Automatic alarm system for cardiovascular medicine department

Abstract

The invention relates to the technical field of cardiovascular medicine, in particular to an automatic alarm system for cardiovascular medicine, which comprises a biomarker analysis module, a physiological parameter analysis module, a cardiovascular risk assessment module, a cardiovascular early warning adjustment module and an alarm trigger notification module. According to the invention, by integrating real-time monitoring of blood biomarkers and cardiovascular physiological parameters, the early recognition capability of cardiovascular disease risks is improved, key biomarkers are dynamically measured and compared with historical marker data, and subtle physiological changes can be captured at the early stage of asymptomatic conditions, so that potential cardiovascular events are warned; through correlation analysis of electrocardiogram, blood pressure and pulse waveforms, the system can accurately draw a comprehensive image of cardiovascular functions, so that more targeted monitoring and intervention are implemented, timeliness and accuracy of medical response are ensured, doctors can formulate targeted monitoring schemes according to real-time data, and the monitoring efficiency is improved. Therefore, deterioration or occurrence of cardiovascular events of patients can be effectively prevented.

Description

Technical Field

[0001] The present invention relates to the technical field of cardiovascular medicine, and in particular to an automatic alarm system for cardiovascular medicine. Background Art

[0002] Cardiovascular medicine focuses on the prevention, diagnosis and treatment of diseases of the heart and vascular system. It uses a variety of medical technologies, including drug therapy, surgical procedures, and various monitoring and diagnostic equipment to manage conditions such as heart disease, hypertension, arrhythmia and arteriosclerosis. With the advancement of technology, cardiovascular medicine continues to introduce advanced equipment and technologies, such as magnetic resonance imaging (MRI), computed tomography (CT) and echocardiography, to improve the accuracy of diagnosis and the effectiveness of treatment.

[0003] Among them, the automatic alarm system for cardiovascular medicine is used to monitor the patient's cardiovascular health status in real time and automatically issue an alarm when an abnormality is detected. Its main purpose is to improve the response speed to cardiovascular emergencies such as myocardial infarction or severe arrhythmia, and reduce the risk of disease deterioration through timely medical intervention. The automatic alarm system can be integrated into the hospital's monitoring equipment and can also be used at home, allowing patients and doctors to understand the cardiovascular health status in real time, thereby achieving early diagnosis and intervention.

[0004] Existing technologies rely on regular medical examinations and static diagnostic equipment, and are insufficient in daily health management and early identification of emergencies. Although traditional technologies such as MRI or CT have advantages in diagnostic accuracy, they are unable to conduct continuous monitoring or provide immediate feedback on the patient's latest health status. This limitation results in medical responses being initiated only when the disease progresses to a later stage, and there is a lack of effective prevention and early intervention measures. For example, for patients with arrhythmia, traditional technologies cannot detect abnormalities immediately in the early stages. By the time obvious symptoms appear, the difficulty and complexity of treatment have increased significantly, which has an adverse impact on both the patient's health and the cost of treatment. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an automatic alarm system for cardiovascular medicine.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: an automatic alarm system for cardiovascular medicine, the system comprising: The biomarker analysis module detects biomarkers associated with cardiovascular disease based on patient blood samples, compares them with historical marker data, determines the degree of change in the current measurement value, and obtains the marker deviation index; The physiological parameter analysis module records the ECG signal, systolic pressure, diastolic pressure and pulse wave waveform according to the marker offset index, and analyzes the relationship between the ECG waveform characteristics, blood pressure fluctuation amplitude and pulse wave rise time to obtain the physiological signal correlation degree; The cardiovascular risk assessment module calls the physiological signal correlation, analyzes the QT interval, ST segment deviation, T wave amplitude and blood pressure fluctuation rate, evaluates the mutual influence between troponin and ST segment deviation, brain natriuretic peptide and blood pressure fluctuation rate, and determines the cardiovascular trend analysis result; The cardiovascular early warning adjustment module analyzes the patient's personal health information based on the cardiovascular trend analysis results, determines a targeted benchmark value matching the patient, adjusts the early warning trigger level, and obtains a targeted early warning adjustment benchmark; The alarm trigger notification module monitors the patient's cardiovascular risk trend based on the targeted warning adjustment benchmark, triggers an alarm when it exceeds the normal range, pushes the patient's status and risk data, and obtains the cardiovascular event alarm status.

[0007] The present invention has improvements in that the marker deviation index includes a deviation value, a trend analysis result, and a historical comparison result; the physiological signal correlation degree specifically includes heart rate synchronization, blood pressure volatility, and pulse waveform consistency; the cardiovascular trend analysis result includes risk level, trend stability, and parameter sensitivity; the targeted early warning adjustment benchmark specifically includes a benchmark setting value and a risk control standard; and the cardiovascular event alarm status includes an alarm status, a risk rating, and a health monitoring result.

