A method for risk assessment of preoperative medication for anesthesia

Abstract

This invention relates to the field of healthcare information technology, specifically to a method for preoperative anesthesia medication risk assessment. This method acquires preoperative anesthesia dosage and surgical time for each historical patient, as well as different types of physiological indicators for each patient at different surgical stages. Based on the preoperative anesthesia dosage and surgical time for each historical patient, it analyzes the changes in different types of physiological indicator data at different surgical stages to determine the risk weights of anesthetic drugs on different types of physiological indicators. Based on these risk weights, an anesthesia medication risk assessment model is constructed, and this model is used for real-time patient anesthesia medication risk assessment. This invention effectively improves the accuracy of risk assessment by adaptively determining the risk weights of anesthetic drugs on different types of physiological indicators and constructing an anesthesia medication risk assessment model based on these risk weights.

Description

Technical Field

[0001] This invention relates to the field of healthcare information technology, specifically to a method for assessing the risk of medication administration before anesthesia. Background Technology

[0002] Some surgeries require anesthesia before the operation. However, since different patients may have some chronic diseases, such as hypertension, diabetes, heart disease, liver and kidney dysfunction, there may be some risks during the anesthesia process. Therefore, in order to ensure the safety of patients' anesthetic medication, it is necessary to conduct a preoperative risk assessment. This can help anesthesiologists identify the patient's high-risk factors and take corresponding preventive measures, such as adjusting the use of medications, increasing intraoperative monitoring, and having backup emergency medications.

[0003] Current methods for assessing medication risk typically involve collecting data on various physiological parameters from patients before or after surgery, and then combining this data for risk assessment. However, these methods often assign equal contribution to all physiological parameters. Since different types of physiological parameters have varying degrees of correlation with medication risk, this approach can easily lead to an inaccurate assessment of the actual impact of different physiological parameters, resulting in inaccurate anesthetic medication risk assessments. Summary of the Invention

[0004] To address the technical problem in existing technologies where the contribution of all physiological parameter data is equal, leading to inaccurate anesthetic drug risk assessment results, the present invention aims to provide a method for preoperative anesthetic drug risk assessment. The specific technical solution adopted is as follows:

[0005] In a first aspect, the present invention provides a method for preoperative anesthesia medication risk assessment, comprising the following steps:

[0006] Obtain preoperative anesthesia dosage and operation time for each historical patient, as well as different types of physiological indicators for each historical patient at different stages of surgery;

[0007] Based on the preoperative anesthetic dose and operation time of each historical patient, the changes in different types of physiological indicators of each historical patient at different stages of operation were analyzed to determine the risk weight of anesthetic drugs on different types of physiological indicators.

[0008] Based on the aforementioned risk weights, an anesthetic drug risk assessment model is constructed, and the constructed anesthetic drug risk assessment model is used to conduct real-time anesthetic drug risk assessment for patients.

[0009] In conjunction with the first aspect above, among some possible implementation methods, risk weights for different types of physiological indicators produced by anesthetic drugs are determined, including:

[0010] Based on the changes in physiological indicators of the target type for each historical patient during the intraoperative and postoperative stages, and in combination with the preoperative anesthetic dose and surgical time for each historical patient, the anesthetic drug influence index was determined. The anesthetic drug influence index reflects the impact of anesthetic drugs on the patient's postoperative recovery.

[0011] Based on the changes in physiological indicators of the target type for each historical patient during the preoperative and intraoperative stages, and the correlation between the changes in physiological indicators of the target type for each historical patient during the preoperative and intraoperative stages, preoperative abnormality impact indicators are determined. These preoperative abnormality impact indicators reflect the impact of abnormal preoperative physiological indicators on abnormal intraoperative physiological indicators.

[0012] Based on the anesthetic drug impact indicators and preoperative abnormality impact indicators, the risk weights of anesthetic drugs on the target type of physiological indicators are determined.

[0013] In conjunction with the first aspect mentioned above, among some possible implementation methods, indicators affecting anesthetic drugs are determined, including:

[0014] Based on the changes in physiological indicators of the target type for each historical patient during the postoperative stage, the postoperative recovery status indicators for each historical patient were determined.

[0015] By combining the operation time of each historical patient, the correlation between the postoperative recovery status indicators and the preoperative anesthetic dose of each historical patient was analyzed to determine the initial anesthetic drug influence indicators.

[0016] Based on the fluctuations of physiological indicators of the target type for each historical patient during the intraoperative stage, and in combination with the preoperative anesthetic dose for each historical patient, the correction coefficient for the anesthetic drug influence index was determined.

[0017] The anesthetic drug impact index is corrected by using the correction coefficient of the anesthetic drug impact index to obtain the corrected final anesthetic drug impact index.

[0018] In conjunction with the first aspect mentioned above, among some possible implementation methods, postoperative recovery status indicators for each historical patient are determined, including:

[0019] Identify abnormal points in the physiological indicators of the target type for each historical patient that exceed the normal range during the postoperative stage;

[0020] Based on the data fluctuations at the abnormal points in the physiological indicator data of the target type, the abnormal values ​​of the abnormal points are determined;

[0021] A first fitted line is obtained by fitting a straight line to the outlier values ​​of all the aforementioned outlier points.

[0022] Linear fitting was performed on the physiological index data of the target type corresponding to each historical patient at the postoperative stage to obtain the second fitted line;

[0023] Based on the difference between the slope of the first fitted line and the slope of the second fitted line, and the difference between each indicator value and the standard indicator value in the physiological indicator data of the target type corresponding to each historical patient in the postoperative stage, the postoperative recovery status indicators of each historical patient are determined.

[0024] In conjunction with the first aspect above, in some possible implementations, determining the outlier value of the outlier point includes:

[0025] Determine a reference extreme point for the abnormal point. If the abnormal point is higher than the normal range, the reference extreme point is the nearest minimum point before the abnormal point in the physiological indicator data of the target type. If the abnormal point is lower than the normal range, the reference extreme point is the nearest maximum point before the abnormal point in the physiological indicator data of the target type.

