A Parkinson's intelligent detection method and system based on data recognition

Abstract

The present invention relates to the field of intelligent detection technology, and specifically to a Parkinson intelligent detection method and system based on data recognition, which includes the following steps: collecting the user's physiological and motion data through a smart watch, a wristband, and a mobile gait detector, recording the gait speed, stride length, and hand tremor frequency, analyzing the smoothness of hand movements, recording the timestamp of each data point, and organizing the data in chronological order to obtain a time series data set. In the present invention, the physiological and motion data collected by intelligent devices are processed through time serialization, carefully tracking every tiny change in Parkinson's disease, using a neural network to analyze the time segment data, effectively distinguishing normal and abnormal patterns, and accurately extracting key behavioral features, which not only enhances the ability to judge Parkinson's disease in the early stage, but also helps doctors adjust treatment plans in a timely manner through continuous monitoring, significantly improving the quality of life of patients and providing continuous medical decision-making support.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent detection, and particularly relates to a Parkinson intelligent detection method and system based on data recognition. Background Art

[0002] The technical field of intelligent detection covers a wide range of applications, from industrial automation to healthcare monitoring. It mainly utilizes sensor data, image recognition, sound recognition, and other forms of data input, and performs pattern recognition and data analysis through algorithms to achieve automatic recognition and evaluation of specific conditions or attributes. It relies on machine learning, deep learning, and artificial intelligence to improve the accuracy and efficiency of detection. It can also be used to assist in diagnosing diseases, monitoring the progression of the condition, and evaluating the treatment effect, providing assistance for clinical decision-making.

[0003] Among them, the Parkinson intelligent detection method based on data recognition is an application example of intelligent detection technology in the medical field. Its purpose is to detect and evaluate the presence and severity of Parkinson's disease by analyzing various data of patients (including movement data, physiological parameters, etc.). Using data recognition technology, it automatically analyzes the behavior and physiological characteristics of patients through algorithms to identify specific patterns of Parkinson's disease, providing a fast and non-invasive auxiliary diagnostic tool to help doctors diagnose Parkinson's disease at an early stage, so as to start treatment and management as early as possible and improve the quality of life of patients.

[0004] Existing technologies often have difficulty in effectively distinguishing the subtle differences between Parkinson's pathological behaviors and daily behaviors, resulting in relying on fewer clinical observations and subjective reports of patients, increasing diagnostic errors and limiting the maximization of treatment effects. In addition, existing technologies usually do not support in-depth analysis and real-time feedback of complex data in terms of data processing capabilities, restricting their application value in the rapidly changing progression of Parkinson's disease. The lack of refined and dynamic data analysis capabilities makes it difficult for doctors to obtain a comprehensive view of the Parkinson's condition, difficult to implement precise disease management strategies, increasing the passivity of treatment and affecting the treatment effect and quality of life of patients. Summary of the Invention

[0005] The purpose of the present invention is to solve the disadvantages existing in the prior art, and to propose a Parkinson intelligent detection method based on data recognition.

[0006] To achieve the above purpose, the present invention adopts the following technical solution: A Parkinson intelligent detection method based on data recognition, including the following steps:

[0007] S1: Collect the physiological and movement data of the user through a smart watch, wristband, and mobile gait detector, record the gait speed, stride length, and hand tremor frequency, analyze the smoothness of hand movement, record the timestamp of each data point, and organize the data in chronological order to obtain a time series data set;

[0008] S2: Divide the time series data set into time windows, count the continuous data points in each time window, calculate the average value and standard deviation of the gait speed, stride length, and hand tremor frequency in each time window, analyze the statistical characteristics of each time window, and obtain time segment data;

[0009] S3: Import the time segment data into a neural network, identify the changes in gait rhythm and the changes in hand tremor frequency and amplitude in each time window, compare with the normal mode, extract key behavior features from each time window for typical physiological behaviors of Parkinson's disease, analyze and record the manifestation form and intensity of each key behavior feature according to the extraction result of the key behavior features, analyze the change trend, mark the key behavior indicators, and form the analysis result of physiological behavior features;

[0010] S4: Based on the analysis result of the physiological behavior features, compare and analyze each key behavior feature with the known standard of the severity of Parkinson's disease, sort the key behavior features according to the degree of influence of each key behavior feature on the condition, comprehensively analyze the duration, frequency, and intensity of the symptoms according to the sorting result, classify the key behavior features according to the severity of the condition, record the disease stage corresponding to each behavior feature, and generate the evaluation result of the severity of Parkinson's disease.

[0011] As a further solution of the present invention, the acquisition steps of the time series data set are as follows:

[0012] S111: Collect the physiological and motion data of the user through a smart watch, wristband, and mobile gait detector, extract the gait speed, stride length, and hand tremor frequency, and record the time stamp of each data point at the same time, and perform preliminary integration on the data to obtain a multi-dimensional data set;

[0013] S112: Based on the multi-dimensional data set, arrange the gait speed, stride length, and hand tremor frequency in chronological order according to the time stamp, and use the formula:

[0014] ;

[0015] Calculate the smoothness index of the hand tremor movement , and at the same time, count the continuous change amplitude of the tremor frequency to generate a preliminary smoothness evaluation result, where, represents the th hand tremor frequency data point, represents the th hand tremor frequency data point, represents the total number of data points;

[0016] S113: Combining the preliminary evaluation results of smoothness, analyze the smoothness characteristics of hand tremor movements according to the time series distribution law, arrange the gait speed, stride length, and hand tremor frequency in chronological order combined with timestamps to generate a time series dataset.

[0017] As a further solution of the present invention, the steps for obtaining the time segment data are as follows:

[0018] S211: According to the timestamps in the time series dataset, divide the time series through a set time window length, extract all data points within the time window according to the start time and end time of each time window, screen the parameter data of gait speed, stride length, and hand tremor frequency, and classify them according to the time window to generate a parameter classification data set within the time window;

[0019] S212: Based on the parameter classification data set within the time window, calculate the average value and standard deviation of the data points of gait speed, stride length, and hand tremor frequency respectively for each data point within the time window, and correspond the statistical characteristics to the time window to establish a time window statistical characteristic set;

[0020] S213: Invoke the time window statistical characteristic set, combine the average value and standard deviation of gait speed, stride length, and hand tremor frequency with the timestamp range of each time window, and integrate all time window data in chronological order to form time segment data.

