Clinical evaluation and prediction method and system for exhaled gas and percutaneous carbon dioxide monitoring

Abstract

The invention relates to the field of medical data processing, in particular to a clinical evaluation and prediction method and system for exhaled gas and percutaneous carbon dioxide monitoring, and the method comprises the steps: determining a target skin area for implementing percutaneous carbon dioxide monitoring according to the body surface temperature data of a target object; according to the percutaneous carbon dioxide partial pressure of the target skin area, obtaining percutaneous carbon dioxide release characteristics; acquiring a relative change relationship between the percutaneous partial pressure of carbon dioxide and the exhaled gas partial pressure of carbon dioxide, and estimating energy metabolism characteristics in combination with percutaneous carbon dioxide release characteristics so as to construct a metabolism model matched with a target object and predict a disease risk change trend; evaluating and screening clinical detection data, and generating a disease risk evaluation result. By comparing and analyzing exhaled air and percutaneous carbon dioxide partial pressure data, the real body state can be comprehensively reflected, the potential health risk of a patient can be quickly predicted and evaluated, and the disease risk evaluation credibility can be improved.

Description

Technical Field

[0001] This invention relates to the field of medical data processing, and more particularly to clinical assessment and prediction methods and systems for exhaled breath and transcutaneous carbon dioxide monitoring. Background Technology

[0002] Arterial blood gas analysis, specifically the partial pressures of oxygen and carbon dioxide, objectively reflects the nature and severity of respiratory failure and is a reliable method for determining whether a patient has low O2 and CO2 retention. However, continuous blood gas analysis requires repeated arterial blood sampling, increasing the complexity of the process and increasing the risk of infection due to repeated invasive procedures. To facilitate continuous, non-invasive monitoring of carbon dioxide partial pressure, exhaled and transcutaneous carbon dioxide partial pressure monitoring is now widely used in clinical settings.

[0003] Currently, transcutaneous gas partial pressure monitoring (TMP) sensors are used to detect the partial pressure of gases in subcutaneous tissue. The main principle is to use electrodes with heating capabilities to increase the temperature of the subcutaneous tissue, accelerating blood flow in the subcutaneous capillaries, thereby increasing the skin's permeability to gases and thus detecting the partial pressure of gases in the subcutaneous tissue. However, currently, exhaled gas and transcutaneous carbon dioxide partial pressures need to be used simultaneously to analyze a patient's health status. This results in excessive data processing volume for gas partial pressure data and fails to provide comprehensive and accurate monitoring of the patient's potential organ and tissue metabolic status. Consequently, it cannot provide a reliable reference for clinical monitoring data processing and reduces the credibility of clinical disease risk assessment. Summary of the Invention

[0004] Unlike existing technologies that only monitor and analyze transcutaneous carbon dioxide partial pressure to identify patient vital signs and predict potential disease risks, these methods only target a single data point and cannot comprehensively reflect the patient's true physical condition. They also cannot quickly predict and assess potential health risks or improve the reliability of disease risk assessments. To fully obtain comprehensive carbon dioxide partial pressure data from patients and quickly and accurately assess their clinical disease risks, this invention provides a clinical assessment and prediction method using exhaled breath and transcutaneous carbon dioxide monitoring. The method includes the following steps: S100: Based on the surface temperature data of the target object, obtain the skin temperature fluctuation characteristics, thereby determining the target skin area for transdermal carbon dioxide monitoring of the target object; based on the transdermal carbon dioxide partial pressure of the target skin area, obtain the transdermal carbon dioxide release characteristics; S200: Simultaneously acquire the exhaled carbon dioxide partial pressure of the target object to obtain the relative change relationship between the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure; estimate the energy metabolism characteristics of the target object based on the relative change relationship and the transcutaneous carbon dioxide release characteristics; S300: Based on the energy metabolism characteristics, construct a metabolic model that matches the target object, thereby predicting the trend of disease risk changes in the target object; S400: Based on the disease risk change trend, evaluate and screen the clinical test data of the target subjects to obtain a reliable clinical test dataset, thereby generating disease risk assessment results.

[0005] Preferably, in S100, skin temperature fluctuation characteristics are obtained based on the surface temperature data of the target object, thereby determining the target skin area for transdermal carbon dioxide monitoring of the target object; transdermal carbon dioxide release characteristics are obtained based on the transdermal carbon dioxide partial pressure of the target skin area, specifically: The global surface thermal infrared dynamic image of the target object is acquired, and the global surface thermal infrared dynamic image is subjected to frame segmentation and transformation analysis to determine the dynamic data of the target object's surface temperature, thereby obtaining the skin temperature change rate of the target object. Based on the skin temperature change rate, the stability of transdermal carbon dioxide release over the entire body surface area of ​​the target object is determined; based on the stability of transdermal carbon dioxide release, the target skin area for transdermal carbon dioxide monitoring of the target object is determined. Transdermal carbon dioxide partial pressure data of the target skin region are collected, and time-difference variation analysis is performed on the transdermal carbon dioxide partial pressure data to obtain the transdermal carbon dioxide release rate of the target skin region, which is used as the transdermal carbon dioxide release characteristic.

