A method and system for predicting the risk of pulmonary arterial hypertension in high altitude areas

Abstract

The present application relates to the technical field of medical data, especially to a highland pulmonary arterial hypertension risk prediction method and system, the model is periodically updated, the collected data is pretreated, the state of risk prediction is determined by comparing the actual model prediction efficiency consistency rate with the preset threshold value; the maximum allowed environmental compensation value is adjusted based on the determination result, the hemoglobin concentration is simulated, and the abnormal fluctuation capture sensitivity is determined, the present application realizes the unified processing of the high-pressure risk prediction system prediction energy efficiency and the optimization of the analysis performance, reduces the system energy consumption, effectively improves the data effectiveness guarantee and resource utilization rate.

Description

Technical Field

[0001] This invention relates to the field of medical data technology, and in particular to a method and system for predicting the risk of pulmonary hypertension in high-altitude areas. Background Technology

[0002] Pulmonary hypertension can lead to right heart failure, and high-altitude areas, due to prolonged hypoxia, are an independent risk factor for pulmonary hypertension. This results in a static working environment for researchers, making it impossible to optimize based on feedback, and compromising the reliability and stability of optimization performance. To avoid potential risks, quantify the predictive efficacy of different measures, optimize technical approaches, and place higher demands on the scientific rigor and comparability of data collection and adjustment results. Early identification methods in many technical solutions can detect anomalies in a timely manner, significantly improving the accuracy of overall risk prediction, thus becoming a necessary and effective means. Therefore, traditional early identification methods are currently one of the main methods for predicting the risk of pulmonary hypertension.

[0003] However, existing prediction models mostly adopt a uniform and simple prediction, which is mostly static, single-modal, and isolated. Most methods can only be used to predict a large amount of invalid and low-quality data, resulting in a waste of resources and failing to systematically and dynamically capture the dynamic correlation between various parameters.

[0004] Meanwhile, existing analytical models have many shortcomings. Key parameters involved in the system often rely on empirical settings or fixed standard values, lacking the ability to perceive users' own conditions in real time, and failing to form a dynamic adjustment mechanism, thus reducing the efficiency of high-pressure risk prediction.

[0005] Chinese Patent Publication No. CN121096612A discloses a method and system for predicting the risk of pulmonary hypertension based on a model, including an area acquisition module and an optimal model determination module. The system determines the optimal prediction model by acquiring the offline area of ​​the subject in real time, and checks the corresponding pulmonary hypertension risk prediction results based on the output data of the prediction model.

[0006] Therefore, although the proposed scheme can determine the optimal prediction model, it still has the following problems: This scheme obtains the area using only a single real-time monitoring method. When other modules of the system malfunction or the environment changes, it cannot intelligently optimize the area data through the model. This results in an inability to effectively handle the consistency of model prediction performance across different detection cycles, thereby reducing the consistency of model prediction performance for pulmonary hypertension risk prediction. Summary of the Invention

[0007] To address this issue, the present invention provides a method and system for predicting the risk of pulmonary hypertension in high-altitude areas, thereby overcoming the problem of low consistency in model prediction performance caused by data processing bias resulting from the inability to generate corresponding update instructions based on environmental changes in existing technologies.

[0008] To achieve the above objectives, the present invention provides a method and system for predicting the risk of pulmonary hypertension in high-altitude areas, comprising, Obtain test sample load data, including blood oxygen saturation and hemoglobin concentration, from case information; Collect environmental data for each detection cycle, including simulated altitude and environmental compensation values; The load data and environmental data are preprocessed, including: cleaning, unit conversion and outlier correction; Based on the preprocessed data, the pulmonary hypertension risk characterization value for the test sample is calculated. The predictive characterization value for the system is determined to meet the standard based on the consistency rate of the model performance based on each hypertension risk characterization value. If it is determined that the system does not meet the standard, the corresponding adjustment instruction is generated based on the determined reason. The maximum permissible environmental compensation value for the system is based on the simulated altitude adjustment, wherein the maximum permissible environmental compensation value is the maximum value of the current environmental adaptability compensation obtained by querying a table. Based on the obtained adjusted maximum permissible environmental compensation value, a retest is performed. If the standard is still not met, the corresponding processing method is selected, including issuing adjustment instructions for simulated hemoglobin concentration and abnormal fluctuation detection sensitivity. After adjustment, under the condition that the criteria are met, the prediction of pulmonary hypertension risk is completed.

[0009] Furthermore, the risk level prediction process includes: The expected high-pressure risk characterization value is calculated as the weighted error sum of the maximum allowable environmental compensation value of simulated hemoglobin concentration of the test sample in each cycle, mapped by a normalization function; The simulated hemoglobin concentration and maximum allowable environmental compensation value of the test sample in each cycle are calculated using a preset mapping function, and recorded as the actual high-pressure risk characterization value. The obtained actual high-pressure risk characterization value is compared with the expected high-pressure risk characterization value; The comparison results are compared with the preset threshold to obtain the statistical model's prediction performance consistency rate. Determine whether the risk characterization value predicted for the current system meets the standard based on the model's prediction performance consistency rate. The model prediction performance consistency rate is the percentage of the number of test samples in which the model's expected high-pressure risk characterization value matches the actual high-pressure risk characterization value. If the risk characterization value predicted by the current system does not meet the standard, the reason for non-compliance is determined based on the average pulmonary oxygenation recovery time in each cycle of the inconsistent sample. The pulmonary oxygenation recovery time is the difference between the average voltage value of the isoelectric line read in the same cardiac cycle and the electrocardiogram signal voltage value at the corresponding measurement point. Continue monitoring once the risk characterization values ​​predicted for the current system meet the standards.