[0008] The present invention is improved in that the biomarker analysis module comprises: The marker concentration conversion submodule detects the concentrations of C-reactive protein, troponin, and brain natriuretic peptide in the patient's blood sample, converts the detection signal of the marker through the biosensor, calculates the corresponding numerical output, and adjusts the data format to generate a marker value set; The historical data comparison submodule obtains the C-reactive protein, troponin and brain natriuretic peptide records in the patient's historical data based on the marker value set, calculates the deviation between the current measurement value and the historical data at the same time node, performs normalization processing, and obtains a normalized deviation value; The deviation index calculation submodule calls the normalized deviation value, analyzes the relative change amplitude between the difference markers, and combines the weight influence of the difference markers to adopt the formula: ; Get the marker offset index ,in, Representative The current detection value of biomarkers, Representative The historical mean of biomarkers, Representative The historical standard deviation of each biomarker, Representative The weighting factor of each biomarker, Represents the total number of markers.

[0009] The present invention is improved in that the physiological parameter analysis module comprises: The physiological signal acquisition submodule collects the electrocardiogram signal, systolic pressure, diastolic pressure and pulse waveform according to the marker deviation index, removes abnormal signals through data integrity detection, and obtains cleaned signal data; The signal feature analysis submodule analyzes the ECG waveform features, blood pressure fluctuation amplitude and pulse wave rise time based on the cleaned signal data, extracts key feature points, and uses the formula: ; Get the signal characteristic strength index ,in, Representative The QRS complex wave value of the ECG signal, Representative Systolic blood pressure value, Representative The pulse wave rise time value, , and are the number of samples of QRS complex, blood pressure value and pulse wave rise time respectively; The physiological signal correlation calculation submodule analyzes the cross-correlation of the ECG waveform characteristics, blood pressure fluctuation amplitude and pulse wave rise time according to the signal characteristic strength index, determines the synchronization and interdependence between the difference signals, and obtains the physiological signal correlation degree.

[0010] The present invention is improved in that the cardiovascular risk assessment module comprises: The short-term trend analysis submodule calls the physiological signal correlation, analyzes the QT interval, ST segment deviation, T wave amplitude and blood pressure fluctuation rate, and measures the short-term change trend of each parameter using the formula: ; Determine short-term trend measurements ,in, Representative The signal value at a moment, Represents the signal value at the previous moment, represents the total number of time points measured; The normalization processing submodule evaluates the mutual influence between troponin and ST segment deviation, brain natriuretic peptide and blood pressure fluctuation rate based on the short-term change trend measurement value, normalizes the data, and obtains the cardiovascular trend analysis result.

[0011] The present invention is improved in that the cardiovascular early warning adjustment module comprises: The patient feature matching submodule collects the patient's age, gender, basic blood pressure, basic heart rate and cardiovascular medical history based on the cardiovascular trend analysis results, screens historical patient data with similar features, and calculates the current patient feature matching coefficient based on the distribution of historical patient data; The reference value calculation submodule uses the formula based on the patient characteristic matching coefficient and the blood pressure and heart rate distribution characteristics of the corresponding population in the historical data: ; Calculates current patient-specific baseline values , get the reference value interval, where represents the blood pressure value of the historically matched patient, represents the patient characteristics matching coefficient, Represents the current patient's basal blood pressure value. represents the number of matched historical patients; The warning level adjustment submodule calls the benchmark value interval, compares it with the cardiovascular risk, identifies the degree of deviation from the benchmark value, and defines the warning trigger level according to the degree of deviation to obtain a targeted warning adjustment benchmark.

[0012] The present invention is improved in that the alarm trigger notification module includes: The cardiovascular risk monitoring submodule obtains the patient's current physiological state parameters, including heart rate, blood pressure and blood oxygen saturation, compares them with the targeted early warning adjustment benchmark, calculates the physiological state deviation value, identifies the physiological state change trend, and obtains the physiological state deviation information; The early warning signal determination submodule analyzes the deviation from the normal range based on the physiological state deviation information and adopts the formula according to the risk assessment data: ; Calculation of cardiovascular event risk index , to determine whether it exceeds the normal range. If the warning conditions are met, the warning signal is triggered, where: represents the physiological state deviation coefficient, represents the normal range threshold, represents the time variation factor, represents the risk weight factor, Represents each risk assessment parameter, Represents the number of risk assessment parameters; The early warning information push submodule pushes the patient's current physiological state, abnormal parameter table and risk assessment data to the doctor based on the early warning signal to obtain the cardiovascular event alarm status.