[0026] Determine the absolute value of the difference between the outlier and its reference extreme point, and the time difference between the outlier and its reference extreme point;

[0027] The ratio of the absolute value of the difference to the time difference is determined as the outlier value of the outlier point.

[0028] In conjunction with the first aspect mentioned above, among some possible implementation methods, initial indicators of the impact of anesthetic drugs are determined, including:

[0029] Using the operation time as the horizontal axis and the postoperative recovery status index as the vertical axis, curve fitting was performed on the postoperative recovery status index of each historical patient to obtain the first fitted curve.

[0030] Using the operation time as the horizontal axis and the preoperative anesthesia dose as the vertical axis, a curve was fitted to the preoperative anesthesia dose of each historical patient to obtain the second fitted curve.

[0031] The mean square error of the first and second fitted curves is determined, and the mean square error is used as the initial anesthetic drug effect index.

[0032] In conjunction with the first aspect mentioned above, among some possible implementation methods, the correction coefficient for the impact index of anesthetic drugs is determined, including:

[0033] Determine the volatility of each indicator value in the physiological indicator data of the target type for each historical patient during the intraoperative stage, and obtain the volatility sequence for each historical patient; based on the distribution of volatility in the volatility sequence, determine the abnormal volatility value of the physiological indicator for each historical patient.

[0034] Using the preoperative anesthetic dose as the x-axis and the abnormal fluctuation value of physiological indicators as the y-axis, a linear fit was performed on the abnormal fluctuation value of physiological indicators of each historical patient to obtain the third fitted line.

[0035] The slope of the third fitted straight line is determined as the correction coefficient for the anesthetic drug influence index.

[0036] In conjunction with the first aspect mentioned above, among some possible implementation methods, preoperative abnormality indicators are determined, including:

[0037] Determine the DTW distance value of the physiological index data of the target type for each historical patient in the preoperative and intraoperative stages, and obtain the physiological index distance value for each historical patient;

[0038] Based on the changes in physiological indicators of the target type for each historical patient during the preoperative stage, abnormal values ​​of preoperative indicators for each historical patient were determined.

[0039] Based on the abnormal values ​​of preoperative indicators, abnormal fluctuation values ​​of physiological indicators, and distance values ​​of physiological indicators, the parameters affecting the abnormal preoperative indicators of each historical patient were determined.

[0040] Using the abnormal values ​​of preoperative indicators on the x-axis and the parameters affecting the abnormal preoperative indicators on the y-axis, a linear fit was performed on the parameters affecting the abnormal preoperative indicators of each historical patient to obtain the fourth fitted line.

[0041] The slope of the fourth fitted line was determined as an indicator of preoperative abnormality.

[0042] In conjunction with the first aspect mentioned above, among some possible implementation methods, abnormal values ​​of preoperative indicators for each historical patient are identified, including:

[0043] Identify abnormal data points that exceed the normal range in the physiological indicators of the target type for each historical patient during the preoperative stage;

[0044] The degree of abnormality of the abnormal data points is determined based on the fluctuation of the indicator values ​​at the abnormal data points and the density of the abnormal data points.

[0045] The average value of the fluctuation of each indicator in the physiological indicator data of the target type for each historical patient in the preoperative stage is determined to obtain the mean fluctuation value.

[0046] Determine the average anomaly score of all the aforementioned outlier data points to obtain the mean anomaly score;

[0047] The product of the mean volatility and the mean abnormality is determined as the preoperative abnormality value for each historical patient.

[0048] In conjunction with the first aspect above, among some possible implementation methods, the risk weights of anesthetic drugs on the physiological indicators of the target type are determined, including:

[0049] The product of the anesthetic drug effect index and the preoperative abnormal effect index is determined to obtain the initial risk weight of the anesthetic drug on the physiological indicators of the target type.

[0050] The sum of the initial risk weights of the effects of anesthetic drugs on all types of physiological indicators is determined to obtain the cumulative weights;

[0051] The ratio of the initial risk weight to the cumulative weight of the anesthetic drug on the physiological indicators of the target type is determined to obtain the risk weight of the anesthetic drug on the physiological indicators of the target type.

[0052] Secondly, the present invention also provides a pre-anesthesia medication risk assessment device, the device comprising:

[0053] The data acquisition module is used to acquire the preoperative anesthesia dosage and operation time of each historical patient, as well as different types of physiological indicators of each historical patient at different stages of surgery.

[0054] The weight acquisition module is used to analyze the changes in different types of physiological indicators of each historical patient at different surgical stages based on the preoperative anesthetic dose and operation time, and to determine the risk weight of anesthetic drugs on different types of physiological indicators.

[0055] The risk assessment module is used to construct an anesthetic drug risk assessment model based on the risk weights, and to use the constructed anesthetic drug risk assessment model to conduct real-time anesthetic drug risk assessment for patients.

[0056] Thirdly, the present invention also provides a pre-anesthesia medication risk assessment system, including a memory and a processor. The memory is used to store executable computer program code, and the processor is used to call and run the executable computer program code from the memory, causing the system to perform the methods in the first aspect or any possible implementation thereof.

[0057] Fourthly, the present invention also provides a computer program product comprising: computer program code, which, when run on a computer, causes the computer to perform the method described in the first aspect or any possible implementation thereof.

[0058] Fifthly, the present invention also provides a computer-readable storage medium storing computer program code that, when executed on a computer, causes the computer to perform the method described in the first aspect or any possible implementation thereof.