[0010] Furthermore, the process of determining the reasons why the predicted risk characterization value for the current system does not meet the standard based on the pulmonary circulation oxygenation recovery time includes: The actual blood oxygen saturation of the test samples was obtained from the case information; Determine the reasons why the predicted risk characterization value for the current system does not meet the standard based on the pulmonary circulation oxygenation recovery time; If the cause is determined to be insufficient pulmonary vascular compensation function, the maximum allowable environmental compensation value is adjusted according to the simulated altitude; wherein, the simulated altitude is the input actual geographical altitude; If the cause is determined to be insufficient coagulation function, the simulated hemoglobin concentration is adjusted according to the comprehensive value of arterial blood oxygen content in inconsistent samples; wherein, the simulated hemoglobin concentration is a characterization value of the individual blood oxygen-carrying capacity of the input test sample through the built-in algorithm of the model; The arterial blood oxygen content P is calculated using the following formula: P=(1.34×ρ×B)+(0.003×V) Where ρ is the simulated hemoglobin concentration; B is the blood oxygen saturation; V is the arterial blood oxygen partial pressure; 1.34 is the oxygen binding coefficient of hemoglobin; and 0.003 is the physical solubility coefficient of oxygen in plasma.

[0011] Furthermore, the process of adjusting the maximum permissible environmental compensation value based on the simulated altitude includes: Obtain the arithmetic mean of the simulated altitude of the test samples within each period; The maximum allowable environmental compensation value is increased based on the simulated altitude, and the increase in the maximum allowable environmental compensation value is negatively correlated with the simulated altitude.

[0012] Furthermore, the adjustment process for the maximum permissible environmental compensation value also includes: The portion of altitude that exceeds a preset threshold during the screening period; The cumulative exposure equivalent value was selected from the altitude of the selected inconsistent samples and recorded as the plateau cumulative exposure index. The maximum allowable environmental compensation value after adjustment is reduced based on the cumulative exposure index of the plateau, and the reduction in the maximum allowable environmental compensation value after adjustment is positively correlated with the cumulative exposure index of the plateau.

[0013] Furthermore, the process of determining whether the risk characterization value predicted by the current system after adjustment meets the standard includes: In response to the first repeated test condition, the cause was determined to be insufficient coagulation function, and the simulated hemoglobin concentration was adjusted according to the comprehensive value of arterial blood oxygen content in inconsistent samples; The first repeated detection condition is that after the system has completed the adjustment of the maximum allowable environmental compensation value, it determines that the risk characterization value predicted by the current system does not meet the standard based on the re-obtained model prediction performance consistency rate.

[0014] Furthermore, the process of adjusting the simulated hemoglobin concentration based on the composite value of arterial blood oxygen content in inconsistent samples includes: Calculate arterial blood oxygen content; The adjustment range for simulated hemoglobin concentration is determined based on arterial blood oxygen content in order to obtain the expected simulated hemoglobin concentration; Calculate the composite value of simulated hemoglobin concentration and obtain the median value of simulated hemoglobin concentration and the expected simulated hemoglobin concentration. The composite value of simulated hemoglobin concentration of consistent samples obtained through medical record information will be adjusted towards the median. The increase in arterial blood oxygen content led to an increase in simulated hemoglobin concentration, and the magnitude of the increase in simulated hemoglobin concentration was positively correlated with arterial blood oxygen content.

[0015] Furthermore, the regulation process of the coagulation function also includes: In response to the second repeated detection condition, it is determined that the reason why the current system's predicted risk characterization value does not meet the standard is that there is a deviation in the data preprocessing process, and an adjustment instruction for the sensitivity of abnormal fluctuation capture is issued according to the size of the dynamic data time window. The second repeated detection condition is that after the system completes the adjustment of the simulated hemoglobin concentration, it determines that the current system's predicted risk characterization value does not meet the standard based on the re-obtained model prediction performance consistency rate.

[0016] Furthermore, the process of determining whether the predicted risk characterization value based on the adjusted reassessment meets the standard includes: Set a time length to calculate historical time data and record it as the time window size; The sensitivity for detecting abnormal fluctuations is increased based on the size of the time window, and the increase in the sensitivity for detecting abnormal fluctuations is positively correlated with the size of the time window; wherein, the sensitivity for detecting abnormal fluctuations is the product of a preset coefficient of variation and the ratio of the preset time window to the actual time window.

[0017] Furthermore, the aforementioned high-altitude pulmonary hypertension risk prediction system includes: The data acquisition module is used to collect load data and environmental data for each testing cycle from the medical record information of the test samples in real time; wherein, the load data includes: blood oxygen saturation and hemoglobin concentration; the environmental data includes: altitude and environmental compensation value; The data processing module, which is connected to the data acquisition module, is used to preprocess the received load data and environmental data. The preprocessing methods include filtering the load data and environmental data, as well as pulmonary circulation oxygenation recovery time, to determine the consistency rate of model prediction performance. A risk characterization calculation module, which is connected to the data processing module, is used to calculate the high-pressure risk characterization value of the test sample based on the preprocessed load data and environmental data output by the data processing module. The risk assessment module, connected to the data processing module, is used to determine whether the predicted risk characterization values ​​for the current system meet the standards based on the consistency rate between each risk characterization value and the actual characterization value. The risk assessment module is also used to determine whether to generate an adjustment instruction based on the determination result, and to determine whether to issue an adjustment instruction to the execution module in the prediction system based on the preprocessed load data and environmental data re-acquired after executing the adjustment instruction. An execution module, which is connected to the risk assessment module, is used to adjust the operating parameters of the corresponding module to the corresponding values ​​according to the adjustment instructions output by the risk assessment module.