[0021] As a further solution of the present invention, the steps for extracting the key behavior characteristics are as follows:

[0022] S311: Import the time segment data into a neural network, fine-tune it through LoRA, synchronously pair the gait speed and stride length in combination with the start and end times of the time window, detect the peaks and valleys of the tremor frequency data within each time window, and generate paired data of gait speed and stride length within each time window;

[0023] S312: Based on the paired data of gait speed and stride length within each time window, analyze the change trends of gait speed and stride length, and use the formula:

[0024] ;

[0025] Calculate the gait rhythm change value within each time window , and generate the gait rhythm analysis result within the time window, where and represent the gait speed at the and the th time points, and represent the and the stride length at the th time point, indicating the total number of data points within the time window;

[0026] S313: Based on the gait rhythm analysis results within the time window, extract the typical physiological behavior characteristics of Parkinson's disease in each time window, combine the abnormal amplitude of the gait rhythm, the degree of change in tremor frequency, and the fluctuation of tremor amplitude, summarize the key behavior characteristics of each time window, and generate the key behavior characteristic extraction result.

[0027] As a further solution of the present invention, the steps for obtaining the physiological behavior characteristic analysis result are:

[0028] S321: Call the key behavior characteristic extraction result, for the key behavior characteristics extracted in each time window, sort out the manifestation form and corresponding value of the key behavior characteristics in the order of the time window, and record the key behavior characteristic type and intensity of each time window to generate the key behavior characteristic manifestation form and intensity record;

[0029] S322: Based on the key behavior characteristic manifestation form and intensity record, perform a time series trend analysis on the intensity of each key behavior characteristic in the order of the time window, analyze the change trend of the characteristic intensity over time, and correspond to the behavior characteristic type to generate the trend analysis result of the key behavior characteristic;

[0030] S323: Combine the trend analysis result of the key behavior characteristic, screen the characteristic type and intensity in the time window, extract the key behavior characteristics that exceed the normal threshold range, and mark the time position and abnormal index correspondingly to generate the physiological behavior characteristic analysis result.

[0031] As a further solution of the present invention, the steps for sorting the key behavior characteristics are:

[0032] S411: Based on the physiological behavior characteristic analysis result, compare the data item by item with the known standard of the severity of Parkinson's disease, calculate the difference between the actual value and the standard value of the key behavior characteristic, and record the magnitude and direction of the difference of each characteristic to generate the key behavior characteristic comparison difference result;

[0033] S412: According to the key behavior characteristic comparison difference result, use the formula:

[0034] ;

[0035] Calculate the comprehensive influence value of the key behavior characteristic on the condition , and generate the comprehensive influence evaluation result of the key behavior characteristic, where is the characteristic intensity difference, is the characteristic frequency difference, is the difference in feature duration;

[0036] S413: Arrange the comprehensive impact evaluation results of the key behavior features in descending order, record the sorting results and the corresponding comprehensive impact values, and organize all the features in sequence according to the degree of impact on the condition to generate the sorting results of the key behavior features.

[0037] As a further solution of the present invention, the steps for obtaining the Parkinson's disease severity evaluation result are as follows:

[0038] S421: According to the sorting results of the key behavior features, organize the manifestation form, intensity, frequency, and duration information of the features item by item in combination with the sorting position, and at the same time mark the corresponding impact level for each type of feature to generate the impact record of the key behavior features;

[0039] S422: According to the impact record of the key behavior features, match the feature manifestation form with the corresponding disease state, and summarize the change trend of each feature in the time dimension according to the significance of frequency and duration. Combine the representativeness of the feature for Parkinson's to generate the classification result of the severity level of the key behavior features;

[0040] S423: Based on the classification result of the severity level of the key behavior features, mark the corresponding disease stage according to the comprehensive manifestation form and classification result of each type of key behavior feature to generate the Parkinson's disease severity evaluation result.

[0041] A Parkinson intelligent detection system based on data recognition, comprising:

[0042] The data acquisition module collects the user's physiological and motion data through a smart watch, a wristband, and a mobile gait detector, records the time stamp of each data point, calculates the smoothness index of the hand tremor movement, and at the same time statistically analyzes the continuous change range of the tremor frequency, and arranges them in chronological order in combination with the time stamp to generate a time series data set;

[0043] The time division module divides the time series according to the time stamp in the time series data set through the set time window length, classifies them according to the time window, calculates the average value and standard deviation of each time window and combines them with the time stamp range of each time window to form time segment data;

[0044] The behavior analysis module imports the time segment data into a neural network to synchronously pair the gait speed and stride length, calculates the gait rhythm change value within each time window, extracts the typical physiological behavior characteristics of Parkinson's disease in each time window, records the key behavior characteristic types and intensities of each time window, analyzes the change trend of the characteristic intensity over time and corresponds it to the behavior characteristic type, extracts the key behavior characteristics beyond the normal threshold range, and marks the corresponding time positions and abnormal indicators, generating the physiological behavior characteristic analysis result;

[0045] Based on the physiological behavior characteristic analysis result, the evaluation and generation module compares the data item by item with the known standards of Parkinson's disease severity, calculates the comprehensive influence value of the key behavior characteristics on the condition according to the difference and arranges them in descending order, organizes the manifestation forms, intensities, frequencies and duration information of the characteristics item by item in combination with the sorting position, and at the same time marks the corresponding influence levels for each type of characteristic, classifies the severity of the key behavior characteristics in combination with the representativeness of the characteristics for Parkinson's disease, and synchronously marks the corresponding disease stages, generating the Parkinson's disease severity evaluation result.

