A physiological environmental risk assessment method based on expiratory response patterns

Abstract

This invention relates to a physiological environmental risk assessment method based on expiratory response patterns, belonging to the field of expiratory analysis and health risk assessment technology. Addressing the shortcomings of existing non-invasive assessment methods in identifying intermediate metabolic transition states and the susceptibility of assessment results to individual baseline differences, this invention proposes a physiological environmental risk assessment method based on a mixed expiratory response pattern. This method collects mixed expiratory response signals using a gas sensor array, constructs a multi-dimensional feature vector characterizing the overall response behavior, and uses feature distance metrics to initially stratify stable, intermediate-risk, and high-risk states. When in an intermediate-risk state, a second-level subdivision is performed by combining baseline response levels and dynamic decay characteristics, generating six types of physiological environmental risk assessment results. This invention is applicable to non-invasive health risk screening and long-term trend assessment in home settings.

Description

Technical Field

[0001] This invention relates to the field of physiological state monitoring and risk assessment technology, specifically to a physiological environment risk assessment method, device, and electronic device based on the exhaled mixed gas response pattern, belonging to the field of non-invasive physiological state assessment and intelligent analysis technology. Background Technology

[0002] Existing physiological status and metabolic risk assessment technologies mostly rely on blood, biochemical indicators or imaging detection methods, which usually have problems such as high invasiveness, high detection cost and limited detection frequency, making it difficult to meet the needs of long-term and continuous status monitoring.

[0003] With the development of non-invasive testing technology, breath sample-based testing methods have gradually attracted attention. However, existing breath testing protocols mostly focus on a single gas or a single numerical indicator. The types of assessment results are easily affected by individual differences, sampling conditions, and environmental interference, resulting in insufficient stability and difficulty in reflecting the overall physiological environmental risk status of the body during multi-pathway metabolic regulation and environmental adaptation.

[0004] Furthermore, existing methods typically only provide rough conclusions such as "normal / abnormal" or "low risk / high risk," making it difficult to effectively identify and further subdivide intermediate transitional states between stable and high-risk states, thus limiting their application value in long-term risk management and early intervention scenarios.

[0005] Therefore, it is necessary to provide a method that can stably stratify and assess physiological environmental risks based on the joint response relationship of exhaled mixed gases, and further subdivide the transitional states between stable and high-risk states. Summary of the Invention

[0006] This invention aims to address the problems of existing breath test technologies, such as limited assessment dimensions, insufficient result stability, and difficulty in effectively identifying and subdividing intermediate transitional risk states, by providing a non-invasive physiological environment risk assessment method based on breath response patterns.

[0007] To achieve the above objectives, the present invention provides the following technical solution: A physiological environmental risk assessment method based on expiratory gas mixture response includes the following steps: S1, Obtain a breath sample from the subject; S2, the exhaled sample is detected by a gas sensor array to obtain a mixed exhaled response signal composed of multiple time-series signals; S3, perform validity verification, outlier removal, smoothing and standardization on the expiratory mixed response signal, and extract a multi-dimensional feature vector to characterize the expiratory response pattern based on these steps. S4. Input the multidimensional feature vector into the pre-trained classification model to obtain a preliminary risk classification result. The preliminary risk classification result is used for subsequent process control and is not directly used as the result for external display. The preliminary risk classification result includes a stable state, an intermediate risk state, and a high risk state, wherein the intermediate risk state is used to trigger the subsequent secondary subdivision judgment.

[0008] S5, when the preliminary risk classification result is the intermediate risk state, the intermediate risk state is further subdivided based on the baseline response characteristics and dynamic decay characteristics in the breath mixed response signal, and the corresponding risk subtype result is output. S6. Based on the preliminary risk classification results and the secondary subdivision judgment results, perform result mapping to generate and output six types of physiological and environmental risk assessment results. These six types of physiological and environmental risk assessment results are the final assessment result types displayed externally.