[0018] Compared with the prior art, the beneficial effects of the present invention are as follows: by setting up a risk assessment module, the present invention can effectively determine whether there is insufficient pulmonary vascular compensation function or insufficient coagulation function in the period by analyzing the case information of test samples in each collection period. At the same time, the risk assessment module can also output corresponding adjustment instructions according to the determined actual situation, thereby effectively eliminating the situation where the risk prediction consistency rate of load data is low due to altitude during the simulation process. While effectively improving the risk prediction consistency rate of test samples in different periods, it effectively avoids the impact of different environments on the stability of load data, thereby effectively improving the prediction efficiency of the solution for high pressure risk of the present invention.

[0019] Furthermore, the risk level prediction method of the present invention determines whether the predicted risk level for the current system meets the standard by comparing the statistical model prediction efficiency of the actual high-pressure risk characterization value and the expected high-pressure risk characterization value. This allows for intuitive quantification of the collected data, thereby quickly determining the actual situation of the load data and environmental data collection process within the current cycle. Through the rapidly determined results, dynamic evaluation of the collected data can be achieved, thereby effectively outputting corresponding adjustment instructions, further improving the efficiency consistency of the high-pressure risk prediction method of the present invention within the cycle.

[0020] Furthermore, the present invention determines the reason why the risk characterization value predicted by the current system does not meet the standard based on the pulmonary circulation oxygenation recovery time. Through the obtained comparison results, the corresponding adjustment command can be effectively selected, thereby ensuring that more accurate data can be obtained after updating through the adjustment command. While further improving the accuracy, it further avoids the occurrence of calculation errors, thereby further improving the efficiency and consistency rate of the solution described in the present invention for predicting high-pressure risks within a cycle.

[0021] Furthermore, the present invention compares the simulated altitude with the preset simulated altitude and adjusts the maximum allowable environmental compensation value based on the comparison result. This not only improves the completeness of the data processing process but also makes the judgment results that meet the standards more scenario-based and intelligent, thereby further improving the efficiency and consistency of the present invention's solution for predicting high-pressure risks within a cycle.

[0022] Furthermore, the altitudes exceeding a preset threshold within the screening period described in this invention are selected from the altitudes in the inconsistent samples, and their corresponding cumulative exposure equivalents are recorded as the plateau cumulative exposure index. The maximum allowable environmental compensation value is then adjusted based on the plateau cumulative exposure index, making the adjustment results more refined and accurate. This further improves data completeness, makes the judgment results more scenario-based, enhances accuracy, and avoids calculation errors, thereby further improving the consistency rate of the high-pressure risk prediction within the period described in this invention.

[0023] Furthermore, in response to the first repeated detection condition, the present invention determines that the cause is insufficient coagulation function, and adjusts the simulated hemoglobin concentration according to the comprehensive value of arterial blood oxygen content in inconsistent samples. This allows for a direct determination of the corresponding cause, thereby making corresponding adjustment instructions based on the determined cause. This further improves the efficiency and consistency of the present invention's scheme for predicting high-pressure risk within a cycle.

[0024] Furthermore, the present invention determines the adjustment range of the simulated hemoglobin concentration based on the arterial blood oxygen content to obtain the expected simulated hemoglobin concentration. The simulated hemoglobin concentration is adjusted according to the arterial blood oxygen content to adjust the arterial blood oxygen content to the corresponding value to ensure more accurate results. Furthermore, corresponding adjustment instructions are generated to ensure more accurate data acquisition. While further improving the response speed, the present invention further avoids deviations in comparison results, thereby further improving the efficiency and consistency rate of the present invention for predicting high-pressure risk within a cycle.

[0025] Furthermore, in response to the second repeated detection condition, the present invention determines that the reason why the predicted risk characterization value of the current system does not meet the standard is due to a deviation in the data preprocessing process, and issues an adjustment command for the sensitivity of abnormal fluctuation capture according to the size of the dynamic data time window. This can effectively improve the decision-making efficiency of the present invention for different situations, thereby effectively avoiding the processing obstacles caused by excessive interference, further improving the compatibility of data processing decisions, and further improving the efficiency consistency rate of the present invention for high-pressure risk prediction within a period.

[0026] Furthermore, the time length set in this invention is used to calculate historical time data and is recorded as the time window size. The sensitivity for capturing abnormal fluctuations is increased according to the time length, thereby intuitively determining whether the time window size affects the sensitivity for capturing abnormal fluctuations. By adjusting the time window size to the corresponding value, more accurate data is obtained. While further improving the response speed, the discrepancy in the comparison results is further avoided, thereby further improving the efficiency and consistency rate of the solution described in this invention for predicting high-pressure risks within a period.