[0059] This invention offers the following advantages: It acquires preoperative anesthetic dosage and surgical time data for each historical patient, as well as different types of physiological indicators at different surgical stages. Based on the preoperative anesthetic dosage and surgical time, it analyzes the changes in different types of physiological indicators at different surgical stages to determine the risk weights of anesthetic drugs on different types of physiological indicators. Based on these risk weights, it constructs an anesthetic drug risk assessment model and uses this model to perform real-time anesthetic drug risk assessment for patients. This invention, by analyzing the changes in different types of physiological indicators at different surgical stages in conjunction with the preoperative anesthetic dosage and surgical time of each historical patient, adaptively determines the risk weights of anesthetic drugs on different types of physiological indicators. Based on these risk weights, it constructs an anesthetic drug risk assessment model for anesthetic drug risk assessment, effectively improving the accuracy of risk assessment. Attached Figure Description

[0060] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0061] Figure 1 This is a flowchart illustrating the steps of a method for assessing the risk of pre-anesthesia medication according to an embodiment of the present invention.

[0062] Figure 2 This is a flowchart illustrating the steps of determining the risk weights of anesthetic drugs on different types of physiological indicators according to an embodiment of the present invention.

[0063] Figure 3 This is a flowchart illustrating the steps for determining the influencing indicators of anesthetic drugs according to an embodiment of the present invention.

[0064] Figure 4 This is a flowchart illustrating the steps for determining preoperative abnormality indicators according to an embodiment of the present invention.

[0065] Figure 5 This is a schematic diagram of the structure of a pre-anesthesia medication risk assessment device according to an embodiment of the present invention;

[0066] Figure 6 This is a schematic diagram of a pre-anesthesia medication risk assessment system according to an embodiment of the present invention. Detailed Implementation

[0067] To clearly illustrate the technical features of this solution, the invention will be described in detail below through specific embodiments and in conjunction with the accompanying drawings.

[0068] Embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. While some embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the invention. It should be understood that the accompanying drawings and embodiments are for illustrative purposes only and are not intended to limit the scope of protection of the invention.

[0069] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0070] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0071] It should be noted that the concepts of "first" and "second" mentioned in this invention are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0072] Although operations or steps are described in a specific order in the accompanying drawings in the embodiments of the present invention, this should not be construed as requiring these operations or steps to be performed in the specific order or serial order shown, or requiring all of the shown operations or steps to be performed to obtain the desired result. In the embodiments of the present invention, these operations or steps may be performed serially; they may be performed in parallel; or a portion of these operations or steps may be performed.

[0073] Furthermore, it is understood that the data involved in the technical solutions of this invention (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions. Unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains, and all parameters or indicators in the formulas involved in this invention are normalized values ​​that have eliminated the influence of dimensions.

[0074] To address the issue of inaccurate anesthetic drug risk assessment results due to the equal contribution of all physiological parameter data, this invention provides a method for preoperative anesthetic drug risk assessment. This method analyzes the changes in target type physiological indicator data of each historical patient at different surgical stages based on the preoperative anesthetic dosage and operation time, determines the risk weight of anesthetic drugs on different types of physiological indicators, and constructs an anesthetic drug risk assessment model based on the risk weight to conduct anesthetic drug risk assessment, effectively improving the accuracy of anesthetic risk assessment.

[0075] The following will describe in detail, with reference to the accompanying drawings, a method for risk assessment of preoperative anesthesia medication provided by an embodiment of the present invention.

[0076] Figure 1 This diagram illustrates the basic flowchart of a pre-anesthesia medication risk assessment method provided by an embodiment of the present invention. Figure 1 As shown, the method specifically includes the following steps:

[0077] Step S100: Obtain the preoperative anesthesia dosage and operation time for each historical patient, as well as different types of physiological indicators for each historical patient at different stages of surgery.

[0078] Specifically, to construct an anesthetic drug risk assessment model for accurate anesthetic drug risk assessment, it is first necessary to leverage the hospital's big data system to obtain historical information from a large number of patients who have undergone similar surgeries. This historical information includes the preoperative anesthetic dosage and surgical time of historical patients, as well as different types of physiological indicator data at different surgical stages. These different surgical stages include the preoperative, intraoperative, and postoperative stages. The postoperative recovery time (i.e., the recovery period) can be determined based on the anesthetic drugs used preoperatively, and the surgical process can be divided into preoperative, intraoperative, and postoperative stages based on the surgical time recorded in the system. The different types of physiological indicator data refer to the time-series data of various physiological indicators obtained by monitoring physiological parameters at different surgical stages of historical patients. These different types of physiological indicators include various physiological indicators affected by anesthetic drug risks, such as heart rate, blood pressure, respiratory rate, and blood oxygen saturation.

[0079] Step S200: Based on the preoperative anesthetic dose and operation time of each historical patient, analyze the changes in different types of physiological indicators of each historical patient at different stages of surgery, and determine the risk weight of anesthetic drugs on different types of physiological indicators.

[0080] Specifically, to construct a risk assessment model for anesthesia medication based on historical patient information, it is necessary to determine the postoperative physiological status of the historical patients and assess their postoperative recovery based on this status. To observe the postoperative recovery status of historical patients, any physiological indicator from their historical data, such as heart rate, is used as a target physiological indicator. The changes in this target physiological indicator data during the postoperative period are analyzed. For example, the smaller the difference between all indicator values ​​and the standard values, the better the postoperative recovery of the historical patient.

[0081] To understand the impact of anesthetic drugs on postoperative recovery, the trends in postoperative recovery of all historical patients can be analyzed based on their surgical time. Simultaneously, the trends in preoperative anesthetic dosage for all historical patients can be analyzed. A greater degree of consistency between these two trends indicates that preoperative anesthetic drug administration may have influenced the patient's recovery. Conversely, a greater similarity in these trends suggests that the preoperative dosage may have had a smaller impact on the patient, indicating that the patient may have developed some drug tolerance.