[0046] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0047] In the present invention, the physiological and motion data collected by the intelligent device are processed through time serialization, carefully tracking every tiny change of Parkinson's disease, using a neural network combined with LoRA to analyze the time segment data, effectively distinguishing normal and abnormal patterns, and accurately extracting key behavior characteristics, which not only enhances the ability to judge Parkinson's disease in the early stage, but also helps doctors adjust the treatment plan in time through continuous monitoring, significantly improving the quality of life of patients and providing continuous medical decision support. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is the main step flowchart of the present invention;

[0049] Figure 2 is the flowchart for obtaining the time series data set of the present invention;

[0050] Figure 3 is the flowchart for obtaining the time segment data of the present invention;

[0051] Figure 4 is the flowchart for extracting the key behavior characteristics of the present invention;

[0052] Figure 5 is the flowchart for obtaining the physiological behavior characteristic analysis result of the present invention;

[0053] Figure 6 is the flowchart for sorting the key behavior characteristics of the present invention;

[0054] Figure 7This is a flowchart for obtaining the assessment results of the severity of Parkinson's disease in the present invention. Specific embodiments

[0055] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0056] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0057] Please refer to Figure 1 , a Parkinson's intelligent detection method based on data recognition, including the following steps:

[0058] S1: Collect the physiological and motion data of the user through a smart watch, a wristband and a mobile gait detector, record the gait speed, stride length and hand tremor frequency, analyze the smoothness of hand movement, record the timestamp of each data point, organize the data in chronological order to obtain a time series data set;

[0059] S2: Divide the time series data set into time windows, count the continuous data points of each time window, calculate the average value and standard deviation of the gait speed, stride length and hand tremor frequency within each time window, analyze the statistical characteristics of each time window to obtain time segment data;

[0060] S3: Import the time segment data into a neural network, fine-tune it through LoRA, identify the changes in gait rhythm and the changes in hand tremor frequency and amplitude within each time window, compare with the normal mode, extract key behavior features from each time window for the typical physiological behaviors of Parkinson's disease, analyze and record the manifestation form and intensity of each key behavior feature according to the key behavior feature extraction results, analyze the change trend, and mark the key behavior indicators to form the physiological behavior feature analysis result;

[0061] S4: Based on the analysis results of physiological and behavioral characteristics, each key behavioral characteristic is compared and analyzed with the known standards of Parkinson's disease severity. The key behavioral characteristics are ranked according to the degree of impact of each key behavioral characteristic on the disease. According to the ranking results, the duration, frequency and intensity of the symptoms are comprehensively analyzed. The key behavioral characteristics are classified according to the severity of the disease, and the disease stage corresponding to each behavioral characteristic is recorded to generate the Parkinson's disease severity assessment results.

[0062] The time series data set includes gait speed data, stride length data, hand tremor frequency data and timestamp records; the time segment data includes average speed, average stride length, average tremor frequency and statistical standard deviation; the physiological and behavioral characteristics analysis results include behavioral rhythm change analysis results, tremor frequency change analysis results, tremor amplitude change analysis results, behavioral intensity and behavioral manifestation records; the Parkinson's disease severity assessment results include key behavioral characteristics ranking results, disease classification and behavioral characteristics disease stage records.

[0063] See also Figure 2 , the steps to obtain the time series data set are:

[0064] S111: Collect user physiological and motion data through smart watches, wristbands and mobile gait detectors, extract gait speed, stride length and hand tremor frequency, record the timestamp of each data point, and perform preliminary integration of the data to obtain a multidimensional data set;

[0065] The user's physiological and motion data are obtained through smart watches, wristbands and mobile gait detectors. First, the original data is obtained according to the built-in sensors of the device, including parameters such as gait speed, stride length and hand tremor frequency. Each collected data point is accompanied by a timestamp record to ensure the accurate distribution of the data on the time axis. Then the original data points are filtered to eliminate missing data or erroneous data caused by signal interference or equipment abnormalities during the collection process. The filtered data are further sorted with timestamp as the primary key so that the time sequence between each data point is clearly visible. On this basis, the integrity of the data is checked to confirm that the three parameters of gait speed, stride length and hand tremor frequency have corresponding values ​​at each timestamp. If there is a single missing data, the missing value is filled by linear interpolation according to the trend of adjacent time points to ensure the continuity of the data. Finally, the processed data is integrated in chronological order to form an initial multidimensional data set containing four dimensions: timestamp, gait speed, stride length and hand tremor frequency.

[0066] S112: Based on the multidimensional data set, the gait speed, stride length and hand tremor frequency are arranged in time order according to the timestamp, using the formula:

[0067] ;

[0068] Calculate the smoothness index of hand tremor movement , and at the same time, statistically analyze the continuous change amplitude of the tremor frequency to generate a preliminary smoothness evaluation result, where represents the th hand tremor frequency data point, represents the th hand tremor frequency data point, represents the total number of data points;

[0069] In the time series, the collected hand tremor frequency data points are 10Hz, 12Hz, 14Hz, 15Hz, and 16Hz respectively, and the total number of data points , substitute the data into the formula for calculation as follows:

[0070] Calculate the sum of the squares of the frequency changes for each pair of adjacent points:

[0071]

[0072] Calculate the absolute change value for each pair of adjacent points:

[0073]

[0074] Combine the above results and divide by the number of data points:

[0075]

[0076] The results show that the smoothness index of hand tremor movement is 3.2, which reflects the comprehensive characteristics of the tremor frequency change. This result is directly used to judge the smoothness of the tremor frequency during the movement process, providing a basis for further analysis of tremor abnormalities.

