Stroke early warning system and method based on intelligent wearing health monitoring

Abstract

The invention discloses a stroke early warning system and method based on intelligent wearing health monitoring, and relates to the technical field of stroke early warning. A current physiological data set and a step length data set are analyzed, a current state analysis result is output, current living habit data is processed, and a current living habit data set is output; according to the method, physiological parameters and the living environment of a patient are monitored in real time, early warning is carried out in advance through data analysis, the risk of stroke is reduced, and after abnormity is detected, the early warning is carried out. The pathogenesis report is generated by integrating the physiology, living habits and environmental factors of the patient, a treatment basis is provided for doctors, personalized early warning analysis is carried out, and the accuracy is improved. An early warning signal can be sent to the patient, an emergency contact person and a medical institution, so that timely rescue in emergency is ensured, and the life safety of the patient is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of stroke warning, and in particular to an early warning system and method for stroke based on smart wearable health monitoring. Background Art

[0002] With the aging of the population and the accelerated pace of life, the incidence of stroke has increased year by year, becoming one of the major diseases threatening human health. Stroke, also known as infarction, is a group of diseases caused by sudden rupture of blood vessels in the brain or blockage of blood vessels that prevents blood from flowing into the brain, causing brain tissue damage. It is characterized by high morbidity, high disability rate and high mortality rate, which brings a heavy burden to individuals, families and society.

[0003] At present, a Chinese patent with application number CN202311088876.1 discloses a stroke risk prediction method and device, wherein an original neural network model is trained based on historical electromyographic signal data to obtain a stroke risk prediction model; the target electromyographic signal of the forearm muscle group of the subject under a specific electrical stimulation signal is collected; the target electromyographic signal is input into the stroke risk prediction model to obtain a stroke risk prediction result, which can utilize the phenomenon of asymmetric arm movement caused by obstructed nerve conduction to achieve stroke risk prediction.

[0004] The above technology makes it difficult to infer the cause of the disease based on past living habits and environmental conditions after predicting the possible onset of the disease, so as to avoid the patient's difficulty in expressing the cause of the disease due to confusion in the language system after the onset of the disease, thereby affecting the treatment effect. Summary of the invention

[0005] The technical problem solved by the present invention is that it is difficult to infer the cause of the disease based on past living habits and environmental conditions after predicting the possible onset of the disease using the above technology, so as to avoid the patient's difficulty in expressing the cause of the disease due to confusion in the language system after the onset of the disease, thereby affecting the treatment effect.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: an early warning system for stroke based on smart wearable health monitoring, comprising a parameter monitoring and analysis module, a habit environment collection module, a cause report generation module and an emergency response guidance module; The parameter monitoring and analysis module is used to collect the patient's current physiological data set and current step length data set, analyze the current physiological data set and the step length data set, and output the current state analysis result; The habit environment acquisition module is used to extract the patient's current living habit data and current environment data set according to the current state analysis result, process the current living habit data, and output it as the current living habit data set; The etiology report generation module is used to establish an etiology prediction model, input the lifestyle dataset and the current environment dataset into the etiology prediction model, and generate a preliminary etiology report; The emergency response guidance module is used to analyze according to the current status analysis results and generate a preliminary cause report, generate a prediction result, generate an early warning signal according to the prediction result, send the early warning signal to the patient end, and send the early warning signal and the preliminary cause report to the patient's emergency contact end and medical institution end.

[0007] Preferably, the parameter monitoring and analysis module includes a physiological data monitoring unit and a physiological data analysis unit; The physiological data monitoring unit is used to collect the patient's current blood pressure data, current heart rate data, current blood oxygen saturation data, current brain wave data, current body temperature data and step length data within a preset first time period, extract the frequency band of the current brain wave data, the frequency band includes a Delta band with a frequency of 0.5Hz-4Hz and an Alpha band with a frequency of 30Hz-100Hz, extract the number of Delta bands and the number of Alpha bands, and output them as current Delta band number data and current Alpha band number data, merge the current blood pressure data, current heart rate data, current blood oxygen saturation data, current Delta band number data, current Alpha band number data and current body temperature data into a current physiological data set, and output the step length data within the preset time period as the current step length data set.

