Heatstroke Prevention and Monitoring System Based on Consciousness, Cognition and Behavioral Characteristics

Abstract

This invention discloses a heatstroke prevention and monitoring system based on conscious cognitive behavioral characteristics, belonging to the field of intelligent medical technology. This invention addresses the problems of existing technologies lacking intelligent analysis and exhibiting a certain degree of subjectivity, making it difficult to ensure the effectiveness of heatstroke prevention and monitoring. It analyzes the patient's physiological signals and behavioral data using a linear discriminant analysis model to predict whether the patient has heatstroke. After predicting heatstroke, a weighted average method is used to further calculate the patient's risk index, and different prevention and monitoring strategies are implemented based on the risk index. Based on this, it can effectively identify whether a patient has heatstroke and the risk index, thereby enabling targeted preventative measures to avoid further disease progression. Simultaneously, through intelligent analysis and judgment, it can effectively reduce the incidence of heatstroke, reduce the consumption of medical resources, and lower the socioeconomic burden.

Description

Technical Field

[0001] This invention relates to the field of intelligent medical technology, specifically a heatstroke prevention and monitoring system based on the recognition of consciousness, cognition, and behavioral characteristics. Background Technology

[0002] Heatstroke is the most severe type of heat illness, caused by an imbalance in thermoregulation resulting from exposure to high temperatures and / or strenuous physical labor. Its main characteristics are elevated core body temperature (>40°C) and abnormalities in the central nervous system. The main types are classic heatstroke and exertional heatstroke, with common causes involving increased heat production, excessive heat acquisition, and impaired heat dissipation. Exertional heatstroke primarily occurs in healthy young adults, often triggered by heavy physical labor or strenuous exercise. Non-exertional heatstroke mainly occurs in the elderly, those with weakened constitutions, and patients with chronic illnesses, caused by passive exposure to heat. Therefore, heatstroke is an extremely serious and potentially life-threatening condition; thus, prevention and monitoring of heatstroke are crucial.

[0003] However, in current technology, the prevention and monitoring of heatstroke typically rely on routine examinations by healthcare professionals to determine whether a patient has heatstroke. This method is inherently subjective; for example, the same examination results may lead to different conclusions depending on the analysis performed by different healthcare professionals. This results in a lack of intelligent analysis in heatstroke diagnosis and makes it difficult to ensure the effectiveness of heatstroke prevention and monitoring.

[0004] Therefore, it does not meet the existing needs, so we propose a heatstroke prevention and monitoring system based on the recognition of consciousness, cognition and behavioral characteristics. Summary of the Invention

[0005] The purpose of this invention is to provide a heatstroke prevention and monitoring system based on conscious cognitive behavioral characteristics. This system analyzes the patient's physiological signals and behavioral data using a linear discriminant analysis model to predict whether the patient has heatstroke. After predicting heatstroke, a weighted average method is used to further calculate the patient's risk index. Different prevention and monitoring strategies are then implemented based on the level of the risk index. Through intelligent analysis, this system can effectively identify whether a patient has heatstroke and the risk index, thereby enabling targeted preventative measures to avoid further disease progression and solving the problems mentioned in the background section.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A heatstroke prevention and monitoring system based on conscious cognitive and behavioral characteristics includes:

[0008] The data collection unit is used to collect physiological signals and behavioral data from patients with heatstroke as Class I data; it is also used to collect physiological signals and behavioral data from normal patients as Class II data; among them, physiological signal data includes: patient body surface temperature, electroencephalogram, electrocardiogram and respiratory biofeedback signals; behavioral data includes: movement frequency, reaction speed and attention behavior indicators.

[0009] The feature extraction unit is used to clean and reduce the dimensionality of the primary and secondary data, and extract feature information reflecting the patient's physical condition and metabolic level from the primary and secondary data respectively; the feature information of patients with heatstroke is used as feature vectors and labeled as positive; and the feature information of patients without heatstroke is used as training samples and labeled as negative.

[0010] The feature recognition unit uses feature vectors and labels as the training set and feature information and labels of binary data as the test set. It learns the feature vectors and label content through a linear discriminant analysis model and outputs the learning results. Then, it analyzes the feature information and label content of the binary data through the learned linear discriminant analysis model to determine whether there are heatstroke features in the feature information of the binary data and outputs the prediction results. The prediction results are compared with the actual results of the binary data to verify the performance of the linear discriminant analysis model.

[0011] The prevention and monitoring unit is used to predict whether a patient has heatstroke using a linear discriminant analysis model. If the patient has heatstroke, the unit further calculates the risk index of the patient's heatstroke and implements different prevention and monitoring strategies based on the level of the risk index.

[0012] Furthermore, the feature extraction unit includes:

[0013] The data processing module is used to clean, denoise, and normalize primary and secondary data.

[0014] The feature extraction module is used to analyze the information content in the first-class and second-class data, and extract heart rate variability, respiratory depth changes and skin resistance as feature information reflecting the patient's physical condition and metabolic level.

[0015] The feature analysis module is used to compare the feature information of patients with heatstroke with that of those without heatstroke, and to analyze whether the feature information of patients with heatstroke differs from that of those without heatstroke under the influence of heatstroke.