[0077] S113: Combine the preliminary smoothness evaluation result, analyze the smoothness characteristics of hand tremor movement according to the time series distribution law, arrange the gait speed, step length, and hand tremor frequency in chronological order combined with the timestamp to generate a time series data set;

[0078] Based on the smoothing analysis results of various parameters in the time series, the time series data is further refined. First, the time series change data of gait speed and stride length are extracted, and the maximum value, minimum value, and change range of gait speed and stride length are calculated. Combining with the tremor movement smoothness index, the smooth intervals and non-smooth intervals in the time series are distinguished. Subsequently, for the non-smooth intervals, the corresponding data points in the time series are analyzed one by one, and the changes in gait speed and stride length are compared with the fluctuation trend of tremor frequency. Further, the data points with too large or discontinuous tremor frequency changes are screened out. At the same time, the corresponding abnormal timestamps are marked in the time series, and the distribution law of the abnormal point data is statistically analyzed to sort out the distribution dense intervals of the abnormal data. Finally, gait speed, stride length, tremor frequency, and timestamps are re-integrated in chronological order to form a complete multi-dimensional time series dataset with marked abnormal points, providing a basis for subsequent analysis.

[0079] Please refer to Figure 3 , the steps for obtaining time segment data are as follows:

[0080] S211: According to the timestamps in the time series dataset, the time series is divided by the set time window length. All data points within the time window are extracted according to the start time and end time of each time window. The parameter data of gait speed, stride length, and hand tremor frequency are screened and classified according to the time window to generate a parameter classification data set within the time window;

[0081] According to the timestamp parameters in the time series dataset, the time series is divided with a set time window length. First, the timestamps of each data point in the time series dataset are extracted, and the timestamps are sorted in chronological order to ensure that there are no duplicate or jumping timestamps. Then, according to the start time and end time range of the preset time window, the timestamp data is divided into multiple time windows. The division of the time window needs to ensure that the time range of each time window is continuous and covers all data points. Subsequently, the values of the three parameters of gait speed, stride length, and hand tremor frequency are extracted within each time window, and the timestamps are matched one by one for each data point within the time window to ensure that all data points within each time window correspond to complete timestamps and the number of data points meets the basic requirements within the time window. Finally, it is checked whether there are invalid data points or data loss in the divided time windows. The abnormal data in the time window is removed or marked, and the data points within the time window are rearranged in chronological order. Finally, a set containing the classification data of gait speed, stride length, and hand tremor frequency within the time window is generated to ensure that all data is reasonably and completely divided according to the time window.

[0082] S212: Based on the parameter classification data set in the time window, for each data point in the time window, respectively calculate the mean value and standard deviation of the gait speed, stride length and hand tremor frequency data points, and correspond the statistical characteristics to the time window to establish a time window statistical characteristic set;

[0083] The parameter classification data set within the time window is called, and the data points in each time window are further processed. First, the numerical data of gait speed, stride length and hand tremor frequency in each time window are extracted, and the validity of each data point is checked one by one. The abnormal data points beyond the reasonable range are eliminated. At the same time, the number of valid data points of gait speed, stride length and hand tremor frequency in each time window is counted to ensure that the statistical analysis uses complete and non-abnormal data. Then, the valid data points in each time window are numerically calculated one by one. The specific operation is as follows: for each parameter (gait speed, stride length length and hand tremor frequency), calculate their average value, that is, add up the values ​​of all valid data points and divide them by the number of data points, then calculate the standard deviation of the values, that is, sum the squares of the differences between the values ​​of each data point and the average value and divide them by the number of data points, and take the square root of the result to generate the average value and standard deviation data of each parameter in the time window. Finally, match the statistical characteristic data with the time window according to the parameter classification to form a statistical characteristic set of the time window, covering the average value and standard deviation of gait speed, stride length and hand tremor frequency, providing a complete statistical characteristic data basis for subsequent integration processing.

[0084] S213: calling the time window statistical feature set, combining the average value and standard deviation of gait speed, stride length and hand tremor frequency with the timestamp range of each time window, integrating all time window data in time order, and forming time segment data;

[0085] Based on the statistical characteristic set of each time window, the mean and standard deviation data of gait speed, stride length and hand tremor frequency in each time window are first extracted and matched with the time range of the time window. The statistical characteristic data of all time windows are arranged in the order of the start time of the time window to ensure that the order of the time windows is consistent with the timestamp order of the original time series. Then, the statistical characteristic data of each time window are checked for completeness to ensure that the mean and standard deviation data of gait speed, stride length and hand tremor frequency exist. Entries with incomplete parameters or abnormal data in the time window are eliminated. At the same time, it is checked whether the time range of the time window overlaps or jumps, and problematic time windows are eliminated or corrected. Finally, the statistical characteristic data of all time windows are integrated in chronological order to generate time segment data containing the statistical characteristics of the time window and the corresponding time range, where each time segment data includes the statistical characteristics of gait speed, stride length and hand tremor frequency in the time window and the corresponding time range, providing an accurate and clear data basis for subsequent time series analysis.

[0086] See also Figure 4 ,The steps for extracting key behavioral features are:

[0087] S311: importing the time segment data into the neural network, fine-tuning it through LoRA, synchronously pairing the gait speed and stride length in combination with the start and end time of the time window, performing peak and trough detection on the tremor frequency data in each time window, and generating paired data of the gait speed and stride length in each time window;

[0088] The time segment data is imported into the neural network. First, LoRA is used to reduce the training parameters and display usage through low-rank adaptation. Then, the gait speed, stride length and hand tremor frequency data of each time window are extracted from the time segment data. All data points are sorted according to the start and end time of the time window to ensure that the data points in the time window are arranged continuously in chronological order. Then, the two sets of gait speed and stride length data are paired point by point with the timestamp as the reference to form the paired data of gait speed and stride length. At the same time, the hand tremor frequency data is processed to mark the peak and trough data points in each time window, and the frequency and time position of the peak and trough are recorded to generate the paired data of gait speed and stride length in each time window and the peak and trough characteristic data of tremor frequency, which provide a basis for subsequent rhythm analysis and frequency characteristic analysis.

