Parkinson quantitative early diagnosis system based on behavior characteristic recognition

Abstract

The application discloses a Parkinson quantitative early diagnosis system based on behavior feature recognition and belongs to the technical field of Parkinson diagnosis. The system comprises an intelligent acquisition device, a quantitative diagnosis platform and an intelligent control treatment device. The intelligent acquisition device is used for collecting patient motion data, patient voice data, patient writing data and patient facial data, determining patient behavior real-time data based on the Internet of Things, and transmitting the patient behavior real-time data based on the Internet of Things to the quantitative diagnosis platform based on a wireless network. The quantitative diagnosis platform is used for pre-processing and analyzing the patient behavior real-time data based on the Internet of Things, performing Parkinson quantitative early diagnosis on the patient, and performing intelligent control treatment on the patient according to the patient diagnosis result. The application solves the problem that the existing Parkinson quantitative early diagnosis on the patient cannot be performed based on behavior feature recognition, and the diagnosis effect on Parkinson patients is poor. The application can perform Parkinson quantitative early diagnosis on the patient based on behavior feature recognition, and can improve the diagnosis effect on Parkinson patients.

Description

TECHNICAL FIELD

[0001] The present application relates to the Parkinson diagnosis technical field, and in particular to a Parkinson quantitative early diagnosis system based on behavior feature recognition. BACKGROUND

[0002] Parkinson's disease is a complex syndrome involving multiple organs, multiple systems and multiple neurotransmitters, and is not a simple movement disorder disease. The progression of the disease itself, drug side effects, motor complications and depression, sleep disorders, pain, fatigue and many other non-motor symptoms of advanced Parkinson's disease patients are intertwined, greatly increasing the difficulty of treatment. Most advanced Parkinson's disease patients cannot take care of themselves and need home treatment, so early diagnosis is crucial to delay disease progression and improve patient quality of life.

[0003] A Parkinson's disease whole-process management mode disclosed in Chinese Patent Publication No. CN117253592A is composed of Parkinson's disease specialist doctors of tertiary hospitals and Parkinson's disease sub-professional community doctors, the Parkinson's disease specialist doctors of tertiary hospitals train the Parkinson's disease sub-professional community doctors to achieve homogeneity in Parkinson's disease diagnosis and treatment; the Parkinson's disease sub-professional community doctors are responsible for the implementation and follow-up of the treatment plan for all enrolled patients and the home treatment of advanced Parkinson's disease patients who cannot take care of themselves; the tertiary hospitals and the community share information through a Parkinson's disease management platform, and doctors and patients communicate through WeChat. This management mode is led by Parkinson's disease specialist doctors and centered on Parkinson's disease sub-professional community doctors, and provides multidisciplinary, whole-process, individualized and online and offline integrated management for early, intermediate and advanced Parkinson's disease patients; however, this patent has the following defects:

[0004] The existing technology cannot perform Parkinson quantitative early diagnosis of patients based on behavior feature recognition, resulting in poor Parkinson patient diagnosis effect. SUMMARY

[0005] The present application provides a Parkinson quantitative early diagnosis system based on behavior feature recognition, which can perform Parkinson quantitative early diagnosis of patients based on behavior feature recognition, improve Parkinson patient diagnosis effect, and solve the problems raised in the above background.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0007] The system comprises an intelligent acquisition device and a quantitative diagnosis platform. The intelligent acquisition device is configured to acquire behavior characteristics of a patient during a behavior activity of the patient, determine real-time data of the behavior of the patient, and transmit the acquired real-time data of the behavior of the patient to the quantitative diagnosis platform based on a wireless transmission technology.

[0008] The writing shaking frequency and the corresponding value of the writing pressure are compared with preset thresholds of the writing shaking frequency and the writing pressure, respectively.

[0009] The quantitative diagnosis platform is configured to construct a model for quantitative early diagnosis of Parkinson's disease based on the behavior characteristics of the patient, analyze the real-time data of the behavior of the patient based on the constructed model, and make a quantitative early diagnosis of Parkinson's disease.

[0010] Preferably, the intelligent acquisition device comprises a motion acquisition unit, a voice acquisition unit, a writing acquisition unit, and a face acquisition unit.

[0011] The motion acquisition unit is configured to monitor and acquire gait data, balance data, and finger tapping data of the patient in real time based on an Internet of Things technology, and acquire motion data of the patient.

[0012] The voice acquisition unit is configured to monitor and acquire voice characteristics and voice content of the patient in real time based on the Internet of Things technology, and acquire voice data of the patient.

[0013] The writing acquisition unit is configured to monitor and acquire writing dynamics data and writing pattern data of the patient in real time based on the Internet of Things technology, and acquire writing data of the patient.

[0014] The face acquisition unit is configured to monitor and acquire facial action data and facial expression data of the patient in real time based on the Internet of Things technology, and acquire facial data of the patient.

[0015] The real-time behavior data of the patient based on the Internet of Things is determined according to the acquired motion data, voice data, writing data, and facial data of the patient.