[0006] Preferably, in S200, the exhaled carbon dioxide partial pressure of the target object is simultaneously acquired to obtain the relative change relationship between the transdermal carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure; based on the relative change relationship and the transdermal carbon dioxide release characteristics, the energy metabolism characteristics of the target object are estimated, specifically: Based on the sampling frequency of the transcutaneous carbon dioxide partial pressure, the exhaled carbon dioxide partial pressure of the target object is acquired synchronously; the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure are continuously compared to obtain the curve of the difference between the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure. Based on the difference change curve, the organ tissue blood flow dynamic characteristics of the target object are estimated; based on the organ tissue blood flow dynamic characteristics and the transdermal carbon dioxide release characteristics, the organ energy metabolism characteristics of the target object are estimated; wherein, the organ energy metabolism characteristics include the organ tissue energy metabolism rate.

[0007] Preferably, in S300, a metabolic model matching the target object is constructed based on the energy metabolism characteristics to predict the trend of disease risk changes in the target object, specifically as follows: Based on the energy metabolism characteristics, including organ and tissue energy metabolism rates and theoretical metabolic models of organs and tissues, an actual metabolic model of the organs and tissues matching the target object is constructed. Based on the time evolution analysis results of the actual metabolic model of the organ tissue, the trend of organ tissue disease risk change of the target object is predicted; wherein, the trend of organ tissue aberration risk change includes the trend of organ tissue disease risk occurrence probability change.

[0008] Preferably, in step S400, based on the disease risk change trend, the clinical test data of the target object are evaluated and screened to obtain a reliable clinical test dataset, thereby generating a disease risk assessment result, specifically as follows: Based on the trend of changes in the probability of occurrence of organ and tissue diseases included in the disease risk change trend, a credible time interval for clinical testing of the target subjects is determined; based on the credible time interval, the clinical testing data of the target subjects are evaluated and screened to obtain a credible clinical testing dataset. Clustering and predictive analysis are performed on the credible clinical test dataset to generate disease risk assessment results.

[0009] On the other hand, the present invention provides a clinical assessment and prediction system for exhaled breath and transcutaneous carbon dioxide monitoring, the system comprising the following modules: The body surface temperature recognition module is used to obtain skin temperature fluctuation characteristics based on the body surface temperature data of the target object, thereby determining the target skin area for transdermal carbon dioxide monitoring of the target object; The transdermal carbon dioxide detection module is used to obtain the transdermal carbon dioxide release characteristics based on the transdermal carbon dioxide partial pressure of the target skin area; The exhaled carbon dioxide detection and processing module is used to simultaneously acquire the exhaled carbon dioxide partial pressure of the target object, thereby obtaining the relative change relationship between the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure. An energy metabolism estimation module is used to estimate the energy metabolism characteristics of the target object based on the relative change relationship and the transdermal carbon dioxide release characteristics. The disease risk prediction module is used to construct a metabolic model that matches the target object based on the energy metabolism characteristics, so as to predict the trend of disease risk change of the target object; The detection data processing module is used to evaluate and screen the clinical detection data of the target object based on the disease risk change trend, obtain a reliable clinical detection dataset, and thus generate disease risk assessment results.

[0010] Preferably, the body surface temperature recognition module is used to obtain skin temperature fluctuation characteristics based on the body surface temperature data of the target object, thereby determining the target skin area for transdermal carbon dioxide monitoring of the target object, specifically: The global surface thermal infrared dynamic image of the target object is acquired, and the global surface thermal infrared dynamic image is subjected to frame segmentation and transformation analysis to determine the dynamic data of the target object's surface temperature, thereby obtaining the skin temperature change rate of the target object. Based on the skin temperature change rate, the stability of transdermal carbon dioxide release over the entire body surface area of ​​the target object is determined; based on the stability of transdermal carbon dioxide release, the target skin area for transdermal carbon dioxide monitoring of the target object is determined. The transdermal carbon dioxide detection module is used to obtain transdermal carbon dioxide release characteristics based on the transdermal carbon dioxide partial pressure of the target skin area, specifically: Transdermal carbon dioxide partial pressure data of the target skin region are collected, and time-difference variation analysis is performed on the transdermal carbon dioxide partial pressure data to obtain the transdermal carbon dioxide release rate of the target skin region, which is used as the transdermal carbon dioxide release characteristic.