[0013] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by integrating real-time monitoring of blood biomarkers and cardiovascular physiological parameters, the ability to identify cardiovascular disease risks in the early stage is improved. By dynamically measuring key biomarkers and comparing them with historical marker data, subtle physiological changes can be captured in the early asymptomatic stage, thereby warning of potential cardiovascular events. By correlating and analyzing electrocardiograms, blood pressure and pulse waveforms, the system can accurately draw a comprehensive picture of cardiovascular function, thereby implementing more targeted monitoring and intervention, ensuring the timeliness and accuracy of medical responses, and enabling doctors to develop targeted monitoring plans based on real-time data, thereby effectively preventing the deterioration or occurrence of cardiovascular events in patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a system flow chart of the present invention; Figure 2 is a flow chart of the biomarker analysis module of the present invention; Figure 3 is a flow chart of the physiological parameter analysis module in the present invention; Figure 4 A flow chart of the cardiovascular risk assessment module of the present invention; Figure 5 This is a flow chart of the central vascular early warning adjustment module of the present invention; Figure 6 This is a flow chart of the alarm trigger notification module in the present invention. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0016] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0017] Example See also Figure 1 The present invention provides a technical solution: an automatic alarm system for cardiovascular medicine comprises: The biomarker analysis module detects biomarkers associated with cardiovascular disease based on patient blood samples, including C-reactive protein, troponin, and brain natriuretic peptide. The biosensor converts the concentration of the biomarker into a digital signal, and compares and analyzes it with the patient's historical biomarker data to determine the degree of change in the current measurement value and obtain the marker deviation index. The physiological parameter analysis module records the ECG signal, systolic pressure, diastolic pressure and pulse wave waveform through ECG monitoring equipment, non-invasive sphygmomanometer and photoelectric capacitance pulse wave sensor according to the marker offset index, removes abnormal signals, and analyzes the relationship between ECG waveform characteristics, blood pressure fluctuation amplitude and pulse wave rise time to obtain the physiological signal correlation; The cardiovascular risk assessment module uses the physiological signal correlation to analyze the QT interval, ST segment deviation, T wave amplitude and blood pressure fluctuation rate, measures the short-term change trend of each parameter, evaluates the mutual influence between troponin and ST segment deviation, brain natriuretic peptide and blood pressure fluctuation rate, and normalizes the data to determine the results of cardiovascular trend analysis; The cardiovascular early warning adjustment module collects and analyzes the patient's age, gender, basic blood pressure, basic heart rate and cardiovascular medical history based on the results of cardiovascular trend analysis, determines the targeted benchmark value for matching patients, compares it with the cardiovascular risk, adjusts the early warning trigger level, and obtains the targeted early warning adjustment benchmark; The alarm trigger notification module continuously monitors the patient's current cardiovascular risk trend based on the targeted warning adjustment benchmark to determine whether it exceeds the normal range. If the warning conditions are met, the warning signal is triggered and the patient's current physiological state, abnormal parameter table and risk assessment data are pushed to the doctor to obtain the cardiovascular event alarm status.

[0018] Marker deviation indicators include deviation value, trend analysis results, and historical comparison results. The physiological signal correlation is specifically heart rate synchronization, blood pressure volatility, and pulse waveform consistency. The cardiovascular trend analysis results include risk level, trend stability, and parameter sensitivity. The targeted early warning adjustment benchmark is specifically the benchmark setting value and risk control standard. The cardiovascular event alarm status includes alarm status, risk classification, and health monitoring results.

[0019] See also Figure 2 , the biomarker analysis module includes: The marker concentration conversion submodule detects the concentrations of C-reactive protein, troponin, and brain natriuretic peptide in the patient's blood sample, converts the detection signal of the marker through the biosensor, calculates the corresponding numerical output, and adjusts the data format to generate a marker value set; After obtaining the patient's blood sample, centrifugal separation technology is used to separate the plasma and cell components to ensure that the plasma portion is used for the determination of biomarkers. Immunoassay reagents are used to detect C-reactive protein, troponin and brain natriuretic peptide. For example, the enzyme-linked immunosorbent assay (ELISA) method is used to bind the marker to the antibody, and the absorbance is detected and the concentration of the marker is converted through an enzyme-catalyzed color reaction. The obtained absorbance data is converted into a standard concentration value, and the concentration value of each marker is calculated according to the standard curve. The converted concentration value unit is ng / mL or pg / mL, and calibration is required for different patient samples. For example, for C-reactive protein, its detection range is generally 0.1-10mg / L, for troponin, its detection range is generally 0.01-10ng / mL, and for brain natriuretic peptide, the detection range is generally 5-500pg / mL. After obtaining the concentration data of each marker, it is converted into a digital signal for subsequent processing. The converted data is formatted and stored as a structured data set, including patient ID, detection time, marker type and its concentration value, to obtain a marker value set.

