Breathing health assessment system based on big data

Abstract

The invention relates to the technical field of health assessment, in particular to a big data-based breathing health assessment system, which comprises a breathing parameter analysis module, an interaction relationship assessment module, a breathing anomaly detection module and a breathing condition assessment module. According to the method, accurate extraction of breathing parameters and evaluation of breathing periodic changes are achieved by analyzing thoracic pressure waveform data, the breathing mode of a user is accurately recognized, physiological parameters are collected, the mutual relation between the physiological parameters and the breathing mode is analyzed, the influence of various physiological factors on breathing health is revealed, the dynamic monitoring capacity on the breathing health is enhanced, and the user experience is improved. According to the method, by combining detection and identification of abnormal breathing parameters, identification and classification of abnormal breathing reasons are achieved, medical professionals are helped to make treatment plans and health management strategies, diagnosis efficiency is improved, the misdiagnosis rate is reduced, and powerful support is provided for management of various chronic diseases by combining continuous trend analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of health assessment, and in particular to a respiratory health assessment system based on big data. Background Art

[0002] The field of health assessment technology focuses on using a variety of tools and methods to analyze and evaluate the health status of individuals. It involves a variety of medical examination methods, including the use of biosensors, medical imaging technology, genetic analysis and big data analysis to achieve accurate monitoring and evaluation of human health status, help medical professionals detect and prevent diseases, assess health risks, and provide personalized health management recommendations. It combines artificial intelligence and machine learning algorithms to optimize data processing and diagnostic accuracy to meet the needs of public health and personal medical care.

[0003] Among them, the respiratory health assessment system focuses on monitoring and evaluating individual respiratory health status. It evaluates the user's respiratory function by analyzing respiratory rate, airflow, oxygenation level and various respiratory-related parameters. It is used for early diagnosis of respiratory diseases, monitoring changes in known respiratory conditions, evaluating treatment effects, and management of chronic respiratory diseases, including asthma and chronic obstructive pulmonary disease. It helps doctors and patients better understand the disease status and make health management decisions by providing real-time data and trend analysis.

[0004] Traditional respiratory health assessment systems rely on regular medical examinations and relatively static data analysis, which limits the ability to continuously monitor and evaluate respiratory health conditions in real time. They perform poorly in situations that require emergency response, including daily health management of COPD or asthma patients, which requires real-time monitoring of patients' respiratory conditions to prevent acute attacks. Traditional technologies cannot meet the needs of immediate intervention and lack the capabilities of batch data processing and real-time analysis, resulting in delays in the optimal treatment time when handling emergency medical events. They lack the ability to comprehensively analyze individual health data and cannot provide personalized health management plans, making it difficult for patients to obtain optimal treatment, affecting treatment outcomes and their quality of life. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and propose a respiratory health assessment system based on big data.

[0006] In order to achieve the above purpose, the present invention adopts the following technical scheme: A respiratory health assessment system based on big data includes: The breathing parameter analysis module analyzes the target pressure waveform data based on the chest pressure waveform data, extracts multiple breathing parameters, identifies the breathing patterns of multiple users, including breathing frequency and breathing depth, evaluates the periodic changes of breathing, and obtains the breathing pattern characteristic information; The interactive relationship evaluation module collects multiple physiological parameters of the user in real time based on the breathing pattern characteristic information, analyzes the mutual influence relationship between the multiple physiological parameters and the breathing pattern, including heart rate, blood pressure, blood oxygen saturation, vital capacity, and airway resistance, evaluates the breathing efficiency of multiple users, and obtains physiological correlation analysis results; Based on the physiological correlation analysis results, the breathing abnormality detection module monitors and identifies abnormal changes in breathing parameters, including breathing rhythm, frequency, and depth, through time series analysis, identifies the causes of abnormalities and classifies breathing abnormalities, including apnea and irregular rhythm, and generates abnormal breathing identification results; The respiratory condition evaluation module analyzes the abnormal breathing of the user based on the abnormal breathing results to evaluate the user's respiratory health status, including vital capacity and airway resistance, and uses time series analysis to calculate the predicted values ​​at multiple time points, evaluate the changing trend of respiratory health, and evaluate the health status.