[0011] Preferably, the exhaled carbon dioxide detection and processing module is used to simultaneously acquire the exhaled carbon dioxide partial pressure of the target object, thereby obtaining the relative change relationship between the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure, specifically: Based on the sampling frequency of the transcutaneous carbon dioxide partial pressure, the exhaled carbon dioxide partial pressure of the target object is acquired synchronously; the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure are continuously compared to obtain the curve of the difference between the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure. The energy metabolism estimation module is used to estimate the energy metabolism characteristics of the target object based on the relative change relationship and the transdermal carbon dioxide release characteristics, specifically: Based on the difference change curve, the organ tissue blood flow dynamic characteristics of the target object are estimated; based on the organ tissue blood flow dynamic characteristics and the transdermal carbon dioxide release characteristics, the organ energy metabolism characteristics of the target object are estimated; wherein, the organ energy metabolism characteristics include the organ tissue energy metabolism rate.

[0012] Preferably, the disease risk prediction module is used to construct a metabolic model matching the target object based on the energy metabolism characteristics, thereby predicting the trend of disease risk changes in the target object, specifically as follows: Based on the energy metabolism characteristics, including organ and tissue energy metabolism rates and theoretical metabolic models of organs and tissues, an actual metabolic model of the organs and tissues matching the target object is constructed. Based on the time evolution analysis results of the actual metabolic model of the organ tissue, the trend of organ tissue disease risk change of the target object is predicted; wherein, the trend of organ tissue aberration risk change includes the trend of organ tissue disease risk occurrence probability change.

[0013] Preferably, the detection data processing module is used to evaluate and screen the clinical detection data of the target object based on the disease risk change trend, obtain a reliable clinical detection dataset, and thereby generate a disease risk assessment result, specifically as follows: Based on the trend of changes in the probability of occurrence of organ and tissue diseases included in the disease risk change trend, a credible time interval for clinical testing of the target subjects is determined; based on the credible time interval, the clinical testing data of the target subjects are evaluated and screened to obtain a credible clinical testing dataset. Clustering and predictive analysis are performed on the credible clinical test dataset to generate disease risk assessment results.

[0014] Compared with the prior art, the present invention has the following beneficial effects: This invention provides a clinical assessment and prediction method and system for exhaled and transcutaneous carbon dioxide monitoring. Based on the target subject's body surface temperature data, it determines the target skin area for transcutaneous carbon dioxide monitoring; based on the transcutaneous carbon dioxide partial pressure in the target skin area, it obtains the transcutaneous carbon dioxide release characteristics; it acquires the relative change relationship between transcutaneous and exhaled carbon dioxide partial pressures, and combines this with the transcutaneous carbon dioxide release characteristics to estimate energy metabolism characteristics, thereby constructing a metabolic model matching the target subject to predict disease risk trends; it evaluates and screens clinical test data to obtain a reliable clinical test dataset and generates disease risk assessment results. This invention, through comparative analysis of exhaled and transcutaneous carbon dioxide partial pressure data, helps to comprehensively reflect the true physical state, rapidly predict and assess patients' potential health risks, and improve the reliability of disease risk assessments. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a flowchart of the clinical assessment and prediction method for exhaled breath and transcutaneous carbon dioxide monitoring provided by the present invention.

[0016] Figure 2 This is a structural diagram of the clinical assessment and prediction system for exhaled breath and transcutaneous carbon dioxide monitoring provided by the present invention. Detailed Implementation

[0017] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for explaining the present invention and not for limiting the present invention. Furthermore, it should be noted that, for ease of description, only the parts related to the present invention are shown in the accompanying drawings, not all structures. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of the present invention.

[0018] The terms "comprising" and "having," and any variations thereof, used in this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0019] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0020] Please see Figure 1 As shown, this invention provides a clinical assessment and prediction method for exhaled breath and transcutaneous carbon dioxide monitoring, the method comprising the following steps: S100: Based on the surface temperature data of the target subject, the skin temperature fluctuation characteristics are obtained, thereby determining the target skin area for transdermal carbon dioxide monitoring of the target subject; based on the transdermal carbon dioxide partial pressure of the target skin area, the transdermal carbon dioxide release characteristics are obtained. S200: Simultaneously acquire the partial pressure of exhaled carbon dioxide of the target subject to obtain the relative change relationship between transdermal carbon dioxide partial pressure and exhaled carbon dioxide partial pressure; based on the relative change relationship and transdermal carbon dioxide release characteristics, estimate the energy metabolism characteristics of the target subject; S300: Based on energy metabolism characteristics, construct a metabolic model that matches the target subject to predict the trend of disease risk changes in the target subject; S400: Based on the trend of disease risk changes, assess and screen the clinical test data of the target subjects to obtain a reliable clinical test dataset, thereby generating disease risk assessment results.