[0020] The historical data comparison submodule obtains the C-reactive protein, troponin, and brain natriuretic peptide records in the patient's historical data based on the marker value set, calculates the deviation between the current measurement value and the historical data at the same time node, performs normalization processing, and obtains the normalized deviation value; Obtain the C-reactive protein, troponin, and brain natriuretic peptide records in the patient's historical data, extract the marker concentration data of the same patient at different time points, set the time span, such as the data within the last 1 month, 3 months, 6 months, or 1 year, calculate the deviation between the current measurement value and the historical data at each time point, and use the mean difference calculation method, that is, calculate the difference between the current measurement value and the mean of the data at multiple time points in the past, and calculate the deviation percentage. When normalizing, use the standardized formula: ,in, is the current measured value, is the historical average, is the historical standard deviation, and the deviation value obtained after normalization is used for subsequent analysis.

[0021] The deviation index calculation submodule calls the normalized deviation value, analyzes the relative change amplitude between the difference markers, and combines the weight influence of the difference markers, using the formula: ; Get the marker offset index ,in, Representative The current detection value of biomarkers, Representative The historical mean of biomarkers, Representative The historical standard deviation of each biomarker, Representative The weighting factor of each biomarker, represents the total number of markers; If the current measured value of C-reactive protein is 2.3 mg / L, the historical mean is 1.8 mg / L, and the standard deviation is 0.5 mg / L, the current measured value of troponin is 0.08 ng / mL, the historical mean is 0.05 ng / mL, and the standard deviation is 0.02 ng / mL, and the current measured value of brain natriuretic peptide is 120 pg / mL, the historical mean is 100 pg / mL, and the standard deviation is 15 pg / mL, and the weights are set to 0.4, 0.3, and 0.3 respectively, then substitute them into the formula for calculation: ; ; ; The calculated marker shift index SR=1.25 indicates that the marker change degree of the current patient has a certain degree of deviation compared with the historical data, which can be used for subsequent analysis.

[0022] See also Figure 3 , the physiological parameter analysis module includes: The physiological signal acquisition submodule collects ECG signals, systolic pressure, diastolic pressure and pulse waveform according to the marker deviation index, removes abnormal signals through data integrity detection, and obtains cleaned signal data; During the acquisition process, each physiological signal is acquired in a different way. The ECG signal records the electrical activity of the heart through electrode patches, the systolic and diastolic pressures measure the arterial blood flow pressure through an inflatable cuff, and the pulse wave waveform is recorded by a photoelectric sensor to record the blood flow pulsation of the finger or earlobe. After all signals are acquired, data integrity detection is required. The detection methods include signal amplitude abnormal value removal, instantaneous peak filtering and signal continuity check. For example, in ECG signal processing, if the RR interval fluctuation in a certain measurement cycle exceeds 20% of the mean, it is determined to be an abnormal signal and removed. In blood pressure data processing, if the deviation of systolic or diastolic pressure measured three times in a row exceeds 10mmHg, it is determined that the measurement error is too large and the abnormal value is removed. The pulse wave waveform detection adopts the coefficient of variation analysis method. If the peak amplitude of the pulse waveform fluctuates by more than 30% in three consecutive acquisitions, the cycle signal is removed. After the abnormal signal is removed, smoothing is performed to reduce the impact of short-term signal fluctuations on subsequent analysis to obtain cleaned signal data.

[0023] The signal feature analysis submodule analyzes the ECG waveform characteristics, blood pressure fluctuation amplitude and pulse wave rise time based on the cleaned signal data, extracts key feature points, and uses the formula: ; Get the signal characteristic strength index ,in, Representative The QRS complex wave value of the ECG signal, Representative Systolic blood pressure value, Representative The pulse wave rise time value, , and are the number of samples of QRS complex, blood pressure value and pulse wave rise time respectively; Analyze the ECG waveform characteristics, blood pressure fluctuation amplitude and pulse wave rise time, and extract key feature points. The ECG waveform characteristics mainly focus on the amplitude and duration of the QRS complex wave. The corresponding characteristics are obtained by calculating the R wave peak and QRS interval time. The blood pressure fluctuation amplitude is obtained by calculating the continuous systolic and diastolic pressure change trends. The pulse wave rise time is calculated based on the time difference from the starting point to the peak of the pulse waveform. Calculate the signal feature strength index. If the data is as follows: QRS complex amplitude data: mV, mV, mV; Systolic blood pressure data: mmHg, mmHg, mmHg; Pulse wave rise time: ms, ms, ms; Substitute into the formula to calculate: ; ; ; ; Calculate the signal characteristic strength index The result shows that the signal characteristic strength index of the individual is within the standard range. If the normal signal characteristic strength index interval of a healthy individual is , then the currently calculated If the blood pressure falls into this range, it indicates that the individual's ECG waveform characteristics, blood pressure fluctuation amplitude and pulse wave rise time are all within the normal physiological range, with no obvious abnormalities. If the value is lower than 95, it indicates that the fluctuation of physiological signals is weakened, such as low heart rate or reduced blood pressure stability. If the value is higher than 110, it indicates that the physiological signal fluctuates violently, such as arrhythmia or high blood pressure. The signal characteristic intensity index can be further used for physiological signal correlation calculation, analyzing the synchronization and correlation between ECG characteristics, blood pressure and pulse waves, so as to evaluate the overall consistency of physiological signals and health status.

