An intelligent monitoring and early warning system for anesthesia equipment
By adopting trend analysis and dynamic adjustment of autoregressive moving average model in the intelligent monitoring and early warning system of anesthesia equipment, combined with the probability evaluation of Bayesian network, the problem of insufficient prediction in the existing technology is solved, and the fluctuations of heart rate and blood pressure are achieved. Accurate identification and risk assessment ensure the safety of patients.
Patent Information
- Application Number
- CN202411322672.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-23
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-09-23
AI Technical Summary
The existing intelligent monitoring and early warning system for anesthesia equipment is insufficient in long-term data analysis and future risk prediction, making it difficult to identify and predict sudden fluctuations, and the prediction sensitivity and accuracy are insufficient in dynamic environments, resulting in the medical team relying on qualitative risk warnings, affecting the impact of Patient safety.
The trend analysis module is used to identify the heart rate and blood pressure fluctuations trends, build an autoregressive moving average model for dynamic adjustment, combine it with Bayesian network for probability risk assessment, and automatically determine whether to issue early warning signals based on preset safety thresholds.
Through time series analysis of heart rate and blood pressure data and dynamic model adjustment, the accuracy and sensitivity of prediction are improved, quantitative risk information is provided, and early warning response is issued in a timely manner, which enhances patient safety guarantees.
Smart Images

Figure CN118830819B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of anesthesia monitoring, and in particular to an intelligent monitoring and early warning system for anesthesia equipment. Background Art
[0002] The field of anesthesia monitoring technology focuses on tracking and analyzing the physiological status of patients during surgery through technical means. The field uses a variety of medical equipment, such as electrocardiograms, sphygmomanometers, pulse oximeters, and respiratory monitors, to continuously monitor the patient's heart activity, blood pressure, blood oxygen level, and breathing. In addition, the system can also monitor brain waves, body temperature, and muscle activity to fully evaluate the patient's state during anesthesia, allowing doctors to obtain instant feedback on the patient's health status and optimize anesthesia management.
[0003] Among them, the intelligent monitoring and early warning system of anesthesia equipment collects patients' physiological data in real time through sensors and uses data analysis technology to analyze this information. The system can automatically identify potential risks and abnormalities and send early warning signals to the medical team in a timely manner. Its main purpose is to provide doctors with accurate decision-making support through real-time data monitoring and intelligent analysis to respond to possible emergencies and ensure patient safety.
[0004] Existing technologies are inadequate in long-term data analysis and future risk prediction. For example, when dealing with complex physiological data, it is difficult to fully identify and predict sudden fluctuations, reducing the possibility of forward-looking decision-making. In addition, the system has difficulty in dynamically adjusting and optimizing the prediction model when encountering a changing clinical environment. At the same time, the system's lack of probabilistic risk assessment has caused the medical team to rely mostly on qualitative risk warnings in emergency situations, resulting in insufficient decision-making, which in turn affects patient safety. Summary of the invention
[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose an intelligent monitoring and early warning system for anesthesia equipment.
[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: an intelligent monitoring and early warning system for anesthesia equipment comprises:
[0007] The trend analysis module collects multiple physiological parameter data of heart rate and blood pressure from monitoring equipment, combines historical monitoring data to perform time series analysis, analyzes the fluctuation trend of current heart rate and blood pressure physiological parameters, identifies sudden fluctuations, and obtains trend prediction values of heart rate and blood pressure;
[0008] The dynamic model establishment and adjustment module constructs an autoregressive moving average model, initializes model parameters according to the trend prediction values of the heart rate and blood pressure, calculates the future trend according to the currently obtained physiological parameters, and generates an adjusted prediction model;
[0009] The probabilistic risk assessment module uses the adjusted prediction model to perform probability calculations on the current and predicted anesthesia risks in the collected physiological parameters through a Bayesian network, analyzes the possibility of potential risks, and divides each risk level into categories to generate probabilistic risk information;
[0010] The early warning response output module evaluates the various risk levels in the probabilistic risk information, determines whether the risk level exceeds a preset safety threshold, and generates an early warning response signal if it is detected that the risk level is exceeded.