[0016] Preferably, the writing acquisition unit comprises a smart writing pen and a writing photographing device, wherein a wireless communication connection is established between the smart writing pen and the writing photographing device.

[0017] The smart writing pen acquires the writing shaking frequency and the writing pressure of the patient in a unit time in real time.

[0018] The writing shaking frequency and the writing pressure are compared with preset thresholds of the writing shaking frequency and the writing pressure, respectively.

[0019] When the number of writing tremors exceeds a preset writing tremor number threshold, but the writing pressure does not exceed the writing pressure threshold, triggering the writing photographing device to take a photograph by the smart writing pen to obtain a first writing image;

[0020] When the number of writing tremors does not exceed a preset writing tremor threshold, but the writing pressure exceeds a writing pressure threshold, a comprehensive determination is made based on the corresponding values ​​of the number of writing tremors and the writing pressure to determine whether to trigger the writing photographing device to take a photograph;

[0021] When the number of writing tremors and the writing pressure do not exceed their corresponding writing tremor number thresholds and writing pressure thresholds, controlling the writing photographing device to take pictures at a preset image acquisition frequency to obtain a second writing image;

[0022] The evaluation weight value of the first writing image is set to be higher than the evaluation weight value corresponding to the second writing image.

[0023] Preferably, comprehensively judging whether to trigger the writing photographing device to take a photo based on the number of writing tremors and the corresponding values ​​of the writing pressure includes:

[0024] When the writing pressure exceeds the writing pressure threshold, extracting the number of writing tremors per unit time in which the number of writing tremors does not exceed the preset writing tremor number threshold as a target tremor number data set;

[0025] Generating a comprehensive writing state parameter using the target tremor frequency dataset and writing pressure; wherein the comprehensive writing state parameter is used to assess whether the current patient's writing state meets the necessity of image acquisition;

[0026] The comprehensive writing state parameter is obtained by the following formula:

[0027]

[0028] Among them, S represents the comprehensive writing state parameter; P represents the writing pressure corresponding to exceeding the writing pressure threshold; P y represents the writing pressure threshold; n represents the number of data contained in the target tremor number data set, wherein the number of data is consistent with the number of unit times during which the writing tremor number does not exceed the preset writing tremor number threshold; C i represents the tremor number value corresponding to the i-th tremor data in the target tremor number data set; N represents the number of unit time the patient has written down; n0 represents the preset reference value of the number of unit time; C y Indicates the preset threshold value of writing tremor times;

[0029] comparing the comprehensive writing state parameter with a preset parameter threshold;

[0030] When the comprehensive writing state parameter is lower than a preset parameter threshold, it is determined that there is no need to trigger the writing photographing device to take a photograph;

[0031] When the comprehensive writing state parameter is not lower than a preset parameter threshold, it is determined that the writing photo taking device needs to be triggered to take a photo;

[0032] using a writing image obtained when the number of writing tremors does not exceed a preset writing tremor number threshold, but the writing pressure exceeds a writing pressure threshold, as a third writing image;

[0033] The evaluation weight value of the third writing image is set to be higher than the evaluation weight value corresponding to the second writing image, but lower than the evaluation weight value corresponding to the first writing image.

[0034] Preferably, the gait data includes stride length, stride width, cadence, gait speed, swing phase, stance phase, gait symmetry, gait variability, trunk swing, arm swing and turning gait;

[0035] Balance data includes standing balance, sitting balance, center of gravity swing, and postural stability;

[0036] Finger tapping data includes tapping frequency, rhythm, force, and finger coordination;

[0037] Speech characteristics include fundamental frequency, intensity, duration, speaking rate, pauses, intonation, articulation clarity, and speech fluency;

[0038] Speech content includes vocabulary, grammatical structure, semantic expression and emotional expression;

[0039] Writing dynamics data includes writing speed, acceleration and pressure, stroke length, width and angle, writing pauses and tremors;

[0040] Writing graphic data includes font size, shape and spacing, handwriting neatness and coherence;

[0041] Facial motion data includes movements of eyebrows, eyes, nose, and mouth;

[0042] Facial expression data includes the frequency, amplitude and duration of expression changes.

[0043] Preferably, the quantitative diagnosis platform includes: a behavioral data preprocessing unit and an early diagnosis evaluation unit;

[0044] The behavior data preprocessing unit is configured to clean, transform, integrate and extract features of the real-time patient behavior data based on the Internet of Things, and determine the patient behavior feature data based on the Internet of Things;

[0045] The early diagnosis and evaluation unit is configured to analyze the patient's behavioral characteristic data based on the Internet of Things, and perform quantitative early diagnosis of Parkinson's disease on the patient, and provide intelligent management and treatment for the patient based on the patient's diagnosis results.

