Respiratory disease risk assessment system and method

Abstract

The invention relates to the field of respiratory disease risk assessment, in particular to a respiratory disease risk assessment system and method. Comprising the steps that physiological data and external data are collected, standardization processing is conducted on the collected physiological data and external data, feature extraction is conducted on the basis of the physiological data and external data obtained after standardization processing through a dynamic interaction feature extraction algorithm, and comprehensive feature values are generated; and calculating a respiratory disease risk index based on the comprehensive characteristic value, dividing risk levels based on the respiratory disease risk index, and generating an assessment report. The technical problem that traditional respiratory disease risk assessment mostly depends on static data, neglects changes of individuals under different life styles and environment conditions, and consequently, assessment results lack personalized adaptability and clinical significance is solved.

Description

Technical Field

[0001] The present invention relates to the field of respiratory disease risk assessment, and particularly to a respiratory disease risk assessment system and method. Background Art

[0002] With the intensification of global environmental changes, the incidence of respiratory diseases has been increasing year by year. Especially chronic obstructive pulmonary disease (COPD), asthma, and other respiratory diseases caused by air pollution not only affect the quality of life of patients but also bring a huge burden to global public health. Therefore, developing a respiratory disease risk assessment system to identify high-risk individuals as early as possible and provide personalized health interventions and treatments has become an important research direction in the current medical and health field.

[0003] Existing risk assessment methods mainly rely on clinical data. Analyzing a single data source often fails to comprehensively reflect the true risks of patients. Moreover, the health status, lifestyle, disease history, etc. of each individual are different, and the traditional "one-size-fits-all" treatment method is difficult to achieve the best treatment effect. The research and application of a respiratory disease risk assessment system not only helps to improve the early diagnosis rate of diseases but also plays an important role in reducing the disease burden and medical costs. With the continuous development of big data technology, artificial intelligence, and the Internet of Things, future risk assessment systems will be more intelligent, precise, and personalized, capable of real-time monitoring of patients' health status and providing targeted intervention plans, providing strong support for the prevention, diagnosis, and treatment of global respiratory diseases, and contributing to the improvement of public health.

[0004] However, the above-mentioned existing respiratory disease risk assessment system and method still have technical problems such as difficulties in long-term monitoring of chronic diseases, insufficient personalized assessment, and insufficient periodicity and frequency of data monitoring. Summary of the Invention

[0005] The present invention provides a respiratory disease risk assessment system and method to solve the technical problem that traditional respiratory disease risk assessments mostly rely on static data, ignoring the changes of individuals under different lifestyles and environmental conditions, resulting in the lack of personalized adaptability and clinical significance of assessment results.

[0006] The respiratory disease risk assessment system and method of the present invention specifically include the following technical solutions: A respiratory disease risk assessment method includes the following steps: S1. Collect physiological data and external data, respectively perform standardized processing on the collected physiological data and external data, and based on the standardized physiological data and external data, use a dynamic interaction feature extraction algorithm to extract features and generate a comprehensive feature value; S2. Calculate the respiratory disease risk index based on the comprehensive eigenvalue, divide the risk levels based on the respiratory disease risk index, and generate an assessment report.

[0007] Preferably, the S1 specifically includes: In the implementation process of the dynamic interaction feature extraction algorithm, calculate the standard deviation within the time window for each standardized physiological data index, subtract the standard deviation of the corresponding physiological data index of the standard normal healthy population from the standard deviation, and divide by the standard deviation of the corresponding physiological data index of the standard normal healthy population to generate a normalized variability component, reflecting the fluctuation deviation of the physiological data index relative to the healthy population.

[0008] Preferably, the S1 specifically includes: In the implementation process of the dynamic interaction feature extraction algorithm, capture the short-term interaction effect between the standardized physiological data index and the standardized external data index by calculating the dynamic interaction intensity factor.

[0009] Preferably, the S1 specifically includes: In the calculation process of the dynamic interaction intensity factor, calculate the absolute value of the deviation of the standardized physiological data index and the standardized external data index on the current day from the mean within the time window respectively, multiply them to get the numerator part, and at the same time calculate the standard deviation of the standardized physiological data index and the standardized external data index within the time window, multiply them as the denominator, and generate a normalized interaction intensity.