[0027] Furthermore, the system of the present invention includes a data acquisition module, a data processing module, a risk characterization calculation module, a risk assessment module, and an execution module, realizing closed-loop management from signal acquisition and intelligent analysis to self-calibration. This reduces the reliance on the professional experience of operators, further improves the accuracy of judgment, and further enhances the accuracy of high-pressure risk prediction, thereby further improving the efficiency consistency of the solution of the present invention for high-pressure risk prediction within a cycle. Attached Figure Description

[0028] Figure 1 This is a flowchart of the method and system for predicting the risk of pulmonary hypertension in high-altitude areas as described in this invention; Figure 2 This is a flowchart illustrating the process of determining whether the risk characterization value for a prediction conforms to a standard based on the prediction performance consistency rate, as described in this invention. Figure 3 This is a flowchart illustrating parameter adjustment based on determined causes, as described in this invention. Figure 4 This is a structural block diagram of the risk prediction system described in this invention. Detailed Implementation

[0029] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0030] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0031] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0032] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0033] It should be noted that the data in this embodiment are all derived from a comprehensive analysis and evaluation of historical test data and corresponding historical test results from the system described in this invention over the three months prior to this test. Before this test, the system described in this invention comprehensively determines the preset values ​​stored in the database based on the analysis results of 25,863 cumulative tests over the previous three months and the processing results after handling 19,584 specific cases. Those skilled in the art will understand that the system described in this invention can determine the above-mentioned parameters for a single item by selecting the value with the highest proportion based on the data distribution as the preset standard parameter, using weighted summation to obtain the value as the preset standard parameter, substituting each historical data point into a specific formula and using the value obtained by the formula as the preset standard parameter, or other selection methods, as long as the system described in this invention can clearly define different specific situations in the single-item judgment process through the obtained values.

[0034] Please see Figure 1As shown, it is a flowchart of the method and system for predicting the risk of pulmonary hypertension in high-altitude areas according to the present invention, including: Obtain test sample load data, including blood oxygen saturation and hemoglobin concentration, from case information; Collect environmental data for each detection cycle, including simulated altitude and environmental compensation values; The load data and environmental data are preprocessed, including: cleaning, unit conversion and outlier correction; Based on the preprocessed data, the pulmonary hypertension risk characterization value for the test sample is calculated. The predictive characterization value for the system is determined to meet the standard based on the consistency rate of the model performance based on each hypertension risk characterization value. If it is determined that the system does not meet the standard, the corresponding adjustment instruction is generated based on the determined reason. The maximum permissible environmental compensation value for the system is based on the simulated altitude adjustment, wherein the maximum permissible environmental compensation value is the maximum value of the current environmental adaptability compensation obtained by querying a table. Based on the obtained adjusted maximum permissible environmental compensation value, a retest is performed. If the standard is still not met, the corresponding processing method is selected, including issuing adjustment instructions for simulated hemoglobin concentration and abnormal fluctuation detection sensitivity. After adjustment, under the condition that the criteria are met, the prediction of pulmonary hypertension risk is completed.

[0035] Specifically, in the risk prediction process for the test sample period described in this embodiment of the invention, the initial data input to the model is periodically updated, and load data and environmental data are collected. The data are preprocessed, and the preprocessed data are compared with the high-pressure risk characterization value to determine whether the consistency rate of risk prediction performance within the period meets the standard. If it is determined that the standard is not met, a corresponding adjustment instruction is generated according to the determined reason, and the system performs the corresponding operation according to the received instruction.

[0036] It is understandable that when the model is making high-pressure risk predictions, it will automatically update itself based on the detected consistency rate of the model prediction performance. It is understood that the model prediction performance consistency rate is the percentage of actual high-pressure risk characterization values ​​that are consistent with preset high-pressure risk characterization values ​​out of the total number of test samples. In this embodiment, the preset high-pressure risk characterization value is 60. Specifically, the system described in this invention stores and manages the collected data and processing results, and constructs a database that can be continuously updated.

[0037] Please see Figure 2 As shown, this is a flowchart illustrating the process of determining whether a risk characterization value for a prediction meets a standard based on the prediction performance consistency rate, as described in this invention. The processing method includes: Specifically, the expected high-pressure risk characterization value is calculated, which is the weighted error of the maximum allowable environmental compensation value of simulated hemoglobin concentration of the test sample in each cycle, mapped by a normalization function; The simulated hemoglobin concentration and maximum allowable environmental compensation value of the test sample in each cycle are calculated using a preset mapping function, and recorded as the actual high-pressure risk characterization value. The obtained actual high-pressure risk characterization value is compared with the expected high-pressure risk characterization value; The comparison results are compared with the preset threshold to obtain the statistical model's prediction performance consistency rate. Determine whether the risk characterization value predicted for the current system meets the standard based on the model's prediction performance consistency rate. The model prediction performance consistency rate is the percentage of the number of test samples in which the model's expected high-pressure risk characterization value matches the actual high-pressure risk characterization value. If the risk characterization value predicted by the current system does not meet the standard, the reason for non-compliance is determined based on the average pulmonary oxygenation recovery time in each cycle of the inconsistent sample. The pulmonary oxygenation recovery time is the difference between the average voltage value of the isoelectric line read in the same cardiac cycle and the electrocardiogram signal voltage value at the corresponding measurement point. Continue monitoring once the risk characterization values ​​predicted for the current system meet the standards.

[0038] In this embodiment, the preset model prediction performance consistency rate C0 = 90%; If the actual model prediction performance consistency rate C is greater than the preset model prediction performance consistency rate C0, the risk assessment module determines that the risk prediction for the current system meets the standard. If the actual model prediction efficiency consistency rate C is less than or equal to the preset model prediction efficiency consistency rate C0, the risk assessment module determines that the risk prediction for the current system does not meet the standard, and the risk assessment module determines the reason for not meeting the standard based on the pulmonary circulation oxygenation recovery time.