[0016] Furthermore, the feature analysis module analyzes whether the feature information of patients with heatstroke differs from that of patients without heatstroke under the influence of heatstroke. Specifically, based on heart rate variability, respiratory depth changes, and skin resistance, the feature vector of each patient is calculated, and it is determined whether there are differences in the feature vector of each patient.

[0017] Calculation of the heart rate variability eigenvector:

[0018] The voltage at each heartbeat point in the electrocardiogram signal is mapped to the original heart rate using a linear interpolation formula. For each heartbeat point, the time interval DT between two adjacent heartbeat points is calculated. For each heartbeat point, the power spectral density estimate (PSDE) corresponding to each time interval DT is calculated. Then, the frequency corresponding to the maximum value of the power spectral density estimate (PSDE) at each heartbeat point is taken as the feature vector.

[0019] Calculation of the eigenvector of respiratory depth change:

[0020] The voltage at each respiratory cycle point in the respiratory signal is mapped to the original respiratory cycle number using a linear interpolation formula. For each respiratory cycle point, the time interval DT between two adjacent respiratory cycle points is calculated. For each respiratory cycle point, the power spectral density estimate (PSDE) corresponding to each time interval DT is calculated. Then, the frequency corresponding to the maximum value of the power spectral density estimate (PSDE) at each respiratory cycle point is taken as the feature vector.

[0021] Calculation of the skin resistance eigenvector:

[0022] The linear interpolation formula is used to map each resistance value in the skin impedance signal to the original skin impedance. For each skin impedance, the time-domain interval DT between two adjacent skin impedances is calculated. For each skin impedance, the power spectral density estimate PSDE corresponding to each time-domain interval DT is calculated. Then, the frequency corresponding to the maximum value of the power spectral density estimate PSDE of each skin impedance is taken as the feature vector.

[0023] The criteria for judgment are as follows: patients with heatstroke have higher values ​​in their feature vectors, while patients without heatstroke have lower values ​​in their feature vectors. Based on this, it is analyzed whether the feature information of patients with heatstroke differs from that of patients without heatstroke under the influence of heatstroke.

[0024] Furthermore, the feature recognition unit includes:

[0025] The model building module is used to create a neural network model. The training set is input into the neural network model, the LDA linear discriminant analysis algorithm is used to train the model, and the training results are output to obtain the linear discriminant analysis model.

[0026] The model evaluation module is used to input the test set into the linear discriminant analysis model for testing, use the linear discriminant analysis model to identify the presence of heatstroke characteristics in the test set, and verify the performance of the linear discriminant analysis model based on the test results.

[0027] Furthermore, the feature recognition unit also includes:

[0028] The feature interpretation module is used to analyze the meaning of each feature after training on the training and test sets is completed.

[0029] Furthermore, the prevention monitoring unit includes:

[0030] The risk analysis module collects the current patient's personal information as an additional factor and uses a weighted average method to calculate the current patient's risk index of having heatstroke;

[0031] The early warning module is used to establish risk thresholds. If a patient's risk index exceeds the set threshold, it indicates that the patient is at high risk of heatstroke and an alarm will be issued in a timely manner to remind medical staff to pay attention to the patient's condition.

[0032] Furthermore, the data collection unit includes:

[0033] The real-time data collection module is used to collect current patient heart rate variability, respiratory depth changes, and skin resistance data through health monitoring devices, serving as basic data for clinical diagnosis or daily health prevention and monitoring.

[0034] Furthermore, the data collection unit also includes:

[0035] Real-time monitoring of the patient's current heart rate data;

[0036] Compare the current patient's heart rate data value with a preset heart rate threshold;

[0037] When the current patient's heart rate data value exceeds the preset heart rate threshold, the tidal volume corresponding to each breath in the preset number of breaths of the current patient is monitored.

[0038] The respiratory abnormality coefficient is obtained by using the tidal volume corresponding to each breath of the current patient within a preset number of breaths;

[0039] The respiratory abnormality coefficient is obtained by the following formula:

[0040]

[0041] Where R represents the respiratory abnormality coefficient; V p V represents the average tidal volume for each breath within a preset breathing count;min This represents the minimum tidal volume for each breath within a preset number of breaths; f represents the respiratory rate of the current breath; f max Indicates the preset maximum permissible respiratory rate; H m This represents the heart rate data value corresponding to an abnormal heart rate; H y This indicates the preset heart rate threshold;

[0042] The respiratory abnormality coefficient is compared with a preset respiratory abnormality coefficient threshold, and the sampling frequency of heart rate variability and respiratory depth change is adjusted according to the comparison result.

[0043] Furthermore, the respiratory abnormality coefficient is compared with a preset respiratory abnormality coefficient threshold, and the sampling frequency of heart rate variability and respiratory depth changes is adjusted according to the comparison result, including:

[0044] The respiratory abnormality coefficient is compared with a preset respiratory abnormality coefficient threshold to obtain a comparison result;

[0045] If the comparison results show that the respiratory abnormality coefficient is not lower than the preset respiratory abnormality coefficient threshold, then there is no need to adjust the acquisition frequency of heart rate variability and respiratory depth change.

[0046] If the comparison result shows that the respiratory abnormality coefficient is lower than the preset respiratory abnormality coefficient threshold, the sampling frequency of heart rate variability and respiratory depth change is adjusted using the respiratory abnormality coefficient to obtain the adjusted sampling frequency of heart rate variability and respiratory depth change.