[0010] Preferably, the S1 specifically includes: In the calculation process of the dynamic interaction intensity factor, introduce a time weighting factor and combine it with the normalized interaction intensity to generate a dynamic interaction intensity factor.

[0011] Preferably, the S1 specifically includes: Generate a comprehensive eigenvalue by linearly combining the normalized variability component and the dynamic interaction intensity factor with weights.

[0012] Preferably, the S2 specifically includes: Perform a weighted linear combination on the comprehensive eigenvalue to calculate the respiratory disease risk index; based on the respiratory disease risk index, divide the risks into three levels: high, medium, and low.

[0013] Preferably, the S2 specifically includes: Integrate the respiratory disease risk index, risk levels, and the clinical significance and intervention suggestions given according to the risk levels into an assessment report, and display it in the form of text and charts through the user terminal.

[0014] A respiratory disease risk assessment system, comprising the following parts: A data acquisition module, a data preprocessing module, a feature extraction module, a risk assessment module, and an assessment report generation module; Data acquisition module: Collect physiological data and external data, and output the collected physiological data and external data to the data preprocessing module; Data preprocessing module: Perform standardization processing on the physiological data and external data collected by the data acquisition module respectively, to obtain the standardized physiological data and external data, and output the standardized physiological data and external data to the feature extraction module; Feature extraction module: Based on the standardized physiological data and external data of the data preprocessing module, adopt a dynamic interaction feature extraction algorithm to extract features, generate a comprehensive feature value, and output the comprehensive feature value to the risk assessment module; Risk assessment module: Calculate the respiratory disease risk index based on the comprehensive feature value of the feature extraction module, divide the risk level, and output the respiratory disease risk index and risk level to the assessment report generation module; Assessment report generation module: Integrate the respiratory disease risk index, risk level of the risk assessment module, as well as the clinical significance and intervention suggestions given according to the risk level into an assessment report, and display it in text and chart forms through a user terminal.

[0015] The beneficial effects of the technical solution of the present invention are: 1. By collecting physiological data and external data through wearable devices and environmental sensors, and performing standardization processing, the high quality and consistency of the data are ensured.

[0016] 2. By adopting a dynamic interaction feature extraction algorithm, it can effectively capture the short-term interaction effects and long-term change trends between the standardized physiological data and external data. By performing weighted combination on the normalized variability component and the dynamic interaction intensity factor, a comprehensive feature value is generated, which can reflect the dynamic changes of individuals in terms of chronic respiratory disease risk. It not only improves the timeliness of the data, but also enhances the personalized adaptation ability to the individual's health status, can reflect the short-term effects of different environmental exposures and physiological fluctuations, and thus improves the accuracy of disease risk assessment.

[0017] 3. Based on the comprehensive feature value, a weighted linear model is used to calculate the respiratory disease risk index, which can comprehensively consider the complex interactions between multi-dimensional data, quantify the respiratory disease risk of individuals, make the risk level of each user more accurate, and facilitate individualized health intervention and management.

[0018] 4. The calculation results of the respiratory disease risk index clearly divide the respiratory disease risk into three risk levels: low, medium, and high. Through accurate respiratory disease risk assessment, users can understand their health status and potential risks in real time, thereby enhancing their attention to health management. Combined with the assessment report in the form of a chart, users can clearly see the changing trend of their health status, further improving their initiative in disease prevention and lifestyle adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a structural diagram of a respiratory disease risk assessment system according to the present invention; Figure 2 It is a flowchart of a respiratory disease risk assessment method according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0020] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0022] The following specifically describes the specific solutions of a respiratory disease risk assessment system and method provided by the present invention in conjunction with the accompanying drawings.