[0024] The physiological signal correlation calculation submodule analyzes the cross-correlation of ECG waveform characteristics, blood pressure fluctuation amplitude and pulse wave rise time according to the signal characteristic strength index, determines the synchronization and interdependence between the difference signals, and obtains the physiological signal correlation degree; There is often a certain time correlation between changes in ECG signals and blood pressure and pulse waves. The degree of linear correlation is measured by calculating the correlation coefficients between different physiological signals using the formula: ,in, is the physiological signal correlation, which is used to indicate the correlation between different signals. Represents two different physiological signals. data points, They are The mean of is the total number of data samples. For example, if the correlation between ECG signal and blood pressure signal is calculated for 100 sets of data, we get , indicating that there is a strong positive correlation between the two. Further analysis of the pulse wave data is performed to calculate the correlation between blood pressure and pulse wave. If , it means that blood pressure and pulse wave have a certain correlation, but it is weak. All signal comparison results are calculated comprehensively to obtain the correlation degree of physiological signals.

[0025] See also Figure 4 , the cardiovascular risk assessment module includes: The short-term trend analysis submodule calls the physiological signal correlation, analyzes the QT interval, ST segment deviation, T wave amplitude and blood pressure fluctuation rate, and measures the short-term change trend of each parameter using the formula: ; Determine short-term trend measurements ,in, Representative The signal value at a moment, Represents the signal value at the previous moment, represents the total number of time points measured; Call the ECG signal and blood pressure signal data, collect data on the QT interval, ST segment deviation, T wave amplitude and blood pressure fluctuation rate, and measure the short-term change trend of each parameter, obtain the signal value corresponding to each time point, organize the time series data, calculate the signal difference between adjacent time points, extract the time interval between the Q wave and the T wave in each heartbeat cycle, and store the sequence of the value changing with time. The ST segment deviation is determined by measuring the ST segment height change in the ECG signal. The potential value of the ST segment at 0.08s after the J point is calculated for each heartbeat cycle, and the difference is calculated with the baseline potential. The T wave amplitude is determined by the amplitude of the T wave peak in the ECG signal. The blood pressure fluctuation rate is calculated by analyzing the arterial blood pressure signal, and the systolic and diastolic pressure change rates in each heartbeat cycle are calculated. The change amount of the above parameters at adjacent time points is calculated and the absolute value is taken. All the changes are summed and divided by the total number of measurement time points, and the short-term change trend of the QT interval, ST segment deviation, T wave amplitude and blood pressure fluctuation rate is calculated to obtain the short-term change trend measurement value; If the QT interval measurement data is: , then substitute into the calculation: ; ; The results show that the short-term change trend measurement value of the QT interval is 10.4ms. According to the conventional standards for cardiovascular health assessment, the short-term fluctuation range of the QT interval should usually be between 5ms-15ms. If the change trend value exceeds this range, it indicates abnormal heart rhythm fluctuations or cardiac electrophysiological instability. The current calculated value of 10.4ms is within the normal fluctuation range, indicating that the QT interval has a moderate fluctuation amplitude in the short term and there is no excessive instability or abnormal changes.

[0026] The normalization processing submodule evaluates the interaction between troponin and ST segment deviation, brain natriuretic peptide and blood pressure fluctuation rate based on the short-term change trend measurement value, normalizes the data, and obtains the cardiovascular trend analysis results; Based on the short-term trend measurement values, the mutual influence between troponin and ST segment deviation, brain natriuretic peptide and blood pressure fluctuation rate was evaluated, and the short-term trend measurement values ​​were called for normalization calculation. The normalization adopted the minimum-maximum normalization method, that is, by linearly transforming the data, it was adjusted to the interval , calculated as: ,in, Represents the short-term trend measurement value, represents the minimum value in the data sample, It represents the maximum value in the data sample. Through this transformation, the data of QT interval, ST segment deviation, T wave amplitude and blood pressure fluctuation rate are comparable. At the same time, the data of troponin and brain natriuretic peptide levels are introduced, and their normalized values ​​are calculated. Finally, the normalized data are combined to obtain the results of cardiovascular trend analysis.