[0007] As a further solution of the present invention, the breathing pattern characteristic information includes breathing frequency parameters, breathing depth parameters, and breathing rhythm parameters. The physiological association analysis results are specifically heart rate data association information, blood pressure data association coefficient, and blood oxygen saturation data association analysis results. The abnormal breathing identification results include abnormal breathing rhythm information, abnormal breathing frequency information, and abnormal breathing depth detection data.

[0008] As a further solution of the present invention, the step of acquiring the respiratory frequency is specifically as follows: Based on the chest pressure waveform data, by identifying the start and end time points of each breath, the time interval of each breathing cycle is calculated using the formula: ; Calculate the time interval of each breathing cycle and obtain the time interval array of each breathing, where: is the time interval of the i-th respiratory cycle, is the end time of the i-th breath, is the start time of the i-th breath; Based on the time interval array, by the formula: ; Calculate and obtain the respiratory rate, where is the respiratory rate, For Array of calculated average breathing time intervals.

[0009] As a further solution of the present invention, the step of acquiring the breathing depth is specifically as follows: Based on the breathing rate, the amplitude of the waveform in the thoracic pressure waveform is measured, using the formula: ; Calculate the depth of each breath and obtain the breathing depth data, where For the The depth of each breath, For the The peak pressure of each breath, For the Baseline pressure for each breath, is the index of the number of breaths considered; Based on the breathing depth data and in combination with the target user's breathing frequency data, the periodic changes of breathing are evaluated to obtain breathing pattern characteristic information.

[0010] As a further solution of the present invention, the step of obtaining the mutual influence relationship is specifically: Based on the respiratory pattern characteristic information, a variety of physiological monitoring devices are used to collect the user's heart rate, blood pressure, blood oxygen saturation, vital capacity, and airway resistance in real time, and combined with the respiratory frequency and breathing depth to construct a physiological parameter data set; Based on the physiological parameter data set, correlation analysis between physiological parameters and breathing patterns was performed to evaluate the dynamic relationship between cardiovascular health status and breathing patterns, using the formula: ; The correlation coefficient between physiological parameters and breathing patterns is calculated to obtain the mutual influence relationship between physiological parameters and breathing patterns, where: Indicates the measured values ​​of physiological parameters, including heart rate, blood pressure, blood oxygen saturation, vital capacity, airway resistance, Represents measurements of breathing patterns, including breathing rate, breathing depth, is the average value of the physiological parameter measurement, is the average value of the breathing pattern measurements, is the correlation coefficient between heart rate and respiratory rate, which quantifies the degree of linear relationship between the two.

[0011] As a further solution of the present invention, the steps of obtaining the breathing efficiency are specifically as follows: Based on the mutual influence relationship, the respiratory efficiency is calculated and analyzed according to the respiratory depth, respiratory rate and blood oxygen saturation data, through the formula: ; Calculating breathing efficiency ,in, For breathing efficiency, For breathing depth, is the respiratory rate, is blood oxygen saturation; Based on the breathing efficiency, combined with correlation coefficients of multiple physiological parameters and the user's breathing pattern, a physiological correlation analysis result is obtained.

[0012] As a further solution of the present invention, the step of acquiring abnormal breathing data is specifically as follows: Based on the physiological correlation analysis results, the respiratory data is preprocessed, including filtering and denoising, and the preprocessed data is used for respiratory rhythm analysis, identification of irregular and abnormal behaviors, and combined with time information to obtain time series data; Based on the time series data, the data is standardized by the formula: ; Calculate the standard score for each time point , get abnormal respiratory events, among which, is the observed value, indicating the time point The specific respiratory parameters measured, is the sample mean, which represents the average level of the collected data. is the sample standard deviation, which indicates the degree of variation of the data. For time point, is the standard score, which is compared with the anomaly detection threshold to detect anomalies in the data; Based on the abnormal breathing events, the causes of abnormal breathing are identified and classified, including apnea and irregular rhythm, and abnormal breathing identification results are generated.

