Parkinson's disease quantitative evaluation system

Abstract

The embodiment of the invention is suitable for the technical field of medical assistance, and provides a Parkinson's disease quantitative evaluation system, which comprises a wearable data acquisition device, a physical sign monitoring device and a data processing device, the data processing device comprises a feature extraction module and a multi-feature fusion analysis module, and the physical sign monitoring device comprises a display screen. The display screen displays action prompt information according to the target evaluation item; the wearable data acquisition device acquires exercise physiological sign data of the Parkinson's disease patient in the action execution process; the physical sign monitoring equipment sends the physiological feature data to a feature extraction module; the feature extraction module extracts feature variables from the physiological sign data, wherein the feature variables comprise motion feature variables and non-motion feature variables; and the multi-feature fusion analysis module performs fusion analysis on the motion feature variable and the non-motion feature variable to obtain an evaluation result of the Parkinson's disease patient. The Parkinson's disease quantitative evaluation system can simplify information acquisition operation during Parkinson's disease quantitative evaluation.

Description

Technical Field

[0001] The present application belongs to the field of medical auxiliary technology, and in particular, relates to a quantitative assessment system for Parkinson's disease. Background Art

[0002] Parkinson's disease (PD) is a common neurodegenerative disease. The first symptom of Parkinson's disease is usually tremor or slow movement of one limb, which then affects the contralateral limb. Clinically, it mainly manifests as motor symptoms such as resting tremor, bradykinesia, muscle rigidity and posture and gait disorders. In addition, non-motor symptoms such as depression, constipation and sleep disorders are also common complaints of Parkinson's patients, which will also affect the quality of life of patients.

[0003] At present, the functional evaluation of Parkinson's disease patients in clinical practice mainly uses the Unified Parkinson's Rating Scale (UPDRS). Taking MDS-UPDRS as an example, the scale consists of four parts: non-motor symptoms in daily life, motor symptoms in daily life, motor function examination and motor complications. When evaluating Parkinson's disease, the scorer needs to combine the information provided by the patient and the scorer's clinical observation and judgment to make a comprehensive score. These scale assessment methods rely on the doctor's personal experience and judgment, are highly subjective, have individual biases, and can only output semi-quantitative assessment results.

[0004] In addition, a lot of communication is required during the clinical observation of patients, which brings a lot of work to doctors and may also lead to problems with miscommunication.

[0005] It can be seen that when monitoring Parkinson's patients, the data collection process is relatively complicated, and the generated evaluation results also need to rely on the doctor's personal experience and judgment. Summary of the invention

[0006] In view of this, an embodiment of the present application provides a Parkinson's disease quantitative assessment system to simplify the information collection operation in the Parkinson's disease quantitative assessment process.

[0007] A first aspect of an embodiment of the present application provides a Parkinson's disease quantitative assessment system, comprising: a wearable data acquisition device, a vital sign monitoring device, and a data processing device, wherein the data processing device comprises a feature extraction module and a multi-feature fusion analysis module, and the vital sign monitoring device comprises a display screen, wherein:

[0008] The display screen is used to display action prompt information according to the target evaluation item selected by the user, and the action prompt information is used to prompt the Parkinson's patient to perform corresponding actions according to the action prompt information;

[0009] The wearable data collection device is used to collect the motion physiological sign data of the Parkinson's patient in the process of performing the action, and send the motion physiological sign data to the sign monitoring device;

[0010] The vital sign monitoring device is used to obtain physiological sign data of Parkinson's patients and send the physiological characteristic data to the feature extraction module;

[0011] The feature extraction module is used to extract feature variables from the physiological sign data, wherein the feature variables include motion feature variables and non-motion feature variables;

[0012] The multi-feature fusion analysis module is used to perform fusion analysis on the motion feature variables and the non-motion feature variables to obtain the evaluation result of the Parkinson's patient.

[0013] In a possible implementation, the vital sign monitoring device further includes a monitoring module.

[0014] The monitoring module is used to determine whether the action performed by the Parkinson's patient meets the requirements of the target evaluation project based on the sports physiological sign data, and to issue an early warning when the action performed by the Parkinson's patient does not meet the requirements of the target evaluation project.

[0015] In a possible implementation, the vital sign monitoring device further includes a camera module.

[0016] The camera module is used to collect image data of the Parkinson's patient in the process of performing the action;

[0017] The monitoring module is further used to determine whether the action performed by the Parkinson's patient meets the requirements of the target evaluation project based on the image data, and to issue an early warning when the action performed by the Parkinson's patient does not meet the requirements of the target evaluation project.

[0018] In one possible implementation,

[0019] The display screen is also used to display one or more assessment items that the Parkinson's patient needs to be assessed on, so as to prompt the Parkinson's patient to select an assessment item, and each of the assessment items is used to assess the movement status of a corresponding body part of the Parkinson's patient.

[0020] In a possible implementation, the display screen includes a first display area and a second display area, the action prompt information includes text information and video information, the first display area is used to display the text information, and the second display area is used to display the video information corresponding to the text information.