[0027] See also Figure 5 , the cardiovascular early warning adjustment module includes: The patient feature matching submodule collects the patient's age, gender, basic blood pressure, basic heart rate and cardiovascular medical history based on the results of cardiovascular trend analysis, screens historical patient data with similar characteristics, and calculates the current patient feature matching coefficient based on the distribution of historical patient data; It is necessary to establish a patient basic information data table to classify different types of patient data. For example, patients can be grouped by age group (20-30 years old, 31-40 years old, 41-50 years old, etc.), and gender information can be recorded to form a preliminary classification. The basic blood pressure and basic heart rate are calculated based on the average of the measured data in multiple time periods. The calculation method can be: basic blood pressure value ,in, is the calculated basal blood pressure, is the blood pressure value at a certain measurement moment, is the number of measurements. For example, a patient measures blood pressure 5 times in one day, which are 120, 122, 118, 121 and 119 respectively. Then the basal blood pressure is calculated as , the basal heart rate is obtained by the same calculation method. In addition, the cardiovascular medical history needs to be queried through the patient's electronic medical record or health record system to confirm whether the patient has records of diseases such as hypertension, coronary heart disease, and arrhythmia. After the data is obtained, by screening historical patient data, patients with similar age, gender, blood pressure and heart rate characteristics are included in the matching set. For example, the current patient is a 45-year-old male with a basal blood pressure of 120 mmHg and a basal heart rate of 70 beats / min. All historical patients aged 40-50 years, male, with a blood pressure of 110-130 mmHg and a heart rate of 60-80 beats / min should be selected in the matching set, and the patient feature matching coefficient is calculated according to the matching rules. The coefficient can be calculated by the deviation of each feature from the historical data, such as: ,in, is the mean blood pressure of historical patients. This calculation process ensures that the matching degree between the current patient characteristics and historical patients can be quantified, and the patient characteristic matching coefficient is obtained.

[0028] The baseline value calculation submodule is based on the patient characteristic matching coefficient and the blood pressure and heart rate distribution characteristics of the corresponding population in the historical data, using the formula: ; Calculates current patient-specific baseline values , get the reference value interval, where represents the blood pressure value of the historically matched patient, represents the patient characteristics matching coefficient, Represents the current patient's basal blood pressure value. represents the number of matched historical patients; If the current patient matches 5 historical patients, the matching coefficients are 0.9, 0.85, 0.88, 0.92 and 0.87, and the blood pressure values ​​are 118, 122, 120, 124 and 119 mmHg, respectively. The current patient's basal blood pressure is 121 mmHg, then: ; ; ; This value is further used to set the baseline value range. For example, if the upper and lower floating range is set to ±5 mmHg, the baseline value range is 102.254 mmHg-112.254 mmHg. If the patient's measured blood pressure falls within this range, the blood pressure is considered to be stable. If it exceeds this range, deviation analysis is required to determine the risk level.

[0029] The warning level adjustment submodule calls the baseline value interval, compares it with the cardiovascular risk, identifies the degree of deviation from the baseline value, and defines the warning trigger level based on the degree of deviation to obtain a targeted warning adjustment benchmark; Calling the baseline value interval, comparing it with the cardiovascular risk, and identifying the degree of deviation beyond the baseline value, it is necessary to determine the risk assessment index, set a safety range centered on the baseline value interval, for example, the baseline value interval is mmHg, the safety range is 102.254mmHg-112.254mmHg. If the current patient's blood pressure falls within this range, it is normal. If it exceeds this range, calculate the degree of deviation. Assuming that the current patient's blood pressure is 115mmHg, it exceeds the upper limit of the baseline value. mmHg, the risk level can be defined: if the deviation is less than 3mmHg, it is set to low risk (slight deviation); if the deviation is between 3-6mmHg, it is set to medium risk (significant deviation); if the deviation is greater than 6mmHg, it is set to high risk (serious deviation). In this example, the deviation is 2.746mmHg, which belongs to the low risk range. If the blood pressure reaches 118mmHg, it exceeds the upper limit of 5.746mmHg and enters the medium risk interval, and a targeted early warning adjustment benchmark is obtained.

[0030] See also Figure 6 , the alarm trigger notification module includes: The cardiovascular risk monitoring submodule obtains the patient's current physiological state parameters, including heart rate, blood pressure and blood oxygen saturation, compares them with the targeted early warning adjustment benchmark, calculates the physiological state deviation value, identifies the physiological state change trend, and obtains the physiological state deviation information; Obtaining the patient's current physiological state parameters involves monitoring heart rate, blood pressure and blood oxygen saturation. Each parameter is collected in real time by medical equipment or wearable devices. For example, heart rate can be measured by photoplethysmography (PPG) or electrocardiogram (ECG), blood pressure can be obtained by electronic sphygmomanometer or cuffless blood pressure monitoring equipment, and blood oxygen saturation is usually detected by pulse oximeter. After obtaining the measured value of each parameter, noise filtering and outlier removal are required to ensure data quality. Subsequently, the targeted early warning adjustment benchmark is called to compare the currently measured data. For example, if a patient If the patient's heart rate is measured to be 87bpm, blood pressure is 135 / 85mmHg, and blood oxygen saturation is 96%, then the data needs to be compared with the warning adjustment benchmark, which is set according to the patient's age, gender, underlying diseases and other factors. Assuming the benchmark value is 60-100bpm for heart rate, 120 / 80mmHg for blood pressure, and 95%-100% for blood oxygen saturation, after comparison, it is found that the blood pressure is high and the blood oxygen saturation is normal. The physiological state deviation value is further calculated. This value is obtained by calculating the degree to which each parameter deviates from the baseline value. For example, the systolic blood pressure deviation value of blood pressure is calculated as follows: ,in, is the current systolic blood pressure, is the baseline systolic blood pressure value. If the baseline systolic blood pressure is 120 mmHg and the current measured systolic blood pressure is 135 mmHg, then mmHg, similarly calculate the deviation values ​​of diastolic blood pressure and other parameters, and obtain the physiological state deviation vector after normalization. Then, calculate the change trend based on the physiological state parameters at multiple moments, and use regression analysis or time series method to calculate the change rate of each parameter to identify the change trend of the physiological state. For example, if the systolic blood pressure rises from 130 mmHg to 140 mmHg in the past 10 minutes, its change rate can be calculated as mmHg / min, combined with the changes in multiple parameters, the physiological state deviation information is calculated, which includes the current measured parameters, deviation values ​​and change trends, and finally the physiological state deviation information is obtained.