[0011] As a further solution of the present invention, the step of analyzing the fluctuation trend of the current heart rate and blood pressure physiological parameters is specifically as follows:
[0012] Real-time heart rate collected from monitoring devices and blood pressure Data, combined with historical heart rate and historical blood pressure , forming a time series array: and , using the formula:
[0013] ,
[0014] and,
[0015] ,
[0016] Calculate the mean of the heart rate and blood pressure time series and ;
[0017] in, and From the array and The value taken from It's at the time Heart rate data, It's at the time Blood pressure data, is the total number of data points, Indicates the location of the data point;
[0018] According to the mean of the heart rate and blood pressure time series and , using the formula:
[0019] ,
[0020] and,
[0021] ,
[0022] Calculate the standard deviation of the current heart rate and blood pressure fluctuation trend and .
[0023] As a further solution of the present invention, the steps for obtaining the trend prediction values of the heart rate and blood pressure are specifically as follows:
[0024] According to the standard deviation of the current heart rate and blood pressure fluctuation trend and , using the formula:
[0025] ,
[0026] and,
[0027] ,
[0028] Calculate sudden heart rate fluctuations and sudden blood pressure fluctuations ;
[0029] in, is the maximum value function;
[0030] According to the sudden heart rate fluctuation and sudden blood pressure fluctuations , using the formula:
[0031] ,
[0032] and,
[0033] ,
[0034] Calculate the trend forecast of heart rate and blood pressure trend prediction values , integrate to obtain the trend prediction values of heart rate and blood pressure;
[0035] in, It is the adjustment coefficient, which is used to adjust the impact of sudden fluctuations on trend forecast.
[0036] As a further solution of the present invention, the step of obtaining the initialization model parameters is specifically as follows:
[0037] According to the trend prediction value of the heart rate and blood pressure trend prediction values , using the formula:
[0038] ,
[0039] and,
[0040] ,
[0041] Initialize the model parameters of heart rate and the model parameters of blood pressure ;
[0042] in, They are the weight coefficients that adjust the impact of the predicted value on parameter initialization;
[0043] According to the model parameters of the heart rate and the model parameters of blood pressure , using the formula:
[0044] ,
[0045] and,
[0046] ,
[0047] Calculate heart rate prediction and blood pressure prediction ;
[0048] in, Indicates at a point in time Historical heart rate data, Indicates at a point in time Historical blood pressure data, is the total number of historical data points, is the heart rate adjustment factor, is the adjustment factor for blood pressure.
[0049] As a further solution of the present invention, the step of obtaining the adjusted prediction model is specifically:
[0050] Collect newly measured heart rate and blood pressure , according to the heart rate prediction value and blood pressure prediction , using the formula:
[0051] ,
[0052] and,
[0053] ,
[0054] Calculate the rate of change of heart rate relative to the predicted model and the rate of change of blood pressure relative to the prediction model ;
[0055] in, is the time interval, is the standardized coefficient, is the smoothing constant;
[0056] According to the rate of change of the heart rate relative to the prediction model and the rate of change of blood pressure relative to the prediction model , using the formula:
[0057] ,
[0058] and,
[0059] ,
[0060] The future of heart rate calculation and the future of blood pressure , and obtain the adjusted prediction model;
[0061] in, The time length is set according to the predicted length of the patient's treatment cycle. To adjust the parameters.
[0062] As a further solution of the present invention, the step of obtaining the possibility of analyzing potential risks is specifically:
[0063] According to the future trend of the heart rate and the future of blood pressure , combined with the newly measured heart rate and blood pressure , using the formula:
[0064] ,
[0065] Compare the current measured value with the model predicted value and calculate the risk probability of the current state ;
[0066] in, is the smoothing parameter;
[0067] The risk probability according to the current state , using the formula:
[0068] ,
[0069] Calculating the probability of anesthesia risk .
[0070] As a further solution of the present invention, the step of obtaining the probabilistic risk information is specifically as follows:
[0071] According to the anesthesia risk probability , using the formula:
[0072] ,
[0073] Calculate risk index ;
[0074] in, is the preset threshold ratio;
[0075] According to the risk index , using the formula:
[0076] ,
[0077] Calculate the risk level value , and obtain probabilistic risk information.
[0078] As a further solution of the present invention, the step of obtaining the early warning response signal is specifically as follows:
[0079] According to the risk level value , using the formula:
[0080] ,
[0081] Calculate the difference between the risk level value and the safety threshold to obtain the risk excess index ;
[0082] in, is the preset safety threshold;
[0083] According to the risk excess index , using the formula:
[0084] ,
[0085] Calculate warning value ,if If it is greater than 0, it is an early warning response signal.