[0021] Furthermore, in S100, based on the target subject's surface temperature data, skin temperature fluctuation characteristics are obtained to determine the target skin area for transdermal carbon dioxide monitoring; based on the transdermal carbon dioxide partial pressure of the target skin area, transdermal carbon dioxide release characteristics are obtained, specifically: The global surface thermal infrared dynamic image of the target object is acquired. The global surface thermal infrared dynamic image is then segmented and transformed to determine the dynamic data of the target object's surface temperature, thereby obtaining the skin temperature change rate of the target object. Based on the rate of change in skin temperature, determine the stability of transdermal carbon dioxide release across the entire body surface area of ​​the target subject; based on the stability of transdermal carbon dioxide release, determine the target skin area for transdermal carbon dioxide monitoring of the target subject. Transdermal carbon dioxide partial pressure data of the target skin area were collected, and time-difference variation analysis was performed on the transdermal carbon dioxide partial pressure data to obtain the transdermal carbon dioxide release rate of the target skin area, which was used as the transdermal carbon dioxide release characteristic.

[0022] Transdermal carbon dioxide (CVD) monitoring utilizes electrodes with heating capabilities to heat the skin of the target subject, increasing blood flow in the subcutaneous capillaries and thus enhancing skin permeability. This allows the gas to be released more smoothly through the subcutaneous tissue. The pressure of the released gas is then measured using electrodes to obtain the corresponding subcutaneous CCD partial pressure. As the above analysis shows, the target subject's skin temperature affects the efficiency of transdermal CCD release and diffusion; only when the transdermal CCD release and diffusion efficiency is sufficiently high can the measured transdermal CCD partial pressure be considered reliable. To ensure the reliability of transdermal carbon dioxide partial pressure detection of the target object, dynamic thermal infrared imaging is first performed on the target object to obtain a global dynamic thermal infrared image of the target object's body surface. The global dynamic thermal infrared image of the body surface is then processed by frame segmentation and transformation analysis to obtain dynamic data of the target object's body surface temperature. The aforementioned dynamic data of body surface temperature refers to the temperature change data of each grid area under the target object's skin within a preset time interval. Then, the aforementioned dynamic data of body surface temperature is analyzed for time variation to obtain the skin temperature change rate (i.e., skin temperature change rate) of each grid area under the target object's skin surface.

[0023] The above analysis shows that transdermal carbon dioxide can only be effectively and continuously released and diffused when the target subject's skin temperature remains consistently high. Only under these conditions can the transdermal carbon dioxide partial pressure be monitored reliably. Therefore, it is necessary to compare the skin temperature change rate of each grid region with a threshold to determine whether the transdermal carbon dioxide release in each grid region is stable. Specifically, the skin temperature change rate of each grid region is compared with a preset change rate threshold. If the skin temperature change rate is less than the preset change rate threshold, the transdermal carbon dioxide release of the corresponding grid region is determined to be stable; otherwise, the transdermal carbon dioxide release of the corresponding grid region is determined to be unstable. Thus, all grid regions with stable transdermal carbon dioxide release are identified as the target skin regions for transdermal carbon dioxide monitoring of the target subject. This ensures that the target skin region is monitored for transdermal carbon dioxide partial pressure only under suitable subcutaneous tissue temperature conditions, guaranteeing the reliability of the transdermal carbon dioxide partial pressure data.

[0024] Transdermal carbon dioxide partial pressure data for each target skin region is collected using a transdermal carbon dioxide partial pressure sensor. It can be understood that the transdermal carbon dioxide partial pressure data is directly proportional to the transdermal carbon dioxide release volume data. By performing time difference variation analysis on the transdermal carbon dioxide partial pressure data, the transdermal carbon dioxide release rate (i.e., the volume of transdermal carbon dioxide released per unit time in each target skin region) can be obtained.

[0025] Furthermore, in S200, the exhaled carbon dioxide partial pressure of the target subject is simultaneously acquired to obtain the relative change relationship between the transdermal carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure; based on the relative change relationship and the transdermal carbon dioxide release characteristics, the energy metabolism characteristics of the target subject are estimated, specifically: Based on the sampling frequency of transcutaneous carbon dioxide partial pressure, the exhaled carbon dioxide partial pressure of the target subject is acquired synchronously; the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure are continuously compared to obtain the curve of the difference between the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure. Based on the difference change curve, the dynamic characteristics of organ and tissue blood flow of the target object are estimated; based on the dynamic characteristics of organ and tissue blood flow and the transdermal carbon dioxide release characteristics, the energy metabolism characteristics of the target object are estimated; among them, the organ energy metabolism characteristics include the energy metabolism rate of organ and tissue.