[0046] Preferably, the behavior data pre-processing unit includes: a behavior data cleaning module and a behavior data conversion module;

[0047] The behavior data cleaning module is configured to clean the real-time patient behavior data based on the Internet of Things;

[0048] Among them, the real-time patient behavior data based on the Internet of Things is checked based on the Python library, duplicate values, missing values ​​and abnormal values ​​in the real-time patient behavior data based on the Internet of Things are identified, and the duplicate values, missing values ​​and abnormal values ​​in the real-time patient behavior data based on the Internet of Things are deleted;

[0049] The behavior data conversion module is configured to convert the real-time patient behavior data based on the Internet of Things;

[0050] Among them, the real-time patient behavior data based on the Internet of Things was normalized based on Z-Score standardization, and the real-time patient behavior data based on the Internet of Things was converted into a standard normal distribution with a mean of 0 and a standard deviation of 1, thereby removing the dimensional differences between the real-time patient behavior data based on the Internet of Things.

[0051] Preferably, the behavior data pre-processing unit further includes: a behavior data integration module and a behavior data extraction module;

[0052] The behavior data integration module is configured to integrate real-time patient behavior data based on the Internet of Things;

[0053] Among them, the real-time patient behavior data based on the Internet of Things is integrated based on the Python library, the real-time patient behavior data based on the Internet of Things is integrated into a unified data view, and the integrated real-time patient behavior data based on the Internet of Things is verified to determine whether the integrated real-time patient behavior data based on the Internet of Things is missing;

[0054] The behavior data extraction module is configured to extract real-time patient behavior data based on the Internet of Things;

[0055] Among them, features related to Parkinson's disease are extracted from the real-time patient behavior data based on the Internet of Things, and the extracted feature vectors are weighted fused to determine the patient behavior feature data based on the Internet of Things.

[0056] Preferably, the early diagnosis and evaluation unit comprises: a diagnosis model training module, wherein the diagnosis model training module is configured to train a quantitative early diagnosis model for Parkinson's disease;

[0057] According to the Parkinson quantitative early diagnosis demand based on behavior feature recognition, collect the patient behavior history data based on Internet of Things, and divide the collected patient behavior history data based on Internet of Things into a training set and a test set;

[0058] Based on the deep learning technology, the training set is used to train the deep learning model, so that the deep learning model autonomously learns the Parkinson quantitative early diagnosis process based on behavior feature recognition, and determines the Parkinson quantitative early diagnosis model based on behavior feature recognition;

[0059] Based on the test set, the Parkinson quantitative early diagnosis model based on behavior feature recognition is tested, the performance of the Parkinson quantitative early diagnosis model based on behavior feature recognition is evaluated based on the accuracy, recall rate and F1 value indicators, and whether the Parkinson quantitative early diagnosis model based on behavior feature recognition can achieve the expected effect is judged;

[0060] According to the test evaluation result, the parameters and structure of the Parkinson quantitative early diagnosis model based on behavior feature recognition are adjusted, and the optimal Parkinson quantitative early diagnosis model is determined through continuous iteration and optimization.

[0061] Preferably, the early diagnosis evaluation unit further comprises a diagnosis evaluation control module; the diagnosis evaluation control module is configured to perform Parkinson quantitative early diagnosis and evaluation control on the patient.

[0062] The optimal Parkinson quantitative early diagnosis model is obtained, and the optimal Parkinson quantitative early diagnosis model is deployed in the actual Parkinson quantitative early diagnosis environment based on behavior feature recognition;

[0063] The patient behavior feature data based on Internet of Things is input into the optimal Parkinson quantitative early diagnosis model, the patient behavior feature data based on Internet of Things is analyzed based on the optimal Parkinson quantitative early diagnosis model, and the patient is diagnosed quantitatively early Parkinson, and the diagnosis result of the patient is determined;

[0064] Based on the patient diagnosis result, the patient behavior feature data is analyzed, the patient's disease evaluation report is determined, the patient is intelligently controlled and treated based on the patient's disease evaluation report, and the treatment effect is monitored in real time, and the patient's control and treatment scheme is dynamically adjusted according to the monitoring condition.

[0065] Compared with the prior art, the beneficial effects of the present application are:

[0066] The present invention determines real-time patient behavior data based on the Internet of Things by collecting patient motion data, patient voice data, patient writing data and patient facial data, determines patient behavior feature data based on the Internet of Things by cleaning, transforming, integrating and extracting features from the real-time patient behavior data based on the Internet of Things, trains a Parkinson's quantitative early diagnosis model based on deep learning technology, analyzes the patient behavior feature data based on the Internet of Things based on the Parkinson's quantitative early diagnosis model, performs quantitative early diagnosis of Parkinson's on the patient, determines the patient's diagnosis result, analyzes the patient behavior feature data based on the patient's diagnosis result, determines the patient's condition assessment report, performs intelligent management and treatment on the patient based on the patient's condition assessment report, monitors the treatment effect in real time, dynamically adjusts the patient's management and treatment plan according to the monitoring situation, can perform quantitative early diagnosis of Parkinson's on the patient based on behavior feature recognition, and can improve the diagnosis effect of Parkinson's patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 This is a module structure diagram of the Parkinson's disease quantitative early diagnosis system based on behavioral feature recognition of the present invention. DETAILED DESCRIPTION

[0068] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0069] In order to solve the problem that the current diagnosis of Parkinson's disease cannot be carried out quantitatively and early based on behavioral characteristics, which leads to poor diagnosis results for Parkinson's disease patients, please refer to Figure 1 , this embodiment provides the following technical solutions:

[0070] The Parkinson's disease quantitative early diagnosis system based on behavioral feature recognition includes: intelligent acquisition equipment and quantitative diagnosis platform.