[0021] In a possible implementation, the wearable data acquisition device includes a plurality of wearable sensors.

[0022] The display screen is also used to display sensor wearing prompt information before the evaluation, and the sensor wearing prompt information is used to prompt the type of sensor to be worn and the sensor wearing position;

[0023] The monitoring module is also used to monitor whether the position of the sensor is correct, and to give a prompt when the position of the sensor is incorrect.

[0024] In one possible implementation,

[0025] The wearable data acquisition device is used to determine the target sensor according to the target assessment item; when the Parkinson's patient performs the action, the sensor data of the target sensor is collected, and the sensor data is sent to the physical sign monitoring device as the exercise physiological sign data.

[0026] In a possible implementation, the vital sign monitoring device further includes a storage module and an information processing module.

[0027] The storage module is used to store the sports physiological sign data;

[0028] The display screen is further used to display operation prompt information after the motor physiological sign data collection of the target evaluation item is completed, and the operation prompt information is used to prompt the Parkinson's patient to select a next operation, and the next operation includes an end operation, a re-collection operation or a continue collection operation, and the continue collection operation is a data collection operation for the next evaluation item;

[0029] The information processing module is used to process the stored sports physiological sign data according to the next step operation.

[0030] In one possible implementation,

[0031] The information processing module is used to discard the sports physiological signs data stored in the storage module when the next operation is the re-collection operation; send the sports physiological signs data stored in the storage module to the data processing device when the next operation is the continue collection operation; and send the sports physiological signs data stored in the storage module to the data processing device when the next operation is the end operation, and send information collection completion information to the data processing device.

[0032] In a possible implementation, the data processing device is used to store the exercise physiological sign data in association with the corresponding evaluation items when receiving the exercise physiological sign data; and to evaluate the exercise condition of the Parkinson's patient based on the received exercise physiological sign data of the Parkinson's patient when receiving the information collection completion information.

[0033] In a possible implementation, the physical sign data includes sports physiological sign data and non-sports physiological sign data, and the feature extraction module includes a sports feature variable extraction submodule and a non-sports feature variable extraction submodule.

[0034] The motion characteristic variable extraction submodule is used to perform time domain analysis and frequency domain analysis on the motion physiological sign data to obtain a plurality of motion characteristic variables, wherein the motion characteristic variables include at least one of tremor amplitude, tremor frequency, gait freezing degree, step length, step speed or step frequency;

[0035] The non-motion characteristic variable extraction submodule is used to generate an electronic scale based on the non-motion physiological sign data, digitally quantify the electronic scale to obtain multiple quantized non-motion physiological sign indicators, and determine multiple non-motion characteristic variables based on the multiple non-motion physiological sign indicators.

[0036] In a possible implementation, a fusion analysis model is embedded in the multi-feature fusion analysis module, and the multi-feature fusion analysis module is used to format the multiple motion feature variables and the multiple non-motion feature variables, and use the fusion analysis model to perform fusion analysis on the formatted multiple motion feature variables and the multiple non-motion feature variables to obtain the evaluation result.

[0037] In a possible implementation, the Parkinson's disease quantitative assessment system further includes a result output module.

[0038] The result output module is used to output the motion feature variable, the non-motion feature variable and / or the evaluation result.

[0039] The Parkinson's disease quantitative assessment system in the embodiment of the present application may include: a wearable data acquisition device, a vital sign monitoring device and a data processing device, the data processing device includes a feature extraction module and a multi-feature fusion analysis module, and the vital sign monitoring device includes a display screen. When performing a quantitative assessment of Parkinson's disease, the display screen may display action prompt information according to the target assessment item selected by the user, thereby prompting the Parkinson's patient to perform the corresponding action according to the action prompt information; the wearable data acquisition device may collect the motion physiological vital sign data of the Parkinson's patient in the process of performing the action, and send the motion physiological vital sign data to the vital sign monitoring device; the vital sign monitoring device is used to obtain the physiological vital sign data of the Parkinson's patient, and send the physiological characteristic data to the feature extraction module; the feature extraction module may be used to extract characteristic variables from the physiological vital sign data, and the characteristic variables include motion characteristic variables and non-motion characteristic variables; the multi-feature fusion analysis module is used to perform fusion analysis on the motion characteristic variables and non-motion characteristic variables to obtain the assessment result of the Parkinson's patient. In this system, Parkinson's disease patients only need to perform corresponding actions according to the prompts on the display screen, and the wearable data acquisition device can automatically collect data. Based on the collected data, the Parkinson's disease quantitative assessment system can automatically extract features and perform feature fusion analysis to automatically obtain the assessment results. Based on the Parkinson's disease quantitative assessment system in this application, Parkinson's disease can be evaluated based on simple operations, and the assessment results can be automatically obtained, which reduces the workload of doctors, and the generated assessment results are more objective. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art.