[0082] However, assessing the impact of anesthetic drugs solely based on the patient's postoperative recovery has limitations. Due to patient independence, tolerance to anesthetic dosage varies. Therefore, it is necessary to further evaluate the impact of preoperative anesthetic drugs by analyzing changes in physiological indicators during the intraoperative phase. For example, abnormal fluctuations in physiological indicators of the target type in historical patients during anesthesia may indicate a significant impact of the current anesthetic dosage on those patients. Therefore, by analyzing changes in physiological indicators of the target type in each historical patient during the intraoperative phase, the extent of the preoperative medication's influence on the patient can be determined, thus providing a more accurate assessment of the impact of anesthetic drugs on postoperative recovery.

[0083] Considering the physiological indicators of different patients' target types is also a necessary part of the preoperative risk assessment of anesthetic drugs. Therefore, it is also necessary to analyze the changes in the physiological indicators of target types of each patient in the preoperative stage, determine the impact of abnormal physiological indicators of target types in the preoperative stage on abnormal fluctuations in the intraoperative stage, and then combine the impact of anesthetic drugs on postoperative recovery to finally obtain the risk weight of anesthetic drugs on the physiological indicators of target types.

[0084] By analyzing the changes in different types of physiological indicators at different surgical stages based on the preoperative anesthetic dose and surgical time of each historical patient, the risk weights of anesthetic drugs on different types of physiological indicators can be determined.

[0085] Step S300: Based on the risk weights, construct an anesthetic drug risk assessment model, and use the constructed anesthetic drug risk assessment model to conduct real-time anesthetic drug risk assessment for patients.

[0086] Specifically, based on the risk weights of anesthetic drugs on different types of physiological indicators as determined above, a risk assessment model for anesthetic drugs is constructed using data from different types of physiological indicators. For example, a multimodal gated spatiotemporal network (MGST-Net) can be used as the risk assessment model for anesthetic drugs. The input layer of this multimodal gated spatiotemporal network is used to input different types of physiological indicator data, the dynamic gating fusion module in the network is used to adjust the risk weights of different types of physiological indicator data, and the spatiotemporal joint analysis layer in the network outputs the risk assessment results of anesthetic drugs through time-dependent modeling and spatial correlation mining.

[0087] When it is necessary to assess the preoperative anesthesia medication of a real-time patient, different types of physiological index data of the patient in the preoperative stage are acquired and input into the anesthesia medication risk assessment model. The model outputs the anesthesia medication risk assessment result for the real-time patient, which is then provided to the anesthesiologist for reference. Based on this anesthesia medication risk assessment result, and in conjunction with other monitoring data of the real-time patient, the anesthesiologist determines the true anesthesia medication risk assessment result for the real-time patient. According to the final true anesthesia medication risk assessment result determined by the anesthesiologist, the anesthesiologist can explain the possible anesthesia risks and the impact of preoperative medication to the patient, ensure informed consent, and adjust the type, dosage, or administration method of anesthetic drugs accordingly. For example, when the preoperative anesthesia medication risk of a patient is high, the anesthesiologist can reduce the preoperative anesthesia dosage according to the patient's specific condition and develop an anesthesia risk management plan, clarifying possible emergency and preventive measures to deal with possible adverse reactions or complications.

[0088] The preoperative anesthesia medication risk assessment method provided in this embodiment analyzes the changes in physiological indicators of target types for each historical patient at different surgical stages based on the preoperative anesthesia dosage and operation time of each patient. It adaptively determines the risk weight of anesthesia medication on different types of physiological indicators, and constructs an anesthesia medication risk assessment model based on the risk weight to conduct anesthesia medication risk assessment, effectively improving the accuracy of risk assessment.

[0089] Furthermore, in some possible implementations, such as Figure 2 As shown, step S200 above determines the risk weights of anesthetic drugs on different types of physiological indicators, which may specifically include the following steps S201-S203:

[0090] S201: Based on the changes in physiological indicators of the target type corresponding to each historical patient during the intraoperative and postoperative stages, and in combination with the preoperative anesthetic dose and surgical time of each historical patient, determine the anesthetic drug influence index. The anesthetic drug influence index reflects the impact of anesthetic drugs on the patient's postoperative recovery.

[0091] S202: Based on the changes in physiological indicators of the target type for each historical patient during the preoperative and intraoperative stages, and the correlation between the changes in physiological indicators of the target type for each historical patient during the preoperative and intraoperative stages, preoperative abnormality impact indicators are determined. These preoperative abnormality impact indicators reflect the impact of abnormal preoperative physiological indicators on abnormal intraoperative physiological indicators.

[0092] S203: Based on the anesthetic drug impact index and the preoperative abnormal impact index, determine the risk weight of the anesthetic drug on the target type of physiological indicators.

[0093] In this embodiment, after surgery under anesthesia, patients undergo a certain recovery period during which their various physiological indicators gradually return to normal. Taking heart rate as an example, the normal range for an adult's heart rate is 60–100 beats per minute. After surgery, the patient's heart rate will increase, and the difference between the heart rate and the normal range will decrease as the recovery time progresses. For the target type of physiological indicator data, analyzing the cases where the physiological indicator data exceeds the normal range and the distance of each indicator value from the baseline value can help assess the patient's postoperative recovery. Furthermore, to obtain the impact of anesthetic drugs on the patient's postoperative recovery, the relationship between the changing trends of postoperative recovery in historical patients and the changing trends of preoperative anesthetic dosage is analyzed. When the relationship between the two is relatively consistent, it indicates that the preoperative dosage of anesthetic drugs had a relatively small impact on the patient. This allows for the determination of anesthetic drug influence indicators to reflect the impact of anesthetic drugs on the postoperative recovery of historical patients. Meanwhile, abnormal fluctuations in various patient indicators during surgery may indicate that the current dosage of anesthetic drugs has a significant impact on the patient. Therefore, by monitoring abnormal changes in various physiological indicators during the intraoperative phase, we can further determine the impact of preoperative medication on the patient during surgery.