[0009] Compared with the prior art, the present invention has the following beneficial effects: 1. By analyzing the overall response pattern of the exhaled gas mixture, rather than a single gas index, the stability of physiological environmental risk assessment is improved; 2. The structure combining hierarchical judgment and transitional state triggering subdivision improves the ability to identify continuous changes in physiological state; 3. It adopts a non-invasive detection method, which is suitable for long-term, repeated monitoring and trend assessment in scenarios such as home and community. Attached Figure Description

[0010] Figure 1 This is a schematic diagram of a physiological and environmental risk assessment method provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of exhalation mixture response signal processing and feature extraction in one embodiment of the present invention; Figure 3 This is a schematic diagram of the two-level subdivision determination logic in one embodiment of the present invention. Detailed Implementation

[0011] The present invention will be further described below with reference to the accompanying drawings and embodiments. Those skilled in the art should understand that the following embodiments are for illustrative purposes only and do not constitute a limitation on the scope of protection of the present invention.

[0012] Example 1: Six Physiological and Environmental Risk Assessment Methods Based on Two-Level Judgment like Figure 1 As shown in the figure, this embodiment provides a physiological environmental risk assessment method based on expiratory response patterns, including the following steps.

[0013] Step S1: Exhaled Breath Sample Collection A breath sample is collected from the subject using a disposable mouthpiece, and the sampling is completed during a single exhalation.

[0014] Step S2: Acquisition of Expiratory Mixture Response Signal A gas sensor array is used to detect exhaled breath samples. Multiple resistance values ​​are collected at fixed time intervals during a single exhalation, forming a time-series exhaled mixed response signal. Here, Rk represents the resistance value of the k-th sampling point collected at fixed time intervals during a single exhalation, where k is a positive integer.

[0015] Step S3: Signal Processing and Feature Extraction The validity of the expiratory mixed response signal was verified, and the data in the feature calculation process was standardized to reduce the impact of dimensional differences on subsequent analysis.

[0016] A multidimensional feature vector for characterizing the expiratory response pattern is extracted from the expiratory mixed response signal. The feature vector is a 21-dimensional feature vector, which is composed of multiple types of features, and the sum of the dimensions of each type of feature is 21.

[0017] Step S4: Preliminary Internal Classification The 21-dimensional feature vector is input into the main classification model. The main classification model is a feature-weighted distance metric model, which obtains preliminary risk classification results by calculating the weighted Euclidean distance between the feature vector of the sample to be tested and the centroid vectors of multiple preset categories.

[0018] The preliminary risk classification results are used for subsequent process control and are not directly presented as results to the public.

[0019] Step S5: Secondary subdivision judgment triggered by intermediate risk status When the initial risk classification result is a preset intermediate risk state, the secondary subdivision judgment process is initiated. For example... Figure 3 As shown, the secondary subdivision determination is based on the following features: Baseline response characteristics: Initial response value R1; Dynamic attenuation characteristics: early attenuation ratio ER = R2 / R1, and tail attenuation ratio TR = R6 / R5.

[0020] By comparing the above characteristics with a preset threshold, the intermediate risk state is subdivided into one of the following four risk subtypes: Output code 21: Mild metabolic regulation fluctuation type; Output code 22: Increased metabolic regulatory load type; Output code 23: Metabolic regulatory stress type; Output code 24: Metabolic regulation capacity is limited.

[0021] Step S6: Result Mapping and Six Outputs Based on the preliminary risk classification results and the secondary subdivision judgment results, the execution results are mapped and six types of physiological and environmental risk assessment results are generated for final output. These six results include: Output code 1: Metabolically relatively stable type; Output code 21: Mild metabolic regulation fluctuation type; Output code 22: Increased metabolic regulatory load type; Output code 23: Metabolic regulatory stress type; Output code 24: Metabolic regulation capacity is limited; Output code 3: High-load metabolic risk environment type.

[0022] When the initial risk classification result is stable, the output result code is 1; When the initial risk classification result is an intermediate risk status, the output result code is 21, 22, 23 or 24 based on the secondary subdivision judgment result; When the initial risk classification result is high risk, the output result code is 3.

[0023] Device and System Examples The present invention also provides a physiological environmental risk assessment device based on exhaled mixed gas response, including an exhaled gas collection unit, a gas detection unit, a signal processing unit, a feature extraction unit, a main classification unit, a secondary subdivision judgment unit, and a result mapping and output unit, wherein each unit works in concert to realize the above method steps.

[0024] Examples of electronic devices and storage media The present invention also provides an electronic device and a computer-readable storage medium, which execute a stored computer program via a processor to implement the physiological and environmental risk assessment method described in the present invention.