[0041] Figure 1 is a schematic diagram of a Parkinson's disease quantitative assessment system provided in an embodiment of the present application;

[0042] Figure 2 is a schematic diagram of a display interface of a display screen provided in an embodiment of the present application;

[0043] Figure 3 is a schematic diagram of a display interface of another display screen provided in an embodiment of the present application;

[0044] Figure 4 This is a schematic diagram of interaction in an information collection process provided by an embodiment of the present application;

[0045] Figure 5 Schematic diagram of a Parkinson's disease quantitative assessment process provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In the following description, specific details such as specific system structures, technologies, etc. are proposed for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from hindering the description of the present application.

[0047] The technical solution of the present application is described below through specific embodiments.

[0048] Reference Figure 1 , shows a schematic diagram of a Parkinson's disease quantitative assessment system provided by an embodiment of the present application. Figure 1 As shown, the Parkinson's disease quantitative assessment system may include: a wearable data acquisition device 11, a vital sign monitoring device 12 and a data processing device 13. The data processing device may include a feature extraction module and a multi-feature fusion analysis module, and the vital sign monitoring device may include a display screen.

[0049] The first symptom of Parkinson's disease is usually tremor or slow movement of one limb, which then affects the contralateral limb. Clinically, it mainly manifests as motor symptoms such as resting tremor, slow movement, muscle rigidity, and posture and gait disorders. In addition, non-motor symptoms such as depression, constipation, and sleep disorders are also common complaints of Parkinson's disease patients, which will also affect the quality of life of patients. Therefore, when conducting a quantitative assessment of Parkinson's disease, it is necessary to conduct an assessment based on motor physiological signs and non-motor physiological signs.

[0050] When evaluating based on motor physiological signs and non-motor physiological signs, multiple evaluation items may be included. For example, when collecting motor physiological signs, hand motor ability evaluation, foot motor ability evaluation, leg motor ability evaluation, etc. may be included. When collecting non-motor physiological signs, it is necessary to evaluate non-motor symptoms in daily life, motor symptoms in daily life, motor function tests, and motor complications, etc. Therefore, the Parkinson's disease quantitative evaluation system may include multiple evaluation items, and each item includes data that needs to be collected.

[0051] When using the Parkinson's disease quantitative assessment system for assessment, the Parkinson's disease quantitative assessment system can provide multiple items for the user to choose from. In a possible implementation, the display screen can display multiple assessment items, such as Figure 2As shown. The user can select one of the evaluation items according to the information displayed on the display screen. The display screen can display one or more evaluation items that Parkinson's patients need to evaluate, so as to prompt Parkinson's patients to select evaluation items. Each evaluation item can be used to evaluate the motor condition of the corresponding body part of Parkinson's patients or to evaluate non-motor symptoms. When making a selection, the user can use voice instructions or key instructions, etc. The Parkinson's disease quantitative evaluation system can collect the user's voice information, or monitor the user's key trigger information, so as to obtain the user's instructions. According to the user's instructions, the target evaluation item selected by the user can be determined.

[0052] After the user selects the target assessment item, the following Figure 3 The display interface is shown. Figure 3 As shown, after the user selects to evaluate item 1, the display interface may display an option to start evaluation, thereby prompting the user to evaluate the target evaluation item. After the user selects to start evaluation, the Parkinson's disease quantitative evaluation system may evaluate the target evaluation item.

[0053] If the target evaluation item is an item for evaluating the patient's motor status, after the user selects the target evaluation item, the display screen can display action prompt information according to the target evaluation item selected by the user, and the action prompt information is used to prompt the Parkinson's patient to perform corresponding actions according to the action prompt information. The action prompt information can be pre-recorded video information and / or text information, and the action prompt information can be stored in a storage module, so that the display screen can obtain the corresponding action prompt information from the storage module according to the target evaluation item and display it.

[0054] When displaying action prompt information, the display screen may first display the action prompt information once so that the user understands the action to be performed, and then synchronously display the action prompt information while the user is performing the action, so that the user can perform the action according to the displayed action prompt information. For example, the display screen may first display a complete action video, after which the user may choose to start performing the action, and the display screen may display the action prompt information in steps, so that the user can perform the action step by step according to the action prompt information.

[0055] In a possible implementation, the display screen may include a first display area and a second display area, the action prompt information may include text information and video information, the first display area may be used to display the text information, and the second display area may be used to display the video information corresponding to the text information. Synchronous display of the video information and the text information can better prompt the patient.

[0056] In a possible implementation, the vital sign monitoring device also includes a camera module and a monitoring module. Among them, the camera module can be a camera set on a display screen that can be used to collect image data of Parkinson's patients in the process of performing actions; the monitoring module can be used to determine whether the actions performed by Parkinson's patients meet the requirements of the target evaluation project based on the image data, and to issue an early warning when the actions performed by Parkinson's patients do not meet the requirements of the target evaluation project. Exemplarily, the Parkinson's disease quantitative assessment system can collect video information of the patient through a camera device, so that target recognition can be performed based on the video information to identify the user's actions during the data collection process. Based on the target detection results, the Parkinson's disease quantitative assessment system can determine whether the user's actions are correct. When it is recognized that the action performed by the user is incorrect, a prompt message can be displayed on the display screen, or a voice broadcast prompt message can be used to prompt the user to correct the action according to the action prompt information.