[0047] The adjusted heart rate variability sampling frequency is obtained using the following formula:

[0048]

[0049] Among them, F h The sampling frequency represents the adjusted heart rate variability; F h0 The sampling frequency represents the heart rate variability before adjustment; R represents the respiratory abnormality coefficient; R y V represents the preset threshold for the respiratory abnormality coefficient; p V represents the average tidal volume for each breath within a preset breathing count; min This represents the minimum tidal volume corresponding to each breath within a preset number of breaths; V max This indicates the maximum tidal volume for each breath within a preset number of breaths.

[0050] Meanwhile, the adjusted sampling frequency for changes in respiratory depth is obtained using the following formula:

[0051]

[0052] Among them, F t This indicates the sampling frequency of the adjusted respiratory depth changes; F t0 This indicates the sampling frequency of changes in respiratory depth before adjustment; V p V represents the average tidal volume for each breath within a preset breathing count; max This represents the maximum tidal volume for each breath within a preset number of breaths; H m This represents the heart rate data value corresponding to an abnormal heart rate; H y This indicates the preset heart rate threshold;

[0053] The health monitoring equipment was controlled to collect data corresponding to heart rate variability and respiratory depth changes according to the adjusted sampling frequency.

[0054] Furthermore, it also includes:

[0055] The human-computer interaction unit is used to visualize and display the patient's current physiological signals and behavioral data, as well as the prediction results and risk index of the linear discriminant analysis model.

[0056] This invention analyzes a patient's physiological signals and behavioral data using a linear discriminant analysis model to predict whether the patient has heatstroke. After predicting heatstroke, a weighted average method is used to calculate the patient's risk index. Different preventative monitoring strategies are then implemented based on the risk index. This method effectively identifies whether a patient has heatstroke and their risk index, allowing for targeted preventative measures to avoid further disease progression. Furthermore, through intelligent analysis and judgment, the invention effectively reduces the incidence of heatstroke, decreases the consumption of medical resources, and lowers the socioeconomic burden. Attached Figure Description

[0057] Figure 1 This is a diagram showing the module composition of the heatstroke prevention and monitoring system based on consciousness, cognition, and behavioral characteristics recognition according to the present invention. Detailed Implementation

[0058] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0059] To address the current technical issues regarding heatstroke prevention and monitoring, which typically rely on routine examinations by healthcare professionals to diagnose heatstroke, and the inherent subjectivity of this method (e.g., different healthcare professionals analyzing the same test results leading to differing conclusions), which hinders both intelligent analysis in heatstroke diagnosis and ensures the effectiveness of heatstroke prevention and monitoring, please refer to [the relevant documentation / reference needed]. Figure 1 This embodiment provides the following technical solution:

[0060] A heatstroke prevention and monitoring system based on conscious cognitive and behavioral characteristics includes:

[0061] The data collection unit is used to collect physiological signals and behavioral data from patients with heatstroke, as Class I data; it is also used to collect physiological signals and behavioral data from healthy patients, as Class II data; among which, physiological signal data includes: patient body surface temperature, electroencephalogram (EEG), electrocardiogram (ECG), and respiratory biofeedback signals; the data collection unit includes:

[0062] The real-time data collection module is used to collect physiological signals and behavioral data such as heart rate variability, respiratory depth changes, and skin resistance from health monitoring devices, such as electrocardiographs, respiratory sensors, or thermometers. This data serves as the basis for clinical diagnosis or daily health prevention and monitoring. Specifically, an abnormally elevated body surface temperature is one of the main factors in determining whether a patient has heatstroke. During the process of elevated body temperature, heatstroke patients experience abnormal changes in their electroencephalogram (EEG), manifested as decreased arousal, slowed frequency, and irregular rhythm. Heatstroke patients experience additional stress on their cardiopulmonary system, which may lead to abnormalities in their electrocardiogram, such as tachycardia, myocardial ischemia, and myocardial necrosis. Respiratory signals in heatstroke patients are also affected, such as shallow breathing and unstable rhythm. Behavioral data includes: movement frequency, reaction speed, and attention behavior indicators. Heatstroke is a severe central nervous system injury caused by prolonged exposure to high temperature and humidity. In the early stages of the disease, abnormal thermoregulation may lead to elevated body temperature, resulting in a decrease in movement frequency. Furthermore, the elevated body temperature damages the central nervous system, altering reaction speed, such as a gradual slowing down of reaction time. Heatstroke patients may also experience problems such as poor concentration and memory loss during the course of the disease, all of which are related to the involvement of the nervous system. Intelligent analysis of the above indicators can help medical staff better understand the pathophysiological mechanisms of heatstroke and provide a basis for clinical diagnosis and treatment.

[0063] The feature extraction unit is used to clean and reduce the dimensionality of the primary and secondary data, and extract feature information reflecting the patient's physical condition and metabolic level from the primary and secondary data respectively; the feature information of patients with heatstroke is used as a feature vector and labeled as positive; the feature information of patients without heatstroke is used as training samples and labeled as negative; the feature extraction unit includes:

[0064] The data processing module is used to clean, denoise, and normalize primary and secondary data to facilitate subsequent analysis. Specifically, it checks the syntax, semantics, and logic of the primary and secondary data to remove obvious errors, duplicates, missing, or corrupted data records, thereby ensuring data accuracy. After data cleaning, denoising and normalization processes are performed to remove noise and inconsistencies hidden in the original data, eliminating unit differences, scaling effects, and outliers, thus ensuring data validity.