[0008] Preferably, the physiological data analysis unit is used to analyze the current physiological data set and the current step length data set: Comparing the current physiological data set with a preset standard data set, wherein the standard data set includes a standard blood pressure threshold, a standard heart rate threshold, a standard blood oxygen saturation threshold, a standard Delta frequency band number threshold, a standard Alpha frequency band number threshold, a standard body temperature threshold, and a standard step length coefficient of variation threshold; Calculate the coefficient of variation of step length from the step length dataset: Calculate the step size mean, the mathematical expression is: in, is the mean step length, is the index of the step number, with a value of 1- , is the total number of steps, For the The step length of the step; Calculate the step size standard deviation, the mathematical expression is: in, is the step size standard deviation; Calculate the step length variation coefficient, mathematical expression: in, is the coefficient of variation of step length; The output is the current step length variation coefficient data; If the current physiological data set and the current step length variation coefficient data satisfy: the current blood pressure data is within the standard blood pressure threshold, the current heart rate data is within the standard heart rate threshold, the current blood oxygen saturation data is within the standard blood oxygen saturation threshold, the current Delta frequency band quantity data is within the standard Delta frequency band quantity threshold, the current Alpha frequency band quantity data is within the standard Alpha frequency band quantity threshold, the current body temperature data is within the standard body temperature threshold, and the current step length variation coefficient data is within or less than the standard compensation variation coefficient threshold, it is determined that the disease is not about to occur; If the current physiological data set and the current step length variation coefficient data meet the following conditions: the current blood pressure data is greater than or less than the standard blood pressure threshold, the current heart rate data is greater than or less than the standard heart rate threshold, the current blood oxygen saturation data is greater than or less than the standard blood oxygen saturation threshold, the current Delta frequency band quantity data is greater than the standard Delta frequency band quantity threshold, the current Alpha frequency band quantity data is less than the standard Alpha frequency band quantity threshold, the current body temperature data is greater than or less than the standard body temperature threshold, or the current step length variation coefficient data is greater than the standard compensation variation coefficient threshold, it is determined that the disease is about to occur; Output the current status analysis result, wherein the current status analysis result includes the onset of disease not yet occurred and the onset of disease at the first level being imminent.

[0009] Preferably, the habitual environment collection module includes a daily data collection unit and a collection data processing unit; The daily data acquisition unit is used to receive the current state analysis result. If the current state analysis result is that the disease is about to occur, the current living habit data and current environmental data within a second time period preset by the patient are extracted from the historical database. The current living habit data include the number of sleep apnea times per hour, the weekly exercise time, the weekly total metabolic amount, the weekly smoking amount and the weekly alcohol intake. The current environmental data set includes the current temperature data, the current PM2.5 concentration value and the current altitude data.

[0010] Preferably, the collected data processing unit is used to process the current living habit data: Record the number of sleep apnea times per hour when the number of sleep apnea times per hour is less than or equal to 15 times, and output it as the current qualified apnea number data; Record the number of weekly exercise hours greater than or equal to 150 minutes, and output the current qualified exercise time quantity data; Record the total weekly metabolic amount greater than or equal to 600 MET, and output it as the current qualified metabolic amount data; Record the number of cigarettes smoked per week when the weekly smoking amount is less than or equal to 10 cigarettes, and output it as the current qualified smoking amount data; Record the number of weekly alcohol intakes less than or equal to 14 drinks per week, and output the current qualified alcohol intake data; The current qualified pause number data, the current qualified exercise duration data, the current qualified metabolic amount data, the current qualified smoking amount data and the current qualified alcohol intake amount data are combined and output as the current life habit data set.

[0011] Preferably, the etiology report generating module includes a prediction model building unit and an etiology report generating unit; The prediction model building unit is used to build a cause prediction model, and the logic of the cause prediction model is: Weight the qualified pause number data, qualified exercise duration data, qualified metabolic volume data, qualified smoking volume data and qualified alcohol intake volume data: The weight of the number of qualified suspensions is 30%; The weight of the qualified exercise duration data is 25%; The weight of qualified metabolic quantity data is 20%; The weight of the qualified smoking quantity data is 15%; The weight of qualified alcohol intake data is 10%; Calculate the weighted total value of qualified pause number data, qualified exercise duration data, qualified metabolic quantity data, qualified smoking quantity data and qualified alcohol intake quantity data, and output as qualified indicator data; Analysis of qualified indicator data: If the qualified index data is greater than the preset standard qualified index data threshold, it is determined that the living habits are normal; If the qualified index data is less than the preset standard qualified index data threshold, it is judged as abnormal living habits; Analysis of temperature data, PM2.5 concentration values ​​and altitude data: If the temperature data, PM2.5 concentration value and altitude data satisfy that the temperature data is greater than or less than the preset suitable temperature threshold, the PM2.5 concentration value is greater than the preset suitable PM2.5 concentration threshold or the altitude data is higher than the preset suitable altitude threshold, it is determined to be an abnormal environment; If the temperature data, PM2.5 concentration value and altitude data satisfy that the temperature data is within the preset suitable temperature threshold, the PM2.5 concentration value is within or less than the preset suitable PM2.5 concentration threshold and the altitude data is lower than the preset suitable altitude threshold, the environment is determined to be normal; Generate a cause of disease report, which includes qualified pause quantity data, qualified exercise duration data, qualified metabolic quantity data, qualified smoking quantity data and qualified alcohol intake data input under normal living habits, abnormal living habits, normal environment, abnormal environment and abnormal living habits, and temperature data, PM2.5 concentration value and altitude data input under abnormal environment.

[0012] Preferably, the etiology report generating unit is used to input the lifestyle data set and the current environment data set into the etiology prediction model to generate a preliminary etiology report, wherein the preliminary etiology report includes the current qualified pause quantity data, the current qualified exercise duration quantity data, the current qualified metabolic quantity data, the current qualified smoking quantity data and the current qualified alcohol intake quantity data input under normal lifestyle habits, abnormal lifestyle habits, normal environment, abnormal environment and abnormal lifestyle habits, and the current temperature data, current PM2.5 concentration value and current altitude data input under abnormal environment.