[0013] As a further solution of the present invention, the steps of obtaining the respiratory health status are specifically as follows: Based on the abnormal breathing recognition result, identify the target user's respiratory pause times and irregular rhythm events, and obtain breathing parameter data in combination with the user's real-time vital capacity and airway resistance data; Based on the respiratory parameter data, the formula: ; Calculate the user's respiratory health status index to obtain respiratory health status assessment information, where: Indicates the number of recorded apnea events, Indicates the number of rhythmic irregularity events, Indicates the depth of breathing, used to assess the amount of air taken in each breath. Respiratory rate, which is the number of breaths per minute. represents the baseline adjustment factor, represents the weight of apnea events, represents the weight of the rhythm irregularity event, represents the weight of breathing depth, represents the weight of the respiratory rate, It is a calculated respiratory health status index that reflects the user's overall respiratory health status and determines the health of the respiratory function based on the value.

[0014] As a further solution of the present invention, the step of obtaining the health status prediction value is specifically as follows: Based on the respiratory health status assessment information, a time series data set is constructed in combination with the timestamp, using the formula: ; Calculate the predicted value of health status and obtain the time series analysis results, where: Indicates at a point in time The respiratory health index, is the constant term of the model, representing the initial health status baseline, is the autoregression coefficient, indicating the The impact of long-term health status on current health index, is the moving average coefficient, used to adjust the The impact of the period error term, is a white noise error term, representing the time point The random perturbation of It is Health status index at a point in time, It is The error term at the time point, and are the orders of the autoregressive and moving average models, respectively; Based on the time series analysis results, by comparing and analyzing the health status evaluation values ​​at multiple time points, the change pattern of the health status is identified and the health status is evaluated.

[0015] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by analyzing the chest pressure waveform data, accurate extraction of respiratory parameters and evaluation of periodic changes in breathing are achieved, the user's breathing pattern is accurately identified, physiological parameters are collected and the relationship with the breathing pattern is analyzed, the impact of various physiological factors on respiratory health is revealed, and the dynamic monitoring capability of respiratory health is enhanced. Combined with the detection and identification of abnormal respiratory parameters, the causes of abnormal breathing can be identified and classified, helping medical professionals to formulate treatment plans and health management strategies, improving diagnostic efficiency, reducing misdiagnosis rate, and combined with continuous trend analysis, providing strong support for the management of various chronic diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a system flow chart of the present invention; Figure 2 A flow chart for calculating respiratory rate for the present invention; Figure 3 A flow chart for calculating the breathing depth of the present invention; Figure 4 A flow chart for obtaining mutual influence relationships for the present invention; Figure 5 A flow chart for analyzing breathing efficiency for the present invention; Figure 6 A flow chart of detecting abnormal breathing data according to the present invention; Figure 7 A flow chart for assessing respiratory health status for the present invention; Figure 8 Flow chart for calculating health status prediction value for the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with 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 intended to limit the present invention.