[0031] The early warning signal determination submodule analyzes the deviation from the normal range based on the physiological state deviation information and adopts the formula according to the risk assessment data: ; Calculation of cardiovascular event risk index , to determine whether it exceeds the normal range. If the warning conditions are met, the warning signal is triggered, where: represents the physiological state deviation coefficient, represents the normal range threshold, represents the time variation factor, represents the risk weight factor, Represents each risk assessment parameter, Represents the number of risk assessment parameters; Analyze the deviation from the normal range. First, calculate the offset, that is, the absolute difference between the physiological state offset information and the normal range threshold. For example, if the currently calculated physiological state offset information is mmHg, and the preset normal range threshold is 10mmHg, then the deviation is mmHg, and then, combined with the risk assessment data, the cardiovascular event risk index was calculated. This index combines the deviation degree of multiple physiological parameters. , , , , , , , then substitute into the formula to calculate: ; ; ; Calculated risk index Compared with the set warning threshold, if the normal threshold is 10, then The threshold is not exceeded, the warning conditions are not met, and there is no need to trigger a warning signal.

[0032] The early warning information push submodule pushes the patient's current physiological status, abnormal parameter table and risk assessment data to the doctor based on the early warning signal to obtain the cardiovascular event alarm status; Based on the warning signal, it is necessary to organize the patient's current physiological status parameters, abnormal parameter table and risk assessment data. First, extract the currently measured physiological parameters, including heart rate, blood pressure, blood oxygen saturation, etc., and screen out abnormal parameters. For example, if a patient's current measured blood pressure is 145 / 90mmHg, and the normal baseline value is 120 / 80mmHg, the blood pressure parameter is marked as abnormal. Then, integrate the risk assessment data, which contains information such as the patient's age, medical history, and medication status. Package all data into a standardized data package and push it to the doctor through the network or other communication methods. For example, the data contains the fields: "Heart rate: 87bpm, blood pressure: 145 / 90mmHg (abnormal), blood oxygen saturation: 96% (normal), cardiovascular event risk index: 8.47 (not exceeding the threshold), no warning is triggered", and the cardiovascular event alarm status is obtained.

[0033] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An automatic alarm system for cardiovascular medicine, characterized in that: The system comprises: The biomarker analysis module detects biomarkers associated with cardiovascular disease based on patient blood samples, compares them with historical marker data, determines the degree of change in the current measurement value, and obtains the marker deviation index; The physiological parameter analysis module records the ECG signal, systolic pressure, diastolic pressure and pulse wave waveform according to the marker offset index, and analyzes the relationship between the ECG waveform characteristics, blood pressure fluctuation amplitude and pulse wave rise time to obtain the physiological signal correlation degree; The cardiovascular risk assessment module calls the physiological signal correlation, analyzes the QT interval, ST segment deviation, T wave amplitude and blood pressure fluctuation rate, evaluates the mutual influence between troponin and ST segment deviation, brain natriuretic peptide and blood pressure fluctuation rate, and determines the cardiovascular trend analysis result; The cardiovascular early warning adjustment module analyzes the patient's personal health information based on the cardiovascular trend analysis results, determines a targeted benchmark value matching the patient, adjusts the early warning trigger level, and obtains a targeted early warning adjustment benchmark; The alarm trigger notification module monitors the patient's cardiovascular risk trend based on the targeted warning adjustment benchmark, triggers an alarm when it exceeds the normal range, pushes the patient's status and risk data, and obtains the cardiovascular event alarm status.

2. The automatic alarm system for cardiovascular medicine according to claim 1, characterized in that: The marker deviation index includes deviation value, trend analysis result, and historical comparison result. The physiological signal correlation degree specifically includes heart rate synchronization, blood pressure volatility, and pulse waveform consistency. The cardiovascular trend analysis result includes risk level, trend stability, and parameter sensitivity. The targeted early warning adjustment benchmark specifically includes benchmark setting value and risk control standard. The cardiovascular event alarm status includes alarm status, risk classification, and health monitoring results.