[0013] Preferably, the emergency response guidance module includes an onset prediction analysis unit and an early warning signal processing unit; The disease prediction analysis unit is used to analyze according to the current state analysis results and generate a preliminary cause report: If the current status analysis result shows that the disease is not about to occur, the body is judged to be in normal condition; If the current status analysis result is an impending onset of illness and the preliminary cause report shows that the lifestyle and environment are normal, it is determined to be a first-level impending onset of illness; If the current status analysis result is that the disease is about to occur and the preliminary cause report is abnormal living habits or abnormal environment, it is judged as the second level of impending disease; If the current status analysis result is that the disease is about to occur and the preliminary cause report is abnormal living habits and abnormal environment, it is judged as the third level of impending disease; The prediction results are output, and the prediction results include normal physical condition, level one impending onset, level two impending onset and level three impending onset.

[0014] Preferably, the warning signal processing unit is used to generate a warning signal according to the prediction result: If the predicted result is that the physical condition is normal, no warning signal is generated; If the prediction result is that the first-level disease is about to occur, a first-level warning signal will be issued; If the prediction result is that the second-level disease is about to occur, a second-level warning signal will be issued; If the prediction result is that the disease is about to occur at level 3, a level 3 warning signal will be issued; The first-level warning signal, the second-level warning signal or the third-level warning signal is sent to the patient end, and the first-level warning signal, the second-level warning signal or the third-level warning signal and the preliminary cause of disease report are sent to the patient's emergency contact end, the emergency contact end and the medical institution end.

[0015] The stroke early warning method based on smart wearable health monitoring is applied to the stroke early warning system based on smart wearable health monitoring, and comprises the following steps: Step S1, collecting the patient's current physiological data set and current step length data set, analyzing the current physiological data set and the step length data set, and outputting the current state analysis result; Step S2, extracting the patient's current living habit data and current environment data set according to the current state analysis result, processing the current living habit data, and outputting it as the current living habit data set; Step S3, establishing a cause prediction model, inputting the lifestyle dataset and the current environment dataset into the cause prediction model, and generating a preliminary cause report; Step S4, analyze according to the current status analysis results and generate a preliminary cause report, generate a prediction result, generate an early warning signal according to the prediction result, send the early warning signal to the patient end, and send the early warning signal and the preliminary cause report to the patient's emergency contact end and medical institution end.

[0016] Beneficial effects of the present invention: The present invention monitors the patient's physiological parameters and living environment in real time, provides early warning through data analysis, reduces the risk of stroke, and generates a cause report based on the patient's physiology, living habits, and environmental factors after detecting an abnormality, providing doctors with a basis for treatment and conducting personalized early warning analysis to improve accuracy. Early warning signals will be sent to patients, emergency contacts, and medical institutions to ensure timely assistance in emergency situations and protect the patient's life safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A basic flow chart of a stroke early warning system based on smart wearable health monitoring provided by an embodiment of the present invention; Figure 2 A flowchart of the steps of a stroke early warning method based on smart wearable health monitoring provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0019] Embodiment 1, refer to Figure 1, provides an early warning system for stroke based on smart wearable health monitoring, including parameter monitoring and analysis module, habit environment collection module, cause report generation module and emergency response guidance module.

[0020] The parameter monitoring and analysis module is used to collect the patient's current physiological data set and current step length data set, analyze the current physiological data set and the step length data set, and output the current state analysis result.

[0021] The habit environment acquisition module is used to extract the patient's current living habit data and current environment data set according to the current state analysis results, process the current living habit data, and output it as the current living habit data set.

[0022] The etiology report generation module is used to establish an etiology prediction model, input the lifestyle dataset and the current environment dataset into the etiology prediction model, and generate a preliminary etiology report.

[0023] The emergency response guidance module is used to analyze the current status analysis results and generate a preliminary cause report, generate a prediction result, generate a warning signal based on the prediction result, send the warning signal to the patient, and send the warning signal and the preliminary cause report to the patient's emergency contact and medical institution.

[0024] The parameter monitoring and analysis module includes a physiological data monitoring unit and a physiological data analysis unit.

[0025] The physiological data monitoring unit is used to collect the patient's current blood pressure data, current heart rate data, current blood oxygen saturation data, current brain wave data, current body temperature data and step length data within a preset first time period, extract the frequency band of the current brain wave data, the frequency band includes a Delta band with a frequency of 0.5Hz-4Hz and an Alpha band with a frequency of 30Hz-100Hz, extract the number of Delta bands and the number of Alpha bands, and output them as current Delta band number data and current Alpha band number data, merge the current blood pressure data, current heart rate data, current blood oxygen saturation data, current Delta band number data, current Alpha band number data and current body temperature data into a current physiological data set, and output the step length data within the preset time period as the current step length data set.

[0026] The physiological data monitoring unit is responsible for collecting multiple physiological data of the patient in real time. Among them, the collection of brain wave data is particularly critical. It can extract the Delta frequency band and Alpha frequency band in the brain wave and calculate their number. These physiological data are integrated into the current physiological data set, providing a detailed data basis for subsequent analysis.