[0071] Among them, the intelligent collection device is used to collect patient movement data, patient voice data, patient writing data and patient facial data, determine the real-time patient behavior data based on the Internet of Things, and transmit the collected real-time patient behavior data based on the Internet of Things to a given quantitative diagnosis platform based on wireless transmission technology;

[0072] In this embodiment, the intelligent data collection device includes:

[0073] The motion acquisition unit is used to monitor and collect the patient's gait data, balance data, and finger tapping data in real time based on the Internet of Things technology to obtain the patient's motion data;

[0074] It should be noted that the gait data includes stride length, stride width, cadence, gait speed, swing phase, stance phase, gait symmetry, gait variability, trunk swing, arm swing and turning gait.

[0075] It should be noted that the balance data includes standing balance, sitting balance, center of gravity swing and posture stability.

[0076] It should be noted that the finger tapping data includes tapping frequency, rhythm, strength and finger coordination.

[0077] The voice collection unit is used to monitor and collect the patient's voice characteristics and voice content in real time based on the Internet of Things technology to obtain the patient's voice data;

[0078] It should be noted that speech features include fundamental frequency, sound intensity, sound duration, speaking speed, pauses, intonation, pronunciation clarity and speech fluency.

[0079] It should be noted that speech content includes vocabulary, grammatical structure, semantic expression and emotional expression;

[0080] A writing collection unit is used to monitor and collect the patient's writing dynamics data and writing graphic data in real time based on the Internet of Things technology to obtain the patient's writing data;

[0081] It should be noted that writing dynamics data includes writing speed, acceleration and pressure, stroke length, width and angle, writing pauses and tremors.

[0082] It should be noted that written graphic data includes font size, shape and spacing, handwriting neatness and coherence;

[0083] A facial acquisition unit is used to monitor and collect the patient's facial movement data and facial expression data in real time based on Internet of Things technology to obtain the patient's facial data;

[0084] It should be noted that facial movement data includes movements of eyebrows, eyes, nose and mouth.

[0085] It should be noted that facial expression data includes the frequency, amplitude and duration of expression changes.

[0086] Among them, the real-time patient behavior data based on the Internet of Things is determined based on the patient's movement data, patient voice data, patient writing data and patient facial data.

[0087] Specifically, by collecting patient movement data, patient voice data, patient writing data and patient facial data, real-time patient behavior data based on the Internet of Things can be determined, which can provide data support for quantitative early diagnosis of Parkinson's disease in patients.

[0088] The quantitative diagnosis platform is used for preprocessing and analyzing the real-time data of patient behaviors based on the Internet of Things, performing quantitative early diagnosis of Parkinson's disease on the patient, and intelligently controlling and treating the patient according to the diagnosis result of the patient.

[0089] Specifically, the writing acquisition unit includes an intelligent writing pen and a writing photographing device, wherein the intelligent writing pen and the writing photographing device are in wireless communication connection.

[0090] The intelligent writing pen acquires the writing tremor frequency and the writing pressure of the patient in unit time in real time.

[0091] The writing tremor frequency and the writing pressure are compared with preset writing tremor frequency threshold and writing pressure threshold, respectively.

[0092] When the writing tremor frequency exceeds the preset writing tremor frequency threshold, but the writing pressure does not exceed the writing pressure threshold, the writing photographing device is triggered to take a photograph by the intelligent writing pen to obtain a first writing image.

[0093] When the writing tremor frequency does not exceed the preset writing tremor frequency threshold, but the writing pressure exceeds the writing pressure threshold, the writing photographing device is triggered to take a photograph by the writing tremor frequency and the writing pressure corresponding value.

[0094] When the writing tremor frequency and the writing pressure do not exceed the corresponding writing tremor frequency threshold and writing pressure threshold, the writing photographing device is controlled to take a photograph at a preset image acquisition frequency to obtain a second writing image.

[0095] The evaluation weight value of the first writing image is set to be higher than the evaluation weight value corresponding to the second writing image.

[0096] The above technical solution has the following technical effects: the intelligent writing pen acquires the writing tremor frequency and the writing pressure of the patient in real time, which can effectively improve the acquisition rate of the writing state information of the patient and the timeliness of data acquisition. At the same time, the writing photographing device is triggered to take a photograph according to the preset writing tremor frequency threshold and the writing pressure threshold, which can effectively improve the accuracy of determining abnormal conditions in the writing process of the patient and the necessity of triggering, and prevent the problem of failing to successfully capture the writing image under important and critical writing features when taking images at a fixed shooting frequency.