[0023] Referring to the attached Figure 1 , which shows a structural diagram of a respiratory disease risk assessment system provided by an embodiment of the present invention. The system includes the following parts: A data acquisition module, a data preprocessing module, a feature extraction module, a risk assessment module, and an assessment report generation module; Data acquisition module: Collect physiological data and external data through wearable devices, environmental sensors, and user terminals, and output the collected physiological data and external data to the data preprocessing module; Data preprocessing module: Perform standardization processing on the physiological data and external data collected by the data acquisition module respectively to obtain the standardized physiological data and external data, and output the standardized physiological data and external data to the feature extraction module; Feature extraction module: Based on the physiological data and external data after the normalization process of the data preprocessing module, it extracts features using the dynamic interaction feature extraction algorithm, generates a comprehensive feature value, and outputs the comprehensive feature value to the risk assessment module; Risk assessment module: Based on the comprehensive feature value of the feature extraction module, it calculates the respiratory disease risk index, divides the risk level, and outputs the respiratory disease risk index and risk level to the assessment report generation module; Assessment report generation module: It integrates the respiratory disease risk index, risk level of the risk assessment module, as well as the clinical significance and intervention suggestions given according to the risk level into an assessment report, and displays it in the form of text and charts through a user terminal (such as a mobile application).

[0024] Refer to the appendix Figure 2 , which shows a flowchart of a respiratory disease risk assessment method provided by an embodiment of the present invention. The method includes the following steps: S1. Collect physiological data and external data, respectively perform normalization processing on the collected physiological data and external data, and based on the normalized physiological data and external data, use the dynamic interaction feature extraction algorithm to extract features and generate a comprehensive feature value; Collect physiological data and external data through wearable devices, environmental sensors, and user terminals to generate daily time series data for subsequent respiratory disease risk assessment. Taking days as the time granularity can ensure that the data collection frequency is suitable for the long-term monitoring of chronic diseases and reduce device power consumption and storage requirements; the physiological data includes heart rate, respiratory rate, blood oxygen saturation, etc.; the external data includes daily smoking duration, sleep duration, air quality index, etc.; Based on medical or environmental standards, determine the minimum and maximum values of each data index, and respectively perform normalization processing on the collected physiological data and external data to generate normalized physiological data and external data; Based on the normalized physiological data and external data, use the dynamic interaction feature extraction algorithm to extract features and generate a comprehensive feature value, which is used for the long-term trend of the normalized physiological data and the dynamic interaction effect with the normalized external data, reflecting the risk of chronic respiratory diseases; The dynamic interaction feature extraction algorithm calculates the standard deviation within the time window for each normalized physiological data index to reflect the short-term fluctuation situation. Subtract the standard deviation of the corresponding physiological data index of the standard normal healthy population from the standard deviation and divide it by the standard deviation of the corresponding physiological data index of the standard normal healthy population to generate a normalized variability component, which reflects the fluctuation deviation of the physiological data index relative to the healthy population. For example, abnormal heart rate variability may be related to the progression of chronic obstructive pulmonary disease; The dynamic interaction feature extraction algorithm calculates the dynamic interaction intensity factor to capture the short-term interaction effect between the physiological data indicators after normalization and the external data indicators after normalization. Specifically, it calculates the absolute value of the deviation of the physiological data indicators after normalization and the external data indicators after normalization on the current day from the mean value within the time window, multiplies them to obtain the numerator part, and at the same time calculates the standard deviation of the physiological data indicators after normalization and the external data indicators after normalization within the time window, multiplies them as the denominator to generate a normalized interaction intensity. Further, a time weighting factor is introduced, and an exponential decay function is used to assign higher weights to the data closer to the current time, emphasizing the importance of recent data, enhancing personalized adaptability, and combining the time weighting factor with the normalized interaction intensity to generate a dynamic interaction intensity factor, which ranges from 0 to 1; The normalized variability component and the dynamic interaction intensity factor are combined through a weighted linear combination to generate a comprehensive eigenvalue; further, a weight constraint is imposed: the sum of the variability weight of the physiological data indicators after normalization and the dynamic interaction intensity weight between the physiological data indicators after normalization and the external data indicators is 1, that is ; The calculation formula