[0026] Exhaled carbon dioxide refers to the carbon dioxide contained in the gas exhaled during human respiration. Considering the cyclical nature of respiration, and focusing on the exhalation process, it mainly includes the initiation phase, the ascending phase, the plateau phase, and the end phase. In the initiation phase, the exhaled gas consists of dead space gas in the respiratory tract and generally does not contain carbon dioxide. In the ascending phase, the gas is a mixture of dead space gas and alveolar gas; as exhalation progresses, the proportion of alveolar gas increases, and the carbon dioxide concentration in the exhaled mixture increases rapidly. The plateau phase is almost horizontal, with the exhaled gas consisting of alveolar gas with a high concentration of carbon dioxide, and the carbon dioxide partial pressure is at its highest. The end phase is the descending phase of inspiration, a steep drop to the baseline level, representing the start of inspiration, and the carbon dioxide concentration drops sharply to zero. Exhaled carbon dioxide can reflect cardiac output and pulmonary perfusion. Therefore, the partial pressure of exhaled carbon dioxide also reflects the functioning of organs and tissues such as the heart and lungs. Thus, comprehensive and accurate measurement of exhaled carbon dioxide partial pressure is of great significance for the targeted determination of energy metabolism and other operational parameters of organs and tissues.

[0027] When a target subject is potentially developing conditions such as pulmonary embolism, a difference will exist between the exhaled and transcutaneous partial pressures of carbon dioxide, and this difference will gradually increase as the condition progresses. Specifically, by continuously comparing the transcutaneous and exhaled carbon dioxide partial pressures, a curve showing the change in the difference between the two pressures is obtained. Based on this curve, the dynamic characteristics of organ and tissue blood flow in the target subject are estimated. It is understandable that when organs such as the heart or lungs have underlying conditions, the blood flow velocity within these organs and tissues decreases. At this time, the percutaneous carbon dioxide partial pressure increases while the exhaled carbon dioxide partial pressure decreases. This difference gradually widens, primarily reflecting a slowdown in the organ's energy metabolism. Based on this analysis, the dynamic characteristics of organ blood flow in the target subject are estimated using the difference curve. Furthermore, the energy metabolism rate of organs such as the heart or lungs is estimated based on these dynamic characteristics and the percutaneous carbon dioxide release characteristics. A convolutional neural network model can be used to process these dynamic characteristics and the percutaneous carbon dioxide release characteristics to obtain the organ's energy metabolism rate, which will not be detailed here.

[0028] Furthermore, in S300, a metabolic model matching the target subject is constructed based on energy metabolism characteristics to predict the trend of disease risk changes in the target subject, specifically as follows: Based on the energy metabolism characteristics, including the energy metabolism rate of organs and tissues and the theoretical metabolic model of organs and tissues, construct an actual metabolic model of organs and tissues that matches the target object; Based on the time evolution analysis results of the actual metabolic model of organs and tissues, the trend of organ and tissue disease risk changes of the target subjects is predicted; among them, the trend of organ and tissue abnormality risk changes includes the trend of the probability of organ and tissue disease occurrence.

[0029] Different types of organs and tissues, such as the heart and lungs, have different physiological structures and functions, resulting in different energy metabolism profiles. These profiles include the organ and tissue energy metabolism rate and the theoretical metabolic model (i.e., the energy consumption model for maintaining basic normal function in a local tissue). To accurately characterize the metabolism of different organs and tissues, an actual metabolic model of the target organ and tissue is constructed based on the organ and tissue energy metabolism rate and the theoretical metabolic model. This ensures that the actual metabolic model is consistent with the corresponding organ and tissue. Furthermore, time-evolution analysis is performed using the actual metabolic model to predict the energy metabolism trend of organs and tissues over a future period. If a sudden event occurs in the energy metabolism of an organ or tissue (such as a sudden drop or increase in the energy metabolism rate) in the future, the predicted probability of organ and tissue disease risk for the target individual will increase. Conversely, if no sudden event occurs (such as a relatively stable energy metabolism rate), the predicted probability of local tissue disease risk for the target individual is low. The model also identifies the time range within which the probability of organ and tissue disease risk exceeds a preset probability threshold, providing a basis for subsequent evaluation and screening of clinical test data.

[0030] Furthermore, in S400, based on the changing trends of disease risk, the clinical testing data of the target subjects are evaluated and screened to obtain a reliable clinical testing dataset, thereby generating disease risk assessment results, specifically: Based on the trends in disease risk, including the trends in the probability of occurrence of organ and tissue diseases, a credible time interval for conducting clinical tests on the target subjects is determined; based on the credible time interval, the clinical test data of the target subjects are evaluated and screened to obtain a credible clinical test dataset. Clustering and predictive analysis are performed on reliable clinical test datasets to generate disease risk assessment results.