[0027] The physiological data analysis unit is used to analyze the current physiological data set and the current step length data set: The current physiological data set is compared with a preset standard data set, wherein the standard data set includes a standard blood pressure threshold, a standard heart rate threshold, a standard blood oxygen saturation threshold, a standard Delta frequency band number threshold, a standard Alpha frequency band number threshold, a standard body temperature threshold, and a standard step length coefficient of variation threshold.

[0028] Calculate the coefficient of variation of step length from the step length dataset: Calculate the step size mean, the mathematical expression is: in, is the mean step length, is the index of the step number, with a value of 1- , is the total number of steps, For the The step length of the step; Calculate the step size standard deviation, the mathematical expression is: in, is the step size standard deviation; Calculate the step length variation coefficient, mathematical expression: in, is the coefficient of variation of step length; The output is the current step length coefficient of variation data.

[0029] If the current physiological data set and the current step length coefficient of variation data satisfy: the current blood pressure data is within the standard blood pressure threshold, the current heart rate data is within the standard heart rate threshold, the current blood oxygen saturation data is within the standard blood oxygen saturation threshold, the current Delta frequency band quantity data is within the standard Delta frequency band quantity threshold, the current Alpha frequency band quantity data is within the standard Alpha frequency band quantity threshold, the current body temperature data is within the standard body temperature threshold and the current step length coefficient of variation data is within or less than the standard compensation coefficient of variation threshold, it is determined that the disease is not about to occur.

[0030] If the current physiological data set and the current step length coefficient of variation data meet the following conditions: the current blood pressure data is greater than or less than the standard blood pressure threshold, the current heart rate data is greater than or less than the standard heart rate threshold, the current blood oxygen saturation data is greater than or less than the standard blood oxygen saturation threshold, the current Delta frequency band quantity data is greater than the standard Delta frequency band quantity threshold, the current Alpha frequency band quantity data is less than the standard Alpha frequency band quantity threshold, the current body temperature data is greater than or less than the standard body temperature threshold, or the current step length coefficient of variation data is greater than the standard compensation coefficient of variation threshold, it is determined that an illness is about to occur.

[0031] Output the current status analysis result, wherein the current status analysis result includes the onset of disease not yet occurred and the onset of disease at the first level being imminent.

[0032] The physiological data analysis unit is responsible for comparing and analyzing the collected physiological data sets and stride length data sets with the preset standard data sets. By calculating the stride length variation coefficient and combining the threshold judgment of various physiological data, it evaluates the patient's current health status and predicts potential stroke risks.

[0033] The parameter monitoring and analysis module is responsible for real-time collection and analysis of the patient's physiological data and step length data to assess the patient's current health status and predict potential stroke risks. Through the collaborative work of the physiological data monitoring unit and the physiological data analysis unit, comprehensive monitoring and accurate analysis of the patient's health status are achieved.

[0034] The habit environment collection module includes a daily data collection unit and a collection data processing unit.

[0035] The daily data acquisition unit is used to receive the current state analysis result. If the current state analysis result is that the disease is about to occur, the current living habit data and current environmental data within a second time period preset by the patient are extracted from the historical database. The current living habit data include the number of sleep apnea times per hour, the weekly exercise time, the weekly total metabolic amount, the weekly smoking amount and the weekly alcohol intake. The current environmental data set includes the current temperature data, the current PM2.5 concentration value and the current altitude data.

[0036] The daily data collection unit can accurately extract the required data from the historical database based on the current status analysis results, ensuring the accuracy and pertinence of the data. It covers multiple aspects of living habits data and environmental data, provides comprehensive information support, and timely extracts the latest living habits and environmental data based on the patient's current status, providing the latest data basis for subsequent processing and analysis.

[0037] The data collection and processing unit is used to process the current living habit data: The number of sleep apnea episodes per hour with sleep apnea episodes less than or equal to 15 times per hour is recorded, and the output is the current qualified apnea episode number data.

[0038] Record the number of weekly exercise minutes that are greater than or equal to 150 minutes, and output the current qualified exercise time data.

[0039] Record the weekly total metabolic quantity that is greater than or equal to 600 MET, and output it as the current qualified metabolic quantity data.

[0040] Record the number of cigarettes smoked per week that is less than or equal to 10 cigarettes per week, and output it as the current qualified number of cigarettes smoked.

[0041] Record the number of weekly alcohol intakes less than or equal to 14 drinks per week, and output the current qualified alcohol intake data.

[0042] The current qualified pause number data, the current qualified exercise duration data, the current qualified metabolic amount data, the current qualified smoking amount data and the current qualified alcohol intake amount data are combined and output as the current life habit data set.

[0043] The data collection and processing unit ensures the consistency and standardization of data processing by setting clear data processing standards, and integrates the processed lifestyle data into a complete data set, providing convenient data support for subsequent health status assessments. By outputting data such as the current number of qualified pauses and the current number of qualified exercise durations, the processing results are more intuitive and easy to understand, making it easier for doctors and patients to quickly understand the patient's lifestyle habits.

