A respiratory disease risk assessment system and method

Abstract

The present invention relates to the field of respiratory disease risk assessment, and in particular to a respiratory disease risk assessment system and method. The system comprises: collecting physiological data and external data, standardizing the collected physiological data and external data respectively, extracting features based on the standardized physiological data and external data using a dynamic interactive feature extraction algorithm to generate comprehensive feature values; calculating a respiratory disease risk index based on the comprehensive feature values, dividing risk levels based on the respiratory disease risk index, and generating an assessment report. This system solves the technical problem that traditional respiratory disease risk assessment relies heavily on static data, neglecting changes in individuals under different lifestyles and environmental conditions, resulting in a lack of personalized adaptability and clinical significance in the assessment results.

Description

Technical Field

[0001] The present invention relates to the field of respiratory disease risk assessment, and in particular 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 increased year by year, especially chronic obstructive pulmonary disease (COPD), asthma, and other respiratory diseases caused by air pollution. These diseases 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 intervention and treatment has become an important research direction in the current medical and health field.

[0003] Existing risk assessment methods rely primarily on clinical data. Analysis of a single data source often fails to fully reflect a patient's true risk. Furthermore, each individual's health status, lifestyle, and medical history vary, making it difficult for traditional "one-size-fits-all" treatments to achieve optimal therapeutic outcomes. The development and application of respiratory disease risk assessment systems will not only help improve early diagnosis rates, but also play an important role in reducing disease burden and healthcare 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 monitoring patient health status in real time and providing targeted intervention plans. These systems will provide strong support for the prevention, diagnosis, and treatment of respiratory diseases worldwide, and contribute 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 difficulty 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 assessment relies mostly on static data, ignores the changes of individuals under different lifestyles and environmental conditions, and causes the assessment results to lack personalized adaptability and clinical significance.

[0006] The present invention provides a respiratory disease risk assessment system and method, which specifically includes the following technical solutions:

[0007] A respiratory disease risk assessment method comprises the following steps:

[0008] S1. Collect physiological data and external data, standardize the collected physiological data and external data, and extract features based on the standardized physiological data and external data using a dynamic interactive feature extraction algorithm to generate comprehensive feature values;

[0009] S2. Based on the comprehensive characteristic values, the respiratory disease risk index is calculated, the risk level is divided based on the respiratory disease risk index, and an assessment report is generated.

[0010] Preferably, the S1 specifically includes:

[0011] In the implementation process of the dynamic interactive feature extraction algorithm, the standard deviation within the time window is calculated for each standardized physiological data indicator. The standard deviation is subtracted from the standard deviation of the corresponding physiological data indicator of the standard normal and healthy population and divided by the standard deviation of the corresponding physiological data indicator of the standard normal and healthy population to generate a normalized variability component, which reflects the fluctuation deviation of the physiological data indicator relative to the healthy population.

[0012] Preferably, the S1 specifically includes:

[0013] In the implementation of the dynamic interaction feature extraction algorithm, the short-term interaction effect between the normalized physiological data indicators and the normalized external data indicators is captured by calculating the dynamic interaction intensity factor.

[0014] Preferably, the S1 specifically includes:

[0015] In the process of calculating the dynamic interaction intensity factor, the absolute values ​​of the deviations between the standardized physiological data indicators and the standardized external data indicators of the current day and the mean values ​​within the time window are calculated respectively, and the numerator is obtained by multiplication. At the same time, the standard deviations of the standardized physiological data indicators and the standardized external data indicators within the time window are calculated and multiplied as the denominator to generate the normalized interaction intensity.

[0016] Preferably, the S1 specifically includes:

[0017] In the calculation process of the dynamic interaction intensity factor, the time weighting factor is introduced, and the time weighting factor is combined with the normalized interaction intensity to generate the dynamic interaction intensity factor.

[0018] Preferably, the S1 specifically includes:

[0019] The normalized variability component and the dynamic interaction intensity factor are combined by weighted linear combination to generate a comprehensive eigenvalue.