[0094] Abnormalities in various physiological indicators during the preoperative stage may indicate that the patient will be more sensitive to postoperative reactions after anesthesia. Therefore, it is necessary to analyze the abnormalities in various physiological indicators during the preoperative stage of historical patients, and combine this with the abnormalities in various physiological indicators during the intraoperative stage of historical patients, as well as the correlation between the changes in the target type of physiological indicator data during the preoperative and intraoperative stages of historical patients, to determine the preoperative abnormality impact indicators, so as to reflect the impact of abnormal preoperative physiological indicators on abnormal intraoperative physiological indicators.

[0095] Furthermore, based on the anesthetic drug impact index and the preoperative abnormality impact index, the risk weights of the anesthetic drugs on each type of physiological indicator are determined. The larger the anesthetic drug impact index and the preoperative abnormality impact index, the higher the risk level of the anesthetic drug on the corresponding type of physiological indicator, and the larger its corresponding risk weight should be. In this embodiment, the product value of the anesthetic drug impact index and the preoperative abnormality impact index is determined, and this product value is used as the initial risk weight of the anesthetic drug on the target type of physiological indicator. The initial risk weights of the anesthetic drug on all different types of physiological indicators are summed to obtain the accumulated weight. The ratio of the initial risk weight to the accumulated weight is calculated, and this ratio is used as the final risk weight of the anesthetic drug on all different types of physiological indicators.

[0096] Furthermore, in some possible implementations, such as Figure 3 As shown, step S201 above determines the influencing indicators of anesthetic drugs, which may specifically include the following steps S2011-S2014:

[0097] S2011: Determine the postoperative recovery status indicators for each historical patient based on the changes in physiological indicators of the target type corresponding to the postoperative stage.

[0098] S2012: Combining the operation time of each historical patient, analyze the correlation between the postoperative recovery status indicators and the changes in the preoperative anesthetic dose of each historical patient to determine the initial anesthetic drug influence indicators.

[0099] S2013: Based on the fluctuation of physiological indicators of the target type corresponding to each historical patient during the intraoperative stage, and in combination with the preoperative anesthetic dose of each historical patient, determine the correction coefficient of the anesthetic drug influence index.

[0100] S2014: Using the aforementioned correction coefficient for the anesthetic drug impact index, the initial anesthetic drug impact index is corrected to obtain the corrected final anesthetic drug impact index.

[0101] In this embodiment, after determining the postoperative recovery status indicators for each historical patient, the correlation between the changing trends of these indicators and the changing trends of preoperative anesthetic dosage is analyzed, taking into account the surgical time of each patient, to determine the initial anesthetic drug influence indicators. Simultaneously, the fluctuations in the target type of physiological indicators during the intraoperative phase are analyzed to determine the abnormal fluctuation values ​​of the physiological indicators for each patient.

[0102] The analysis of the abnormal fluctuations in the physiological indicators of historical patients with changes in preoperative anesthetic dosage revealed that as the preoperative anesthetic dosage increased, the abnormal fluctuations in the physiological indicators of historical patients also gradually increased. This indicates that the physiological indicators of patients become less stable during the surgical phase as the anesthetic dosage increases, suggesting that the anesthetic drugs may cause emergency situations during the surgical phase. Thus, the correction coefficient for the influence of anesthetic drugs on the indicators can be determined.

[0103] The initial anesthetic drug impact index, determined above, is corrected using a correction coefficient to obtain the final corrected anesthetic drug impact index. In this embodiment, the product of the initial anesthetic drug impact index and the correction coefficient can be determined, and this product value is used as the final corrected anesthetic drug impact index.

[0104] Furthermore, in some possible implementations, step S2011 above, which determines the postoperative recovery status indicators for each historical patient, may specifically include the following steps:

[0105] Identify abnormal points in the physiological indicators of the target type for each historical patient that exceed the normal range during the postoperative stage;

[0106] Based on the data fluctuations at the abnormal points in the physiological indicator data of the target type, the abnormal values ​​of the abnormal points are determined;

[0107] A first fitted line is obtained by fitting a straight line to the outlier values ​​of all the aforementioned outlier points.

[0108] Linear fitting was performed on the physiological index data of the target type corresponding to each historical patient at the postoperative stage to obtain the second fitted line;

[0109] Based on the difference between the slope of the first fitted line and the slope of the second fitted line, and the difference between each indicator value and the standard indicator value in the physiological indicator data of the target type corresponding to each historical patient in the postoperative stage, the postoperative recovery status indicators of each historical patient are determined.

[0110] In this embodiment, for the physiological indicator data of the target type corresponding to each historical patient in the postoperative stage, abnormal points exceeding the normal range are identified in the physiological indicator data. Taking heart rate as an example of the target type physiological indicator, the normal range of heart rate for a normal adult is 60–100 beats / minute. Therefore, heart rate values ​​outside the 60–100 beats / minute range are considered abnormal points. It is determined whether each abnormal point is above or below the normal range. Based on the determination result, the nearest minimum or maximum value before the abnormal point is obtained as a reference extreme value. If the abnormal point is above the normal range, the reference extreme value is the nearest minimum value before the abnormal point; if the abnormal point is below the normal range, the reference extreme value is the nearest maximum value before the abnormal point. The time difference between each abnormal point and its reference extreme value is determined, and then the ratio of the absolute value of the difference between each abnormal point and its reference extreme value to the time difference is determined. This ratio is determined as the abnormal value of each abnormal point. The larger the outlier, the greater the fluctuation in the target type of physiological indicators of the patient in this area, and the range of fluctuation exceeds the normal value.

[0111] By combining the time of the physiological index values, linear fitting was performed on all abnormal values ​​corresponding to each historical patient to obtain the first fitted line, and the slope of the first fitted line was obtained. Simultaneously, linear fitting was performed on the physiological index data of the target type for each historical patient at the postoperative stage to obtain a second fitted line, and the slope of the second fitted line was obtained. .