[0018] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are 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 therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0019] See also Figure 1 , the respiratory health assessment system based on big data includes: The breathing parameter analysis module analyzes the target pressure waveform data based on the chest pressure waveform data, extracts multiple breathing parameters, identifies the breathing patterns of multiple users, including breathing frequency and breathing depth, evaluates the periodic changes of breathing, and obtains the breathing pattern characteristic information; The interactive relationship evaluation module collects multiple physiological parameters of users in real time based on the characteristic information of breathing patterns, analyzes the mutual influence relationship between multiple physiological parameters and breathing patterns, including heart rate, blood pressure, blood oxygen saturation, vital capacity, and airway resistance, evaluates the breathing efficiency of multiple users, and obtains physiological correlation analysis results; Based on the results of physiological correlation analysis, the respiratory anomaly detection module monitors and identifies abnormal changes in respiratory parameters, including respiratory rhythm, frequency, and depth, through time series analysis, identifies the causes of abnormalities and classifies respiratory anomalies, including apnea and irregular rhythm, and generates abnormal respiratory identification results; The respiratory condition evaluation module is based on the abnormal breathing recognition results. It analyzes the user's abnormal breathing and evaluates the user's respiratory health status, including vital capacity and airway resistance. It also uses time series analysis to calculate the predicted values ​​at multiple time points, evaluate the changing trend of respiratory health, and evaluate the health status.

[0020] The breathing pattern characteristic information includes breathing frequency parameters, breathing depth parameters, and breathing rhythm parameters. The physiological correlation analysis results are specifically heart rate data correlation information, blood pressure data correlation coefficient, and blood oxygen saturation data correlation analysis results. The abnormal breathing identification results include abnormal breathing rhythm information, abnormal breathing frequency information, and abnormal breathing depth detection data.

[0021] See also Figure 2 The specific steps for obtaining the respiratory frequency are as follows: Based on the chest pressure waveform data, by identifying the start and end time points of each breath, the time interval of each respiratory cycle is calculated, using the formula: Calculate the time interval of each breathing cycle and obtain the time interval array of each breathing, where: is the time interval of the i-th respiratory cycle, is the end time of the i-th breath, is the start time of the i-th breath.

[0022] formula: ; Parameter meaning and acquisition method: : The time interval between each breath, calculated by the difference between the end time and the start time; : is the end time of the i-th breath, which is identified by the falling edge of the chest pressure waveform; : is the start time of the i-th breath, which is identified by the rising edge of the chest pressure waveform; Calculation example: Set a breath to start at 0 seconds and end at 2 seconds; Calculate the breathing time interval: ; The calculated results The target breathing interval is 2 seconds, which is used to calculate the average breathing cycle interval.

[0023] Based on the time interval array, by the formula: Calculate the respiratory rate, where is the respiratory rate, For Array of calculated average breathing time intervals.

[0024] Parameter meaning and acquisition method: : The number of breaths per minute, measured by The reciprocal of is multiplied by 60; : The average value of all breathing time intervals, given by The values ​​of the array are averaged; Calculation example: Set the interval time to , calculate the average time interval: ; Calculate respiratory rate: ; Calculated Breaths / minute indicates an average of 30 breaths per minute, reflecting the typical respiratory rate of a normal adult at rest. This calculation helps assess respiratory health.

[0025] See also Figure 3 , the specific steps for obtaining breathing depth are: Based on the respiratory rate data, measure the amplitude of the waveform in the chest pressure waveform, using the formula: ; Calculate the depth of each breath and obtain the breathing depth data, where For the The depth of each breath, For the The peak pressure of each breath, For the Baseline pressure for each breath, is the index of the number of breaths considered; Based on the breathing depth data and combined with the target user's breathing frequency data, the periodic changes of breathing are evaluated to obtain the breathing pattern characteristic information.

[0026] Parameter meaning and acquisition method: : The depth of each breath, calculated by the difference between peak pressure and baseline pressure.

[0027] : No. The peak pressure of each breath is identified by the highest point in the chest pressure waveform data.

[0028] : No. The baseline pressure of a breath is usually the stable pressure value before the start of the respiratory cycle, which is obtained by identifying the stable low point in the chest pressure waveform data.

[0029] Calculation example: The peak and baseline pressures of the three respiratory events in the monitoring data are set as follows: First breath: peak pressure is 20 cmH2O, baseline pressure is 5 cmH2O.