[0086] Compared with the prior art, the advantages and positive effects of the present invention are:
[0087] In the present invention, by performing time series analysis on heart rate and blood pressure data and combining it with historical monitoring data, it is possible to identify sudden fluctuations and predict future trends, thereby providing data support for immediate and accurate medical intervention. In addition, the autoregressive moving average model is used to dynamically adjust and optimize model parameters, and anesthesia risks are evaluated based on current and predicted data, thereby improving the accuracy of predictions. Using Bayesian networks for probability calculations, potential risk levels can be more accurately evaluated and classified, providing the medical team with quantitative risk information. Finally, the results of the risk assessment can automatically determine whether the safety threshold is exceeded, and issue a warning response signal in a timely manner, thereby strengthening the protection of patient safety. BRIEF DESCRIPTION OF THE DRAWINGS
[0088] Figure 1 is a system flow chart of the present invention;
[0089] Figure 2 A flow chart of the steps for obtaining the fluctuation trend of the current heart rate and blood pressure physiological parameters analyzed by the present invention;
[0090] Figure 3 A flow chart of steps for obtaining trend prediction values of heart rate and blood pressure according to the present invention;
[0091] Figure 4 A flowchart of the steps for obtaining the initialization model parameters of the present invention;
[0092] Figure 5 A flowchart of the steps for obtaining the adjusted prediction model of the present invention;
[0093] Figure 6 A flow chart of the steps for obtaining the possibility of analyzing potential risks for the present invention;
[0094] Figure 7 A flowchart of the steps for obtaining probabilistic risk information of the present invention;
[0095] Figure 8 This is a flow chart of the steps for obtaining the early warning response signal of the present invention. DETAILED DESCRIPTION
[0096] 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.
[0097] 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" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the 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, "multiple" means two or more, unless otherwise clearly and specifically defined.
[0098] See also Figure 1 , an intelligent monitoring and early warning system for anesthesia equipment includes:
[0099] The trend analysis module collects multiple physiological parameter data of heart rate and blood pressure from monitoring equipment, combines historical monitoring data to perform time series analysis, analyzes the fluctuation trend of current heart rate and blood pressure physiological parameters, identifies sudden fluctuations, and obtains trend prediction values of heart rate and blood pressure;
[0100] The dynamic model building and adjustment module constructs an autoregressive moving average model, initializes the model parameters according to the trend prediction values of heart rate and blood pressure, calculates the future trend according to the currently obtained physiological parameters, and generates an adjusted prediction model;
[0101] The probabilistic risk assessment module uses the adjusted prediction model to perform probability calculations on the current and predicted anesthesia risks in the collected physiological parameters through a Bayesian network, analyzes the likelihood of potential risks, and divides each risk level into categories to generate probabilistic risk information;
[0102] The early warning response output module evaluates the various risk levels in the probabilistic risk information and determines whether the risk level exceeds the preset safety threshold. If it is detected that the risk level exceeds the threshold, an early warning response signal is generated;
[0103] The trend prediction values of heart rate and blood pressure include the future minimum, maximum and average heart rate, and the corresponding minimum, maximum and average blood pressure. The adjusted prediction model includes new model coefficients, predicted error range and prediction update frequency. The probabilistic risk information includes the probability of occurrence of each anesthesia risk, risk level and risk factor of the risk level. The early warning response signal is specifically a warning light of multiple levels.
[0104] See also Figure 2 ,The specific steps for obtaining the fluctuation trend of the current heart rate and blood pressure physiological parameters are as follows:
[0105] Real-time heart rate collected from monitoring devices and blood pressure Data, combined with historical heart rate and historical blood pressure , forming a time series array: and , using the formula:
[0106] ,
[0107] and,
[0108] ,
[0109] Calculate the mean of the heart rate and blood pressure time series and ;
[0110] in, and From the array and The value taken from It's at the time Heart rate data, It's at the time Blood pressure data, is the total number of data points Indicates the location of the data point;
[0111] Based on the mean of heart rate and blood pressure time series and , using the formula:
[0112] ,
[0113] and,
[0114] ,
[0115] Calculate the standard deviation of the current heart rate and blood pressure fluctuation trend and ;
[0116] The calculation process is as follows:
[0117] The following data is obtained from the monitoring device:
[0118] Real-time heart rate ;
[0119] Real-time blood pressure ;
[0120] Heart rate history: ;
[0121] Historical blood pressure: ;
[0122] Combine real-time data to build a complete time series array:
[0123] Heart rate array ;
[0124] Blood pressure array ;
[0125] For the formula:
[0126] ,
[0127] For the formula:
[0128] ,
[0129] For the formula:
[0130] ,
[0131] ,
[0132] For the formula:
[0133] ,
[0134] ,
[0135] Set the baseline value to the heart rate standard deviation and blood pressure standard deviation , calculate the standard deviation of the heart rate Slightly higher than the baseline value, indicating that the heart rate has moderate fluctuations, but still within the normal range, suggesting that the heart rate changes are not too drastic and the patient's heart rate is relatively stable. This value is lower than the baseline value, indicating that blood pressure is very stable with small fluctuations, which means that blood pressure is well controlled, which is very beneficial for the management and monitoring of hypertension.