[0112] The slope of the second fitted line slope of the first fitted line By comparing and combining the differences between each indicator value in the target type's physiological indicator data and the standard indicator value, the postoperative recovery status indicators of each historical patient are determined. Among these, if the slope of the second fitted straight line... The larger the value of , the greater the slope of the first fitted line. The smaller the value, the fewer instances of postoperative physiological indicators exceeding the normal range occur, indicating a better postoperative recovery and a higher corresponding postoperative recovery status indicator. Furthermore, comparing all values ​​of the target type's physiological indicators with standard values ​​reveals that smaller differences between all values ​​and the standard values ​​indicate a closer approximation of the patient's postoperative physiological indicators to normal levels, further suggesting a better postoperative recovery and a higher corresponding postoperative recovery status indicator. The standard value refers to a reference value for normal indicators, which can be the median of the normal range for the target type's physiological indicators.

[0113] In this embodiment, the postoperative recovery status index of each historical patient is calculated using the following formula:

[0114] ;

[0115] In the formula: Indicators representing the postoperative recovery status of each patient in their history; The slope of the first fitted straight line represents the physiological index data of the target type for each historical patient at the postoperative stage; The slope of the second fitted line represents the physiological index data of the target type for each historical patient at the postoperative stage; This represents the average of the absolute values ​​of the differences between all physiological indicator values ​​and the standard indicator values ​​in the target type of physiological indicator data for each historical patient at the postoperative stage. Represents an infinite decimal greater than 0, used to prevent the denominator from being zero; This represents the hyperbolic tangent function, used for normalizing numerical values.

[0116] By using the above methods, corresponding to each type of physiological indicator data, we can obtain the postoperative recovery status indicators of each historical patient. The higher the value of the postoperative recovery status indicator, the more the physiological indicators of the historical patient gradually approach the normal level after surgery, and the better the patient's postoperative recovery. When the patient's postoperative recovery is poor, it may be due to excessive dosage of anesthetic drugs or the patient's own physical condition. Therefore, we can use the postoperative status of historical patients to reflect the impact of the preoperative medication.

[0117] Furthermore, in some possible implementations, step S2012 above, which determines the initial anesthetic drug effect indicators, may specifically include the following steps:

[0118] Using the operation time as the horizontal axis and the postoperative recovery status index as the vertical axis, curve fitting was performed on the postoperative recovery status index of each historical patient to obtain the first fitted curve.

[0119] Using the operation time as the horizontal axis and the preoperative anesthesia dose as the vertical axis, a curve was fitted to the preoperative anesthesia dose of each historical patient to obtain the second fitted curve.

[0120] The mean square error of the first and second fitted curves is determined, and the mean square error is used as the initial anesthetic drug effect index.

[0121] In this embodiment, to obtain the impact of anesthetic drugs on the postoperative recovery of patients, curve fitting was performed on the postoperative recovery status indicators of each historical patient based on their surgical time points, resulting in a fitted curve of the postoperative recovery status over a certain period of time, which is recorded as the first fitted curve. Simultaneously, curve fitting was also performed on the preoperative anesthetic dose of each historical patient based on their surgical time points, resulting in a fitted curve of the anesthetic dose over a certain period of time, which is recorded as the second fitted curve.

[0122] To determine the impact of anesthetic medication on postoperative recovery, the mean squared error (MSE) of the first and second fitted curves was obtained. The MSE reflects the influence of anesthetic medication on postoperative recovery; a larger MSE value indicates a greater difference between the two fitted curves, suggesting a poorer recovery with an increasing anesthetic dosage. This indicates that preoperative anesthetic medication may have affected the patient's recovery. Conversely, a smaller MSE indicates a more similar trend between the recovery curve and the anesthetic dosage curve, suggesting that the preoperative medication dosage may have had a smaller impact on the patient, indicating potential drug tolerance. The MSE of the first and second fitted curves was used as the initial indicator of the impact of anesthetic medication.

[0123] Furthermore, in some possible implementations, step S2013 above, which determines the correction coefficient for the anesthetic drug impact index, may specifically include the following steps:

[0124] Determine the volatility of each indicator value in the physiological indicator data of the target type for each historical patient during the intraoperative stage, and obtain the volatility sequence for each historical patient;

[0125] Based on the distribution of volatility in the volatility sequence, the abnormal volatility values ​​of physiological indicators for each historical patient are determined.

[0126] Using the preoperative anesthetic dose as the x-axis and the abnormal fluctuation value of physiological indicators as the y-axis, a linear fit was performed on the abnormal fluctuation value of physiological indicators of each historical patient to obtain the third fitted line.

[0127] The slope of the third fitted straight line is determined as the correction coefficient for the anesthetic drug influence index.

[0128] In this embodiment, for the physiological indicator data of the target type corresponding to each historical patient during the intraoperative stage, the absolute value of the difference between each indicator value and its predecessor is recorded as the volatility of each indicator value. This allows the acquisition of a volatility sequence corresponding to all indicator values ​​in the physiological indicator data. The maximum value in the volatility sequence is recorded as an abnormal volatility point. The average value of each abnormal volatility point and its nearest other abnormal volatility points is determined to obtain the first average volatility. The average value of all volatility points between each abnormal volatility point and its nearest other abnormal volatility points is determined to obtain the second average volatility. The interval distance between each abnormal volatility point and its nearest other abnormal volatility points is determined. When the first average volatility is larger, the second average volatility is smaller, and the interval distance is smaller, it indicates that the abnormal volatility points are more densely packed and the volatility values ​​of the data points between the abnormal volatility points are smaller. Therefore, it indicates that the abnormal volatility of the physiological indicator data is more obvious, thus allowing the determination of the abnormal volatility values ​​of the physiological indicators for each historical patient.