[0039] It is understood that the database pre-stores the minimum allowable model prediction performance consistency rate threshold for different types of data. Therefore, the above-mentioned assignment of the preset model prediction performance consistency rate is only a preferred embodiment of the system of the present invention. The present invention does not impose specific restrictions on the value of the preset model prediction performance consistency rate, as long as the comparison result between the obtained model prediction performance consistency rate and the preset model prediction performance consistency rate can directly characterize the analysis of the risk assessment module.

[0040] Specifically, the process described in this embodiment of the invention for determining the reason why the predicted risk characterization value for the current system does not meet the standard based on the pulmonary circulation oxygenation recovery time includes: The actual blood oxygen saturation of the test samples was obtained from the case information; Determine the reasons why the predicted risk characterization value for the current system does not meet the standard based on the pulmonary circulation oxygenation recovery time; If the cause is determined to be insufficient pulmonary vascular compensation function, the maximum allowable environmental compensation value is adjusted according to the simulated altitude; wherein, the simulated altitude is the input actual geographical altitude; If the cause is determined to be insufficient coagulation function, the simulated hemoglobin concentration is adjusted according to the comprehensive value of arterial blood oxygen content in inconsistent samples; wherein, the simulated hemoglobin concentration is a characterization value of the individual blood oxygen-carrying capacity of the input test sample through the built-in algorithm of the model; The arterial blood oxygen content P is calculated using the following formula: P=(1.34×ρ×B)+(0.003×V) Where ρ is the simulated hemoglobin concentration; B is the blood oxygen saturation; V is the arterial blood oxygen partial pressure; 1.34 is the oxygen binding coefficient of hemoglobin; 0.003 is the physical solubility coefficient of oxygen in plasma; in this embodiment, the preset pulmonary circulation oxygenation recovery time T0 = 10 min; If the actual pulmonary circulation oxygenation recovery time T is greater than the preset pulmonary circulation oxygenation recovery time T0, the risk assessment module determines that it does not meet the standard because the pulmonary vascular compensation function is insufficient, and generates instructions to optimize the processing method of the maximum allowable environmental compensation value. If the actual pulmonary oxygenation recovery time T is less than or equal to the preset pulmonary oxygenation recovery time T0, the risk assessment module determines that it does not meet the standard because the coagulation function interferes with the model, and generates instructions to optimize the processing method of simulated hemoglobin concentration.

[0041] Please see Figure 3 As shown, it is a flowchart of the parameter adjustment based on determined causes according to the present invention, and the process includes: Specifically, the process of adjusting the maximum permissible environmental compensation value based on the simulated altitude as described in this embodiment of the invention includes: The arithmetic mean of the simulated altitude of the test samples in each period is obtained, and the maximum allowable environmental compensation value E is increased according to the simulated altitude, and the increase of the maximum allowable environmental compensation value is negatively correlated with the simulated altitude. In this embodiment, the first preset simulated altitude h1=3000m, the second preset simulated altitude h2=4500m, the first environmental adjustment coefficient n1=1.65, the second environmental adjustment coefficient n2=1.45, and the third environmental adjustment coefficient n3=1.25. If the simulated altitude h is greater than the second preset simulated altitude h2, the risk assessment module determines to use the third environmental adjustment coefficient n3 to adjust the maximum allowable environmental compensation value E. If the simulated altitude h is less than or equal to the second preset simulated altitude h2 and greater than the first preset simulated altitude h1, the risk assessment module determines to use the second environmental adjustment coefficient n2 to adjust the maximum allowable environmental compensation value E. If the simulated altitude h is less than or equal to the first preset simulated altitude h1, the risk assessment module determines to use the first environmental adjustment coefficient n1 to adjust the maximum allowable environmental compensation value E. When the risk assessment module uses the a-th environmental adjustment coefficient na to adjust the maximum permissible environmental compensation value E, a=1, 2, 3, the adjusted maximum permissible environmental compensation value E'=E×na is set.

[0042] It is understood that the risk assessment module of the present invention re-determines whether the standard is met based on the adjusted model prediction performance consistency rate, and issues an instruction to adjust the reported value in the prediction process if the standard is not met.

[0043] Specifically, the adjustment process of the maximum permissible environmental compensation value described in the embodiments of the present invention further includes: The altitudes exceeding a preset threshold within the screening period are selected. The cumulative exposure equivalent value is calculated from the altitudes in the inconsistent samples and recorded as the plateau cumulative exposure index. The maximum allowable environmental compensation value is reduced based on the plateau cumulative exposure index, and the reduction in the maximum allowable environmental compensation value is positively correlated with the plateau cumulative exposure index. In this embodiment, the first preset plateau cumulative exposure index θ1 = 2.0 km / year, the second preset plateau cumulative exposure index θ2 = 5.0 km / year, the first environmental correction coefficient k1 = 0.55, the second environmental correction coefficient k2 = 0.75, and the third environmental correction coefficient k3 = 0.95. If the cumulative exposure index θ of the plateau is greater than the second preset cumulative exposure index θ2 of the plateau, the risk assessment module determines the maximum permissible environmental compensation value E' after correction and adjustment using the third environmental correction coefficient k3. If the cumulative exposure index of the plateau θ is less than or equal to the second preset cumulative exposure index of the plateau θ2 and greater than the first preset cumulative exposure index of the plateau θ1, the risk assessment module determines the maximum permissible environmental compensation value E' after correction and adjustment using the second environmental correction coefficient k2. If the cumulative exposure index of the plateau θ is less than or equal to the first preset cumulative exposure index of the plateau θ1, the risk assessment module determines the maximum permissible environmental compensation value E' after correction and adjustment using the first environmental correction coefficient k1. When the risk assessment module uses the d-th environmental correction coefficient kd to correct the adjusted maximum permissible environmental compensation value E', d=1, 2, 3, the adjusted maximum permissible environmental compensation value E''' is set to E'×kd.