[0136] See also Figure 3 , the steps for obtaining the trend prediction values of heart rate and blood pressure are as follows:
[0137] According to the standard deviation of the current heart rate and blood pressure fluctuation trend and , using the formula:
[0138] ,
[0139] and,
[0140] ,
[0141] Calculate sudden heart rate fluctuations and sudden blood pressure fluctuations ;
[0142] in, is the maximum function, used to find the maximum value in a sequence;
[0143] According to sudden heart rate fluctuations and sudden blood pressure fluctuations , using the formula:
[0144] ,
[0145] and,
[0146] ,
[0147] Calculate the trend forecast of heart rate and blood pressure trend prediction values , integrate to obtain the trend prediction values of heart rate and blood pressure;
[0148] in, is the adjustment coefficient, which is used to adjust the impact of sudden fluctuations on trend forecasts;
[0149] The calculation process is as follows:
[0150] For the formula:
[0151] ,
[0152] and,
[0153] ,
[0154] Setting parameters , , , ;
[0155] ,
[0156] ,
[0157] Setting parameters ;
[0158] For the formula:
[0159] ,
[0160] and,
[0161] ,
[0162] Setting parameters , , , ;
[0163] ,
[0164] ,
[0165] Set the baseline value to heart rate and blood pressure The calculated heart rate prediction value is , slightly above baseline, indicating a possible slight trend toward increased heart rate, which could be due to short-term changes in mood or physical activity. The blood pressure prediction is , which is also slightly higher than the baseline, indicating a slight upward trend in blood pressure.
[0166] See also Figure 4 , the specific steps to obtain the initialization model parameters are:
[0167] Predicted value based on heart rate trend and blood pressure trend prediction values , using the formula:
[0168] ,
[0169] and,
[0170] ,
[0171] Initialize the model parameters of heart rate and the model parameters of blood pressure ;
[0172] in, They are the weight coefficients that adjust the impact of the predicted value on parameter initialization;
[0173] Model parameters based on heart rate and the model parameters of blood pressure , using the formula:
[0174] ,
[0175] and,
[0176] ,
[0177] Calculate heart rate prediction and blood pressure prediction ;
[0178] in, Indicates at a point in time Historical heart rate data, Indicates at a point in time Historical blood pressure data, is the total number of historical data points, is the adjustment factor of the heart rate, which is used to fine-tune the model output of the heart rate according to the predicted value. is the adjustment factor for blood pressure, which is used to fine-tune the model output of blood pressure according to the predicted value;
[0179] The calculation process is as follows:
[0180] For the formula:
[0181] ,
[0182] and,
[0183] ,
[0184] Setting parameters , , , , , ;
[0185] ,
[0186] ,
[0187] For the formula:
[0188] ,
[0189] and,
[0190] ,
[0191] Setting parameters , , ;
[0192] ,
[0193] ,
[0194] Set the baseline value to heart rate and blood pressure , the heart rate output by the model and blood pressure Both are slightly higher than the baseline value. This means that the heart rate and blood pressure have increased slightly, but are still within the normal range, which may indicate a slight physiological change or response to external stress. This fine adjustment indicates that the patient's physiological state is basically stable.