[0065] The feature extraction module analyzes the information content in both primary and secondary data sets, extracting heart rate variability, respiratory depth changes, and skin resistance as characteristic information reflecting the patient's physical condition and metabolic level. Specifically, by analyzing heart rate variability, the module understands the patient's sympathetic and parasympathetic nerve tone, thereby assessing the patient's physical condition; by analyzing respiratory depth, the module understands the patient's respiratory status, further evaluating their physical condition; and by analyzing skin resistance, the module understands the patient's metabolic level and physical condition. By extracting these effective feature information, a foundation is provided for subsequent data analysis and decision-making.

[0066] The feature analysis module is used to compare the feature information of patients with heatstroke with that of patients without heatstroke, and to analyze whether the feature information of patients with heatstroke differs from that of patients without heatstroke under the influence of heatstroke. Specifically, based on heart rate variability, respiratory depth changes, and skin resistance, feature vectors are calculated for each patient, and it is determined whether there are differences in the feature vectors of each patient.

[0067] Calculation of the heart rate variability eigenvector:

[0068] The voltage at each heartbeat point in the electrocardiogram (ECG) signal is mapped to the original heart rate using a linear interpolation formula. For each heartbeat point, the time-domain interval DT between two adjacent heartbeat points is calculated. For each heartbeat point, the power spectral density estimate (PSDE) corresponding to each time-domain interval DT is calculated. Then, the frequency corresponding to the maximum value of the PSDE at each heartbeat point is taken as the feature vector. In this embodiment, for example, the ECG signal at this point is interpolated with the ECG signals at adjacent heartbeat points using a linear interpolation formula to obtain the heart rate corresponding to the voltage at this heartbeat point. Subsequently, the time-domain interval DT between two adjacent heartbeat points is calculated. If the heart rate of a heartbeat point is f1, then the heart rates corresponding to its preceding and following heartbeat points are f0 = f1 - dt and f2 = f1 + dt, respectively.

[0069] Where f0 is the previous heartbeat point; f2 is the next heartbeat point; and dt is the time interval between two adjacent heartbeat points.

[0070] Secondly, the power spectral density estimate (PSDE) for each time interval DT is calculated using the Fourier transform algorithm. By converting the electrocardiogram signal from the time domain to the frequency domain and averaging the power spectral density of each heartbeat, the power spectral density estimate (PSDE) for each time interval DT is obtained.

[0071] Finally, the frequency corresponding to the maximum value of the power spectral density estimation (PSDE) at each heartbeat point is taken as the feature vector to better capture the high-frequency components of cardiac activity, thereby improving the feature extraction effect.

[0072] Calculation of the eigenvector of respiratory depth change:

[0073] The voltage at each respiratory cycle point in the respiratory signal is mapped to the original number of respiratory cycles using a linear interpolation formula. For each respiratory cycle point, the time interval DT between two adjacent respiratory cycle points is calculated. For each respiratory cycle point, the power spectral density estimate (PSDE) corresponding to each time interval DT is calculated. Then, the frequency corresponding to the maximum value of the PSDE at each respiratory cycle point is taken as the feature vector. In this embodiment, for example, the respiratory signal at each respiratory cycle point is interpolated with the respiratory signal at adjacent respiratory cycle points using a linear interpolation formula to obtain the original number of respiratory cycles corresponding to the voltage at that respiratory cycle point. Subsequently, the time interval DT between two adjacent respiratory cycle points is calculated. If the number of respiratory cycles at a respiratory cycle point is T0, then the original number of respiratory cycles corresponding to its previous and next respiratory cycle points are T0-dt and T0+dt, respectively; where dt is the time interval between two adjacent respiratory cycle points.

[0074] Secondly, the power spectral density estimate (PSDE) for each time interval DT is calculated using the Fourier transform algorithm. By converting the respiratory signal from the time domain to the frequency domain and averaging the power spectral density at each respiratory cycle point, the power spectral density estimate (PSDE) for each time interval DT is obtained.

[0075] Finally, the frequency corresponding to the maximum value of the power spectral density estimation PSDE at each respiratory cycle point is taken as the feature vector to better capture the periodic changes in respiratory activity, thereby improving the feature extraction effect.

[0076] Calculation of the skin resistance eigenvector:

[0077] The linear interpolation formula maps each resistance value in the skin impedance signal to the original skin impedance. For each skin impedance, the time-domain interval DT between two adjacent skin impedances is calculated. For each skin impedance, the power spectral density estimate (PSDE) corresponding to each time-domain interval DT is calculated. Then, the frequency corresponding to the maximum value of the PSDE for each skin impedance is taken as the feature vector. In this embodiment, for example, for each skin impedance, the linear interpolation formula maps its corresponding resistance value to the original skin impedance to obtain the original resistance value of each skin impedance. Subsequently, the time-domain interval DT between two adjacent skin impedances is calculated. If the value of a skin impedance is R0, then the original skin impedances corresponding to its previous and next skin impedances are R0-dt and R0+dt, respectively; where dt is the time interval between two adjacent skin impedances.

[0078] Secondly, the power spectral density estimate (PSDE) for each time interval DT is calculated using the Fourier transform algorithm. By converting the skin impedance signal from the time domain to the frequency domain and then averaging the power spectrum of each skin impedance, the power spectral density estimate (PSDE) for each time interval DT is obtained.