[0044] Specifically, the process described in this embodiment of the invention for determining whether the risk characterization value predicted by the current system after adjustment meets the standard includes: In response to the first repeated test condition, the cause was determined to be insufficient coagulation function, and the simulated hemoglobin concentration was adjusted according to the comprehensive value of arterial blood oxygen content in inconsistent samples; The first repeated detection condition is that after the system has completed the adjustment of the maximum allowable environmental compensation value, it determines that the risk characterization value predicted by the current system does not meet the standard based on the re-obtained model prediction performance consistency rate.

[0045] Specifically, the process of adjusting the simulated hemoglobin concentration based on the composite value of arterial blood oxygen content in inconsistent samples, as described in this embodiment of the invention, includes: Arterial blood oxygen content is calculated, and the adjustment range for simulated hemoglobin concentration is determined based on the arterial blood oxygen content to obtain the expected simulated hemoglobin concentration. A comprehensive value of simulated hemoglobin concentration is calculated, and the median of the comprehensive value and the expected simulated hemoglobin concentration is obtained. The comprehensive value of simulated hemoglobin concentration of consistent samples obtained through medical record information is adjusted towards the median. The simulated hemoglobin concentration is increased according to the arterial blood oxygen content, and the increase in simulated hemoglobin concentration is positively correlated with the arterial blood oxygen content. In this embodiment, the first preset arterial blood oxygen content g1 = 12 mL / dL, the second preset arterial blood oxygen content g2 = 18 mL / dL, the first blood oxygen adjustment coefficient m1 = 1.25, the second blood oxygen adjustment coefficient m2 = 1.45, and the third blood oxygen adjustment coefficient m3 = 1.65. If the arterial blood oxygen content g is greater than the second preset arterial blood oxygen content g2, the risk assessment module determines to use the third blood oxygen regulation coefficient m3 to adjust the simulated hemoglobin concentration s. If the arterial blood oxygen content g is less than or equal to the second preset arterial blood oxygen content g2 and greater than the first preset arterial blood oxygen content g1, the risk assessment module determines to use the second blood oxygen regulation coefficient m2 to adjust the simulated hemoglobin concentration s. If the arterial blood oxygen content g is less than or equal to the first preset arterial blood oxygen content g1, the risk assessment module determines to use the first blood oxygen regulation coefficient m1 to adjust the simulated hemoglobin concentration s. When the detection system uses the f-th blood oxygen regulation coefficient mf to adjust the simulated hemoglobin concentration s, f=1, 2, 3, the adjusted simulated hemoglobin concentration s'=s×mf is set.

[0046] Specifically, the coagulation function regulation process described in this embodiment of the invention further includes: In response to the second repeated detection condition, it is determined that the reason why the current system's predicted risk characterization value does not meet the standard is that there is a deviation in the data preprocessing process, and an adjustment instruction for the sensitivity of abnormal fluctuation capture is issued according to the size of the dynamic data time window. The second repeated detection condition is that after the system completes the adjustment of the simulated hemoglobin concentration, it determines that the current system's predicted risk characterization value does not meet the standard based on the re-obtained model prediction performance consistency rate.

[0047] Specifically, the process for determining whether the predicted risk characterization value, based on the adjusted reassessment, meets the standard, as described in this embodiment of the invention includes: A set time length is used to calculate historical time data, and this is recorded as the time window size. The sensitivity for detecting abnormal fluctuations is increased according to the time length, and the increase in the sensitivity for detecting abnormal fluctuations is positively correlated with the time window size. The sensitivity for detecting abnormal fluctuations is the product of a preset coefficient of variation and the ratio of a preset time window to the actual time window. In this embodiment, the first preset time window size z1 = 5 min, the second preset time window size z2 = 30 min, the first window adjustment coefficient η1 = 1.36, the second window adjustment coefficient η2 = 1.56, and the third window adjustment coefficient η3 = 1.86. If the time window size z is greater than the second preset time window size z2, the risk assessment module determines to use the third window adjustment coefficient η3 to adjust the abnormal fluctuation capture sensitivity y. If the time window size z is less than or equal to the second preset time window size z2 and greater than the first preset time window size z1, the risk assessment module determines to use the second window adjustment coefficient η2 to adjust the abnormal fluctuation capture sensitivity y. If the time window size z is less than or equal to the first preset time window size z1, the risk assessment module determines to use the first window adjustment coefficient η1 to adjust the abnormal fluctuation capture sensitivity y. When the risk assessment module uses the j-th window to adjust the abnormal fluctuation capture sensitivity y to the adjustment coefficient ηj, j=1, 2, 3, the adjusted abnormal fluctuation capture sensitivity y'=y×ηj is set.