[0195] See also Figure 5 , the specific steps for obtaining the adjusted prediction model are:
[0196] Collect newly measured heart rate and blood pressure , based on the heart rate prediction and blood pressure prediction , using the formula:
[0197] ,
[0198] and,
[0199] ,
[0200] Calculate the rate of change of heart rate relative to the predicted model and the rate of change of blood pressure relative to the prediction model ;
[0201] in, is the time interval, is the standardized coefficient, adjusting the standardized level of the rate of change, is a smoothing constant to reduce the impact of mutations in calculations;
[0202] Based on the rate of change of heart rate relative to the prediction model and the rate of change of blood pressure relative to the prediction model , using the formula:
[0203] ,
[0204] and,
[0205] ,
[0206] The future of heart rate calculation and the future of blood pressure , and obtain the adjusted prediction model;
[0207] in, The time length is set according to the predicted length of the patient's treatment cycle. To adjust the parameters and enhance the model's response to the absolute value of the changing trend;
[0208] The calculation process is as follows:
[0209] Step 1: For the formula:
[0210] ,
[0211] and,
[0212] ,
[0213] Setting parameters , , , ;
[0214] ,
[0215] ,
[0216] For the formula:
[0217] ,
[0218] ,
[0219] Setting parameters For 30 days, is 0.1;
[0220] ,
[0221] ,
[0222] Set the baseline value to heart rate and blood pressure Calculation results and The predicted values for both heart rate and blood pressure showed an increase compared to baseline values, suggesting that there may be physiological or environmental factors that may cause an increase in heart rate and blood pressure over the next month.
[0223] See also Figure 6 ,The specific steps for obtaining the possibility of analyzing potential risks are:
[0224] According to the future trend of heart rate and the future of blood pressure , combined with the newly measured heart rate and blood pressure , using the formula:
[0225] ,
[0226] Compare the current measured value with the model predicted value and calculate the risk probability of the current state ;
[0227] in, is a smoothing parameter used to reduce the impact of mutations and outliers in the calculation;
[0228] According to the risk probability of the current state , using the formula:
[0229] ,
[0230] Calculating the probability of anesthesia risk ;
[0231] The calculation process is as follows:
[0232] For the formula:
[0233] ,
[0234] Setting parameters , , , ;
[0235] ,
[0236] ,
[0237] ,
[0238] ,
[0239] (about 24.56%);
[0240] For the formula:
[0241] ,
[0242] ,
[0243] ,
[0244] ,
[0245] ,
[0246] (about 55.32%);
[0247] The baseline value is set to 50% of the anesthesia risk probability as the high risk threshold, and the calculation results are Exceeding baseline values indicates that current heart rate and blood pressure trends may increase the risk during anesthesia and recommend further evaluation and possible preventive measures.
[0248] See also Figure 7 , the specific steps for obtaining probabilistic risk information are:
[0249] According to the probability of anesthesia risk , using the formula:
[0250] ,
[0251] Calculate risk index ;
[0252] in, It is a preset threshold ratio used for standardized risk assessment;
[0253] According to the risk index , using the formula:
[0254] ,
[0255] Calculate the risk level value , get the probabilistic risk information;
[0256] The calculation process is as follows:
[0257] For the formula:
[0258] ,
[0259] Setting parameters is 55.32%, is 100%, or 1.0;
[0260] ,
[0261] For the formula:
[0262] ,
[0263] ,
[0264] Result interpretation and benchmark comparison The benchmark value of the risk level is set to 0.5, which is the 50% risk level cutoff point. The calculated risk level If the value is lower than the benchmark value of 0.5, it indicates that the patient is currently in a relatively low-risk state. This means that although there is a certain anesthesia risk, the risk level is within an acceptable range and the patient may not need additional preventive measures.
[0265] See also Figure 8 , the specific steps for obtaining the early warning response signal are:
[0266] According to the risk level , using the formula:
[0267] ,
[0268] Calculate the difference between the risk level value and the safety threshold to obtain the risk excess index ;
[0269] in, is the preset safety threshold;
[0270] According to the risk excess index , using the formula:
[0271] ,
[0272] Calculate warning value ,if If it is greater than 0, then it is an early warning response signal;
[0273] The calculation process is as follows:
[0274] Step 1: For the formula:
[0275] ,
[0276] Setting parameters , ;
[0277] ,
[0278] This result indicates that the risk level is below the safety threshold and does not exceed the risk level.
[0279] For the formula:
[0280] ,
[0281] Setting parameters ;
[0282] ,
[0283] The results meant that there was no need to issue an early warning response signal because the calculated risk level did not exceed the set safety threshold.