[0044] The habit environment collection module provides more comprehensive background information for the patient's health status assessment by collecting and analyzing the patient's daily living habit data and environmental data. It consists of two core parts: the daily data collection unit and the collection data processing unit. Each of them has different responsibilities and together realizes the effective collection and processing of the patient's living habits and environmental data.

[0045] The etiology report generation module includes a prediction model building unit and an etiology report generation unit.

[0046] The prediction model building unit is used to build a cause prediction model, the logic of which is: Weight the qualified pause number data, qualified exercise duration data, qualified metabolic volume data, qualified smoking volume data and qualified alcohol intake volume data: The weight of the qualified suspension number data is 30%.

[0047] The weight of the qualified exercise duration data is 25%.

[0048] The weight of qualified metabolic quantity data is 20%.

[0049] The weight of the qualified smoking quantity data is 15%.

[0050] The qualifying alcohol intake data was weighted at 10%.

[0051] Calculate the weighted total value of qualified pause number data, qualified exercise duration data, qualified metabolic volume data, qualified smoking volume data and qualified alcohol intake data, and output as qualified indicator data.

[0052] Analysis of qualified indicator data: If the qualified index data is greater than the preset standard qualified index data threshold, it is judged that the living habits are normal.

[0053] If the qualified index data is less than the preset standard qualified index data threshold, it is judged as abnormal living habits.

[0054] Analysis of temperature data, PM2.5 concentration values ​​and altitude data: If the temperature data, PM2.5 concentration value and altitude data satisfy the condition that the temperature data is greater than or less than the preset suitable temperature threshold, the PM2.5 concentration value is greater than the preset suitable PM2.5 concentration threshold or the altitude data is higher than the preset suitable altitude threshold, it is judged as an environmental abnormality.

[0055] If the temperature data, PM2.5 concentration value and altitude data satisfy the conditions that the temperature data is within the preset suitable temperature threshold, the PM2.5 concentration value is within or less than the preset suitable PM2.5 concentration threshold and the altitude data is lower than the preset suitable altitude threshold, the environment is judged to be normal.

[0056] Generate a cause of disease report, which includes qualified pause quantity data, qualified exercise duration data, qualified metabolic quantity data, qualified smoking quantity data and qualified alcohol intake data input under normal living habits, abnormal living habits, normal environment, abnormal environment and abnormal living habits, and temperature data, PM2.5 concentration value and altitude data input under abnormal environment.

[0057] The prediction model building unit performs weighted processing on the living habits data, assigns different weights according to the relative importance of each factor, so as to more accurately reflect the patient's living habits. Based on the weighted data, the qualified indicator data is calculated and compared with the preset standard qualified indicator data threshold to determine whether the patient's living habits are normal, comprehensively and objectively reflect the patient's living habits, conduct in-depth analysis of the environmental data, and determine whether the environment is normal according to the preset appropriate threshold. This step helps to reveal the possible impact of environmental factors on the patient's health. Based on the above analysis and evaluation results, a cause prediction model is constructed to automatically generate a preliminary cause analysis report based on the input living habits data set and environmental data set.

[0058] The etiology report generation unit is used to input the lifestyle data set and the current environment data set into the etiology prediction model to generate a preliminary etiology report, wherein the preliminary etiology report includes the current qualified pause quantity data, the current qualified exercise duration quantity data, the current qualified metabolic quantity data, the current qualified smoking quantity data and the current qualified alcohol intake quantity data input under normal lifestyle habits, abnormal lifestyle habits, normal environment, abnormal environment and abnormal lifestyle habits, and the current temperature data, current PM2.5 concentration value and current altitude data input under abnormal environment.

[0059] The etiology report generation unit receives the lifestyle dataset and the current environment dataset as inputs to the etiology prediction model, inputs the input data into the etiology prediction model, and automatically generates a preliminary etiology report based on the logic and algorithm of the model, so that doctors can quickly understand the patient's health status and potential causes.

[0060] The etiology report generation module provides patients with personalized etiology analysis reports by comprehensively analyzing patients' living habit data and environmental data.

[0061] The emergency response guidance module includes an incidence prediction and analysis unit and an early warning signal processing unit.

[0062] The morbidity prediction analysis unit is used to analyze the current status and generate a preliminary cause report: If the current status analysis result shows that the disease is not about to occur, the body is judged to be in normal condition If the current status analysis result is that the disease is about to occur and the preliminary cause report shows that the living habits and environment are normal, it is judged as a first-level impending disease.

[0063] If the current status analysis result is that the disease is about to occur and the preliminary cause report is abnormal lifestyle habits or abnormal environment, it is judged as a second-level impending disease.

[0064] If the current status analysis result is that the disease is about to occur and the preliminary cause report is abnormal living habits and abnormal environment, it is judged as a third-level impending disease.

[0065] The prediction results are output, and the prediction results include normal physical condition, level one impending onset, level two impending onset and level three impending onset.

[0066] The disease prediction analysis unit accurately judges the patient's health status based on the patient's current status analysis results and preliminary cause report. Through comprehensive analysis of multiple factors, it can predict whether the patient is about to get sick and the severity of the disease. It adopts a multi-level judgment mechanism to divide the disease prediction results into four levels: normal physical condition, level one, level two, and level three, which helps doctors and patients understand the patient's health status and potential risks more clearly.