[0079] Finally, the frequency corresponding to the maximum value of the power spectral density estimation PSDE for each skin impedance is taken as the feature vector to better capture changes in skin impedance and thus improve the feature extraction effect.

[0080] The criteria for judgment are as follows: patients with heatstroke have higher values ​​in their eigenvectors, while patients without heatstroke have lower values. Based on this, the analysis examines whether the eigenvectors of patients with heatstroke differ from those of patients without heatstroke. For example, regarding skin impedance: patients with heatstroke experience changes in skin impedance due to the heatstroke, which alters the frequency of their eigenvectors, resulting in higher values ​​than those of patients without heatstroke. Therefore, by comparing the skin impedance eigenvectors of different patients, the analysis examines whether there are differences in skin impedance under the influence of heatstroke. If there is a significant difference between the eigenvectors of patients with and without heatstroke, it indicates that heatstroke may affect this characteristic.

[0081] The feature recognition unit is used to take feature vectors and labels as the training set and feature information and labels of binary data as the test set; learn the feature vectors and label content through a linear discriminant analysis model and output the learning results; then analyze the feature information and label content of the binary data through the learned linear discriminant analysis model to determine whether heatstroke features exist in the feature information of the binary data and output the prediction results; compare the prediction results with the actual results of the binary data to verify the performance of the linear discriminant analysis model; the feature recognition unit includes:

[0082] The model building module imports necessary databases, such as TensorFlow and NumPy, and sets model parameters, such as batch size and number of iterations, and loads training set data X and Y; it creates a neural network model and defines the model structure, loss function, and optimizer; it divides the training set into k subsets and inputs them into the neural network model, uses the LDA linear discriminant analysis algorithm to train the model, and outputs the training results to obtain the linear discriminant analysis model; during the training process, it calculates the mean squared error to find the optimal model parameters.

[0083] The model evaluation module imports a pre-trained linear discriminant analysis (LDA) model and loads the feature data of the test set. The loaded test set is then input into the LDA model for testing. The test set features are converted to a format acceptable to the LDA model. The correlation matrix between the test set data and feature information is obtained by calculating the covariance matrix. Subsequently, the LDA model is used to identify the presence of heatstroke characteristics in the test set. The performance of the LDA model is verified based on the test results for subsequent analysis and decision-making.

[0084] The feature interpretation module is used to analyze the meaning of each feature after training on the training and test sets. For example, changes in breathing depth may reflect changes in oxygen supply in patients with heatstroke; an increase in heart rate may indicate an increase in the tension of the sympathetic nervous system.

[0085] The prevention and monitoring unit is used to apply the validated linear discriminant analysis model to real-world scenarios. It predicts whether a patient currently has heatstroke using the model. If heatstroke is suspected, it further calculates the patient's risk index and implements different prevention and monitoring strategies based on the risk index. The prevention and monitoring unit includes:

[0086] The risk analysis module collects the patient's personal information as supplementary factors, such as age, gender, body temperature, and body mass index (BMI), clinical manifestations such as persistent fever, excessive sweating, and altered consciousness, as well as information on other chronic diseases, recent surgical procedures, and current medication use. It then uses a weighted average method to calculate the patient's risk index for heatstroke. This involves quantifying the patient's various indicators and medical history, assigning them appropriate weights, and using a weighted average method to calculate the risk index, resulting in a comprehensive assessment. This assessment helps medical staff determine the likelihood of the patient having heatstroke.

[0087] The early warning module is used to construct risk thresholds. If a patient's risk index exceeds the set threshold, it indicates that the patient is at high risk of heatstroke and an alarm needs to be issued in time to remind medical staff to pay attention to the patient's condition. The risk prediction results are converted into a heat map, with darker colors indicating a higher risk of disease.

[0088] The human-computer interaction unit is used to visualize and display the patient's current physiological signals and behavioral data, as well as the prediction results and risk index of the linear discriminant analysis model.

[0089] The beneficial effects achieved by the above methods are as follows: Through the above operations, it is possible to effectively identify whether a patient has heatstroke and the risk index of the disease, so that targeted preventive measures can be taken to avoid the further development of the disease; at the same time, through intelligent analysis and judgment, it is possible to effectively reduce the incidence of heatstroke, reduce the consumption of medical resources, and reduce the social and economic burden.

[0090] Working principle: The system analyzes the patient's physiological signals and behavioral data using a linear discriminant analysis model to predict the likelihood of the patient having heatstroke. After predicting that the patient has heatstroke, a weighted average method is used to further calculate the risk index of the disease. Different prevention and monitoring strategies are then implemented for the patient based on the level of the risk index.

[0091] Specifically, the data collection unit further includes:

[0092] Real-time monitoring of the patient's current heart rate data;

[0093] Compare the current patient's heart rate data value with a preset heart rate threshold;

[0094] When the current patient's heart rate data value exceeds the preset heart rate threshold, the tidal volume corresponding to each breath in the preset number of breaths of the current patient is monitored.