3. The automatic alarm system for cardiovascular medicine according to claim 1, characterized in that: The biomarker analysis module comprises: The marker concentration conversion submodule detects the concentrations of C-reactive protein, troponin, and brain natriuretic peptide in the patient's blood sample, converts the detection signal of the marker through the biosensor, calculates the corresponding numerical output, and adjusts the data format to generate a marker value set; The historical data comparison submodule obtains the C-reactive protein, troponin and brain natriuretic peptide records in the patient's historical data based on the marker value set, calculates the deviation between the current measurement value and the historical data at the same time node, performs normalization processing, and obtains a normalized deviation value; The deviation index calculation submodule calls the normalized deviation value, analyzes the relative change amplitude between the difference markers, and combines the weight influence of the difference markers to adopt the formula: ； Get the marker offset index ,in, Representative The current test value of the biomarker, Representative The historical mean of biomarkers, Representative The historical standard deviation of each biomarker, Representative The weighting factor of each biomarker, Represents the total number of markers.

4. The automatic alarm system for cardiovascular medicine according to claim 1, characterized in that: The physiological parameter analysis module comprises: The physiological signal acquisition submodule collects the electrocardiogram signal, systolic pressure, diastolic pressure and pulse waveform according to the marker deviation index, removes abnormal signals through data integrity detection, and obtains cleaned signal data; The signal feature analysis submodule analyzes the ECG waveform features, blood pressure fluctuation amplitude and pulse wave rise time based on the cleaned signal data, extracts key feature points, and uses the formula: ； Get the signal characteristic strength index ,in, Representative The QRS complex wave value of the ECG signal, Representative Systolic blood pressure value, Representative The pulse wave rise time value, , and are the number of samples of QRS complex, blood pressure value and pulse wave rise time respectively; The physiological signal correlation calculation submodule analyzes the cross-correlation of the ECG waveform characteristics, blood pressure fluctuation amplitude and pulse wave rise time according to the signal characteristic strength index, determines the synchronization and interdependence between the difference signals, and obtains the physiological signal correlation degree.

5. The automatic alarm system for cardiovascular medicine according to claim 1, characterized in that: The cardiovascular risk assessment module includes: The short-term trend analysis submodule calls the physiological signal correlation, analyzes the QT interval, ST segment deviation, T wave amplitude and blood pressure fluctuation rate, and measures the short-term change trend of each parameter using the formula: ； Determine short-term trend measurements ,in, Representative The signal value at a moment, Represents the signal value at the previous moment, represents the total number of time points measured; The normalization processing submodule evaluates the mutual influence between troponin and ST segment deviation, brain natriuretic peptide and blood pressure fluctuation rate based on the short-term change trend measurement value, normalizes the data, and obtains the cardiovascular trend analysis result.

6. The automatic alarm system for cardiovascular medicine according to claim 1, characterized in that: The cardiovascular early warning adjustment module includes: The patient feature matching submodule collects the patient's age, gender, basic blood pressure, basic heart rate and cardiovascular medical history based on the cardiovascular trend analysis results, screens historical patient data with similar features, and calculates the current patient feature matching coefficient based on the distribution of historical patient data; The reference value calculation submodule uses the formula based on the patient characteristic matching coefficient and the blood pressure and heart rate distribution characteristics of the corresponding population in the historical data: ； Calculates patient-specific baseline values , get the reference value interval, where represents the blood pressure value of the historically matched patient, represents the patient characteristics matching coefficient, Represents the current patient's basal blood pressure value. represents the number of matched historical patients; The warning level adjustment submodule calls the benchmark value interval, compares it with the cardiovascular risk, identifies the degree of deviation from the benchmark value, and defines the warning trigger level according to the degree of deviation to obtain a targeted warning adjustment benchmark.

7. The automatic alarm system for cardiovascular medicine according to claim 1, characterized in that: The alarm trigger notification module includes: The cardiovascular risk monitoring submodule obtains the patient's current physiological state parameters, including heart rate, blood pressure and blood oxygen saturation, compares them with the targeted early warning adjustment benchmark, calculates the physiological state deviation value, identifies the physiological state change trend, and obtains the physiological state deviation information; The early warning signal determination submodule analyzes the deviation from the normal range based on the physiological state deviation information and adopts the formula according to the risk assessment data: ； Calculation of cardiovascular event risk index , to determine whether it exceeds the normal range. If the warning conditions are met, the warning signal is triggered, where: represents the physiological state deviation coefficient, represents the normal range threshold, represents the time variation factor, represents the risk weight factor, Represents each risk assessment parameter, Represents the number of risk assessment parameters; The early warning information push submodule pushes the patient's current physiological state, abnormal parameter table and risk assessment data to the doctor based on the early warning signal to obtain the cardiovascular event alarm status.

Images