[0057] In the embodiment of the present application, during the quantitative assessment of Parkinson's disease, the patient can wear a wearable data acquisition device, so that data can be collected through the wearable data acquisition device. The wearable data acquisition device can be used to collect the motor physiological sign data of the Parkinson's patient during the execution of the action, and send the motor physiological sign data to the sign monitoring device.

[0058] Exemplarily, the wearable data acquisition device may include multiple inertial sensors and / or multiple pressure sensors and a data receiver. For example, the inertial sensor may be a Bluetooth 9-axis inertial sensor, and the data receiver may be a Bluetooth data receiver. Based on the sensor, the wearable data acquisition device may detect the patient's motion data. Based on the data receiver, the wearable data acquisition device may receive sensor data.

[0059] In one possible implementation, the wearable device may include multiple wearable sensors. When collecting data for different evaluation items, it may be necessary to collect data from different positions of the human body. Therefore, the positions of sensors may be different for different evaluation items. Before collecting data for the target evaluation item, the display screen may display sensor wearing prompt information, and the sensor wearing prompt information is used to prompt the type of sensor to be worn and the sensor wearing position. Based on the sensor wearing prompt information displayed on the display screen, the user can wear the sensor correctly.

[0060] In a possible implementation, the Parkinson's disease quantitative assessment system may further include a monitoring module, which may be used to monitor whether the position of the sensor worn is correct, and to provide a prompt when the position of the sensor worn is incorrect. Exemplarily, the Parkinson's disease quantitative assessment system may collect video information of the patient through a camera device, so that target recognition may be performed based on the video information to identify the sensor worn by the user. Based on the target detection result, the Parkinson's disease quantitative assessment system may determine whether the position of the user's sensor is worn correctly. When it is identified that the sensor data worn by the user is insufficient or the wearing position is incorrect, a prompt message may be displayed on the display screen, or a prompt message may be broadcasted by voice. This prompts the user to wear the sensor correctly.

[0061] In a possible implementation, it is also possible to determine whether the worn sensor is correct through the collected sensor data. Exemplarily, the above monitoring module can determine whether the currently collected sensor data is within the expected range. If the sensor data is not within the expected range, it is determined that the worn sensor is incorrect. For example, when monitoring the walking state, if the movement posture of the right foot cannot be monitored, the inertial sensor may not be worn at the right foot position. At this time, the display screen and voice module can be used to prompt the user to check whether the sensor at the right foot position is correctly configured.

[0062] In another possible implementation, the sensors on the wearable data acquisition device can also be fixed and do not need to be worn. When collecting data, the vital sign monitoring device can send the target evaluation items to the wearable data acquisition device, and the wearable data acquisition device can determine the target sensor that needs to collect data based on the target evaluation items; when the Parkinson's patient performs actions, the wearable data acquisition device can collect the sensor data of the target sensor and send the sensor data as motion physiological sign data to the vital sign monitoring device. Based on this, the user only needs to wear the wearable data acquisition device and perform actions according to the prompts to collect motion physiological sign data, which simplifies the execution process of the data acquisition operation.

[0063] During the data collection process, prompts can be given through the display screen throughout the process, so that the operations during the data collection process are simpler and clearer. In a possible implementation, the vital sign monitoring device also includes a storage module and an information processing module. Among them, the storage module can be used to store sports physiological signs data; the display screen can also be used to display operation prompt information after the sports physiological signs data collection of the target evaluation project is completed, and the operation prompt information can be used to prompt Parkinson's patients to select the next operation, wherein the next operation includes ending the operation, recollecting the operation or continuing the collection operation. Among them, the ending operation is to end the current data collection operation, that is, all the evaluation projects that need to be collected data have completed the data collection work; the recollecting operation is to perform data collection operations on the current evaluation project again; the continuing collection operation can be to perform data collection operations on the next evaluation project of the current evaluation project. The information processing module can be used to process the stored sports physiological signs data according to the next operation. When the information processing module processes the stored exercise physiological signs data according to the next operation, the following operations can be performed specifically: when the next operation is a re-collection operation, the exercise physiological signs data stored in the storage module is discarded; when the next operation is a continue collection operation, the exercise physiological signs data stored in the storage module is sent to the data processing device; when the next operation is an end operation, the exercise physiological signs data stored in the storage module is sent to the data processing device, and information collection completion information is sent to the data processing device.

[0064] The vital sign monitoring device in this application can interact with the patient to collect the patient's exercise physiological vital sign data. During the collection process, the interface of the display screen can play the video corresponding to the action prompt information, thereby guiding the patient to complete the corresponding assessment test items. Based on the video prompt information on the display screen, the patient can more easily understand the actions to be performed, thereby reducing the cost of communication between doctors and patients.