[0030] Second breath: peak pressure is 21cmH2O, baseline pressure is 6cmH2O; The third breath: peak pressure is 19cmH2O, baseline pressure is 4cmH2O; Calculate the first time: ; Calculate the second time: ; Calculate the third time: ; The results showed that the depth of each breath was 15cmH2O, which was used to assess the adequacy of breathing and potential physiological needs. The depth of breathing was quantified through a calculation process to help medical professionals and health monitoring systems assess individual breathing patterns.

[0031] See also Figure 4 , the steps for obtaining the mutual influence relationship are as follows: Based on the characteristic information of breathing patterns, a variety of physiological monitoring devices are used to collect the user's heart rate, blood pressure, blood oxygen saturation, vital capacity, and airway resistance in real time, and combined with the breathing frequency and breathing depth to build a physiological parameter data set; Based on the physiological parameter data set, the correlation analysis between physiological parameters and breathing patterns was performed to evaluate the dynamic relationship between cardiovascular health status and breathing patterns, using the formula: ; The correlation coefficient between physiological parameters and breathing patterns is calculated to obtain the mutual influence relationship between physiological parameters and breathing patterns, where: Indicates the measured values ​​of physiological parameters, including heart rate, blood pressure, blood oxygen saturation, vital capacity, airway resistance, Represents measurements of breathing patterns, including breathing rate, breathing depth, is the average value of the physiological parameter measurement, is the average value of the breathing pattern measurements, is the correlation coefficient between heart rate and respiratory rate, which quantifies the degree of linear relationship between the two.

[0032] formula: ; Parameter meaning: : It is the measurement value of physiological parameters, including heart rate, blood pressure, blood oxygen saturation, vital capacity, and airway resistance, which are collected by physiological monitoring equipment; : Represents the measurement value of breathing pattern, including breathing rate and breathing depth, obtained by analyzing chest pressure; : The average value of the target physiological parameter measurement; : The average value of the target breathing pattern measurements; : The correlation coefficient between heart rate and respiratory rate, used to quantify the degree of linear relationship between the two; Calculation example: The physiological parameter considered is heart rate, the breathing pattern is breathing frequency, and the heart rate of the target user over a period of time is , the respiratory rate is , the average values ​​of heart rate and respiratory rate are, , ; calculate and Correlation between: ; The calculation results revealed a positive correlation between heart rate and respiratory rate. The analysis process is very important for understanding the interaction between physiological activities and breathing patterns.

[0033] See also Figure 5 The specific steps for obtaining respiratory efficiency are as follows: Based on the mutual influence relationship, the respiratory efficiency is calculated and analyzed according to the respiratory depth, respiratory rate and blood oxygen saturation data, and the formula is: ; Calculating breathing efficiency ,in, For breathing efficiency, For breathing depth, is the respiratory rate, is blood oxygen saturation; Based on breathing efficiency, the correlation coefficients of multiple physiological parameters and user breathing patterns are combined to obtain physiological correlation analysis results.

[0034] formula: ; Parameter meaning and acquisition method: : Respiratory depth, obtained by analyzing chest pressure, used to indicate the amount of air inhaled per breath; : Respiratory rate, obtained by analyzing chest pressure, indicating the number of breaths per minute; : Blood oxygen saturation, obtained by pulse oximetry, indicates the oxygen saturation in the blood; Calculation example: Set the target user's breathing depth for ml, respiratory rate for bpm, blood oxygen saturation level for %; Calculate breathing efficiency: ; ; The calculated results Indicates the user's respiratory efficiency. The value is used to evaluate the optimized breathing state. The calculation process is measured by considering the product of breathing depth, frequency and oxygenation level to evaluate the patient's respiratory efficiency and help medical professionals evaluate the patient's respiratory efficiency in different health conditions.