[0031] This study extracts the probability trends of organ and tissue disease risk changes. Based on these trends, it determines the time range within which the probability of an organ or tissue disease exceeding a preset probability threshold is expected. Extending this extended time range forward and backward by a certain time length from the earliest and latest points of this range, it establishes a reliable time interval for clinical testing of the target subject. Then, using this reliable time interval as a benchmark, the clinical testing data from the target subject is filtered, extracting only data generated within this reliable time interval. This extracted data forms a reliable clinical testing dataset. A neural network model (such as an LSTM network model) is then used to perform clustering and predictive analysis on the reliable clinical testing dataset to generate disease risk assessment results. These results may include information such as the type of disease the target subject may have and the stage of disease onset.

[0032] Please see Figure 2 As shown, this invention provides a clinical assessment and prediction system for exhaled breath and transcutaneous carbon dioxide monitoring, which includes the following modules: The body surface temperature recognition module is used to obtain skin temperature fluctuation characteristics based on the body surface temperature data of the target object, thereby determining the target skin area for transdermal carbon dioxide monitoring of the target object; The transdermal carbon dioxide detection module is used to obtain the transdermal carbon dioxide release characteristics based on the transdermal carbon dioxide partial pressure of the target skin area; The exhaled carbon dioxide detection and processing module is used to simultaneously acquire the partial pressure of exhaled carbon dioxide of the target object, thereby obtaining the relative change relationship between transdermal carbon dioxide partial pressure and exhaled carbon dioxide partial pressure. The energy metabolism estimation module is used to estimate the energy metabolism characteristics of the target object based on relative changes and transdermal carbon dioxide release characteristics. The disease risk prediction module is used to construct a metabolic model that matches the target object based on energy metabolism characteristics, thereby predicting the trend of disease risk changes in the target object; The detection data processing module is used to evaluate and screen the clinical detection data of target subjects based on the trend of disease risk changes, obtain a reliable clinical detection dataset, and thus generate disease risk assessment results.

[0033] Furthermore, the skin surface temperature recognition module is used to obtain skin temperature fluctuation characteristics based on the target object's skin surface temperature data, thereby determining the target skin area for transdermal carbon dioxide monitoring of the target object, specifically: The global surface thermal infrared dynamic image of the target object is acquired. The global surface thermal infrared dynamic image is then segmented and transformed to determine the dynamic data of the target object's surface temperature, thereby obtaining the skin temperature change rate of the target object. Based on the rate of change in skin temperature, determine the stability of transdermal carbon dioxide release across the entire body surface area of ​​the target subject; based on the stability of transdermal carbon dioxide release, determine the target skin area for transdermal carbon dioxide monitoring of the target subject. The transdermal carbon dioxide detection module is used to obtain the transdermal carbon dioxide release characteristics based on the transdermal carbon dioxide partial pressure of the target skin area, specifically: Transdermal carbon dioxide partial pressure data of the target skin area were collected, and time-difference variation analysis was performed on the transdermal carbon dioxide partial pressure data to obtain the transdermal carbon dioxide release rate of the target skin area, which was used as the transdermal carbon dioxide release characteristic.

[0034] Furthermore, the exhaled carbon dioxide detection and processing module is used to simultaneously acquire the partial pressure of exhaled carbon dioxide of the target object, thereby obtaining the relative change relationship between the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure, specifically: Based on the sampling frequency of transcutaneous carbon dioxide partial pressure, the exhaled carbon dioxide partial pressure of the target subject is acquired synchronously; the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure are continuously compared to obtain the curve of the difference between the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure. The energy metabolism estimation module is used to estimate the energy metabolism characteristics of a target object based on relative changes and transdermal carbon dioxide release characteristics. Specifically: Based on the difference change curve, the dynamic characteristics of organ and tissue blood flow of the target object are estimated; based on the dynamic characteristics of organ and tissue blood flow and the transdermal carbon dioxide release characteristics, the energy metabolism characteristics of the target object are estimated; among them, the organ energy metabolism characteristics include the energy metabolism rate of organ and tissue.

[0035] Furthermore, the disease risk prediction module is used to construct a metabolic model matching the target object based on energy metabolism characteristics, thereby predicting the trend of disease risk changes in the target object, specifically: Based on the energy metabolism characteristics, including the energy metabolism rate of organs and tissues and the theoretical metabolic model of organs and tissues, construct an actual metabolic model of organs and tissues that matches the target object; Based on the time evolution analysis results of the actual metabolic model of organs and tissues, the trend of organ and tissue disease risk changes of the target subjects is predicted; among them, the trend of organ and tissue abnormality risk changes includes the trend of the probability of organ and tissue disease occurrence.