for the comprehensive eigenvalue is: ; where represents the comprehensive eigenvalue of the th physiological data indicator after normalization on the th day and the th external data indicator; represents the variability weight of the th physiological data indicator after normalization, and the value range is , which is optimized by a machine learning model (such as a neural network) to meet the weight constraint; represents the th day time window the standard deviation of the th physiological data indicator after normalization within; represents the standard deviation of the th physiological data indicator of the standard normal healthy population, which is used as a benchmark to reflect the deviation of the individual physiological index variability from the healthy population; represents the dynamic interaction intensity weight between the th physiological data indicator and the th external data indicator after normalization, which reflects the importance of a specific interaction, and the value range is , which is optimized by a machine learning model (such as a neural network) to meet the weight constraint; represents the mean value of the dynamic interaction intensity factor within the time window; represents the time window length; represents the th physiological data index after standardization on the th day and the th external data index, and the calculation formula of the dynamic interaction intensity factor is as follows: ; where represents the th physiological data index after standardization on the th day; represents the th physiological data index after standardization within the time window on the th day; represents the th physiological data index after standardization on the th day and the absolute deviation between the th physiological data index after standardization within the time window; represents the standard deviation of the physiological data index after standardization within the time window; represents the th external data index after standardization on the th day; represents the th external data index after standardization within the time window on the th day; represents the th external data index after standardization on the th day and the absolute deviation between the th external data index after standardization within the time window; represents the standard deviation of the external data index after standardization within the time window; represents the time weighting factor, which assigns higher weights to data closer to the current time through an exponential decay function, emphasizing the dynamic interaction intensity of the data on the current day. The calculation formula is: , and the value range is ; represents the decay parameter of the time weighting factor, which is used to control the decay speed of the time weighting, and the value range is ; Using the standard normal healthy population standard deviation to normalize variability can accurately reflect individual health deviations, enhance clinical significance, introduce dynamic interaction intensity factors, capture the short-term effects of recent environmental exposures, adapt to individual lifestyle and environmental changes, improve personalized assessment capabilities, simplify the calculation process of comprehensive eigenvalue through linear combination and weight constraints, ensure that the range of comprehensive eigenvalue is controllable, and is easy to clinically interpret; S2. Calculate the respiratory disease risk index based on the comprehensive eigenvalue, divide the risk levels based on the respiratory disease risk index, and generate an assessment report. Based on the comprehensive eigenvalue, use the existing weighted linear model to calculate the respiratory disease risk index. The formula is as follows: ; Where, represents the respiratory disease risk index on the th day, quantifying the risk of chronic respiratory diseases of an individual on the th day. The higher the respiratory disease risk index, the greater the risk, which is used to guide intervention. represents the number of physiological data index items; represents the number of external data index items; represents the weight coefficient of the comprehensive eigenvalue, which is used to adjust the contribution of each comprehensive eigenvalue in the respiratory disease risk index, reflecting the impact of the interaction of different physiological-external data indicators on the respiratory disease risk. The value range is , and is optimized through a machine learning model (such as a neural network). According to the respiratory disease risk index, the risk is divided into three levels, including: low risk, that is, the respiratory disease risk index is less than 0.3; medium risk, that is, the respiratory disease risk index is between 0.3 and 0.7; high risk, that is, the respiratory disease risk index is greater than or equal to 0.7. The following clinical significance and intervention suggestions are given based on the risk level: low risk indicates that the respiratory system function is normal and the impact of external factors (such as smoking or air pollution) is small, and it is recommended to maintain a healthy lifestyle; medium risk indicates that there is a certain disease risk, which may be due to abnormal physiological indicators or the accumulation of external factors, and it is recommended to reduce smoking, optimize sleep and consult a doctor; high risk indicates a significant risk of disease deterioration, and it is recommended to seek medical attention immediately, quit smoking and avoid polluted environments. Integrate the respiratory disease risk index, risk level, and the clinical significance and intervention suggestions given according to the risk level into an assessment report, and display it in the form of text and charts through a user terminal (such as a mobile application). By generating an accurate respiratory disease risk index, dividing clear low, medium, and high risk levels, providing personalized clinical significance and intervention suggestions, it can improve the user's awareness of their health status and coping ability.