[0035] See also Figure 6 ,The specific steps for obtaining abnormal breathing data are: Based on the results of physiological correlation analysis, the respiratory data is preprocessed, including filtering and denoising. The preprocessed data is used for respiratory rhythm analysis, identification of irregular and abnormal behaviors, and combined with time information to obtain time series data; Based on time series data, the data is standardized through the formula: ; Calculate the standard score for each time point , get abnormal respiratory events, among which, is the observed value, indicating the time point The specific respiratory parameters measured, is the sample mean, which represents the average level of the collected data. is the sample standard deviation, which indicates the degree of variation of the data. For time point, is the standard score, which is compared with the anomaly detection threshold to detect anomalies in the data; Based on abnormal breathing events, the causes of abnormal breathing are identified and classified, including apnea and irregular rhythm, and abnormal breathing identification results are generated.

[0036] formula: ; Parameter meaning and acquisition method: : is the time point The observed values ​​are obtained by analyzing the fluctuation of chest pressure, including respiratory rate and respiratory depth; : is the sample mean, which is calculated by calculating all The average value of is obtained; : is the sample standard deviation, calculated by and The square root of the mean of the sum of squared deviations is obtained; Calculation example: Assume that the respiratory rate data collected within one hour is [16, 18, 15, 20, 19]; calculate :; ; calculate :; ; for ,calculate : ; The calculated result of 1.294 indicates that the respiratory rate of this data point deviates from the average level by 1.294 standard deviations. The result is used to identify abnormal respiratory events and evaluate the abnormality of respiratory parameters through real-time data monitoring.

[0037] See also Figure 7 , the specific steps for obtaining respiratory health status are: Based on the abnormal breathing recognition results, the target user's respiratory pauses and irregular rhythm events are identified, and the breathing parameter data is obtained by combining the user's real-time vital capacity and airway resistance data; Based on the respiratory parameter data, the formula: ; Calculate the user's respiratory health status index to obtain respiratory health status assessment information, where: Indicates the number of recorded apnea events, Indicates the number of rhythmic irregularity events, Indicates the depth of breathing, used to assess the amount of air taken in each breath. Respiratory rate, which is the number of breaths per minute. represents the baseline adjustment factor, represents the weight of apnea events, represents the weight of the rhythm irregularity event, represents the weight of breathing depth, represents the weight of the respiratory rate, It is a calculated respiratory health status index that reflects the user's overall respiratory health status and determines the health of the respiratory function based on the value.

[0038] formula: ; Parameter definition and acquisition method: : The number of apnea events, recorded in real time during sleep at night by a respiratory monitoring device; : The number of rhythm irregularity events, obtained by continuous heart rate and respiration monitoring; : The average depth of each breath, as measured by a lung function testing device; : Respiratory rate, i.e. the number of breaths in one minute, obtained through a respiratory rate monitoring device; : Adjustment coefficients set based on clinical research data and patient statistical analysis; Calculation example: Setting the number of apnea events for a target user , irregular rhythm events , average breathing depth Rise, respiratory rate times / minute, adjustment factor ; The results show that the target user's respiratory health index The index is 7.94, which is a low index, indicating that the user has respiratory health problems and needs medical attention. The value reflects the user's respiratory apnea frequency, regularity of rhythm, breathing depth, and frequency, and is used for clinical evaluation and monitoring.

[0039] See also Figure 8 , the specific steps for obtaining the health status prediction value are: Based on the respiratory health status assessment information, the time series data set is constructed in combination with the timestamp, using the formula: ; Calculate the predicted value of health status and obtain the time series analysis results, where: Indicates at a point in time Respiratory health index, is the constant term of the model, representing the initial health status baseline, is the autoregression coefficient, indicating the The impact of long-term health status on current health index, is the moving average coefficient, used to adjust the The impact of the period error term, is a white noise error term, representing the time point The random perturbation of It is Health status index at a point in time, It is The error term at the time point, and are the orders of the autoregressive and moving average models, respectively; Based on the results of time series analysis, by comparing and analyzing the health status assessment values ​​at multiple time points, the changing pattern of health status is identified and the health status is evaluated.