[0097] When either the number of writing tremors or the writing pressure exceeds a threshold, the system adopts a different photo-taking strategy. Specifically, when the number of writing tremors exceeds the threshold but the writing pressure does not, the system immediately triggers a photo capture; when neither exceeds the threshold, photos are taken at the preset image acquisition frequency. This photo capture triggering strategy can effectively improve the targeted nature of photo capture, thereby improving the accuracy of subsequent Parkinson's disease assessments. Furthermore, the system assigns a higher evaluation weight to the first writing image (i.e., the photo captured under specific conditions) than to the second writing image (i.e., the image captured at the preset frequency). This weighting method allows for a greater focus on key image data during the analysis process, thereby improving the accuracy and effectiveness of the assessment.

[0098] Specifically, comprehensively judging whether to trigger the writing camera to take a photo based on the number of writing tremors and the corresponding values ​​of the writing pressure includes:

[0099] When the writing pressure exceeds the writing pressure threshold, extracting the number of writing tremors per unit time in which the number of writing tremors does not exceed the preset writing tremor number threshold as a target tremor number data set;

[0100] Generating a comprehensive writing state parameter using the target tremor frequency dataset and writing pressure; wherein the comprehensive writing state parameter is used to assess whether the current patient's writing state meets the necessity of image acquisition;

[0101] The comprehensive writing state parameter is obtained by the following formula:

[0102]

[0103] Among them, S represents the comprehensive writing state parameter; P represents the writing pressure corresponding to exceeding the writing pressure threshold; P y represents the writing pressure threshold; n represents the number of data contained in the target tremor number data set, wherein the number of data is consistent with the number of unit times during which the writing tremor number does not exceed the preset writing tremor number threshold; C i represents the tremor number value corresponding to the i-th tremor data in the target tremor number data set; N represents the number of unit time the patient has written down; n0 represents the preset reference value of the number of unit time; C y Indicates the preset threshold value of writing tremor times;

[0104] comparing the comprehensive writing state parameter with a preset parameter threshold;

[0105] When the comprehensive writing state parameter is lower than a preset parameter threshold, it is determined that there is no need to trigger the writing photographing device to take a photograph;

[0106] When the comprehensive writing state parameter is not lower than a preset parameter threshold, it is determined that the writing photo taking device needs to be triggered to take a photo;

[0107] using a writing image obtained when the number of writing tremors does not exceed a preset writing tremor number threshold, but the writing pressure exceeds a writing pressure threshold, as a third writing image;

[0108] The evaluation weight value of the third writing image is set to be higher than the evaluation weight value corresponding to the second writing image, but lower than the evaluation weight value corresponding to the first writing image.

[0109] The technical effects of the above technical solution are as follows: By introducing the comprehensive writing state parameter S, the above technical solution can more precisely assess the patient's writing state. By combining the number of writing tremors and writing pressure for comprehensive evaluation, the accuracy of the assessment of the patient's actual writing condition can be effectively improved. Furthermore, the above technical solution utilizes the number of tremors and pressure changes within different time units during the patient's writing process, and extracts the target tremor number dataset to obtain the comprehensive writing state parameter. This can effectively improve the tracking between the comprehensive writing state parameter and subtle changes in the patient's writing state, thereby effectively improving the sensitivity and accuracy of capturing subtle changes in the patient's writing state. Furthermore, the above technical solution assigns weights to writing images acquired under different conditions. The assessment weight value of the third writing image is higher than that of the second writing image but lower than that of the first writing image. This weighting method not only considers the differences in the importance of images under different conditions, but also maintains the rationality and consistency of the weighting assignment. It can effectively improve the distinction between the importance of the first, second, and third writing images, thereby improving the accuracy of subsequent early Parkinson's disease diagnosis.

[0110] In this embodiment, the quantitative diagnosis platform includes: a behavior data preprocessing unit and an early diagnosis evaluation unit.

[0111] Among them, the behavior data preprocessing unit is used to clean, transform, integrate and extract features of the real-time patient behavior data based on the Internet of Things, and determine the patient behavior feature data based on the Internet of Things;

[0112] It should be noted that the behavior data pre-processing unit includes:

[0113] Behavioral data cleaning module, used to clean real-time patient behavior data based on the Internet of Things;

[0114] Among them, the real-time patient behavior data based on the Internet of Things is checked based on the Python library, duplicate values, missing values ​​and abnormal values ​​in the real-time patient behavior data based on the Internet of Things are identified, and the duplicate values, missing values ​​and abnormal values ​​in the real-time patient behavior data based on the Internet of Things are deleted;

[0115] Behavioral data transformation module, used to transform real-time patient behavior data based on the Internet of Things;

[0116] Among them, the real-time patient behavior data based on the Internet of Things is normalized based on Z-Score standardization, and the real-time patient behavior data based on the Internet of Things is converted into a standard normal distribution with a mean of 0 and a standard deviation of 1, thereby removing the dimensional differences between the real-time patient behavior data based on the Internet of Things;

[0117] Behavioral data integration module, used to integrate real-time patient behavior data based on the Internet of Things;

[0118] Among them, the real-time patient behavior data based on the Internet of Things is integrated based on the Python library, the real-time patient behavior data based on the Internet of Things is integrated into a unified data view, and the integrated real-time patient behavior data based on the Internet of Things is verified to determine whether the integrated real-time patient behavior data based on the Internet of Things is missing;

[0119] Behavioral data extraction module, used to extract real-time patient behavior data based on the Internet of Things;

[0120] Among them, features related to Parkinson's disease are extracted from the real-time patient behavior data based on the Internet of Things, and the extracted feature vectors are weighted fused to determine the patient behavior feature data based on the Internet of Things.