[0129] In this embodiment, the abnormal fluctuation values ​​of physiological indicators for each historical patient can be calculated using the following formula:

[0130] ;

[0131] In the formula: This indicates abnormal fluctuations in physiological indicators for each historical patient. This represents the number of abnormal fluctuation points in the fluctuation sequence of physiological indicators corresponding to the target type for each historical patient during the intraoperative stage. Represents the th in the volatility sequence The first average volatility corresponding to each abnormal fluctuation point , Represents the th in the volatility sequence One abnormal fluctuation point Indicates the volatility sequence and the first Other abnormal fluctuation points closest to the current abnormal fluctuation point; Represents the th in the volatility sequence The second average volatility corresponds to the nth abnormal fluctuation point, and this second average volatility is determined by analyzing the volatility sequence of the nth abnormal fluctuation point. The average of all volatility values ​​between an abnormal fluctuation point and its nearest other abnormal fluctuation points is obtained; Represents the th in the volatility sequence The distance between an abnormal fluctuation point and its nearest other abnormal fluctuation points can be determined by comparing the distance between the first abnormal fluctuation point and the next abnormal fluctuation point. The absolute value of the difference between an abnormal fluctuation point and the corresponding index of its nearest other abnormal fluctuation point in the volatility sequence is obtained; Represents an infinite decimal greater than 0, used to prevent the denominator from being zero; This represents the hyperbolic tangent function, used for normalizing numerical values.

[0132] Following the above method, for the physiological index data of the target type, the abnormal fluctuation values ​​of physiological indicators for each historical patient can be determined. Using the preoperative anesthetic dose as the x-axis and the abnormal fluctuation values ​​of physiological indicators as the y-axis, a linear fit is performed on the abnormal fluctuation values ​​of physiological indicators for each historical patient, resulting in a third fitted line. The slope of the third fitted line is obtained. A smaller slope indicates that the physiological indicators of the target type are more stable during the operation as the anesthetic dose increases, suggesting that the anesthetic has a better impact on the patient's condition during surgery. A larger slope indicates that the physiological indicators of the target type are less stable during the operation as the anesthetic dose increases, suggesting that the anesthetic may cause emergency situations during surgery. The slope of the third fitted line is used as a correction coefficient for the anesthetic drug influence index, which is used to correct the initial anesthetic drug influence index, thus obtaining the corrected final anesthetic drug influence index.

[0133] Furthermore, in some possible implementations, such as Figure 4 As shown, step S202 above determines the preoperative abnormality indicators, which may specifically include the following steps S2021-S2025:

[0134] S2021: Determine the DTW distance value of the physiological index data of the target type for each historical patient in the preoperative and intraoperative stages, and obtain the physiological index distance value for each historical patient.

[0135] S2022: Based on the changes in physiological indicators of the target type for each historical patient during the preoperative stage, determine the abnormal values ​​of the preoperative indicators for each historical patient.

[0136] S2023: Based on the abnormal values ​​of preoperative indicators, abnormal fluctuation values ​​of physiological indicators, and distance values ​​of physiological indicators, determine the parameters affecting the abnormal preoperative indicators of each historical patient.

[0137] S2024: Using the abnormal values ​​of preoperative indicators as the horizontal axis and the parameters affecting the abnormal preoperative indicators as the vertical axis, a linear fit is performed on the parameters affecting the abnormal preoperative indicators of each historical patient to obtain the fourth fitted line.

[0138] S2025: Determine the slope of the fourth fitted line as an indicator of preoperative abnormal influence.

[0139] In this embodiment, based on the changes in physiological indicator data of the target type for each historical patient during the preoperative stage, preoperative abnormal values ​​of indicators are determined. These preoperative abnormal values ​​reflect the abnormality of the target type's physiological indicator data before surgery. The DTW distance value of the target type's physiological indicator data for each historical patient during the preoperative and intraoperative stages is determined. This DTW distance value reflects the similarity between the target type's physiological indicator data of historical patients during the preoperative and intraoperative stages; the smaller the DTW distance value, the higher the similarity. Based on the preoperative abnormal values, abnormal fluctuation values ​​of physiological indicators, and physiological indicator distance values ​​of each historical patient, a preoperative abnormality impact parameter is determined to reflect the degree of influence of preoperative abnormalities in the target type's physiological indicator data on its intraoperative abnormal fluctuations. Larger values ​​for preoperative abnormalities and abnormal fluctuation values ​​of physiological indicators, and smaller values ​​for DTW distance values, indicate more abnormal preoperative target type physiological indicator data and similar intraoperative changes. This suggests a greater influence of the patient's preoperative target type physiological indicator data on intraoperative abnormal fluctuations, and consequently, a larger value for the corresponding preoperative abnormality impact parameter.

[0140] In this embodiment, the preoperative abnormality impact parameter for each historical patient can be calculated using the following formula:

[0141] ;

[0142] In the formula: These are parameters influencing abnormal preoperative indicators in each historical patient. This indicates abnormal values ​​of preoperative indicators for each historical patient; This indicates abnormal fluctuations in physiological indicators for each historical patient. This represents the physiological indicators of the target type for each patient in the preoperative stage. Physiological indicator data corresponding to the target type during the intraoperative phase of Distance value, this The value of is usually not zero; This represents the hyperbolic tangent function, used for normalizing numerical values.

[0143] Following the above method, the parameters influencing preoperative abnormalities in each historical patient can be determined. Using the abnormal preoperative values ​​as the x-axis and the parameters influencing preoperative abnormalities as the y-axis, a linear fit is performed on these parameters for each historical patient, resulting in a fourth fitted line. The slope of this fourth fitted line is then obtained. A larger slope indicates a higher degree of abnormality in the patient's preoperative physiological indicators for the target type. This makes it more likely that these physiological indicators will fluctuate abnormally during the intraoperative phase, suggesting that abnormal fluctuations in the patient's target type physiological indicators during the intraoperative phase are more likely to be caused by preoperative anesthetic medication.