[0025] In summary, a respiratory disease risk assessment system and method are completed.

[0026] The order of the invention embodiments is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be beneficial.

[0027] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

[0028] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for assessing the risk of respiratory diseases, characterized in that, It includes the following steps: S1. Collect physiological data and external data, perform standardization processing on the collected physiological data and external data respectively. Based on the standardized physiological data and external data, use a dynamic interaction feature extraction algorithm to extract features and generate a comprehensive feature value; S2. Based on the comprehensive feature value, calculate the respiratory disease risk index, divide the risk levels based on the respiratory disease risk index, and generate an evaluation report.

2. The method for assessing the risk of respiratory diseases according to claim 1, wherein The specific content of S1 includes: During the implementation of the dynamic interaction feature extraction algorithm, calculate the standard deviation within the time window for each standardized physiological data index, subtract the standard deviation of the corresponding physiological data index of the standard normal healthy population from the standard deviation and divide it by the standard deviation of the corresponding physiological data index of the standard normal healthy population to generate a normalized variability component, which reflects the fluctuation deviation of the physiological data index relative to the healthy population.

3. The method for assessing the risk of respiratory diseases according to claim 1, characterized in that The specific content of S1 includes: During the implementation of the dynamic interaction feature extraction algorithm, capture the short-term interaction effect between the standardized physiological data index and the standardized external data index by calculating the dynamic interaction intensity factor.

4. The method for assessing the risk of respiratory diseases according to claim 3, wherein The specific content of S1 includes: During the calculation of the dynamic interaction intensity factor, calculate the absolute value of the deviation of the standardized physiological data index and the standardized external data index on the current day from the mean within the time window respectively, multiply them to get the numerator part. At the same time, calculate the standard deviation of the standardized physiological data index and the standardized external data index within the time window, multiply them as the denominator, and generate a normalized interaction intensity.

5. The method for assessing the risk of respiratory diseases according to claim 4, characterized in that, The specific content of S1 includes: During the calculation of the dynamic interaction intensity factor, introduce a time weighting factor and combine it with the normalized interaction intensity to generate a dynamic interaction intensity factor.

6. The method for assessing the risk of respiratory diseases according to claim 5, wherein, The specific content of S1 includes: Generate a comprehensive feature value by weighted linear combination of the normalized variability component and the dynamic interaction intensity factor.

7. A method for assessing the risk of respiratory diseases according to claim 1, characterized in that The specific content of S2 includes: Perform weighted linear combination on the comprehensive feature value to calculate the respiratory disease risk index; based on the respiratory disease risk index, divide the risks into three levels: high, medium, and low.

8. A method for assessing the risk of respiratory diseases according to claim 7, characterized in that, The specific content of S2 includes: Integrate the respiratory disease risk index, risk level, clinical significance, and intervention suggestions given according to the risk level into an evaluation report, and display it in the form of text and charts through the user terminal.

9. A respiratory disease risk assessment system applied to the respiratory disease risk assessment method described in claim 1, characterized in that, It includes the following parts: Data acquisition module, data preprocessing module, feature extraction module, risk assessment module, evaluation report generation module; Data acquisition module: Collect physiological data and external data, and output the collected physiological data and external data to the data preprocessing module; Data preprocessing module: Perform standardization processing on the physiological data and external data collected by the data acquisition module respectively to obtain the standardized physiological data and external data, and output the standardized physiological data and external data to the feature extraction module; Feature extraction module: Based on the standardized physiological data and external data of the data preprocessing module, use a dynamic interaction feature extraction algorithm to extract features, generate a comprehensive feature value, and output the comprehensive feature value to the risk assessment module; Risk assessment module: Calculate the respiratory disease risk index based on the comprehensive eigenvalue of the feature extraction module, divide the risk levels, and output the respiratory disease risk index and risk levels to the assessment report generation module; Assessment report generation module: Integrate the respiratory disease risk index, risk levels, clinical significance, and intervention suggestions given according to the risk levels of the risk assessment module into an assessment report, and display it in the form of text and charts through the user terminal.

Images