[0020] Preferably, the S2 specifically includes:

[0021] The comprehensive eigenvalues ​​are weighted linearly combined to calculate the respiratory disease risk index; based on the respiratory disease risk index, the risk is divided into three levels: high, medium, and low.

[0022] Preferably, the S2 specifically includes:

[0023] The respiratory disease risk index, risk level, and clinical significance and intervention recommendations based on the risk level are integrated into an evaluation report and displayed in text and chart form through the user terminal.

[0024] A respiratory disease risk assessment system, comprising the following parts:

[0025] Data acquisition module, data preprocessing module, feature extraction module, risk assessment module, and assessment report generation module;

[0026] Data acquisition module: collects physiological data and external data, and outputs the collected physiological data and external data to the data preprocessing module;

[0027] Data preprocessing module: standardizes the physiological data and external data collected by the data acquisition module to obtain standardized physiological data and external data, and outputs the standardized physiological data and external data to the feature extraction module;

[0028] Feature extraction module: Based on the physiological data and external data that have been standardized by the data preprocessing module, a dynamic interactive feature extraction algorithm is used to extract features, generate comprehensive feature values, and output the comprehensive feature values ​​to the risk assessment module;

[0029] Risk assessment module: Calculates the respiratory disease risk index based on the comprehensive feature value of the feature extraction module, divides the risk level, and outputs the respiratory disease risk index and risk level to the assessment report generation module;

[0030] Evaluation report generation module: Integrates the respiratory disease risk index, risk level, and clinical significance and intervention recommendations given based on the risk level of the risk assessment module into an evaluation report, which is displayed in text and chart form through the user terminal.

[0031] The beneficial effects of the technical solution of the present invention are:

[0032] 1. Physiological data and external data are collected through wearable devices and environmental sensors, and standardized to ensure high data quality and consistency.

[0033] 2. The dynamic interaction feature extraction algorithm can effectively capture the short-term interaction effects and long-term change trends between standardized physiological data and external data. By weightedly combining the normalized variability component and the dynamic interaction intensity factor, a comprehensive characteristic value is generated, which can reflect the dynamic changes of individuals in chronic respiratory disease risks. It not only improves the timeliness of the data, but also enhances the personalized adaptability to the individual's health status. It can reflect the short-term effects and physiological fluctuations of exposure to different environments, thereby improving the accuracy of disease risk assessment.

[0034] 3. Based on the comprehensive eigenvalues, a weighted linear model is used to calculate the respiratory disease risk index, which can comprehensively consider the complex interactions between multidimensional data, quantify the individual's respiratory disease risk, make the risk level of each user more accurate, and facilitate individualized health intervention and management.

[0035] 4. The calculation results of the respiratory disease risk index clearly divide respiratory disease risks 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 evaluation report in the form of a chart, users can clearly see the changing trends of their health status, further improving their initiative in disease prevention and lifestyle adjustments. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a structural diagram of a respiratory disease risk assessment system according to the present invention;

[0037] Figure 2 This is a flow chart of a respiratory disease risk assessment method according to the present invention. DETAILED DESCRIPTION

[0038] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0039] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0040] The following describes in detail a specific scheme of a respiratory disease risk assessment system and method provided by the present invention with reference to the accompanying drawings.

[0041] Refer to the attached Figure 1 , which shows a structure diagram of a respiratory disease risk assessment system provided by one embodiment of the present invention, the system includes the following parts:

[0042] Data acquisition module, data preprocessing module, feature extraction module, risk assessment module, and assessment report generation module;

[0043] Data acquisition module: collects physiological data and external data through wearable devices, environmental sensors and user terminals, and outputs the collected physiological data and external data to the data preprocessing module;

[0044] Data preprocessing module: standardizes the physiological data and external data collected by the data acquisition module to obtain standardized physiological data and external data, and outputs the standardized physiological data and external data to the feature extraction module;

[0045] Feature extraction module: Based on the physiological data and external data that have been standardized by the data preprocessing module, a dynamic interactive feature extraction algorithm is used to extract features, generate comprehensive feature values, and output the comprehensive feature values ​​to the risk assessment module;

[0046] Risk assessment module: Based on the comprehensive feature values ​​of the feature extraction module, calculate the respiratory disease risk index, divide the risk level, and output the respiratory disease risk index and risk level to the assessment report generation module;

[0047] Assessment report generation module: Integrates the respiratory disease risk index, risk level, and clinical significance and intervention recommendations based on the risk level from the risk assessment module into an assessment report, which is displayed in text and chart form through a user terminal (such as a mobile phone application).