[0065] In addition, the Parkinson's disease quantitative assessment system in this application can also be embedded in patient information management software or assessment software. Patient management can be performed based on the patient information management software. For example, the patient's basic information, name, age, gender, number, etc. can be entered, and after the assessment is completed, the patient's assessment results can be recorded.

[0066] Figure 4 is a schematic diagram of an interaction in an information collection process provided by an embodiment of the present application; Figure 4 As shown, when the evaluation is being performed, a button for starting the evaluation may be displayed on the display screen. After the user triggers the button, an action example of the evaluation item 1 may be displayed on the display screen. After an action is displayed, the display screen may prompt the user to start the action, so that data can be collected during the user's action. Figure 4As shown, a back button pre and a forward button next can be displayed on the display screen. Among them, the back button can be used to perform data collection operations on the previous evaluation project, and the forward button is used to continue the data collection operation on the next evaluation project. After the user triggers the back button or the forward button on the display screen, the corresponding data can be continued to be collected based on the user's choice. For example, if the back button is triggered, it is equivalent to triggering a recollection operation on the previous evaluation project. At this time, the corresponding data in the storage module can be discarded, and the data collection of the previous evaluation project can be re-performed based on the above process. If the forward button is triggered, it is equivalent to triggering a recollection operation on the next evaluation project. At this time, the data collection of the next evaluation project can be re-performed based on the above process. After the corresponding data is collected for each evaluation project, the evaluation results can be displayed on the display screen, and the user can choose to save the evaluation results or export the evaluation results.

[0067] In the process of obtaining the evaluation results based on the evaluation items, data processing is required to obtain the evaluation results. The above-mentioned vital sign monitoring device can be used to obtain the physiological sign data of Parkinson's patients and send the physiological feature data to the feature extraction module in the data processing device. The physiological sign data includes exercise physiological sign data and non-exercise physiological sign data. The data processing device can process the physiological sign data based on the feature extraction module and the multi-feature fusion analysis module to obtain the Parkinson's disease evaluation results.

[0068] In a possible implementation, when the data processing device receives the exercise physiological sign data, it associates the exercise physiological sign data with the corresponding evaluation items and stores them; when the information collection completion information is received, the exercise condition of the Parkinson's patient is evaluated based on the received exercise physiological sign data of the Parkinson's patient.

[0069] In a possible implementation, the vital sign monitoring device may include a patient motion monitoring module and a non-motion physiological characteristic electronic scale module. If the target evaluation item selected by the user is an item for evaluating the patient's motion status, based on the above data collection process, the motion monitoring module can obtain the sensor data collected by the wearable data collection device, thereby obtaining the patient's motion physiological sign data.

[0070] If the user's target evaluation project is a project to evaluate the patient's motor status, the non-exercise physiological characteristics electronic scale module can be used to collect the patient's non-exercise physiological signs. When collecting the patient's non-exercise physiological signs, the evaluation form of the corresponding project can be displayed on the display screen. When the user chooses to start the evaluation, the display screen can display the questions and result options in the evaluation form in sequence, so that the user can select the result option of the corresponding question according to the prompt information on the display screen and according to his own condition. Based on the user's selection, the non-exercise physiological characteristics electronic scale module can obtain the user's condition corresponding to each question in the evaluation form. The non-exercise physiological characteristics electronic scale module can quantify each answer option corresponding to the question in the evaluation form, so that the corresponding non-exercise physiological characteristics quantitative data can be obtained according to the user's answer, and the non-exercise physiological characteristics quantitative data can be a non-exercise physiological characteristics electronic scale.

[0071] After collecting the sports physiological sign data and the non-sports physiological sign data, features may be extracted from the collected sports physiological sign data and the non-sports physiological sign data, so as to perform an assessment based on the features.

[0072] The above-mentioned feature extraction module can be used to extract feature variables from physiological sign data, and the feature variables include motion feature variables and non-motion feature variables. Among them, the motion feature variables are extracted from motion physiological signs, and the non-motion feature variables are extracted from non-motion physiological sign data. The non-motion feature variables are used to characterize the severity of non-motor symptoms of Parkinson's patients, and these non-motor symptoms can be clinical manifestation symptoms of Parkinson's patients. For example, the non-motor feature variables may include depression feature variables, constipation feature variables, and sleep disorder feature variables, wherein the depression feature variables, constipation feature variables, and sleep disorder feature variables can be used to characterize the degree of depression, the degree of constipation, and the sleep condition of Parkinson's patients, respectively.

[0073] In a possible implementation, the feature extraction module includes a motion feature variable extraction submodule and a non-motion feature variable extraction submodule. The motion feature variable extraction submodule can be used to perform time domain analysis and frequency domain analysis on the motion physiological sign data, so as to obtain multiple motion feature variables, and the motion feature variables include at least one of tremor amplitude, tremor frequency, gait freezing degree, step length, pace or step frequency. Exemplarily, the patient's motion physiological sign data can be preprocessed to filter out the noise caused by environmental interference; the preprocessed motion physiological sign data is input into the constructed motion feature extraction model, and the motion feature extraction model can perform time domain and frequency domain analysis on the motion physiological sign data to obtain multiple motion feature variables. In a possible implementation, the motion feature extraction model can be obtained by training deep learning based on a large amount of motion physiological sign data. In another possible implementation, the motion feature extraction model can also include multiple calculation formulas, for example, the step length, pace or step frequency of the patient when walking can be calculated based on the inertial sensor data of the patient's legs.