[0121] Specifically, by cleaning, transforming, integrating and extracting features of real-time patient behavior data based on the Internet of Things, the patient behavior feature data based on the Internet of Things is determined, where the patient behavior feature data includes gait parameters, voice features, writing dynamics features, facial expression features, etc.

[0122] Among them, the early diagnosis and evaluation unit is used to analyze the patient behavioral characteristic data based on the Internet of Things, and conduct quantitative early diagnosis of Parkinson's disease in patients. According to the patient's diagnosis results, the patient is given intelligent management and treatment.

[0123] It should be noted that the early diagnosis and evaluation unit includes:

[0124] Diagnostic model training module, used to train Parkinson's disease quantitative early diagnosis model;

[0125] Based on the demand for quantitative early diagnosis of Parkinson's disease based on behavioral feature recognition, the patient behavior history data based on the Internet of Things is collected and divided into training sets and test sets;

[0126] Based on deep learning technology, a training set is used to train the deep learning model, allowing the deep learning model to autonomously learn the quantitative early diagnosis process of Parkinson's disease based on behavioral feature recognition, and determine the quantitative early diagnosis model of Parkinson's disease based on behavioral feature recognition;

[0127] Based on the test set, the Parkinson's disease quantitative early diagnosis model based on behavioral feature recognition was tested. The performance of the model was evaluated based on the accuracy, recall rate, and F1 value indicators to determine whether the model based on behavioral feature recognition can achieve the expected results.

[0128] Based on the test and evaluation results, the parameters and structure of the Parkinson's disease quantitative early diagnosis model based on behavioral feature recognition were adjusted. After continuous iterative optimization, the optimal Parkinson's disease quantitative early diagnosis model was determined.

[0129] Diagnosis, evaluation and control module, used for quantitative early diagnosis, evaluation and control of Parkinson's disease in patients;

[0130] Obtain the optimal Parkinson's disease quantitative early diagnosis model and deploy it in a practical Parkinson's disease quantitative early diagnosis environment based on behavioral feature recognition;

[0131] Inputting the patient behavioral characteristic data based on the Internet of Things into the optimal Parkinson's quantitative early diagnosis model, analyzing the patient behavioral characteristic data based on the Internet of Things based on the optimal Parkinson's quantitative early diagnosis model, and performing a quantitative Parkinson's early diagnosis on the patient to determine the patient's diagnosis result;

[0132] Among them, based on the patient's diagnosis results, the patient's behavioral characteristic data is analyzed to determine the patient's condition assessment report, and the patient is given intelligent management and treatment based on the patient's condition assessment report. The treatment effect is monitored in real time, and the patient's management and treatment plan is dynamically adjusted according to the monitoring situation.

[0133] Therefore, based on the Parkinson's quantitative early diagnosis model, the patient behavior characteristic data based on the Internet of Things is analyzed, and Parkinson's quantitative early diagnosis is performed on the patient to determine the patient's diagnosis result. Based on the patient's diagnosis result, the patient's behavior characteristic data is analyzed to determine the patient's condition assessment report. Based on the patient's condition assessment report, the patient is given intelligent management and treatment, and the treatment effect is monitored in real time. The patient's management and treatment plan is dynamically adjusted according to the monitoring situation. Parkinson's quantitative early diagnosis can be performed on the patient based on behavioral characteristic identification, which can improve the diagnosis effect of Parkinson's patients.

[0134] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting; it is not intended to exclude myriad other embodiments of the present application that other inventors can develop based on the same general inventive concepts embodied by the described embodiments. That is, although the present application is described in terms of particular embodiments and implementations, it is to be understood that the terminology used is for the purpose of descriptive clarity and that it should be taken in its broadest possible sense. For example, the terms "a", "an", and "the" include both singular and plural referents unless the context clearly dictates otherwise. The terms "comprises", "comprising", "includes", "including" and the like can be used in conjunction with the term "consisting of to include the elements or steps listed after such conjunctive language, but not to the exclusion of other elements or steps. The singular forms "a", "an" and "the" include plural referents unless the context clearly dictates otherwise.

[0135] While the embodiments of the application have been shown and described herein, it is understood that modifications, substitutions, changes, and alterations can be made by those skilled in the art without departing from the spirit and scope of the present application, which is defined by the appended claims and their equivalents.