[0048] Refer to the attached Figure 2 , which shows a flow chart of a respiratory disease risk assessment method provided by one embodiment of the present invention, the method comprising the following steps:

[0049] S1. Collect physiological data and external data, standardize the collected physiological data and external data respectively, and extract features based on the standardized physiological data and external data using a dynamic interactive feature extraction algorithm to generate a comprehensive feature value;

[0050] Physiological and external data are collected through wearable devices, environmental sensors, and user terminals to generate daily time series data for subsequent respiratory disease risk assessment. This data collection frequency is based on daily granularity, ensuring that it is suitable for long-term monitoring of chronic diseases and reducing device power consumption and storage requirements. Physiological data includes heart rate, respiratory rate, and blood oxygen saturation. External data includes daily smoking duration, sleep duration, and air quality index.

[0051] Determine the minimum and maximum values ​​of each data indicator based on medical or environmental standards, standardize the collected physiological data and external data, and generate standardized physiological data and external data;

[0052] Based on the standardized physiological data and external data, a dynamic interactive feature extraction algorithm is used to extract features and generate comprehensive feature values. These are used to integrate the long-term trends of the standardized physiological data and the dynamic interaction effects with the standardized external data to reflect the risk of chronic respiratory diseases.

[0053] The dynamic interactive feature extraction algorithm calculates the standard deviation within a time window for each normalized physiological data indicator to reflect short-term fluctuations. The standard deviation is subtracted from the standard deviation of the corresponding physiological data indicator of a standard normal healthy population and divided by the standard deviation of the corresponding physiological data indicator of a standard normal healthy population to generate a normalized variability component, which reflects the fluctuation deviation of the physiological data indicator relative to the healthy population. For example, abnormal heart rate variability may be associated with the progression of chronic obstructive pulmonary disease.

[0054] The dynamic interaction feature extraction algorithm is used to capture the short-term interaction effect between the standardized physiological data indicators and the standardized external data indicators by calculating the dynamic interaction intensity factor. Specifically, the absolute values ​​of the deviations of the standardized physiological data indicators and the standardized external data indicators of the current day from the mean value in the time window are calculated respectively, and the numerator is obtained after multiplication. At the same time, the standard deviations of the standardized physiological data indicators and the standardized external data indicators in the time window are calculated and multiplied as the denominator to generate the normalized interaction intensity. The time weighting factor is further introduced, and the exponential decay function is used to give higher weights to data closer to the current time, emphasizing the importance of recent data and enhancing personalized adaptability. The time weighting factor is combined with the normalized interaction intensity to generate a dynamic interaction intensity factor, which ranges from 0 to 1.

[0055] The normalized variability component and the dynamic interaction intensity factor are combined by weighted linear combination to generate a comprehensive eigenvalue. Furthermore, a weight constraint is imposed: the sum of the variability weight of the normalized physiological data indicator and the dynamic interaction intensity weight of the normalized physiological data indicator and the external data indicator is 1, that is, ;

[0056] The calculation formula of the comprehensive eigenvalue is:

[0057] ;

[0058] in, Indicates the After standardization Physiological data indicators and The comprehensive characteristic value of the external data indicators; Represents the first The variability weight of each physiological data indicator, the value range , optimized through machine learning models (such as neural networks) to meet weight constraints; Indicates the Day time window After internal standardization Standard deviation of physiological data indicators; Represents the standard normal healthy population The standard deviation of each physiological data indicator serves as a benchmark, reflecting the deviation of the variability of individual physiological indicators relative to that of healthy people; Represents the first Physiological data indicators and The dynamic interaction intensity weight of an external data indicator reflects the importance of a specific interaction and has a value range of , optimized through machine learning models (such as neural networks) to meet weight constraints; represents the mean value of the dynamic interaction intensity factor within the time window; Indicates the length of the time window; Indicates the After standardization Physiological data indicators and The dynamic interaction intensity factor of an external data indicator is calculated as follows:

[0059] ;

[0060] in, Indicates the After standardization Physiological data indicators; Indicates the After normalization within the time window of 1 day The mean of physiological data indicators; Indicates the After standardization The physiological data indicators and the first The absolute deviation of the mean of each physiological data indicator; Represents the standard deviation of physiological data indicators after normalization within the time window; Indicates the After standardization External data indicators; Indicates the After normalization within the time window of 1 day The mean of the external data indicators; Indicates the After standardization The external data indicators and the first The absolute deviation of the mean of the external data indicator; Indicates the standard deviation of the external data indicator after normalization within the time window; It represents the time weighting factor. It uses an exponential decay function to assign higher weights to data closer to the current time, emphasizing the dynamic interaction intensity of the data on that day. The calculation formula is: , value range ; Indicates the attenuation parameter of the time weighting factor, which is used to control the attenuation speed of the time weighting. The value range is ;

[0061] Normalizing variability using the standard deviation of a healthy population accurately reflects individual health deviations, enhances clinical significance, introduces a dynamic interaction intensity factor to capture the short-term effects of recent environmental exposures, adapts to individual lifestyles and environmental changes, and enhances personalized assessment capabilities. Through linear combinations and weight constraints, the calculation process of the comprehensive eigenvalue is simplified, ensuring that the range of the comprehensive eigenvalue is controllable and easy to interpret clinically.

[0062] S2. Calculate the respiratory disease risk index based on the comprehensive characteristic value, divide the risk level based on the respiratory disease risk index, and generate an assessment report;

[0063] Based on the comprehensive eigenvalues, the existing weighted linear model was used to calculate the respiratory disease risk index, and the formula is as follows:

[0064] ;

[0065] in, Indicates the The respiratory disease risk index of the day is used to quantify the individual's The risk of chronic respiratory disease in a certain period of time is used to guide intervention. Indicates the number of physiological data indicators; Indicates the number of external data indicator 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 and reflect the impact of the interaction between different physiological and external data indicators on the risk of respiratory disease. The value range is , optimized through machine learning models (such as neural networks);

[0066] 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; based on the risk level, the following clinical significance and intervention recommendations are given: low risk indicates that the respiratory system functions normally and the impact of external factors (such as smoking or air pollution) is small. 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. It is recommended to reduce smoking, optimize sleep and consult a doctor; high risk means that the risk of disease worsening is significant. It is recommended to seek medical attention immediately, quit smoking and avoid polluted environments;

[0067] The respiratory disease risk index, risk level, and clinical significance and intervention recommendations based on the risk level are integrated into an assessment report and displayed in text and chart form through user terminals (such as mobile applications); by generating an accurate respiratory disease risk index, clearly dividing low, medium, and high risk levels, providing personalized clinical significance and intervention recommendations, and improving users' understanding of and response to their health status.

[0068] In summary, a respiratory disease risk assessment system and method are completed.

[0069] The order in which the embodiments of the invention are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0070] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0071] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A respiratory disease risk assessment method, characterized in that: The following steps are involved: S1. Collect and standardize physiological data and external data including daily smoking duration, sleep duration, and air quality index. Based on the standardized physiological data and external data, use a dynamic interactive feature extraction algorithm to extract features and generate a comprehensive feature value. The formula is: ， in, Indicates the After standardization Physiological data indicators and The comprehensive characteristic value of the external data indicators; Represents the first The variability weight of each physiological data indicator; Indicates the Day time window After internal standardization Normalized variability components of physiological data indicators; Indicates the Day time window After internal standardization Standard deviation of physiological data indicators; Represents the standard normal healthy population Standard deviation of physiological data indicators; Represents the first Physiological data indicators and Dynamic interaction intensity weight of external data indicators; Indicates the length of the time window; Indicates the After standardization Physiological data indicators and The dynamic interaction intensity factor of the external data indicator is as follows: ， in, Indicates the After standardization Physiological data indicators; Indicates the After normalization within the time window of 1 day The mean of physiological data indicators; Indicates the After standardization External data indicators; Indicates the After normalization within the time window of 1 day The mean of the external data indicators; represents the time weighting factor; S2. Based on the comprehensive characteristic values, the respiratory disease risk index is calculated, the risk level is divided based on the respiratory disease risk index, and an assessment report is generated.