[0036] Furthermore, the detection data processing module is used to evaluate and screen the clinical detection data of target subjects based on the changing trends of disease risk, obtain a reliable clinical detection dataset, and thus generate disease risk assessment results, specifically: Based on the trends in disease risk, including the trends in the probability of occurrence of organ and tissue diseases, a credible time interval for conducting clinical tests on the target subjects is determined; based on the credible time interval, the clinical test data of the target subjects are evaluated and screened to obtain a credible clinical test dataset. Clustering and predictive analysis are performed on reliable clinical test datasets to generate disease risk assessment results.

[0037] The clinical assessment and prediction system for exhaled and transcutaneous carbon dioxide monitoring of the present invention operates and has the same effect as the aforementioned clinical assessment and prediction method for exhaled and transcutaneous carbon dioxide monitoring, and will not be described again here.

[0038] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of a necessary general-purpose hardware platform, or by a combination of hardware and software. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a computer product. The present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0039] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Other embodiments may also be used. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A clinical assessment and prediction method for exhaled and transcutaneous carbon dioxide monitoring, characterized in that, The method includes the following steps: S100: Based on the surface temperature data of the target object, obtain the skin temperature fluctuation characteristics, thereby determining the target skin area for transdermal carbon dioxide monitoring of the target object; based on the transdermal carbon dioxide partial pressure of the target skin area, obtain the transdermal carbon dioxide release characteristics; S200: Simultaneously acquire the exhaled carbon dioxide partial pressure of the target object to obtain the relative change relationship between the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure; estimate the energy metabolism characteristics of the target object based on the relative change relationship and the transcutaneous carbon dioxide release characteristics; S300: Based on the energy metabolism characteristics, construct a metabolic model that matches the target object, thereby predicting the trend of disease risk changes in the target object; S400: Based on the disease risk change trend, evaluate and screen the clinical test data of the target subjects to obtain a reliable clinical test dataset, thereby generating disease risk assessment results.

2. The method according to claim 1, characterized in that, In S100, based on the surface temperature data of the target object, skin temperature fluctuation characteristics are obtained to determine the target skin area for transdermal carbon dioxide monitoring of the target object; based on the transdermal carbon dioxide partial pressure of the target skin area, transdermal carbon dioxide release characteristics are obtained, specifically: The global surface thermal infrared dynamic image of the target object is acquired, and the global surface thermal infrared dynamic image is subjected to frame segmentation and transformation analysis to determine the dynamic data of the target object's surface temperature, thereby obtaining the skin temperature change rate of the target object. Based on the skin temperature change rate, the stability of transdermal carbon dioxide release over the entire body surface area of ​​the target object is determined; based on the stability of transdermal carbon dioxide release, the target skin area for transdermal carbon dioxide monitoring of the target object is determined. Transdermal carbon dioxide partial pressure data of the target skin region are collected, and time-difference variation analysis is performed on the transdermal carbon dioxide partial pressure data to obtain the transdermal carbon dioxide release rate of the target skin region, which is used as the transdermal carbon dioxide release characteristic.

3. The method according to claim 1, characterized in that, In S200, the exhaled carbon dioxide partial pressure of the target object is simultaneously acquired to obtain the relative change relationship between the transdermal carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure; based on the relative change relationship and the transdermal carbon dioxide release characteristics, the energy metabolism characteristics of the target object are estimated, specifically: Based on the sampling frequency of the transcutaneous carbon dioxide partial pressure, the exhaled carbon dioxide partial pressure of the target object is acquired synchronously; the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure are continuously compared to obtain the curve of the difference between the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure. Based on the difference change curve, the organ tissue blood flow dynamic characteristics of the target object are estimated; based on the organ tissue blood flow dynamic characteristics and the transdermal carbon dioxide release characteristics, the organ energy metabolism characteristics of the target object are estimated; wherein, the organ energy metabolism characteristics include the organ tissue energy metabolism rate.

4. The method according to claim 1, characterized in that, In S300, based on the energy metabolism characteristics, a metabolic model matching the target object is constructed to predict the disease risk change trend of the target object, specifically as follows: Based on the energy metabolism characteristics, including organ and tissue energy metabolism rates and theoretical metabolic models of organs and tissues, an actual metabolic model of the organs and tissues matching the target object is constructed. Based on the time evolution analysis results of the actual metabolic model of the organ tissue, the trend of organ tissue disease risk change of the target object is predicted; wherein, the trend of organ tissue aberration risk change includes the trend of organ tissue disease risk occurrence probability change.

5. The method according to claim 1, characterized in that, In S400, based on the stated disease risk change trend, the clinical testing data of the target subjects are evaluated and screened to obtain a reliable clinical testing dataset, thereby generating disease risk assessment results, specifically as follows: Based on the trend of changes in the probability of occurrence of organ and tissue diseases included in the disease risk change trend, a credible time interval for clinical testing of the target subjects is determined; based on the credible time interval, the clinical testing data of the target subjects are evaluated and screened to obtain a credible clinical testing dataset. Clustering and predictive analysis are performed on the credible clinical test dataset to generate disease risk assessment results.