Claims

1. A quantitative early diagnosis system for Parkinson's disease based on behavioral feature recognition, characterized by: include: An intelligent collection device and a quantitative diagnosis platform, wherein the intelligent collection device is configured to collect patient behavior characteristics during patient behavior activities, determine real-time patient behavior data, and transmit the collected real-time patient behavior data to a given quantitative diagnosis platform based on wireless transmission technology; The intelligent collection device includes a writing collection unit; The writing collection unit includes an intelligent writing pen and a writing and photographing device, wherein a wireless communication connection is established between the intelligent writing pen and the writing and photographing device; The smart writing pen collects the patient's writing tremor frequency and writing pressure per unit time in real time; Comparing the number of writing tremors and the writing pressure with a preset writing tremor number threshold and a preset writing pressure threshold respectively; When the number of writing tremors exceeds a preset writing tremor number threshold, but the writing pressure does not exceed the writing pressure threshold, triggering the writing photographing device to take a photograph by the smart writing pen to obtain a first writing image; When the number of writing tremors does not exceed a preset writing tremor threshold, but the writing pressure exceeds a writing pressure threshold, a comprehensive determination is made based on the corresponding values ​​of the number of writing tremors and the writing pressure to determine whether to trigger the writing photographing device to take a photograph; When the number of writing tremors and the writing pressure do not exceed their corresponding writing tremor number thresholds and writing pressure thresholds, controlling the writing photographing device to take pictures at a preset image acquisition frequency to obtain a second writing image; Setting the evaluation weight value of the first writing image to be higher than the evaluation weight value corresponding to the second writing image; A comprehensive judgment is made based on the corresponding values ​​of the number of writing tremors and the writing pressure to determine whether to trigger the writing camera to take a photo, including: When the writing pressure exceeds the writing pressure threshold, extracting the number of writing tremors per unit time in which the number of writing tremors does not exceed the preset writing tremor number threshold as a target tremor number data set; Generating a comprehensive writing state parameter using the target tremor frequency dataset and writing pressure; wherein the comprehensive writing state parameter is used to assess whether the current patient's writing state meets the necessity of image acquisition; The comprehensive writing state parameter is obtained by the following formula: Among them, S represents the comprehensive writing state parameter; P represents the writing pressure corresponding to exceeding the writing pressure threshold; P y represents the writing pressure threshold; n represents the number of data contained in the target tremor number data set, wherein the number of data is consistent with the number of unit times during which the writing tremor number does not exceed the preset writing tremor number threshold; C i represents the tremor number value corresponding to the i-th tremor data in the target tremor number data set; N represents the number of unit time the patient has written down; n0 represents the preset reference value of the number of unit time; C y Indicates the preset threshold value of writing tremor times; comparing the comprehensive writing state parameter with a preset parameter threshold; When the comprehensive writing state parameter is lower than a preset parameter threshold, it is determined that there is no need to trigger the writing photographing device to take a photograph; When the comprehensive writing state parameter is not lower than a preset parameter threshold, it is determined that the writing photo taking device needs to be triggered to take a photo; using a writing image obtained when the number of writing tremors does not exceed a preset writing tremor number threshold, but the writing pressure exceeds a writing pressure threshold, as a third writing image; Setting the evaluation weight value of the third writing image to be higher than the evaluation weight value corresponding to the second writing image, but lower than the evaluation weight value corresponding to the first writing image; The quantitative diagnosis platform is configured to construct a model for quantitative early diagnosis of Parkinson's disease based on the patient's behavioral characteristics, and to analyze the patient's real-time behavioral data and perform quantitative early diagnosis of Parkinson's disease based on the constructed model.

2. The Parkinson's disease quantitative early diagnosis system based on behavioral feature recognition according to claim 1, characterized in that: The intelligent acquisition device includes: a motion acquisition unit, a voice acquisition unit, a writing acquisition unit and a face acquisition unit; The motion acquisition unit is configured to monitor and collect the patient's gait data, balance data, and finger tapping data in real time based on the Internet of Things technology to obtain the patient's motion data; The voice collection unit is configured to monitor and collect the patient's voice characteristics and voice content in real time based on the Internet of Things technology to obtain the patient's voice data; The writing collection unit includes an intelligent writing pen and a writing camera. The intelligent writing pen is used to monitor and collect the patient's writing dynamics data in real time based on the Internet of Things technology to obtain the patient's writing data. The writing camera is used to collect writing graphic data. The facial acquisition unit is configured to monitor and collect the patient's facial movement data and facial expression data in real time based on the Internet of Things technology to obtain the patient's facial data; Among them, the real-time patient behavior data based on the Internet of Things is determined based on the collected patient movement data, patient voice data, patient writing data and patient facial data.

3. The Parkinson's disease quantitative early diagnosis system based on behavioral feature recognition according to claim 2, characterized in that: The gait data includes stride length, stride width, cadence, gait speed, swing phase, stance phase, gait symmetry, gait variability, trunk swing, arm swing and turning gait; Balance data includes standing balance, sitting balance, center of gravity swing, and postural stability; Finger tapping data includes tapping frequency, rhythm, force, and finger coordination; Speech characteristics include fundamental frequency, intensity, duration, speaking rate, pauses, intonation, articulation clarity, and speech fluency; Speech content includes vocabulary, grammatical structure, semantic expression and emotional expression; Writing dynamics data includes writing speed, acceleration and pressure, stroke length, width and angle, writing pauses and tremors; Writing graphic data includes font size, shape and spacing, handwriting neatness and coherence; Facial motion data includes movements of eyebrows, eyes, nose, and mouth; Facial expression data includes the frequency, amplitude and duration of expression changes.