[0025] Summary and Explanation The above embodiments are merely illustrative examples of the present invention. Those skilled in the art can make various modifications or equivalent substitutions to the present invention without departing from its spirit and scope, and all such modifications or substitutions should fall within the scope of protection of the present invention.

Claims

1. A physiological environmental risk assessment method based on expiratory mixed-gas response, characterized in that, Includes the following steps: S1, Obtain a breath sample from the subject; S2, the exhaled sample is detected by a gas sensor array to obtain a mixed exhaled response signal composed of multiple time-series signals; S3, preprocess the expiratory mixed response signal, the preprocessing includes at least outlier removal, smoothing and standardization, and on this basis, extract a multidimensional feature vector to characterize the expiratory response pattern; S4, input the multidimensional feature vector into the pre-trained classification model to obtain preliminary risk classification results, which include stable state, intermediate risk state and high risk state; S5, when the preliminary risk classification result is the intermediate risk state, the intermediate risk state is further subdivided based on the baseline response characteristics and dynamic decay characteristics in the breath mixed response signal, and the corresponding risk subtype result is output. S6, integrate the preliminary risk classification results and the risk subtype results to generate and output six types of physiological and environmental risk assessment results.

2. The method according to claim 1, characterized in that: The exhalation mixture response signal is a time-series signal composed of multiple resistance values ​​collected by the gas sensor at fixed time intervals during a single exhalation. The exhalation mixture response signal is a time-series signal of resistance values ​​that change over time.

3. The method according to claim 1, characterized in that: The multidimensional feature vector is a 21-dimensional feature vector, which includes: The proportional features, overall change features, logarithmic layer features, second-order difference features based on logarithmic layer features, morphological features, and quadratic fitting features calculated from the time series signal, wherein the sum of the dimensions of each type of feature is 21.

4. The method according to claim 1, characterized in that: The classification model is a feature-weighted distance metric model, which calculates the weighted Euclidean distance between the feature vector of the sample to be tested and the centroid vectors of multiple preset categories to determine the preliminary risk classification result.

5. The method according to claim 1, characterized in that: In the second-level subdivision determination The baseline response feature is the initial response value R1 of the expiratory mixed response signal; where Rk represents the resistance value of the kth sampling point collected at fixed time intervals during a single exhalation. The dynamic attenuation characteristics include the early attenuation ratio ER and the tail attenuation ratio TR; ER = R2 / R1, TR = R6 / R5; By comparing the baseline response characteristics and the dynamic decay characteristics with preset thresholds, the intermediate risk state is divided into different risk subtypes.

6. The method according to claim 5, characterized in that: The preset threshold is determined through statistical analysis of training samples or calibration experiments.

7. The method according to claim 5, characterized in that: The risk subtypes include mild metabolic regulation fluctuation, increased metabolic regulation load, persistent metabolic regulation pressure, and limited metabolic regulation capacity, and each risk subtype corresponds to a different threshold combination range of baseline response characteristics and dynamic decay characteristics.

8. A physiological environmental risk assessment device based on expiratory mixed gas response, characterized in that, include: The exhalation sampling unit is used to acquire exhalation samples from the test subject; A gas detection unit, including a gas sensor array, is used to detect the exhaled breath sample to obtain an exhaled breath mixture response signal; The signal processing unit is used to perform preprocessing on the expiratory mixed response signal, including at least outlier removal and smoothing. The feature extraction unit is used to extract multidimensional feature vectors from the preprocessed breath-mixed response signal. The main classification unit is used to run a pre-trained classification model based on the multidimensional feature vector to obtain preliminary risk classification results; The secondary subdivision determination unit is used to perform secondary subdivision determination based on baseline response characteristics and dynamic decay characteristics when the preliminary risk classification result is the intermediate risk state, and output the risk subtype result. The results integration and output unit is used to integrate the preliminary risk classification results and the risk subtype results to generate and output six types of physiological and environmental risk assessment results.

9. An electronic device, characterized in that, Includes memory and processor, among which: The memory contains computer programs; When the processor is configured to execute the computer program, it implements the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program that, when run on a processor, performs the method as described in any one of claims 1 to 7.

Images