[0074] The non-motion feature variable extraction submodule can be used to generate an electronic scale based on non-motion physiological sign data, digitally quantify the electronic scale to obtain multiple quantized non-motion physiological sign indicators, and determine multiple non-motion feature variables based on the multiple non-motion physiological sign indicators. Exemplarily, the non-motion physiological characteristic electronic scale can be read according to a specific protocol, and the information in the electronic scale can be digitally quantified; each quantized indicator can be extracted as a non-motion feature variable; thereby obtaining a non-motion feature variable. The non-motion physiological sign data can include sleep data. If the user has no sleep problems, the corresponding score can be 0; if the user has sleep problems, but can usually rest all night, for example, the sleep time is more than 6 hours, and the number of night awakenings is 1 to 2 times, the score is 1; if the user has sleep problems and sometimes cannot stay asleep all night, for example, the sleep time is more than 5 hours, and the number of night awakenings is more than 3 times, the score is 2; if the user has sleep problems and it is difficult to stay asleep all night, but usually can sleep more than half of the time, for example, the sleep time is 3-5 hours, the score is 3; if the user usually cannot fall asleep most of the night, for example, the sleep time is less than 3 hours, the score is 4. The corresponding score of the sleep data can be a non-motion feature variable, which is used to characterize the user's sleep condition. The higher the score, the worse the user's sleep, that is, the more severe the symptoms of Parkinson's patients. Based on digital quantification, the score value corresponding to each indicator can be obtained. In one possible implementation, the score value can be used as a non-motion feature variable; in another possible implementation, the score values ​​corresponding to each indicator can also be normalized, and the normalized score value can be used as a non-motion feature variable.

[0075] After obtaining the characteristic variables and the non-motor characteristic variables, analysis can be performed based on the characteristic variables and the non-motor characteristic variables to obtain Parkinson's disease assessment results.

[0076] The above-mentioned multi-feature fusion analysis module can be used to perform fusion analysis on motion feature variables and non-motion feature variables to obtain the evaluation results of Parkinson's patients. In a possible implementation, a fusion analysis model is embedded in the multi-feature fusion analysis module, and the multi-feature fusion analysis module is used to format multiple motion feature variables and multiple non-motion feature variables, and use the fusion analysis model to perform fusion analysis on the formatted multiple motion feature variables and multiple non-motion feature variables to obtain the evaluation results. Exemplarily, the motion feature variables and non-motion feature variables can be formatted according to a certain protocol to eliminate the errors caused by different dimensions; then the formatted feature variables are input into the trained fusion analysis model to output the evaluation results of the patient's Parkinson's symptoms.

[0077] The above-mentioned Parkinson's disease quantitative assessment system also includes a result output module, which can be used to output motion feature variables, non-motion feature variables and / or assessment results. Among them, the motion feature variables and non-motion feature variables are equivalent to intermediate process results, and the process results may include, for example, stride length, step frequency, tremor amplitude, etc. The result output module can generate an electronic document based on the process results and the assessment results, and the user can export the electronic document to view the assessment results. In addition, the display screen can also display the electronic document, so that the user can view the assessment results.

[0078] In addition, based on the Parkinson's disease quantitative assessment system in the present application, Parkinson's disease can also be assessed only based on motion characteristics. The Parkinson's disease quantitative assessment system in the present application can be used to assess Parkinson's disease based on motion characteristics. The assessment process of Parkinson's disease can be as follows: when the patient clicks on the display screen to enter the Parkinson's disease assessment, the video corresponding to the action prompt information can be displayed on the display screen interface of the physical sign monitoring device. The interface software on the physical sign monitoring device can display the prompts of the single assessment action in sequence, and play the audio and video of the corresponding action, thereby instructing the patient to perform the corresponding assessment action according to the prompt information. The video action can be played continuously in the display area of ​​the display screen, and the playback duration does not exceed 10s, so that the patient can understand the assessment action to be performed. After the video is played, the display screen can be displayed as a pop-up window to prompt the patient to start the action; when the patient clicks the start test / start assessment button on the display screen interface, the test assessment of this project can be performed. At this time, if the patient is wearing a wearable data acquisition device, after clicking start, the physical sign monitoring device can send a data acquisition instruction to the wearable data acquisition device. After receiving the data collection instruction, the wearable device data collection device can start collecting data on the patient's movements and upload the collected data to the vital sign monitoring device in real time through Bluetooth or HUB data transfer.