[0284] 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 intelligent monitoring and early warning system for anesthesia equipment, characterized in that: The system comprises: The trend analysis module collects multiple physiological parameter data of heart rate and blood pressure from monitoring equipment, combines historical monitoring data to perform time series analysis, analyzes the fluctuation trend of current heart rate and blood pressure physiological parameters, identifies sudden fluctuations, and obtains trend prediction values of heart rate and blood pressure; The steps of analyzing the fluctuation trend of the current heart rate and blood pressure physiological parameters are specifically as follows: Real-time heart rate collected from monitoring devices and blood pressure Data, combined with historical heart rate and historical blood pressure , forming a time series array: and , using the formula: ; and; ; Calculate the mean of the heart rate and blood pressure time series and ; in, and From the array and The value taken from It's at the time Heart rate data, It's at the time Blood pressure data, is the total number of data points, Indicates the location of the data point; According to the mean of the heart rate and blood pressure time series and , using the formula: ; and; ; Calculate the standard deviation of the current heart rate and blood pressure fluctuation trend and ; The steps for obtaining the trend prediction values of the heart rate and blood pressure are specifically as follows: According to the standard deviation of the current heart rate and blood pressure fluctuation trend and , using the formula: ; and; ; Calculate sudden heart rate fluctuations and sudden blood pressure fluctuations ; in, is the maximum value function; According to the sudden heart rate fluctuation and sudden blood pressure fluctuations , using the formula: ; and; ; Calculate the trend forecast of heart rate and blood pressure trend prediction values , integrate to obtain the trend prediction values of heart rate and blood pressure; in, is the adjustment coefficient, which is used to adjust the impact of sudden fluctuations on trend forecasts; The dynamic model establishment and adjustment module constructs an autoregressive moving average model, initializes model parameters according to the trend prediction values of the heart rate and blood pressure, calculates the future trend according to the currently obtained physiological parameters, and generates an adjusted prediction model; The steps for obtaining the initialization model parameters are specifically as follows: According to the trend prediction value of the heart rate and blood pressure trend prediction values , using the formula: ; and; ; Initialize the model parameters of heart rate and the model parameters of blood pressure ; in, They are the weight coefficients that adjust the impact of the predicted value on parameter initialization; According to the model parameters of the heart rate and the model parameters of blood pressure , using the formula: ; and; ; Calculate heart rate prediction and blood pressure prediction ; in, Indicates at a point in time Historical heart rate data, Indicates at a point in time Historical blood pressure data, is the total number of historical data points, is the heart rate adjustment factor, is the adjustment factor for blood pressure; The steps for obtaining the adjusted prediction model are specifically as follows: Collect newly measured heart rate and blood pressure , according to the heart rate prediction value and blood pressure prediction , using the formula: ; and; ; Calculate the rate of change of heart rate relative to the predicted model and the rate of change of blood pressure relative to the prediction model ; in, is the time interval, is the standardized coefficient, is the smoothing constant; According to the rate of change of the heart rate relative to the prediction model and the rate of change of blood pressure relative to the prediction model , using the formula: ; and; ; The future of heart rate calculation and the future of blood pressure , and obtain the adjusted prediction model; in, The time length is set according to the predicted length of the patient's treatment cycle. To adjust the parameters; The probabilistic risk assessment module uses the adjusted prediction model to perform probability calculations on the current and predicted anesthesia risks in the collected physiological parameters through a Bayesian network, analyzes the possibility of potential risks, and divides each risk level into categories to generate probabilistic risk information; The steps for obtaining the possibility of analyzing potential risks are specifically as follows: According to the future trend of the heart rate and the future of blood pressure , combined with the newly measured heart rate and blood pressure , using the formula: ; Compare the current measured value with the model predicted value and calculate the risk probability of the current state ; in, is the smoothing parameter; Based on the risk probability of the current state , using the formula: ; Calculating the probability of anesthesia risk ; The early warning response output module evaluates the various risk levels in the probabilistic risk information, determines whether the risk level exceeds a preset safety threshold, and generates an early warning response signal if it is detected that the risk level is exceeded.
2. The intelligent monitoring and early warning system for anesthesia equipment according to claim 1, characterized in that: The steps for obtaining the probabilistic risk information are specifically as follows: According to the anesthesia risk probability , using the formula: ; Calculate risk index ; in, is the preset threshold ratio; According to the risk index , using the formula: ; Calculate the risk level value , and obtain probabilistic risk information.
3. The intelligent monitoring and early warning system for anesthesia equipment according to claim 2 is characterized in that: The steps of obtaining the early warning response signal are specifically as follows: According to the risk level value , using the formula: ; Calculate the difference between the risk level value and the safety threshold to obtain the risk excess index ; in, is the preset safety threshold; According to the risk excess index , using the formula: ; Calculate warning value ,if If it is greater than 0, it is an early warning response signal.