[0040] formula: ; Parameter explanation and acquisition method: : At time point A respiratory health index, obtained directly from the patient's health record; : Constant term, which is automatically calculated by statistical software during the model fitting process and represents the baseline level of the model; : Autoregressive parameter, indicating the The impact of the previous health status on the current health index is calculated through historical data during the model fitting process; : Moving average parameter, used to adjust the The impact of the period error term is also calculated using historical data during the model fitting process; : White noise error term, representing random disturbance, usually assumed to be normally distributed with mean 0 and certain standard deviation; : No. The health status index at a point in time is obtained from historical health data; : No. The error term at the time point is generated by the model calculation; and is the order of the model, determined by the autocorrelation function and partial autocorrelation function plots of the data; Calculation example: Set data points , , , , , , , ; calculate : ; The results showed that at time The predicted respiratory health index was 7.7, indicating that the respiratory health status had improved compared with the health index at the previous two time points. The results helped medical professionals assess the patient's health improvement trend and adjust treatment strategies.

[0041] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A respiratory health assessment system based on big data, characterized in that: The system comprises: The breathing parameter analysis module analyzes the target pressure waveform data based on the chest pressure waveform data, extracts multiple breathing parameters, identifies the breathing patterns of multiple users, including breathing frequency and breathing depth, evaluates the periodic changes of breathing, and obtains the breathing pattern characteristic information; The interactive relationship evaluation module collects multiple physiological parameters of the user in real time based on the breathing pattern characteristic information, analyzes the mutual influence relationship between the multiple physiological parameters and the breathing pattern, including heart rate, blood pressure, blood oxygen saturation, vital capacity, and airway resistance, evaluates the breathing efficiency of multiple users, and obtains physiological correlation analysis results; Based on the physiological correlation analysis results, the breathing abnormality detection module monitors and identifies abnormal changes in breathing parameters, including breathing rhythm, frequency, and depth, through time series analysis, identifies the causes of abnormalities and classifies breathing abnormalities, including apnea and irregular rhythm, and generates abnormal breathing identification results; The respiratory condition evaluation module analyzes the abnormal breathing of the user based on the abnormal breathing results to evaluate the user's respiratory health status, including vital capacity and airway resistance, and uses time series analysis to calculate the predicted values ​​at multiple time points, evaluate the changing trend of respiratory health, and evaluate the health status.

2. The respiratory health assessment system based on big data according to claim 1, characterized in that: The breathing pattern characteristic information includes breathing frequency parameters, breathing depth parameters, and breathing rhythm parameters. The physiological association analysis results are specifically heart rate data association information, blood pressure data association coefficient, and blood oxygen saturation data association analysis results. The abnormal breathing identification results include abnormal breathing rhythm information, abnormal breathing frequency information, and abnormal breathing depth detection data.

3. The respiratory health assessment system based on big data according to claim 1, characterized in that: The steps for obtaining the respiratory frequency are specifically as follows: Based on the chest pressure waveform data, by identifying the start and end time points of each breath, the time interval of each breathing cycle is calculated using the formula: ; Calculate the time interval of each breathing cycle and obtain the time interval array of each breathing, where: is the time interval of the i-th respiratory cycle, is the end time of the i-th breath, is the start time of the i-th breath; Based on the time interval array, by the formula: ; Calculate and get the respiratory rate, where is the respiratory rate, For Array of calculated average breathing time intervals.

4. The respiratory health assessment system based on big data according to claim 3 is characterized in that: The steps for obtaining the breathing depth are specifically as follows: Based on the breathing rate, the amplitude of the waveform in the thoracic pressure waveform is measured, using the formula: ; Calculate the depth of each breath and obtain the breathing depth data, where For the The depth of each breath, For the The peak pressure of each breath, For the Baseline pressure for each breath, is the index of the number of breaths considered; Based on the breathing depth data and in combination with the target user's breathing frequency data, the periodic changes of breathing are evaluated to obtain breathing pattern characteristic information.