[0067] The warning signal processing unit is used to generate a warning signal based on the prediction results: If the predicted result is that the physical condition is normal, no warning signal is generated.

[0068] If the predicted result is that a level 1 disease is about to occur, a level 1 warning signal will be issued.

[0069] If the prediction result is that a level 2 disease is about to occur, a level 2 warning signal will be issued.

[0070] If the prediction result is that the disease is about to occur at level three, a level three warning signal will be issued.

[0071] The first-level warning signal, the second-level warning signal or the third-level warning signal is sent to the patient end, and the first-level warning signal, the second-level warning signal or the third-level warning signal and the preliminary cause of disease report are sent to the patient's emergency contact end, the emergency contact end and the medical institution end.

[0072] The warning signal processing unit automatically generates a corresponding warning signal based on the prediction results of the disease prediction analysis unit. The level of the warning signal matches the severity of the disease prediction, ensuring the accuracy and effectiveness of the warning. The warning signal is sent to the patient, emergency contact and medical institution. The multi-channel sending method ensures the wide dissemination and timely receipt of the warning information. While issuing the warning signal, the warning signal processing unit can also send relevant information such as the preliminary cause report to the relevant parties, which helps doctors and patients to have a deeper understanding of the patient's health status and potential causes, so as to formulate more effective treatment and prevention measures.

[0073] The emergency response guidance module provides patients with timely and accurate disease predictions and warning signals. It consists of two core parts: the disease prediction analysis unit and the warning signal processing unit, which together achieve accurate monitoring and early warning of patients' health status.

[0074] The present invention can monitor the patient's physiological parameters and living environment in real time, find abnormalities in time through data analysis, and send out early warning signals in advance, so that the patient can take measures or seek medical treatment in time, thereby reducing the risk and harm of stroke. When abnormalities are detected, a comprehensive analysis will be conducted based on the patient's physiological parameters, living habits and environmental factors to generate a preliminary etiology report, which is particularly important for stroke patients, because they are prone to expression confusion after the onset of the disease, which affects the subsequent diagnosis and treatment of doctors. The etiology report can provide doctors with preliminary treatment basis, help them understand the patient's condition and cause more quickly, formulate more effective treatment plans, and conduct personalized early warning analysis based on the individual differences and historical data of the patient. By comparing the patient's current physiological parameters with the standard data set, and combining living habits and environmental factors, the system can more accurately judge the patient's health status and reduce false positives and false negatives. When a warning signal is issued, the signal will not only be sent to the patient end, but also to the patient's emergency contact end and medical institution end at the same time. This multi-party linkage method can ensure that patients can receive timely rescue and treatment in an emergency, further protecting the patient's life safety.

[0075] Example 2, refer to Figure 2 , provides an early warning method for stroke based on smart wearable health monitoring, including the following steps: Step S1, collecting the patient's current physiological data set and current step length data set, analyzing the current physiological data set and the step length data set, and outputting the current state analysis result.

[0076] Step S1 collects and analyzes the patient's current physiological data set and stride length data set to accurately reflect the patient's immediate physiological state and walking activity, and outputs the current state analysis result to provide basic data for subsequent steps.

[0077] Step S2, extracting the patient's current living habit data and current environment data set according to the current state analysis result, processing the current living habit data, and outputting it as the current living habit data set.

[0078] Step S2 extracts and processes the patient's current living habit data and environmental data set according to the current state analysis results to form a current living habit data set, providing key information for subsequent cause prediction.

[0079] Step S3, establish a cause prediction model, input the living habit data set and the current environment data set into the cause prediction model, and generate a preliminary cause report.

[0080] Step S3 uses the etiology prediction model, combined with the lifestyle dataset and the environmental dataset, to generate a preliminary etiology report, revealing the patient's possible health risks and providing a basis for the generation of early warning signals.

[0081] Step S4, analyze according to the current status analysis results and generate a preliminary cause report, generate a prediction result, generate an early warning signal according to the prediction result, send the early warning signal to the patient end, and send the early warning signal and the preliminary cause report to the patient's emergency contact end and medical institution end.

[0082] Step S4 comprehensively analyzes the current status analysis results and the preliminary cause report, generates a prediction result, and generates a warning signal of a corresponding level according to the prediction result. The warning signal is sent to the patient, emergency contact and medical institution in a timely manner to ensure that the patient receives timely attention and medical assistance.

[0083] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0084] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. The stroke early warning system based on smart wearable health monitoring is characterized by: It includes parameter monitoring and analysis module, habit environment collection module, cause report generation module and emergency response guidance module; The parameter monitoring and analysis module is used to collect the patient's current physiological data set and current step length data set, analyze the current physiological data set and the step length data set, and output the current state analysis result; The habit environment acquisition module is used to extract the patient's current living habit data and current environment data set according to the current state analysis result, process the current living habit data, and output it as the current living habit data set; The etiology report generation module is used to establish an etiology prediction model, input the lifestyle dataset and the current environment dataset into the etiology prediction model, and generate a preliminary etiology report; The emergency response guidance module is used to analyze according to the current status analysis results and generate a preliminary cause report, generate a prediction result, generate an early warning signal according to the prediction result, send the early warning signal to the patient end, and send the early warning signal and the preliminary cause report to the patient's emergency contact end and medical institution end.