[0089] S312: Based on the paired data of gait speed and stride length in each time window, the changing trend of gait speed and stride length is analyzed using the formula:

[0090] ;

[0091] Calculate the gait rhythm change value within each time window , and generate the gait rhythm analysis result within the time window. Among them, and represent the gait speeds at the th and th time points, and represent the stride lengths at the th and th time points, represents the total number of data points within the time window;

[0092] A time window contains 5 data points, and its gait speeds are respectively , , , , , and the stride lengths are respectively , , , , , then the calculation process is as follows:

[0093] Calculate the sum of squares of changes in gait speed:

[0094]

[0095] Calculate the sum of squares of changes in stride length:

[0096]

[0097] Add the two parts of change values and divide by the total number of data points:

[0098]

[0099] The result shows that the gait rhythm change value within the current time window is , which reflects the comprehensive change characteristics of gait speed and stride length within the time window, and provides a quantitative basis for subsequent gait rhythm analysis.

[0100] S313: Based on the gait rhythm analysis result within the time window, extract the typical physiological behavior characteristics of Parkinson's disease in each time window, combine the abnormal amplitude of gait rhythm, the change degree of tremor frequency, and the fluctuation of tremor amplitude, summarize the key behavior characteristics of each time window, and generate the key behavior characteristic extraction result;

[0101] Based on the abnormal detection results of gait rhythm and tremor frequency changes within a time window, first call the gait rhythm change value and the peak-valley characteristic data of tremor frequency within the time window, analyze the gait rhythm change and tremor frequency change within each time window, associate the gait rhythm change value with the peaks and valleys of the tremor frequency, detect whether there are significant abnormal fluctuations, and then mark the time windows with abnormal fluctuations according to the detection results of each time window, extract the tremor frequency change amplitude and time position therein, classify and organize the typical physiological behavior characteristics of Parkinson's disease, and finally summarize the key behavior characteristics of each time window and record their relevant parameters to generate the key behavior characteristic extraction results within the time window.

[0102] Please refer to Figure 5 , and the steps for obtaining the analysis results of physiological behavior characteristics are as follows:

[0103] S321: Call the key behavior characteristic extraction results. For the key behavior characteristics extracted in each time window, organize the manifestation forms and corresponding values of the key behavior characteristics in the order of time windows, and record the key behavior characteristic types and intensities of each time window to generate the record of the manifestation forms and intensities of key behavior characteristics;

[0104] Call the key behavior characteristic extraction results. First, extract the basic information of the key behavior characteristics from the time window data, including the abnormal amplitude of gait rhythm, the change amplitude of tremor frequency, and the position data of tremor fluctuations. Organize the characteristic data in the order of the start time and end time of the time window to ensure that the characteristic data within the time window can completely correspond to each time period. During the extraction process, check the key behavior characteristics of each time window to confirm whether there are data missing or abnormal values in the numerical value of the abnormal amplitude of gait rhythm and the change amplitude of tremor frequency. For the missing data points, perform linear interpolation processing according to the change trend of adjacent points within the time window, and at the same time mark the abnormal values that are significantly beyond the normal range to ensure the data integrity of each time window. Subsequently, classify the extracted characteristic data, record the abnormal amplitude of gait rhythm as an independent category of characteristic data, and organize the change amplitude of tremor frequency and the tremor fluctuation position into a group in chronological order to form a classification record table of behavior characteristics. Finally, integrate the characteristic manifestation forms and intensity information of all time windows in time series to generate a complete record including the abnormal amplitude of gait rhythm, the change amplitude of tremor frequency, and their fluctuation positions, providing basic data support for the subsequent trend analysis of key behavior characteristics.

[0105] S322: Based on the record of the manifestation forms and intensities of key behavior characteristics, perform a time series trend analysis on the intensity of each key behavior characteristic in the order of time windows, analyze the change trend of the characteristic intensity over time, and correspond it to the behavior characteristic type to generate the trend analysis results of key behavior characteristics;

[0106] Based on the recording of the manifestation forms and intensities of key behavioral characteristics, first extract characteristic data such as the abnormal amplitude of gait rhythm, the change amplitude of tremor frequency, and the tremor fluctuation position. Arrange the characteristic intensity values in the order of time windows to form a time series, and ensure that the intensity value of each characteristic corresponds one-to-one with the start and end times of the corresponding time window. For each key behavioral characteristic, perform a time-window-by-time-window analysis of the characteristic intensity changes within the time window, calculate the intensity difference between each adjacent time window to measure the change amplitude within the time window, and at the same time record the change amplitude corresponding to the time series position to form the time series information of the characteristic intensity changes. Subsequently, according to the change amplitude of the characteristic intensity within the time window, calculate the change trend value of the entire time series, quantify the overall change trend by accumulating the change amplitude time-window-by-time-window and dividing by the total number of time windows, and at the same time record the positive and negative direction information of the change trend to distinguish whether the characteristic intensity shows an increasing or decreasing trend. Finally, organize and correspond the change trend information with each type of behavioral characteristic to generate a complete trend analysis result including the abnormal amplitude of gait rhythm and the change amplitude of tremor frequency, laying a foundation for subsequent abnormal feature screening.

[0107] S323: Combine the trend analysis results of key behavioral characteristics, screen the characteristic types and intensities in the time window, extract the key behavioral characteristics that exceed the normal threshold range, and mark the time positions and abnormal indicators correspondingly to generate the physiological behavioral characteristic analysis result;

[0108] Combine the change trend information of key behavioral characteristics within the time window. First, screen the change trend values and intensity values of each characteristic, extract the characteristic types with change trend values exceeding the normal range, and at the same time screen the key behavioral characteristics with intensity values outside the normal range to ensure that the screened characteristics are all abnormal characteristics. Subsequently, mark the time window positions of the screened abnormal characteristics, and record the start and end times of the time window corresponding to the abnormal intensity and change trend of the characteristic. For the screened abnormal characteristics, further classify and organize them according to the characteristic types, and record the time window range, intensity value, and change trend information of each type of abnormal characteristic respectively to ensure the integrity of the abnormal behavioral characteristic record. Finally, integrate all the screened and classified abnormal characteristics into a list of key behavioral indicators, and organize the list in the order of time windows to generate a complete key behavioral indicator marking result, ensuring that it includes the time window range, behavioral characteristic type, intensity value, and change trend information, providing accurate and detailed data support for generating a complete physiological behavioral characteristic analysis result.