5. The respiratory health assessment system based on big data according to claim 1, characterized in that: The steps for obtaining the mutual influence relationship are specifically as follows: Based on the respiratory pattern characteristic information, a variety of physiological monitoring devices are used to collect the user's heart rate, blood pressure, blood oxygen saturation, vital capacity, and airway resistance in real time, and combined with the respiratory frequency and breathing depth to construct a physiological parameter data set; Based on the physiological parameter data set, correlation analysis between physiological parameters and breathing patterns was performed to evaluate the dynamic relationship between cardiovascular health status and breathing patterns, using the formula: ; The correlation coefficient between physiological parameters and breathing patterns is calculated to obtain the mutual influence relationship between physiological parameters and breathing patterns, where: Represents the measured value of a physiological parameter, represents a measurement of the breathing pattern, is the average value of the physiological parameter measurement, is the average value of the breathing pattern measurements, is the correlation coefficient between heart rate and respiratory rate.

6. The respiratory health assessment system based on big data according to claim 5, characterized in that: The steps for obtaining the respiratory efficiency are specifically as follows: Based on the mutual influence relationship, the respiratory efficiency is calculated and analyzed according to the respiratory depth, respiratory rate and blood oxygen saturation data, through the formula: ; Calculating breathing efficiency ,in, For breathing efficiency, For breathing depth, is the respiratory rate, is blood oxygen saturation; Based on the breathing efficiency, combined with correlation coefficients of multiple physiological parameters and the user's breathing pattern, a physiological correlation analysis result is obtained.

7. The respiratory health assessment system based on big data according to claim 1, characterized in that: The steps for acquiring the abnormal breathing data are specifically as follows: Based on the physiological correlation analysis results, the respiratory data is preprocessed, including filtering and denoising, and the preprocessed data is used for respiratory rhythm analysis, identification of irregular and abnormal behaviors, and combined with time information to obtain time series data; Based on the time series data, the data is standardized by the formula: ; Calculate the standard score for each time point , get abnormal respiratory events, among which, is the observed value, is the sample mean, is the sample standard deviation, For time point, is the standard score, which is compared with the anomaly detection threshold to detect anomalies in the data; Based on the abnormal breathing events, the causes of abnormal breathing are identified and classified, including apnea and irregular rhythm, and abnormal breathing identification results are generated.

8. The respiratory health assessment system based on big data according to claim 1, characterized in that: The steps for obtaining the respiratory health status are specifically as follows: Based on the abnormal breathing recognition result, identify the target user's respiratory pause times and irregular rhythm events, and obtain breathing parameter data in combination with the user's real-time vital capacity and airway resistance data; Based on the respiratory parameter data, the formula: ; Calculate the user's respiratory health status index to obtain respiratory health status assessment information, where: Indicates the number of recorded apnea events, Indicates the number of rhythmic irregularity events, Indicates the depth of breathing, Respiratory rate, represents the baseline adjustment factor, represents the weight of apnea events, represents the weight of the rhythm irregularity event, represents the weight of breathing depth, represents the weight of the respiratory rate, is the calculated respiratory health status index.

9. The respiratory health assessment system based on big data according to claim 8, characterized in that: The steps for obtaining the health status prediction value are specifically as follows: Based on the respiratory health status assessment information, a time series data set is constructed in combination with the timestamp, using the formula: ; Calculate the predicted value of health status and obtain the time series analysis results, where: Indicates at a point in time The respiratory health index, is the constant term of the model, is the autoregression coefficient, indicating the The impact of long-term health status on current health index, is the moving average coefficient, used to adjust the The impact of the period error term, is a white noise error term, representing the time point The random perturbation of It is Health status index at a point in time, It is The error term at the time point, and are the orders of the autoregressive and moving average models, respectively; Based on the time series analysis results, by comparing and analyzing the health status assessment values ​​at multiple time points, the change pattern of the health status is identified and the health status is assessed.

Images