[0048] It is understood that the database pre-stores minimum allowable time window size thresholds for different types of parameters. Therefore, the above-mentioned assignment of values ​​for the first preset time window size and the second preset time window size is only a preferred embodiment of the system of the present invention. The present invention does not impose specific restrictions on the values ​​of each preset time window size, as long as the comparison results between the obtained time window size and each preset time window size can directly characterize the analysis of each parameter by the risk assessment module. The risk assessment module also adjusts the sensitivity of the data anomaly capture, and if the risk prediction for the current system does not meet the standard based on the adjusted anomaly capture sensitivity, the risk assessment module issues an update instruction to the database.

[0049] Please see Figure 4 As shown, it is a structural block diagram of the risk prediction system of the present invention, including: The data acquisition module is used to collect load data and environmental data for each testing cycle from the medical record information of the test sample in real time; wherein, the load data includes: blood oxygen saturation and hemoglobin concentration; the environmental data includes: altitude and environmental compensation value; The data processing module is connected to the data acquisition module and is used to preprocess the received load data and environmental data. The preprocessing methods include filtering the load data and environmental data, as well as pulmonary circulation oxygenation recovery time, in order to determine the consistency rate of model prediction performance. The risk characterization calculation module is connected to the data processing module and is used to calculate the high-pressure risk characterization value of the test sample based on the preprocessed load data and environmental data output by the data processing module. The risk assessment module is connected to the data processing module and is used to determine whether the risk characterization value predicted for the current system meets the standard based on the consistency rate between each risk characterization value and the actual characterization value. The risk assessment module is also used to determine whether to generate an adjustment instruction based on the determination result, and to determine whether to issue an adjustment instruction to the execution module in the prediction system based on the preprocessed load data and environmental data re-acquired after executing the adjustment instruction. The execution module is connected to the risk assessment module and is used to adjust the operating parameters of the corresponding module to the corresponding value according to the adjustment instructions output by the risk assessment module.

[0050] Specifically, during operation, the system of the present invention collects corresponding load data periodically by the data acquisition module and sends the collected data to the data processing module. The data processing module preprocesses the received data and sends the processed data to the database. The risk assessment module compares the data obtained by the data processing module with the consistency rate of the model prediction performance stored in the database to determine whether the consistency rate of the model prediction performance in each period meets the standard. If the standard is not met, a corresponding processing instruction is generated based on the determined reason. The execution module performs the corresponding operation according to the received instruction.

[0051] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0052] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for predicting the risk of pulmonary hypertension in high-altitude areas, characterized in that, include: Obtain test sample load data, including blood oxygen saturation and hemoglobin concentration, from case information; Collect environmental data for each detection cycle, including simulated altitude and environmental compensation values; The load data and environmental data are preprocessed, including: cleaning, unit conversion and outlier correction; Based on the preprocessed data, the pulmonary hypertension risk characterization value for the test sample is calculated. The predictive characterization value for the system is determined to meet the standard based on the consistency rate of the model performance based on each hypertension risk characterization value. If it is determined that the system does not meet the standard, the corresponding adjustment instruction is generated based on the determined reason. The maximum permissible environmental compensation value for the system is based on the simulated altitude adjustment, wherein the maximum permissible environmental compensation value is the maximum value of the current environmental adaptability compensation obtained by querying a table. Based on the obtained adjusted maximum permissible environmental compensation value, a retest is performed. If the standard is still not met, the corresponding processing method is selected, including issuing adjustment instructions for simulated hemoglobin concentration and abnormal fluctuation detection sensitivity. After adjustment, under the condition that the criteria are met, the prediction of pulmonary hypertension risk is completed.

2. The method for predicting the risk of pulmonary hypertension in high-altitude areas according to claim 1, characterized in that, The risk level prediction process includes: The expected high-pressure risk characterization value is calculated as the weighted error sum of the maximum allowable environmental compensation value of simulated hemoglobin concentration of the test sample in each cycle, mapped by a normalization function; The simulated hemoglobin concentration and maximum allowable environmental compensation value of the test sample in each cycle are calculated using a preset mapping function, and recorded as the actual high-pressure risk characterization value. The obtained actual high-pressure risk characterization value is compared with the expected high-pressure risk characterization value; The comparison results are compared with the preset threshold to obtain the statistical model's prediction performance consistency rate. Determine whether the risk characterization value predicted for the current system meets the standard based on the model's predictive performance consistency rate. The model prediction performance consistency rate is the percentage of the number of test samples in which the model's expected high-pressure risk characterization value matches the actual high-pressure risk characterization value. If the risk characterization value predicted by the current system does not meet the standard, the reason for non-compliance is determined based on the average pulmonary oxygenation recovery time in each cycle of the inconsistent sample. The pulmonary oxygenation recovery time is the difference between the average voltage value of the isoelectric line read in the same cardiac cycle and the electrocardiogram signal voltage value at the corresponding measurement point. Continue monitoring once the risk characterization values ​​predicted for the current system meet the standards.

3. The method for predicting the risk of pulmonary hypertension in high-altitude areas according to claim 2, characterized in that, The process of determining the reasons why the predicted risk characterization value for the current system does not meet the standard based on the pulmonary oxygenation recovery time includes: The actual blood oxygen saturation of the test samples was obtained from the case information; Determine the reasons why the predicted risk characterization value for the current system does not meet the standard based on the pulmonary circulation oxygenation recovery time; If the cause is determined to be insufficient pulmonary vascular compensation function, the maximum allowable environmental compensation value is adjusted according to the simulated altitude; wherein, the simulated altitude is the input actual geographical altitude; If the cause is determined to be insufficient coagulation function, the simulated hemoglobin concentration is adjusted according to the comprehensive value of arterial blood oxygen content in inconsistent samples; wherein, the simulated hemoglobin concentration is a characterization value of the individual blood oxygen-carrying capacity of the input test sample through the built-in algorithm of the model; The arterial blood oxygen content P is calculated using the following formula: P=(1.34×ρ×B)+(0.003×V) Where ρ is the simulated hemoglobin concentration; B is the blood oxygen saturation; V is the arterial blood oxygen partial pressure; 1.34 is the oxygen binding coefficient of hemoglobin; and 0.003 is the physical solubility coefficient of oxygen in plasma.