2. The stroke early warning system based on smart wearable health monitoring as claimed in claim 1, characterized in that: The parameter monitoring and analysis module includes a physiological data monitoring unit and a physiological data analysis unit; The physiological data monitoring unit is used to collect the patient's current blood pressure data, current heart rate data, current blood oxygen saturation data, current brain wave data, current body temperature data and step length data within a preset first time period, extract the frequency band of the current brain wave data, the frequency band includes a Delta band with a frequency of 0.5Hz-4Hz and an Alpha band with a frequency of 30Hz-100Hz, extract the number of Delta bands and the number of Alpha bands, and output them as current Delta band number data and current Alpha band number data, merge the current blood pressure data, current heart rate data, current blood oxygen saturation data, current Delta band number data, current Alpha band number data and current body temperature data into a current physiological data set, and output the step length data within the preset time period as the current step length data set.

3. The stroke early warning system based on smart wearable health monitoring as claimed in claim 2, characterized in that: The physiological data analysis unit is used to analyze the current physiological data set and the current step length data set: Comparing the current physiological data set with a preset standard data set, wherein the standard data set includes a standard blood pressure threshold, a standard heart rate threshold, a standard blood oxygen saturation threshold, a standard Delta frequency band number threshold, a standard Alpha frequency band number threshold, a standard body temperature threshold, and a standard step length coefficient of variation threshold; Calculate the coefficient of variation of step length from the step length dataset: Calculate the step size mean, the mathematical expression is: in, is the mean step length, is the index of the step number, with a value of 1- , is the total number of steps, For the The step length of the step; Calculate the step size standard deviation, the mathematical expression is: in, is the step size standard deviation; Calculate the step length variation coefficient, mathematical expression: in, is the coefficient of variation of step length; The output is the current step length coefficient of variation data; If the current physiological data set and the current step length variation coefficient data satisfy: the current blood pressure data is within the standard blood pressure threshold, the current heart rate data is within the standard heart rate threshold, the current blood oxygen saturation data is within the standard blood oxygen saturation threshold, the current Delta frequency band quantity data is within the standard Delta frequency band quantity threshold, the current Alpha frequency band quantity data is within the standard Alpha frequency band quantity threshold, the current body temperature data is within the standard body temperature threshold, and the current step length variation coefficient data is within or less than the standard compensation variation coefficient threshold, it is determined that the disease is not about to occur; If the current physiological data set and the current step length variation coefficient data meet the following conditions: the current blood pressure data is greater than or less than the standard blood pressure threshold, the current heart rate data is greater than or less than the standard heart rate threshold, the current blood oxygen saturation data is greater than or less than the standard blood oxygen saturation threshold, the current Delta frequency band quantity data is greater than the standard Delta frequency band quantity threshold, the current Alpha frequency band quantity data is less than the standard Alpha frequency band quantity threshold, the current body temperature data is greater than or less than the standard body temperature threshold, or the current step length variation coefficient data is greater than the standard compensation variation coefficient threshold, it is determined that the disease is about to occur; Output the current status analysis result, wherein the current status analysis result includes the onset of disease not yet occurred and the onset of disease at the first level being imminent.

4. The stroke early warning system based on smart wearable health monitoring as claimed in claim 3, characterized in that: The habit environment collection module includes a daily data collection unit and a collection data processing unit; The daily data acquisition unit is used to receive the current state analysis result. If the current state analysis result is that the disease is about to occur, the current living habit data and current environmental data within a second time period preset by the patient are extracted from the historical database. The current living habit data include the number of sleep apnea times per hour, the weekly exercise time, the weekly total metabolic amount, the weekly smoking amount and the weekly alcohol intake. The current environmental data set includes the current temperature data, the current PM2.5 concentration value and the current altitude data.

5. The stroke early warning system based on smart wearable health monitoring as claimed in claim 4, characterized in that: The collected data processing unit is used to process the current living habit data: Record the number of sleep apnea times per hour when the number of sleep apnea times per hour is less than or equal to 15 times, and output it as the current qualified apnea number data; Record the number of weekly exercise hours greater than or equal to 150 minutes, and output the current qualified exercise time quantity data; Record the total weekly metabolic amount greater than or equal to 600 MET, and output it as the current qualified metabolic amount data; Record the number of cigarettes smoked per week when the weekly smoking amount is less than or equal to 10 cigarettes, and output it as the current qualified smoking amount data; Record the number of weekly alcohol intakes less than or equal to 14 drinks per week, and output the current qualified alcohol intake data; The current qualified pause number data, the current qualified exercise duration data, the current qualified metabolic amount data, the current qualified smoking amount data and the current qualified alcohol intake amount data are combined and output as the current life habit data set.