6. A clinical assessment and prediction system for exhaled breath and transcutaneous carbon dioxide monitoring, characterized in that, The system includes the following modules: The body surface temperature recognition module is used to obtain skin temperature fluctuation characteristics based on the body surface temperature data of the target object, thereby determining the target skin area for transdermal carbon dioxide monitoring of the target object; The transdermal carbon dioxide detection module is used to obtain the transdermal carbon dioxide release characteristics based on the transdermal carbon dioxide partial pressure of the target skin area; The exhaled carbon dioxide detection and processing module is used to simultaneously acquire the exhaled carbon dioxide partial pressure of the target object, thereby obtaining the relative change relationship between the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure. An energy metabolism estimation module is used to estimate the energy metabolism characteristics of the target object based on the relative change relationship and the transdermal carbon dioxide release characteristics. The disease risk prediction module is used to construct a metabolic model that matches the target object based on the energy metabolism characteristics, so as to predict the trend of disease risk change of the target object; The detection data processing module is used to evaluate and screen the clinical detection data of the target object based on the disease risk change trend, obtain a reliable clinical detection dataset, and thus generate disease risk assessment results.

7. The system according to claim 6, characterized in that, The body surface temperature recognition module is used to obtain skin temperature fluctuation characteristics based on the body surface temperature data of the target object, thereby determining the target skin area for transdermal carbon dioxide monitoring of the target object, specifically: The global surface thermal infrared dynamic image of the target object is acquired, and the global surface thermal infrared dynamic image is subjected to frame segmentation and transformation analysis to determine the dynamic data of the target object's surface temperature, thereby obtaining the skin temperature change rate of the target object. Based on the skin temperature change rate, the stability of transdermal carbon dioxide release over the entire body surface area of ​​the target object is determined; based on the stability of transdermal carbon dioxide release, the target skin area for transdermal carbon dioxide monitoring of the target object is determined. The transdermal carbon dioxide detection module is used to obtain transdermal carbon dioxide release characteristics based on the transdermal carbon dioxide partial pressure of the target skin area, specifically: Transdermal carbon dioxide partial pressure data of the target skin region are collected, and time-difference variation analysis is performed on the transdermal carbon dioxide partial pressure data to obtain the transdermal carbon dioxide release rate of the target skin region, which is used as the transdermal carbon dioxide release characteristic.

8. The system according to claim 6, characterized in that, The exhaled carbon dioxide detection and processing module is used to simultaneously acquire the partial pressure of exhaled carbon dioxide of the target object, thereby obtaining the relative change relationship between the transdermal carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure, specifically: Based on the sampling frequency of the transcutaneous carbon dioxide partial pressure, the exhaled carbon dioxide partial pressure of the target object is acquired synchronously; the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure are continuously compared to obtain the curve of the difference between the transcutaneous carbon dioxide partial pressure and the exhaled carbon dioxide partial pressure. The energy metabolism estimation module is used to estimate the energy metabolism characteristics of the target object based on the relative change relationship and the transdermal carbon dioxide release characteristics, specifically: Based on the difference change curve, the organ tissue blood flow dynamic characteristics of the target object are estimated; based on the organ tissue blood flow dynamic characteristics and the transdermal carbon dioxide release characteristics, the organ energy metabolism characteristics of the target object are estimated; wherein, the organ energy metabolism characteristics include the organ tissue energy metabolism rate.

9. The system according to claim 6, characterized in that, The disease risk prediction module is used to construct a metabolic model matching the target object based on the energy metabolism characteristics, thereby predicting the trend of disease risk changes in the target object, specifically: Based on the energy metabolism characteristics, including organ and tissue energy metabolism rates and theoretical metabolic models of organs and tissues, an actual metabolic model of the organs and tissues matching the target object is constructed. Based on the time evolution analysis results of the actual metabolic model of the organ tissue, the trend of organ tissue disease risk change of the target object is predicted; wherein, the trend of organ tissue aberration risk change includes the trend of organ tissue disease risk occurrence probability change.

10. The system according to claim 6, characterized in that, The detection data processing module is used to evaluate and screen the clinical detection data of the target object based on the disease risk change trend, obtain a reliable clinical detection dataset, and thus generate disease risk assessment results, specifically: Based on the trend of changes in the probability of occurrence of organ and tissue diseases included in the disease risk change trend, a credible time interval for clinical testing of the target subjects is determined; based on the credible time interval, the clinical testing data of the target subjects are evaluated and screened to obtain a credible clinical testing dataset. Clustering and predictive analysis are performed on the credible clinical test dataset to generate disease risk assessment results.

Images