[0109] Please refer to Figure 6 , the sorting steps of key behavioral characteristics are as follows:

[0110] S411: Based on the analysis results of physiological behavior characteristics, compare the data item by item with the known standards of Parkinson's disease severity, calculate the difference between the actual value and the standard value of the key behavior characteristics, record the magnitude and direction of the difference for each characteristic, and generate the comparison difference result of the key behavior characteristics.

[0111] Call the analysis results of physiological behavior characteristics. First, for each key behavior characteristic, extract data contents such as its manifestation form, intensity, and change trend. Organize these data in the order of time windows to ensure that the key behavior characteristics in each time window can accurately correspond to their time range and behavior content. During the organization process, classify the manifestation form and intensity of the key behavior characteristics to ensure that characteristic information such as gait rhythm, tremor frequency, and tremor amplitude is respectively summarized into separate data sets by category. At the same time, extract the change trend of the characteristics and record it in association with the manifestation form and intensity of each category of characteristics. Subsequently, compare the organized key behavior characteristic data item by item with the known standards of Parkinson's disease severity, extract the difference between the actual value and the standard value of the key behavior characteristics, and record the magnitude and direction of the difference. During the comparison process, check the integrity of the difference calculation to ensure that each characteristic type contains complete manifestation form, intensity, and trend information. At the same time, mark the positive and negative of the difference to clarify whether the deviation exceeds the standard range or is lower than the standard range. For the characteristic data with large deviations, record its characteristic category and related differences, and check all calculation results. Finally, generate the comparison difference result for each key behavior characteristic, providing basic data support for subsequent comprehensive calculation and ranking.

[0112] S412: According to the comparison difference result of the key behavior characteristics, use the formula:

[0113] ;

[0114] Calculate the comprehensive influence value of the key behavior characteristics on the condition , and generate the comprehensive influence evaluation result of the key behavior characteristics. Among them, is the characteristic intensity difference, is the characteristic frequency difference, is the characteristic duration difference;

[0115] The actual values of the intensity, frequency, and duration of a certain key behavior characteristic are respectively , , , and the corresponding known standard values are respectively , , , then the calculation of each difference is:

[0116] Calculate the characteristic intensity difference :

[0117]

[0118] Calculate the difference in characteristic frequencies :

[0119]

[0120] Calculate the difference in characteristic durations :

[0121]

[0122] Substitute into the formula to calculate the comprehensive influence value:

[0123]

[0124] The results show that the comprehensive influence value of the current key behavior characteristics , indicating that there are deviations in the differences in the three aspects of this characteristic, which can be used as the basis for subsequent sorting and classification, and used to measure the comprehensive influence degree of the characteristic on the condition.

[0125] S413: Sort in descending order according to the comprehensive influence evaluation results of the key behavior characteristics, record the sorting results and the corresponding comprehensive influence values, and organize all the characteristics in order of the degree of influence on the condition to generate the sorting results of the key behavior characteristics;

[0126] According to the comprehensive influence value of each key behavior characteristic, sort them in descending order. First, extract the characteristic with the highest comprehensive influence value, and associate and record its corresponding characteristic type, intensity, and manifestation form with the influence value to ensure that the influence degree of each characteristic is associated with its value. Subsequently, organize all the characteristics in order from largest to smallest influence value, and mark the sorting position for each type of characteristic. During the sorting process, for characteristics with the same comprehensive influence value, give priority to considering the high and low of their intensity and duration, arrange the characteristics with larger intensity in the front, and mark their specific sorting logic. After completing the sorting, integrate the manifestation form, comprehensive influence value, intensity, and sorting results of each characteristic into a characteristic sorting list to ensure that each characteristic has complete record information in the list. Finally, generate the sorting results of the key behavior characteristics sorted by the degree of influence on the condition, providing comprehensive and detailed reference data for subsequent classification and disease stage marking.

[0127] Please refer to Figure 7 , the steps to obtain the evaluation results of the severity of Parkinson's disease are as follows:

[0128] S421: According to the sorting results of the key behavior characteristics, organize the manifestation form, intensity, frequency, and duration information of the characteristics item by item in combination with the sorting position, and at the same time mark the corresponding influence level for each type of characteristic to generate the key behavior characteristic influence record;

[0129] Call the sorting results of the key behavior features, extract the core data contents such as the comprehensive influence value, sorting position, and manifestation form corresponding to each feature from them, sort them in order according to the sorting position, and ensure data integrity. First, extract the manifestation form, intensity, frequency, and duration information of the features in turn according to the level of the comprehensive influence value, check each feature item by item, confirm whether the intensity and frequency are consistent within the data range, and mark the priority of each feature. For the features with higher rankings, focus on marking the change relationship between the feature range and the actual performance during the sorting process, especially accurately record the duration of the features with high influence values to ensure that no key details are missed in subsequent analysis. During the data sorting process, group all the key behavior features in order to ensure that the intensity, frequency, and duration corresponding to each group of data can correspond to its sorting logic, and finally generate the influence records of the key behavior features sorted by priority, laying an accurate data foundation for subsequent feature analysis.

[0130] S422: According to the influence records of the key behavior features, match the feature manifestation form with the corresponding disease state, and summarize the change trend of each feature in the time dimension according to the significance of the frequency and duration. Combine the representativeness of the feature to Parkinson's disease to generate the classification result of the severity level of the key behavior features;

[0131] Based on the sorted influence records of the key behavior features, analyze the correlation between the intensity, frequency, and duration of each feature item by item. First, extract the significant feature parameters in the manifestation form, and sort the feature frequency and duration in segments according to their change ranges. For the significant fluctuations in the duration, compare the intensity parameter with the change trend of the duration, and extract the change features corresponding to the key time points. At the same time, for the frequency change of the feature, classify and summarize the fluctuation range of the frequency, and combine the change trend of the intensity to extract the significant performance of the key feature in terms of frequency. Correspond the sorted frequency and duration data with the feature intensity item by item to ensure that the data can comprehensively reflect the feature performance. During the analysis process, record the manifestation form and parameter range of each feature in detail, associate the significant changes in the manifestation form with the severity level, provide accurate data support for subsequent classification, and at the same time generate a preliminary basis for the severity level classification.