[0095] The respiratory abnormality coefficient is obtained by using the tidal volume corresponding to each breath of the current patient within a preset number of breaths;

[0096] The respiratory abnormality coefficient is obtained by the following formula:

[0097]

[0098] Where R represents the respiratory abnormality coefficient; V p V represents the average tidal volume for each breath within a preset breathing count; min This represents the minimum tidal volume for each breath within a preset number of breaths; f represents the respiratory rate of the current breath; f max Indicates the preset maximum permissible respiratory rate; H m This represents the heart rate data value corresponding to an abnormal heart rate; H y This indicates the preset heart rate threshold;

[0099] The respiratory abnormality coefficient is compared with a preset respiratory abnormality coefficient threshold, and the sampling frequency of heart rate variability and respiratory depth change is adjusted according to the comparison result.

[0100] The technical effects of the above solution are as follows: The system can monitor the patient's heart rate data in real time and immediately compare it with a preset heart rate threshold. This real-time monitoring capability helps to detect abnormal heart rates in a timely manner, providing medical personnel with timely early warning information so that necessary medical measures can be taken. When the patient's heart rate is detected to exceed the preset threshold, the system will further monitor the tidal volume corresponding to each breath within a preset respiratory rate. Tidal volume is an important indicator for measuring respiratory depth, and by monitoring it, more detailed respiratory status information can be obtained. Using the monitored tidal volume data, the system can calculate a respiratory abnormality coefficient, which comprehensively considers the average and minimum tidal volume, respiratory rate, and the degree of heart rate abnormality, providing a comprehensive indicator for assessing the patient's respiratory status. By comparing the calculated respiratory abnormality coefficient with the preset threshold, the system can dynamically adjust the collection frequency of heart rate variability and respiratory depth changes according to the patient's real-time condition. This dynamic adjustment mechanism helps to reduce unnecessary monitoring when the patient's condition is stable, saving resources; and increases the monitoring frequency when the patient's condition deteriorates, so as to more accurately capture changes in physiological parameters. This technological solution, through real-time monitoring, early warning, and refined assessment, helps improve the efficiency of medical personnel in monitoring patients' physiological states, enabling timely detection and handling of potential medical problems. Simultaneously, the mechanism for dynamically adjusting the data collection frequency helps balance the efficiency of medical resource utilization with the needs of patient safety. By presetting different heart rate thresholds and respiratory abnormality coefficient thresholds, the system can be personalized for different patients or different conditions, thereby better meeting clinical needs. This personalized setting helps improve the targetedness and effectiveness of medical treatment.

[0101] In summary, this technical solution achieves precise monitoring and early warning of patients' physiological status by real-time monitoring of their heart rate and respiratory parameters and using a respiratory abnormality coefficient for comprehensive assessment. Simultaneously, by dynamically adjusting the data acquisition frequency, it improves the efficiency of medical resource utilization and patient safety, providing strong support for personalized medicine.

[0102] Specifically, the respiratory abnormality coefficient is compared with a preset respiratory abnormality coefficient threshold, and the sampling frequency of heart rate variability and respiratory depth changes is adjusted according to the comparison result, including:

[0103] The respiratory abnormality coefficient is compared with a preset respiratory abnormality coefficient threshold to obtain a comparison result;

[0104] If the comparison results show that the respiratory abnormality coefficient is not lower than the preset respiratory abnormality coefficient threshold, then there is no need to adjust the acquisition frequency of heart rate variability and respiratory depth change.

[0105] If the comparison result shows that the respiratory abnormality coefficient is lower than the preset respiratory abnormality coefficient threshold, the sampling frequency of heart rate variability and respiratory depth change is adjusted using the respiratory abnormality coefficient to obtain the adjusted sampling frequency of heart rate variability and respiratory depth change.

[0106] The adjusted heart rate variability sampling frequency is obtained using the following formula:

[0107]

[0108] Among them, F h The sampling frequency represents the adjusted heart rate variability; F h0 The sampling frequency represents the heart rate variability before adjustment; R represents the respiratory abnormality coefficient; R y V represents the preset threshold for the respiratory abnormality coefficient; p V represents the average tidal volume for each breath within a preset breathing count; min This represents the minimum tidal volume corresponding to each breath within a preset number of breaths; V max This indicates the maximum tidal volume for each breath within a preset number of breaths.

[0109] Meanwhile, the adjusted sampling frequency for changes in respiratory depth is obtained using the following formula:

[0110]

[0111] Among them, F t This indicates the sampling frequency of the adjusted respiratory depth changes; F t0 This indicates the sampling frequency of changes in respiratory depth before adjustment; V p V represents the average tidal volume for each breath within a preset breathing count; max This represents the maximum tidal volume for each breath within a preset number of breaths; H m This represents the heart rate data value corresponding to an abnormal heart rate; H y This indicates the preset heart rate threshold;

[0112] The health monitoring equipment was controlled to collect data corresponding to heart rate variability and respiratory depth changes according to the adjusted sampling frequency.