6. The stroke early warning system based on smart wearable health monitoring as claimed in claim 5, characterized in that: The etiology report generation module includes a prediction model building unit and an etiology report generation unit; The prediction model building unit is used to build a cause prediction model, and the logic of the cause prediction model is: Weight the qualified pause number data, qualified exercise duration data, qualified metabolic volume data, qualified smoking volume data and qualified alcohol intake volume data: The weight of the number of qualified suspensions is 30%; The weight of the qualified exercise duration data is 25%; The weight of qualified metabolic quantity data is 20%; The weight of the qualified smoking quantity data is 15%; The weight of qualified alcohol intake data is 10%; Calculate the weighted total value of qualified pause number data, qualified exercise duration data, qualified metabolic quantity data, qualified smoking quantity data and qualified alcohol intake quantity data, and output as qualified indicator data; Analysis of qualified indicator data: If the qualified index data is greater than the preset standard qualified index data threshold, it is determined that the living habits are normal; If the qualified index data is less than the preset standard qualified index data threshold, it is judged as abnormal living habits; Analysis of temperature data, PM2.5 concentration values ​​and altitude data: If the temperature data, PM2.5 concentration value and altitude data satisfy that the temperature data is greater than or less than the preset suitable temperature threshold, the PM2.5 concentration value is greater than the preset suitable PM2.5 concentration threshold or the altitude data is higher than the preset suitable altitude threshold, it is determined to be an abnormal environment; If the temperature data, PM2.5 concentration value and altitude data satisfy that the temperature data is within the preset suitable temperature threshold, the PM2.5 concentration value is within or less than the preset suitable PM2.5 concentration threshold and the altitude data is lower than the preset suitable altitude threshold, the environment is determined to be normal; Generate a cause of disease report, which includes qualified pause quantity data, qualified exercise duration data, qualified metabolic quantity data, qualified smoking quantity data and qualified alcohol intake data input under normal living habits, abnormal living habits, normal environment, abnormal environment and abnormal living habits, and temperature data, PM2.5 concentration value and altitude data input under abnormal environment.

7. The stroke early warning system based on smart wearable health monitoring as claimed in claim 6, characterized in that: The etiology report generating unit is used to input the lifestyle data set and the current environment data set into the etiology prediction model to generate a preliminary etiology report, wherein the preliminary etiology report includes the current qualified pause quantity data, the current qualified exercise duration quantity data, the current qualified metabolic quantity data, the current qualified smoking quantity data and the current qualified alcohol intake quantity data input under normal lifestyle habits, abnormal lifestyle habits, normal environment, abnormal environment and abnormal lifestyle habits, and the current temperature data, current PM2.5 concentration value and current altitude data input under abnormal environment conditions.

8. The stroke early warning system based on smart wearable health monitoring as claimed in claim 7, characterized in that: The emergency response guidance module includes an onset prediction and analysis unit and an early warning signal processing unit; The disease prediction analysis unit is used to analyze according to the current state analysis results and generate a preliminary cause report: If the current status analysis result shows that the disease is not about to occur, the body is judged to be in normal condition; If the current status analysis result is an impending onset of illness and the preliminary cause report shows that the lifestyle and environment are normal, it is determined to be a first-level impending onset of illness; If the current status analysis result is that the disease is about to occur and the preliminary cause report is abnormal living habits or abnormal environment, it is judged as the second level of impending disease; If the current status analysis result is that the disease is about to occur and the preliminary cause report is abnormal living habits and abnormal environment, it is judged as the third level of impending disease; The prediction results are output, and the prediction results include normal physical condition, level one impending onset, level two impending onset and level three impending onset.

9. The stroke early warning system based on smart wearable health monitoring as claimed in claim 8, characterized in that: The warning signal processing unit is used to generate a warning signal according to the prediction result: If the predicted result is that the physical condition is normal, no warning signal is generated; If the prediction result is that the first-level disease is about to occur, a first-level warning signal will be issued; If the prediction result is that the second-level disease is about to occur, a second-level warning signal will be issued; If the prediction result is that the disease is about to occur at level 3, a level 3 warning signal will be issued; The first-level warning signal, the second-level warning signal or the third-level warning signal is sent to the patient end, and the first-level warning signal, the second-level warning signal or the third-level warning signal and the preliminary cause of disease report are sent to the patient's emergency contact end, the emergency contact end and the medical institution end.

10. A stroke early warning method based on smart wearable health monitoring, which is applied to a stroke early warning system based on smart wearable health monitoring as claimed in any one of claims 1 to 9, characterized in that: The following steps are involved: Step S1, collecting the patient's current physiological data set and current step length data set, analyzing the current physiological data set and the step length data set, and outputting the current state analysis result; Step S2, extracting the patient's current living habit data and current environment data set according to the current state analysis result, processing the current living habit data, and outputting it as the current living habit data set; Step S3, establishing a cause prediction model, inputting the lifestyle dataset and the current environment dataset into the cause prediction model, and generating a preliminary cause report; Step S4, analyze according to the current status analysis results and generate a preliminary cause report, generate a prediction result, generate an early warning signal according to the prediction result, send the early warning signal to the patient end, and send the early warning signal and the preliminary cause report to the patient's emergency contact end and medical institution end.

Images