[0132] S423: Based on the classification result of the severity level of the key behavior features, mark the corresponding disease stage according to the comprehensive manifestation form and classification result of each type of key behavior feature to generate the assessment result of the severity of Parkinson's disease;

[0133] Call the classification basis of severity degree. According to the sorted key behavioral feature data, group each type of feature and correspond it to different disease stages. First, extract the severity classification results of the features, group and sort the features in order of mild, moderate, and severe, ensuring that the feature range in each group can cover the main manifestations of the disease stage. For the mild classification group, extract the features with relatively small changes in frequency and duration, and record them in association with the corresponding manifestation forms. At the same time, check each feature in the moderate classification group and the severe classification group one by one to confirm the corresponding relationship between the change range of intensity and duration and the disease stage. After completing the grouping, for each group of classified features, record its disease stage information and associate parameters such as manifestation form, intensity, frequency, and duration to generate the final classification record. Through the collation of each group of data, form the Parkinson's disease severity assessment results including the disease stage, manifestation form, and complete feature data, ensuring that doctors can conduct accurate analysis based on specific classification information during subsequent diagnosis.

[0134] A Parkinson's intelligent detection system based on data recognition, comprising:

[0135] The data acquisition module collects users' physiological and motion data through smart watches, wristbands, and mobile gait detectors, records the time stamps of each data point, calculates the smoothness index of hand tremor movement, and at the same time statistically analyzes the continuous change range of tremor frequency. Combined with the time stamps, arrange them in chronological order to generate a time series data set;

[0136] The time division module divides the time series according to the time stamps in the time series data set through the set time window length, classifies them according to the time window, calculates the average value and standard deviation of each time window and combines them with the time stamp range of each time window to form time segment data;

[0137] The behavior analysis module imports the time segment data into the neural network to synchronize and pair the gait speed and stride length, calculates the gait rhythm change value within each time window, extracts the typical physiological behavior features of Parkinson's disease in each time window, records the key behavior feature types and intensities of each time window, analyzes the change trend of feature intensity over time and corresponds it to the behavior feature type, extracts the key behavior features that exceed the normal threshold range, and marks the time position and abnormal indicators correspondingly to generate the physiological behavior feature analysis results;

[0138] The evaluation and generation module, based on the physiological behavior feature analysis results, compares the data item by item with the known standards of Parkinson's disease severity, calculates the comprehensive influence value of the key behavior features on the disease according to the difference and arranges them in descending order. Combine the sorting position to sort out the manifestation form, intensity, frequency, and duration information of the features item by item. At the same time, mark the corresponding influence level for each type of feature, classify the severity of the key behavior features in combination with the representativeness of the features to Parkinson's disease, and synchronously mark the corresponding disease stage to generate the Parkinson's disease severity assessment results.

[0139] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A Parkinson's intelligent detection method based on data recognition, characterized in that: The following steps are involved: S1: Collect user physiological and motion data through smart watches, wristbands and mobile gait detectors, record gait speed, stride length and hand tremor frequency, analyze the smoothness of hand movement, record the timestamp of each data point, organize the data in chronological order, and obtain a time series data set; S2: dividing the time series data set into time windows, counting the continuous data points in each time window, calculating the average and standard deviation of gait speed, stride length and hand tremor frequency in each time window, analyzing the statistical characteristics of each time window, and obtaining time segment data; S3: Import the time segment data into the neural network, perform fine-tuning through LoRA, identify the changes in gait rhythm and hand tremor frequency and amplitude in each time window, compare with the normal pattern, extract key behavioral features from each time window for typical physiological behaviors of Parkinson's disease, analyze and record the manifestation and intensity of each key behavioral feature based on the key behavioral feature extraction results, analyze the change trend, mark the key behavioral indicators, and form the physiological behavioral feature analysis results; S4: Based on the analysis results of the physiological and behavioral characteristics, each key behavioral characteristic is compared and analyzed with the known standards of Parkinson's disease severity, and the key behavioral characteristics are sorted according to the degree of influence of each key behavioral characteristic on the disease. According to the sorting results, the duration, frequency and intensity of the symptoms are comprehensively analyzed, and the key behavioral characteristics are classified according to the severity of the disease. The disease stage corresponding to each behavioral characteristic is recorded to generate the Parkinson's disease severity assessment result; The steps of extracting the key behavior features are: S311: importing the time segment data into a neural network, synchronously pairing the gait speed and stride length in combination with the start and end time of the time window, performing peak and trough detection on the tremor frequency data in each time window, and generating paired data of the gait speed and stride length in each time window; S312: Based on the paired data of gait speed and stride length in each time window, the changing trend of gait speed and stride length is analyzed using the formula: ； Calculate the gait rhythm change value in each time window , generate gait rhythm analysis results within the time window, where, and Indicates and Gait speed at each time point, and Indicates and The stride length at each time point, Represents the total number of data points in the time window; S313: Based on the gait rhythm analysis results within the time window, typical physiological behavioral characteristics of Parkinson's disease in each time window are extracted, and the key behavioral characteristics of each time window are summarized in combination with the abnormal amplitude of the gait rhythm, the degree of change of the tremor frequency and the fluctuation of the tremor amplitude, to generate the key behavioral characteristics extraction results.