[0079] After completing a single assessment, the patient can click the interface button on the display screen to proceed to the next assessment. At this time, the vital sign monitoring device can save the data of the single assessment and the assessment item label. In addition, it can also jump to the previous reassessment. At this time, the last assessment data of the assessment item is still temporarily stored; after the end of this assessment, the vital sign monitoring device can discard the last data of the assessment and store the newly collected data locally to start collecting again.

[0080] After all assessment items are completed, the patient can click Finish / End. At this point, the vital sign monitoring device can send all the exercise physiological sign data to the data processing device. The data processing device can call the algorithm, correspond all the collected data to the assessment items, analyze the data of each assessment item in turn, and finally generate the patient's overall movement symptom parameters, such as gait-related parameters. Call the algorithm again, and based on the results of each exercise parameter, the algorithm comprehensively analyzes and calculates the patient's overall exercise status to generate an assessment result. The assessment results can be saved to the local software storage and browsing, and can also be exported or printed for patients or doctors to view.

[0081] The Parkinson's disease quantitative assessment system in this application is based on wearable data acquisition equipment and sign monitoring equipment. Patients can clearly know the actions that need to be performed, so that sensor data can be automatically collected through wearable data acquisition equipment. The sensor data can objectively characterize the user's motor physiological signs. Based on this, objective evaluation of motor function can be achieved, the motor data collection process can be simplified, the cost of doctor-patient communication can be reduced, and the workload of doctors can be reduced. The Parkinson's disease patient assessment system in this application can be integrated and analyzed based on motor physiological sign data and non-motor physiological sign data, and automatically generate Parkinson's disease quantitative assessment results, which reduces the workload of doctors and makes the assessment results more accurate and objective. In the process of generating the assessment results, the motion sensor monitoring combined with the scale is combined to make the assessment of Parkinson's disease more comprehensive. In addition, the Parkinson's disease quantitative assessment system can realize the collection and recording of all typical characteristics of Parkinson's disease, is easy to operate, and has comprehensive information management. It can also freely configure the assessment project combination according to the patient's symptom performance to improve the assessment efficiency.

[0082] The Parkinson's disease patient assessment system in this application can be embedded in a hospital management system for use. Figure 5 FIG. 1 is a schematic diagram showing a Parkinson's disease patient assessment process provided by an embodiment of the present application. Figure 5 As shown, when the patient is admitted to the hospital, he or she can register for outpatient or hospital admission. After the patient is admitted to the hospital, the clinician can first make a preliminary diagnosis of the condition and determine the application items, that is, determine the assessment items that the patient needs to undergo. For example, if the patient mainly manifests tremors in the upper limbs and hands, the upper limb-tremor assessment item can be selected; if the patient mainly manifests gait abnormalities, the lower limb-gait assessment item can be selected.

[0083] After determining the application project, if you need to use motion sensors to check the motor function, prepare the corresponding acquisition equipment. For example, if you need to evaluate the motor ability of the upper limbs, you can prepare two sensors for the left and right hands; if you need to evaluate the gait and movement status of the lower limbs, you can prepare sensors for the left and right thighs.

[0084] After the equipment and materials are prepared, you can log in to the medical evaluation system, create new patient information, and enter the Parkinson's disease application module, which can be the Parkinson's disease quantitative evaluation system mentioned above. In the Parkinson's disease application module, you can select the corresponding evaluation items. After the evaluation items are determined, the system prompts the sensors and wearing positions required to complete all test items. The evaluation items can be divided into basic, advanced and scale evaluations. Among them, the basic evaluation items can be gait and upper limb tremor evaluations, which are also two typical symptoms and evaluation items for Parkinson's patients. Advanced evaluation items include other motor function examinations in the UPDRS III part, including finger test, fist test, rotation test, leg flexibility and other sub-test items. Based on the patient's own state, you can freely choose the evaluation combination of sub-test items. The scale evaluation includes other evaluation items of UPDRS in addition to the above evaluation items, and clinical staff will subjectively score and evaluate according to the patient's symptoms.

[0085] After completing all test items, the Parkinson's disease quantitative assessment system can conduct a comprehensive analysis of the collected information and output the clinical symptom assessment results of the patient. For example, the assessment result can be: the patient's total score is XX points, of which the motor function test score is XX points (tremor XX points, gait XX points), and the non-motor function score is XX points. The single assessment results can be output in the form of charts or text. For example, resting tremor analysis, tremor amplitude 2cm, mild tremor, etc.

[0086] After completing all tests, remove the wearable device and generate a report, which can be stored as an electronic document or output to a printer.

[0087] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application is described in detail with reference to the above-mentioned embodiments, a person skilled in the art should understand that the technical solutions described in the above-mentioned embodiments can still be modified, or some of the 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 quantitative assessment system for Parkinson's disease, It is characterized in that include: Wearable data acquisition equipment, vital sign monitoring equipment and data processing equipment, the data processing equipment includes a feature extraction module and a multi-feature fusion analysis module, the vital sign monitoring equipment includes a display screen, wherein: The display screen is used to display action prompt information according to the target evaluation item selected by the user, and the action prompt information is used to prompt the Parkinson's patient to perform corresponding actions according to the action prompt information; The wearable data collection device is used to collect the motion physiological sign data of the Parkinson's patient in the process of performing the action, and send the motion physiological sign data to the sign monitoring device; The vital sign monitoring device is used to obtain physiological sign data of Parkinson's patients and send the physiological characteristic data to the feature extraction module; The feature extraction module is used to extract feature variables from the physiological sign data, wherein the feature variables include motion feature variables and non-motion feature variables; The multi-feature fusion analysis module is used to perform fusion analysis on the motion feature variables and the non-motion feature variables to obtain the evaluation result of the Parkinson's patient.