[0113] The technical effects of the above solution are as follows: By comparing the respiratory abnormality coefficient with a preset threshold, the system can intelligently determine whether the acquisition frequency needs to be adjusted. When the respiratory abnormality coefficient is high (i.e., not lower than the preset threshold), the system maintains the original acquisition frequency to ensure sufficient data for accurate assessment when the patient's condition is unstable. When the respiratory abnormality coefficient is low, the system dynamically reduces the acquisition frequency based on the coefficient value, thereby reducing unnecessary resource consumption while ensuring monitoring effectiveness. The adjustment formula considers multiple factors, including the respiratory abnormality coefficient, the average, minimum, and maximum tidal volume, and heart rate data, which together determine the adjusted acquisition frequency. This personalized adjustment strategy can better adapt to the physiological characteristics and disease changes of different patients, improving the targeting and accuracy of monitoring. By dynamically adjusting the acquisition frequency, the system can increase data acquisition points during critical periods, thereby more accurately capturing the changing trends of the patient's physiological parameters. At the same time, reducing data acquisition points during non-critical periods helps reduce data noise and improve the overall quality of monitoring data. Reducing unnecessary monitoring can reduce interference with patients, especially during long-term monitoring, which helps improve patient comfort and acceptance, thus promoting the smooth progress of monitoring work. Real-time, accurate, and personalized monitoring data provides strong support for clinical decision-making. Physicians can use this data to more accurately assess a patient's condition and develop more effective treatment plans, thereby improving treatment outcomes and patient satisfaction. The adjustment formulas and threshold settings in this technology offer a degree of flexibility and scalability. As medical technology and clinical needs evolve, these parameters can be easily adjusted and optimized to adapt to new monitoring requirements and treatment strategies.

[0114] In summary, this technical solution, through a sampling frequency adjustment strategy based on respiratory abnormality coefficients, achieves refined management and resource optimization of patient physiological parameters, improves monitoring efficiency and accuracy, enhances patient comfort and acceptance, and promotes improved clinical decision-making and treatment outcomes. Furthermore, this technical solution demonstrates good scalability and flexibility, providing strong support for the future development of medical monitoring technologies.

[0115] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "possessing," or any other variations thereof are intended to cover non-exclusive possession, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0116] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that variations, modifications, substitutions and alterations may be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A heatstroke prevention and monitoring system based on consciousness, cognition, and behavioral characteristics, characterized in that: include: The data collection unit is used to collect physiological signals and behavioral data of patients with heatstroke as a type of data. It is also used to collect physiological signals and behavioral data from normal patients as Class II data; among which, physiological signal data includes: patient body surface temperature, electroencephalogram, electrocardiogram and respiratory biofeedback signals; behavioral data includes: movement frequency, reaction speed and attention behavior indicators; The data collection unit includes: The real-time collection module is used to collect current patient heart rate variability, respiratory depth changes and skin resistance data through health monitoring devices, as basic data for clinical diagnosis or daily health prevention and monitoring. The data collection unit further includes: Real-time monitoring of the patient's current heart rate data; Compare the current patient's heart rate data value with a preset heart rate threshold; When the current patient's heart rate data value exceeds the preset heart rate threshold, the tidal volume corresponding to each breath in the preset number of breaths of the current patient is monitored. The respiratory abnormality coefficient is obtained by using the tidal volume corresponding to each breath of the current patient within a preset number of breaths; The respiratory abnormality coefficient is obtained by the following formula: Where R represents the respiratory abnormality coefficient; V p V represents the average tidal volume for each breath within a preset breathing count; min This represents the minimum tidal volume for each breath within a preset number of breaths; f represents the respiratory rate of the current breath; f max Indicates the preset maximum permissible respiratory rate; H m This represents the heart rate data value corresponding to an abnormal heart rate; H y This indicates the preset heart rate threshold; The respiratory abnormality coefficient is compared with a preset respiratory abnormality coefficient threshold, and the sampling frequency of heart rate variability and respiratory depth change is adjusted according to the comparison result. The feature extraction unit is used to clean and reduce the dimensionality of the primary and secondary data, and extract feature information reflecting the patient's physical condition and metabolic level from the primary and secondary data respectively; the feature information of patients with heatstroke is used as feature vectors and labeled as positive; and the feature information of patients without heatstroke is used as training samples and labeled as negative. The feature recognition unit uses feature vectors and labels as the training set and feature information and labels of binary data as the test set. It learns the feature vectors and label content through a linear discriminant analysis model and outputs the learning results. Then, it analyzes the feature information and label content of the binary data through the learned linear discriminant analysis model to determine whether there are heatstroke features in the feature information of the binary data and outputs the prediction results. The prediction results are compared with the actual results of the binary data to verify the performance of the linear discriminant analysis model. The prevention and monitoring unit is used to predict whether a patient has heatstroke using a linear discriminant analysis model. If the patient has heatstroke, the unit further calculates the risk index of the patient's heatstroke and implements different prevention and monitoring strategies based on the level of the risk index.

2. The heatstroke prevention and monitoring system based on consciousness, cognition, and behavioral characteristics recognition according to claim 1, characterized in that: The feature extraction unit includes: The data processing module is used to clean, denoise, and normalize primary and secondary data. The feature extraction module is used to analyze the information content in the first-class and second-class data, and extract heart rate variability, respiratory depth changes and skin resistance as feature information reflecting the patient's physical condition and metabolic level. The feature analysis module is used to compare the feature information of patients with heatstroke with that of those without heatstroke, and to analyze whether the feature information of patients with heatstroke differs from that of those without heatstroke under the influence of heatstroke.