2. The Parkinson's intelligent detection method based on data recognition according to claim 1 is characterized in that: The steps for obtaining the time series data set are: S111: Collect user physiological and motion data through smart watches, wristbands and mobile gait detectors, extract gait speed, stride length and hand tremor frequency, record the timestamp of each data point, and perform preliminary integration of the data to obtain a multidimensional data set; S112: Based on the multidimensional data set, gait speed, stride length and hand tremor frequency are arranged in time order according to timestamps, using the formula: ； Calculating smoothness index of hand tremor movement , and at the same time, the continuous change amplitude of the tremor frequency is counted to generate a preliminary evaluation result of smoothness, where Indicates hand tremor frequency data points, Indicates hand tremor frequency data points, Indicates the total number of data points; S113: In combination with the preliminary smoothness evaluation result, the smoothness characteristics of the hand tremor movement are analyzed according to the time series distribution law, and the gait speed, stride length, and hand tremor frequency are arranged in chronological order in combination with the timestamp to generate a time series data set.

3. The Parkinson's disease intelligent detection method based on data recognition according to claim 2 is characterized in that: The steps for obtaining the time segment data are as follows: S211: dividing the time series by a set time window length according to the timestamp in the time series data set, extracting all data points in the time window according to the start time and end time of each time window, screening the gait speed, stride length and hand tremor frequency parameter data, and classifying them according to the time window to generate a parameter classification data set in the time window; S212: Based on the parameter classification data set within the time window, for each data point within the time window, respectively calculate the mean value and standard deviation of the gait speed, stride length and hand tremor frequency data points, and correspond the statistical characteristics to the time window to establish a time window statistical characteristic set; S213: calling the time window statistical feature set, combining the mean and standard deviation of gait speed, stride length and hand tremor frequency with the timestamp range of each time window, integrating all time window data in chronological order to form time segment data.

4. The Parkinson's disease intelligent detection method based on data recognition according to claim 1 is characterized in that: The steps for obtaining the physiological behavior characteristic analysis result are: S321: calling the key behavior feature extraction result, sorting the key behavior feature expression forms and corresponding values ​​according to the time window sequence for the key behavior feature extracted in each time window, and recording the key behavior feature type and intensity of each time window to generate a key behavior feature expression form and intensity record; S322: Based on the key behavior feature expression form and strength record, perform time series trend analysis on the strength of each key behavior feature in time window order, analyze the change trend of the feature strength over time, and generate trend analysis results of the key behavior features in correspondence with the behavior feature type; S323: In combination with the trend analysis results of the key behavioral features, the feature types and intensities in the time window are screened, the key behavioral features that exceed the normal threshold range are extracted, and the time positions and abnormal indicators are marked accordingly to generate physiological behavioral feature analysis results.

5. The Parkinson's disease intelligent detection method based on data recognition according to claim 4 is characterized in that: The steps for sorting the key behavior features are: S411: Based on the physiological behavior feature analysis results, the data is compared with the known Parkinson's disease severity standards item by item, the difference between the actual value and the standard value of the key behavior feature is calculated, and the difference size and direction of each feature are recorded to generate the key behavior feature comparison difference result; S412: According to the comparison difference result of the key behavior feature, the formula is used: ； Calculate the comprehensive impact of key behavioral characteristics on the condition , generate comprehensive impact assessment results of key behavioral characteristics, among which, is the characteristic intensity difference, is the characteristic frequency difference, is the characteristic duration difference; S413: Arrange the key behavior characteristics in descending order according to the comprehensive impact assessment results, record the sorting results and the corresponding comprehensive impact values, sort all the characteristics in order according to the degree of impact of the disease, and generate the key behavior characteristics sorting results.

6. The Parkinson's disease intelligent detection method based on data recognition according to claim 5 is characterized in that: The steps for obtaining the Parkinson's disease severity assessment result are: S421: According to the ranking results of the key behavior features, the manifestation form, intensity, frequency and duration information of the features are sorted item by item in combination with the ranking positions, and the corresponding impact level is marked for each type of feature to generate a key behavior feature impact record; S422: According to the key behavior feature impact record, the feature expression form is matched with the corresponding disease state, and the change trend of each feature in the time dimension is summarized according to the significance of frequency and duration, and the key behavior feature severity classification result is generated in combination with the representativeness of the feature for Parkinson's disease; S423: Based on the severity classification results of the key behavioral characteristics, the corresponding disease stage is marked according to the comprehensive manifestation and classification results of each type of key behavioral characteristics to generate a Parkinson's disease severity assessment result.

7. A Parkinson's intelligent detection system based on data recognition, characterized in that: The system is used to execute the Parkinson's intelligent detection method based on data recognition according to any one of claims 1 to 6, comprising: The data acquisition module collects the user's physiological and motion data through smart watches, wristbands and mobile gait detectors, records the timestamp of each data point, calculates the smoothness index of hand tremor movement, and counts the continuous change amplitude of tremor frequency. Combined with the timestamp, it is arranged in chronological order to generate a time series data set; The time partitioning module partitions the time series by the set time window length according to the timestamps in the time series data set, and classifies according to the time windows, calculates the mean and standard deviation of each time window and combines them with the timestamp range of each time window to form time segment data; The behavior analysis module imports the time segment data into a neural network to synchronously pair the gait speed and stride length, calculates the gait rhythm change value in each time window, extracts the typical physiological behavior characteristics of Parkinson's disease in each time window, records the key behavior characteristic type and intensity of each time window, analyzes the change trend of the characteristic intensity over time and corresponds it with the behavior characteristic type, extracts the key behavior characteristics that exceed the normal threshold range, and marks the time position and abnormal indicators accordingly, and generates the physiological behavior characteristic analysis results; The assessment generation module compares the data with the known standards of Parkinson's disease severity item by item based on the physiological and behavioral characteristics analysis results, calculates the comprehensive impact value of the key behavioral characteristics on the disease according to the difference and arranges them in descending order, sorts out the manifestation, intensity, frequency and duration information of the characteristics item by item based on the sorting position, and marks the corresponding impact level of each type of feature. The key behavioral characteristics are classified according to the representativeness of Parkinson's disease based on the characteristics, and the corresponding disease stage is simultaneously marked to generate a Parkinson's disease severity assessment result.

Images