4. The Parkinson's disease quantitative early diagnosis system based on behavioral feature recognition according to claim 3, characterized in that: The quantitative diagnosis platform includes: a behavioral data preprocessing unit and an early diagnosis evaluation unit; The behavior data preprocessing unit is configured to clean, transform, integrate and extract features of the real-time patient behavior data based on the Internet of Things, and determine the patient behavior feature data based on the Internet of Things; The early diagnosis and evaluation unit is configured to analyze the patient's behavioral characteristic data based on the Internet of Things, and perform quantitative early diagnosis of Parkinson's disease on the patient, and provide intelligent management and treatment for the patient based on the patient's diagnosis results.

5. The Parkinson's disease quantitative early diagnosis system based on behavioral feature recognition according to claim 4 is characterized in that: The behavior data preprocessing unit includes: a behavior data cleaning module and a behavior data conversion module; The behavior data cleaning module is configured to clean the real-time patient behavior data based on the Internet of Things; Among them, the real-time patient behavior data based on the Internet of Things is checked based on the Python library, duplicate values, missing values ​​and abnormal values ​​in the real-time patient behavior data based on the Internet of Things are identified, and the duplicate values, missing values ​​and abnormal values ​​in the real-time patient behavior data based on the Internet of Things are deleted; The behavior data conversion module is configured to convert the real-time patient behavior data based on the Internet of Things; Among them, the real-time patient behavior data based on the Internet of Things was normalized based on Z-Score standardization, and the real-time patient behavior data based on the Internet of Things was converted into a standard normal distribution with a mean of 0 and a standard deviation of 1, thereby removing the dimensional differences between the real-time patient behavior data based on the Internet of Things.

6. The Parkinson's disease quantitative early diagnosis system based on behavioral feature recognition according to claim 5, characterized in that: The behavior data pre-processing unit further includes: a behavior data integration module and a behavior data extraction module; The behavior data integration module is configured to integrate real-time patient behavior data based on the Internet of Things; Among them, the real-time patient behavior data based on the Internet of Things is integrated based on the Python library, the real-time patient behavior data based on the Internet of Things is integrated into a unified data view, and the integrated real-time patient behavior data based on the Internet of Things is verified to determine whether the integrated real-time patient behavior data based on the Internet of Things is missing; The behavior data extraction module is configured to extract real-time patient behavior data based on the Internet of Things; Among them, features related to Parkinson's disease are extracted from the real-time patient behavior data based on the Internet of Things, and the extracted feature vectors are weighted fused to determine the patient behavior feature data based on the Internet of Things.

7. The Parkinson's disease quantitative early diagnosis system based on behavioral feature recognition according to claim 6, characterized in that: The early diagnosis and evaluation unit includes: a diagnosis model training module, wherein the diagnosis model training module is configured to train a quantitative early diagnosis model for Parkinson's disease; Based on the demand for quantitative early diagnosis of Parkinson's disease based on behavioral feature recognition, the patient behavior history data based on the Internet of Things is collected and divided into training sets and test sets; Based on deep learning technology, a training set is used to train the deep learning model, allowing the deep learning model to autonomously learn the quantitative early diagnosis process of Parkinson's disease based on behavioral feature recognition, and determine the quantitative early diagnosis model of Parkinson's disease based on behavioral feature recognition; Based on the test set, the Parkinson's disease quantitative early diagnosis model based on behavioral feature recognition was tested. The performance of the model was evaluated based on the accuracy, recall rate, and F1 value indicators to determine whether the model based on behavioral feature recognition can achieve the expected results. According to the test evaluation results, the parameters and structure of the Parkinson's disease quantitative early diagnosis model based on behavioral feature recognition are adjusted. After continuous iterative optimization, the optimal Parkinson's disease quantitative early diagnosis model is determined.

8. The Parkinson's disease quantitative early diagnosis system based on behavioral feature recognition according to claim 7, characterized in that: The early diagnosis and evaluation unit further includes: a diagnosis, evaluation and control module; the diagnosis, evaluation and control module is configured to perform quantitative early diagnosis and evaluation and control of Parkinson's disease on the patient; Obtain the optimal Parkinson's disease quantitative early diagnosis model and deploy it in a practical Parkinson's disease quantitative early diagnosis environment based on behavioral feature recognition; Inputting the patient behavioral characteristic data based on the Internet of Things into the optimal Parkinson's quantitative early diagnosis model, analyzing the patient behavioral characteristic data based on the Internet of Things based on the optimal Parkinson's quantitative early diagnosis model, and performing a quantitative Parkinson's early diagnosis on the patient to determine the patient's diagnosis result; Among them, based on the patient's diagnosis results, the patient's behavioral characteristic data is analyzed to determine the patient's condition assessment report, and the patient is given intelligent management and treatment based on the patient's condition assessment report. The treatment effect is monitored in real time, and the patient's management and treatment plan is dynamically adjusted according to the monitoring situation.

Images