2. The system according to claim 1, It is characterized in that The vital sign monitoring device also includes a monitoring module, The monitoring module is used to determine whether the action performed by the Parkinson's patient meets the requirements of the target evaluation project based on the sports physiological sign data, and to issue an early warning when the action performed by the Parkinson's patient does not meet the requirements of the target evaluation project.

3. The system according to claim 2, It is characterized in that The vital sign monitoring device also includes a camera module. The camera module is used to collect image data of the Parkinson's patient in the process of performing the action; The monitoring module is further used to determine whether the action performed by the Parkinson's patient meets the requirements of the target evaluation project based on the image data, and to issue an early warning when the action performed by the Parkinson's patient does not meet the requirements of the target evaluation project.

4. The system according to claim 1, It is characterized in that The display screen is also used to display one or more assessment items that the Parkinson's patient needs to be assessed on, so as to prompt the Parkinson's patient to select an assessment item, and each of the assessment items is used to assess the movement status of a corresponding body part of the Parkinson's patient.

5. A system according to any one of claims 1 to 4, It is characterized in that The display screen includes a first display area and a second display area, the action prompt information includes text information and video information, the first display area is used to display the text information, and the second display area is used to display the video information corresponding to the text information.

6. The system according to claim 2 or 3, It is characterized in that The wearable data acquisition device includes a plurality of wearable sensors. The display screen is also used to display sensor wearing prompt information before the evaluation, and the sensor wearing prompt information is used to prompt the type of sensor to be worn and the sensor wearing position; The monitoring module is also used to monitor whether the position of the sensor is correct, and to give a prompt when the position of the sensor is incorrect.

7. The system of claim 6, It is characterized in that The wearable data acquisition device is used to determine the target sensor according to the target assessment item; when the Parkinson's patient performs the action, the sensor data of the target sensor is collected, and the sensor data is sent to the physical sign monitoring device as the exercise physiological sign data.

8. The system of claim 1, It is characterized in that The vital sign monitoring device also includes a storage module and an information processing module. The storage module is used to store the sports physiological sign data; The display screen is further used to display operation prompt information after the motor physiological sign data collection of the target evaluation item is completed, and the operation prompt information is used to prompt the Parkinson's patient to select a next operation, and the next operation includes an end operation, a re-collection operation or a continue collection operation, and the continue collection operation is a data collection operation for the next evaluation item; The information processing module is used to process the stored sports physiological sign data according to the next step operation.

9. The system of claim 8, It is characterized in that The information processing module is used to discard the sports physiological signs data stored in the storage module when the next operation is the re-collection operation; send the sports physiological signs data stored in the storage module to the data processing device when the next operation is the continue collection operation; and send the sports physiological signs data stored in the storage module to the data processing device when the next operation is the end operation, and send information collection completion information to the data processing device.

10. The system of claim 9, It is characterized in that The data processing device is used to associate and store the exercise physiological sign data with corresponding evaluation items when receiving the exercise physiological sign data; and to evaluate the exercise condition of the Parkinson's patient based on the received exercise physiological sign data of the Parkinson's patient when receiving the information collection completion information.

11. The system of claim 1, It is characterized in that The physical sign data includes sports physiological sign data and non-sports physiological sign data, and the feature extraction module includes a sports feature variable extraction submodule and a non-sports feature variable extraction submodule. The motion characteristic variable extraction submodule is used to perform time domain analysis and frequency domain analysis on the motion physiological sign data to obtain a plurality of motion characteristic variables, wherein the motion characteristic variables include at least one of tremor amplitude, tremor frequency, gait freezing degree, step length, step speed or step frequency; The non-motion characteristic variable extraction submodule is used to generate an electronic scale based on the non-motion physiological sign data, digitally quantify the electronic scale to obtain multiple quantized non-motion physiological sign indicators, and determine multiple non-motion characteristic variables based on the multiple non-motion physiological sign indicators.

12. The system of claim 1, It is characterized in that The multi-feature fusion analysis module has a built-in fusion analysis model, which is used to format the multiple motion feature variables and the multiple non-motion feature variables, and use the fusion analysis model to perform fusion analysis on the formatted multiple motion feature variables and the multiple non-motion feature variables to obtain the evaluation result.

13. The system of claim 1, It is characterized in that The Parkinson's disease quantitative assessment system also includes a result output module. The result output module is used to output the motion feature variable, the non-motion feature variable and / or the evaluation result.

Images