4. The method for predicting the risk of pulmonary hypertension in high-altitude areas according to claim 3, characterized in that, The process of adjusting the maximum permissible environmental compensation value based on the simulated altitude includes: Obtain the arithmetic mean of the simulated altitude of the test samples within each period; The maximum allowable environmental compensation value is increased based on the simulated altitude, and the increase in the maximum allowable environmental compensation value is negatively correlated with the simulated altitude.

5. The method for predicting the risk of pulmonary hypertension in high-altitude areas according to claim 4, characterized in that, The adjustment process for the maximum permissible environmental compensation value also includes: The portion of altitude that exceeds a preset threshold during the screening period; The cumulative exposure equivalent value was selected from the altitude of the selected inconsistent samples and recorded as the plateau cumulative exposure index. The maximum allowable environmental compensation value after adjustment is reduced based on the cumulative exposure index of the plateau, and the reduction in the maximum allowable environmental compensation value after adjustment is positively correlated with the cumulative exposure index of the plateau.

6. The method for predicting the risk of pulmonary hypertension in high-altitude areas according to claim 5, characterized in that, The process of determining whether the risk characterization value predicted by the current system after adjustment meets the standard includes: In response to the first repeated test condition, the cause was determined to be insufficient coagulation function, and the simulated hemoglobin concentration was adjusted according to the comprehensive value of arterial blood oxygen content in inconsistent samples; The first repeated detection condition is that after the system has completed the adjustment of the maximum allowable environmental compensation value, it determines that the risk characterization value predicted by the current system does not meet the standard based on the re-obtained model prediction performance consistency rate.

7. The method for predicting the risk of pulmonary hypertension in high-altitude areas according to claim 6, characterized in that, The process of adjusting the simulated hemoglobin concentration based on the composite value of arterial blood oxygen content in inconsistent samples includes: Calculate arterial blood oxygen content; The adjustment range for simulated hemoglobin concentration is determined based on arterial blood oxygen content in order to obtain the expected simulated hemoglobin concentration; Calculate the composite value of simulated hemoglobin concentration and obtain the median value of simulated hemoglobin concentration and the expected simulated hemoglobin concentration. The composite value of simulated hemoglobin concentration of consistent samples obtained through medical record information will be adjusted towards the median. The increase in arterial blood oxygen content led to an increase in simulated hemoglobin concentration, and the magnitude of the increase in simulated hemoglobin concentration was positively correlated with arterial blood oxygen content.

8. The method for predicting the risk of pulmonary hypertension in high-altitude areas according to claim 7, characterized in that, The process of regulating coagulation function also includes: In response to the second repeated detection condition, it is determined that the reason why the current system's predicted risk characterization value does not meet the standard is that there is a deviation in the data preprocessing process, and an adjustment instruction for the sensitivity of abnormal fluctuation capture is issued according to the size of the dynamic data time window. The second repeated detection condition is that after the system completes the adjustment of the simulated hemoglobin concentration, it determines that the current system's predicted risk characterization value does not meet the standard based on the re-obtained model prediction performance consistency rate.

9. The method for predicting the risk of pulmonary hypertension in high-altitude areas according to claim 8, characterized in that, The process of determining whether the predicted risk characterization value based on the adjusted reassessment meets the standard includes: Set a time length to calculate historical time data and record it as the time window size; The sensitivity for detecting abnormal fluctuations is increased based on the time length, and the increase in sensitivity is positively correlated with the size of the time window; wherein, the sensitivity for detecting abnormal fluctuations is the product of a preset coefficient of variation and the ratio of a preset time window to the actual time window.

10. The pulmonary hypertension risk prediction system for high-altitude areas according to claim 1, characterized in that, include: The data acquisition module is used to collect load data and environmental data for each testing cycle from the medical record information of the test samples in real time; wherein, the load data includes: blood oxygen saturation and hemoglobin concentration; the environmental data includes: altitude and environmental compensation value; The data processing module, which is connected to the data acquisition module, is used to preprocess the received load data and environmental data. The preprocessing methods include filtering the load data and environmental data, as well as pulmonary circulation oxygenation recovery time, to determine the consistency rate of model prediction performance. A risk characterization calculation module, which is connected to the data processing module, is used to calculate the high-pressure risk characterization value of the test sample based on the preprocessed load data and environmental data output by the data processing module. The risk assessment module, connected to the data processing module, is used to determine whether the predicted risk characterization values ​​for the current system meet the standards based on the consistency rate between each risk characterization value and the actual characterization value. The risk assessment module is also used to determine whether to generate an adjustment instruction based on the determination result, and to determine whether to issue an adjustment instruction to the execution module in the prediction system based on the preprocessed load data and environmental data re-acquired after executing the adjustment instruction. An execution module, which is connected to the risk assessment module, is used to adjust the operating parameters of the corresponding module to the corresponding values ​​according to the adjustment instructions output by the risk assessment module.

Images