feature combination are subjected to feature fusion using the multi-feature fusion classification model to obtain a fusion feature value; The fusion feature value is clustered, and the evaluation result of the current Parkinson's motor symptoms of the to-be-tested Parkinson's patient is determined according to the clustering result.

7. A Parkinsonian motor symptom assessment device, characterized by, It includes: The motion symptom evaluation mode determination module is configured to obtain historical evaluation data of a Parkinson's patient to be tested, and determine a motion symptom evaluation mode for evaluating the current Parkinson's motion symptom of the Parkinson's patient to be tested according to the historical evaluation data, wherein the motion symptom evaluation mode comprises at least one group of motion evaluation items; The motion data acquisition module is configured to collect motion monitoring data corresponding to the motion evaluation items completed by the Parkinson's patient to be tested, wherein the motion monitoring data is collected by configuring at least one group of wearable sensors; The feature combination determination module is configured to determine an evaluation feature combination for evaluating the current Parkinson's motion symptom of the Parkinson's patient to be tested according to the motion monitoring data; The motion symptom evaluation module is configured to input the evaluation feature combination into a trained multi-feature fusion classification model to obtain an evaluation result of the current Parkinson's motion symptom of the Parkinson's patient to be tested. The motion symptom evaluation mode determination module, when obtaining the historical evaluation data of the Parkinson's patient to be tested and determining the motion symptom evaluation mode for evaluating the current Parkinson's motion symptom of the Parkinson's patient to be tested according to the historical evaluation data, comprises the following steps: constructing a motion symptom evaluation mode model according to historical Parkinson's evaluation data and UPDRS evaluation tables of different Parkinson's patients; inputting the historical evaluation data into a data screening layer of the motion symptom evaluation mode model to obtain a Parkinson's patient information vector; inputting the Parkinson's patient information vector into a feature extraction layer of the motion symptom evaluation mode model to obtain a medical history feature of the Parkinson's patient; inputting the medical history feature into a result output layer of the motion symptom evaluation mode model to obtain the motion symptom evaluation mode.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the method of any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. The computer program is executed by the processor to implement the method of any one of claims 1 to 6.

Images