3. The heatstroke prevention and monitoring system based on consciousness, cognition, and behavioral characteristics recognition according to claim 2, characterized in that: The feature analysis module analyzes whether the feature information of patients with heatstroke differs from that of patients without heatstroke under the influence of heatstroke. Specifically, it calculates the feature vector for each patient based on heart rate variability, respiratory depth changes, and skin resistance, and determines whether there are differences in the feature vectors of each patient. Calculation of the heart rate variability eigenvector: The voltage at each heartbeat point in the electrocardiogram signal is mapped to the original heart rate using a linear interpolation formula. For each heartbeat point, the time interval DT between two adjacent heartbeat points is calculated. For each heartbeat, calculate the power spectral density estimate (PSDE) for each time interval DT; then take the frequency corresponding to the maximum value of the PSDE for each heartbeat as the feature vector. Calculation of the eigenvector of respiratory depth change: The voltage at each respiratory cycle point in the respiratory signal is mapped to the original respiratory cycle number using a linear interpolation formula. For each respiratory cycle point, the time interval DT between two adjacent respiratory cycle points is calculated. For each respiratory cycle point, the power spectral density estimate (PSDE) corresponding to each time interval DT is calculated. Then, the frequency corresponding to the maximum value of the power spectral density estimate (PSDE) at each respiratory cycle point is taken as the feature vector. Calculation of the skin resistance eigenvector: Each resistance value in the skin impedance signal is mapped to the original skin impedance using a linear interpolation formula. For each skin impedance, the time-domain interval DT between two adjacent skin impedances is calculated. For each skin impedance, calculate the power spectral density estimate (PSDE) for each time interval DT; then take the frequency corresponding to the maximum value of the PSDE for each skin impedance as the feature vector. The criteria for judgment are as follows: patients with heatstroke have higher values ​​in their feature vectors, while patients without heatstroke have lower values ​​in their feature vectors. Based on this, it is analyzed whether the feature information of patients with heatstroke differs from that of patients without heatstroke under the influence of heatstroke.

4. The heatstroke prevention and monitoring system based on consciousness, cognition, and behavioral characteristics recognition according to claim 1, characterized in that: The feature recognition unit includes: The model building module is used to create a neural network model. The training set is input into the neural network model, the LDA linear discriminant analysis algorithm is used to train the model, and the training results are output to obtain the linear discriminant analysis model. The model evaluation module is used to input the test set into the linear discriminant analysis model for testing, use the linear discriminant analysis model to identify the presence of heatstroke characteristics in the test set, and verify the performance of the linear discriminant analysis model based on the test results.

5. The heatstroke prevention and monitoring system based on consciousness, cognition, and behavioral characteristics recognition according to claim 4, characterized in that: The feature recognition unit further includes: The feature interpretation module is used to analyze the meaning of each feature after training on the training and test sets is completed.

6. The heatstroke prevention and monitoring system based on consciousness, cognition, and behavioral characteristics recognition according to claim 1, characterized in that: The prevention and monitoring unit includes: The risk analysis module collects the current patient's personal information as an additional factor and uses a weighted average method to calculate the current patient's risk index of having heatstroke; The early warning module is used to establish risk thresholds. If a patient's risk index exceeds the set threshold, it indicates that the patient is at high risk of heatstroke and an alarm will be issued in a timely manner to remind medical staff to pay attention to the patient's condition.

7. The heatstroke prevention and monitoring system based on consciousness, cognition, and behavioral characteristics recognition according to claim 1, characterized in that: The respiratory abnormality coefficient is compared with a preset respiratory abnormality coefficient threshold, and the sampling frequency of heart rate variability and respiratory depth changes is adjusted according to the comparison result, including: The respiratory abnormality coefficient is compared with a preset respiratory abnormality coefficient threshold to obtain a comparison result; If the comparison results show that the respiratory abnormality coefficient is not lower than the preset respiratory abnormality coefficient threshold, then there is no need to adjust the acquisition frequency of heart rate variability and respiratory depth change. If the comparison result shows that the respiratory abnormality coefficient is lower than the preset respiratory abnormality coefficient threshold, the sampling frequency of heart rate variability and respiratory depth change is adjusted using the respiratory abnormality coefficient to obtain the adjusted sampling frequency of heart rate variability and respiratory depth change. The adjusted heart rate variability sampling frequency is obtained using the following formula: Among them, F h The sampling frequency represents the adjusted heart rate variability; F h0 The sampling frequency represents the heart rate variability before adjustment; R represents the respiratory abnormality coefficient; R y V represents the preset threshold for the respiratory abnormality coefficient; p V represents the average tidal volume for each breath within a preset breathing count; min This represents the minimum tidal volume corresponding to each breath within a preset number of breaths; V max This indicates the maximum tidal volume for each breath within a preset number of breaths. Meanwhile, the adjusted sampling frequency for changes in respiratory depth is obtained using the following formula: Among them, F t This indicates the sampling frequency of the adjusted respiratory depth changes; F t0 This indicates the sampling frequency of changes in respiratory depth before adjustment; V p V represents the average tidal volume for each breath within a preset breathing count; max This represents the maximum tidal volume for each breath within a preset number of breaths; H m This represents the heart rate data value corresponding to an abnormal heart rate; H y This indicates the preset heart rate threshold; The health monitoring equipment was controlled to collect data corresponding to heart rate variability and respiratory depth changes according to the adjusted sampling frequency.

8. The heatstroke prevention and monitoring system based on consciousness, cognition, and behavioral characteristics recognition according to claim 1, characterized in that: Also includes: The human-computer interaction unit is used to visualize and display the patient's current physiological signals and behavioral data, as well as the prediction results and risk index of the linear discriminant analysis model.

Images