2. A respiratory disease risk assessment method according to claim 1, characterized in that: Said S1 specifically includes: In the implementation process of the dynamic interactive feature extraction algorithm, the standard deviation within the time window is calculated for each standardized physiological data indicator. The standard deviation is subtracted from the standard deviation of the corresponding physiological data indicator of the standard normal and healthy population and divided by the standard deviation of the corresponding physiological data indicator of the standard normal and healthy population to generate a normalized variability component, which reflects the fluctuation deviation of the physiological data indicator relative to the healthy population.

3. A respiratory disease risk assessment method according to claim 1, characterized in that: Said S1 specifically includes: In the implementation of the dynamic interaction feature extraction algorithm, the short-term interaction effect between the normalized physiological data indicators and the normalized external data indicators is captured by calculating the dynamic interaction intensity factor.

4. A respiratory disease risk assessment method according to claim 3, characterized in that: Said S1 specifically includes: In the process of calculating the dynamic interaction intensity factor, the absolute values ​​of the deviations between the standardized physiological data indicators and the standardized external data indicators of the current day and the mean values ​​within the time window are calculated respectively, and the numerator is obtained by multiplication. At the same time, the standard deviations of the standardized physiological data indicators and the standardized external data indicators within the time window are calculated and multiplied as the denominator to generate the normalized interaction intensity.

5. A respiratory disease risk assessment method according to claim 4, characterized in that: Said S1 specifically includes: In the calculation process of the dynamic interaction intensity factor, the time weighting factor is introduced, and the time weighting factor is combined with the normalized interaction intensity to generate the dynamic interaction intensity factor.

6. A respiratory disease risk assessment method according to claim 5, characterized in that: Said S1 specifically includes: The normalized variability component and the dynamic interaction intensity factor are combined by weighted linear combination to generate a comprehensive eigenvalue.

7. A respiratory disease risk assessment method according to claim 1, characterized in that: Said S2 specifically includes: The comprehensive eigenvalues ​​are weighted linearly combined to calculate the respiratory disease risk index; based on the respiratory disease risk index, the risk is divided into three levels: high, medium, and low.

8. A respiratory disease risk assessment method according to claim 7, characterized in that: Said S2 specifically includes: The respiratory disease risk index, risk level, and clinical significance and intervention recommendations based on the risk level are integrated into an evaluation report and displayed in text and chart form through the user terminal.

9. A respiratory disease risk assessment system, applied to the respiratory disease risk assessment method according to claim 1, characterized in that: Includes the following sections: Data acquisition module, data preprocessing module, feature extraction module, risk assessment module, and assessment report generation module; Data acquisition module: collects physiological data and external data, and outputs the collected physiological data and external data to the data preprocessing module; Data preprocessing module: standardizes the physiological data and external data collected by the data acquisition module to obtain standardized physiological data and external data, and outputs the standardized physiological data and external data to the feature extraction module; Feature extraction module: Based on the physiological data and external data that have been standardized by the data preprocessing module, a dynamic interactive feature extraction algorithm is used to extract features, generate comprehensive feature values, and output the comprehensive feature values ​​to the risk assessment module; Risk assessment module: Calculates the respiratory disease risk index based on the comprehensive feature value of the feature extraction module, divides the risk level, and outputs the respiratory disease risk index and risk level to the assessment report generation module; Evaluation report generation module: Integrates the respiratory disease risk index, risk level, and clinical significance and intervention recommendations given based on the risk level of the risk assessment module into an evaluation report, which is displayed in text and chart form through the user terminal.

Images