[0144] Furthermore, in some possible implementations, step S2022 above, which identifies abnormal preoperative indicators for each historical patient, may specifically include the following steps:

[0145] Identify abnormal data points that exceed the normal range in the physiological indicators of the target type for each historical patient during the preoperative stage;

[0146] The degree of abnormality of the abnormal data points is determined based on the fluctuation of the indicator values ​​at the abnormal data points and the density of the abnormal data points.

[0147] The average value of the fluctuation of each indicator in the physiological indicator data of the target type for each historical patient in the preoperative stage is determined to obtain the mean fluctuation value.

[0148] Determine the average anomaly score of all the aforementioned outlier data points to obtain the mean anomaly score;

[0149] The product of the mean volatility and the mean abnormality is determined as the preoperative abnormality value for each historical patient.

[0150] In this embodiment, for the physiological indicator data of the target type corresponding to each historical patient in the preoperative stage, data points exceeding the normal range in the physiological indicator data are identified and recorded as abnormal data points. The average absolute value of the difference between each abnormal data point and its left and right adjacent data points is determined and recorded as the fluctuation index. Simultaneously, the proportion of abnormal data points within the nearest neighbor range of each abnormal data point is determined and recorded as the density of abnormal data points. The product of the fluctuation index and the abnormality density is determined and recorded as the abnormality degree. Furthermore, based on the mean fluctuation degree of all data points in the physiological indicator data and the mean abnormality degree of all abnormal data points, the abnormal values ​​of the preoperative indicators for each historical patient are determined.

[0151] Furthermore, in some possible implementations, step S300, based on risk weights, constructs an anesthetic drug risk assessment model and uses this model to conduct real-time anesthetic drug risk assessment for patients, including the following steps: When it is necessary to assess the preoperative anesthetic medication for real-time patients, different types of physiological indicator data of the real-time patient in the preoperative stage are obtained, and the physiological indicator characteristics of the same type of physiological indicator data are obtained, such as using the variance of all indicator values ​​in the physiological indicator data as the physiological indicator characteristics. The cumulative value of the product of all physiological indicator characteristics and the risk weights of the corresponding type of physiological indicator data is then normalized using a normalization function to obtain the anesthetic drug risk assessment result for the real-time patient. The normalization function can be reasonably selected as needed, such as choosing... The hyperbolic tangent function normalizes the accumulated value.

[0152] Based on the same inventive concept, embodiments of the present invention also provide a pre-anesthesia medication risk assessment device, such as... Figure 5 As shown, the device includes:

[0153] The data acquisition module is used to acquire the preoperative anesthesia dosage and operation time of each historical patient, as well as different types of physiological indicators of each historical patient at different stages of surgery.

[0154] The weight acquisition module is used to analyze the changes in different types of physiological indicators of each historical patient at different surgical stages based on the preoperative anesthetic dose and operation time, and to determine the risk weight of anesthetic drugs on different types of physiological indicators.

[0155] The risk assessment module is used to construct an anesthetic drug risk assessment model based on the risk weights, and to use the constructed anesthetic drug risk assessment model to conduct real-time anesthetic drug risk assessment for patients.

[0156] It should be noted that the device provided in the above embodiments is only an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above.

[0157] Based on the same inventive concept, embodiments of the present invention also provide a pre-anesthesia medication risk assessment system, such as... Figure 6 As shown, the system includes: a memory 601, a processor 602, and computer program code 603 stored in the memory 601 and running on the processor 602, wherein when the processor 602 executes the computer program code 603, the system can perform any of the aforementioned pre-anesthesia medication risk assessment methods.

[0158] In this embodiment of the invention, the system can be divided into functional modules according to the above method example. For example, each module can correspond to a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0159] Based on the same inventive concept, embodiments of the present invention also provide a computer program product, which includes: computer program code, which, when run on a computer, causes the computer to execute any of the aforementioned methods for pre-anesthesia medication risk assessment.

[0160] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium storing computer program code, which, when executed on a computer, causes the computer to perform any of the aforementioned methods for pre-anesthesia medication risk assessment.

[0161] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for assessing the risk of preoperative medication use during anesthesia, characterized in that, Includes the following steps: Obtain preoperative anesthesia dosage and operation time for each historical patient, as well as different types of physiological indicators for each historical patient at different stages of surgery; Based on the preoperative anesthetic dose and operation time of each historical patient, the changes in different types of physiological indicators of each historical patient at different stages of operation were analyzed to determine the risk weight of anesthetic drugs on different types of physiological indicators. Based on the aforementioned risk weights, an anesthetic drug risk assessment model is constructed, and the constructed anesthetic drug risk assessment model is used to conduct real-time anesthetic drug risk assessment for patients. Determine the risk weights of anesthetic drugs on different types of physiological indicators, including: Based on the changes in physiological indicators of the target type for each historical patient during the intraoperative and postoperative stages, and in combination with the preoperative anesthetic dose and surgical time for each historical patient, the anesthetic drug influence index was determined. The anesthetic drug influence index reflects the impact of anesthetic drugs on the patient's postoperative recovery. Based on the changes in physiological indicators of the target type for each historical patient during the preoperative and intraoperative stages, and the correlation between the changes in physiological indicators of the target type for each historical patient during the preoperative and intraoperative stages, preoperative abnormality impact indicators are determined. These preoperative abnormality impact indicators reflect the impact of abnormal preoperative physiological indicators on abnormal intraoperative physiological indicators. Based on the anesthetic drug impact indicators and preoperative abnormality impact indicators, the risk weights of anesthetic drugs on the target type of physiological indicators are determined. Determine the influencing factors of anesthetic drugs, including: Based on the changes in physiological indicators of the target type for each historical patient during the postoperative stage, the postoperative recovery status indicators for each historical patient were determined. By combining the operation time of each historical patient, the correlation between the postoperative recovery status indicators and the preoperative anesthetic dose of each historical patient was analyzed to determine the initial anesthetic drug influence indicators. Based on the fluctuations of physiological indicators of the target type for each historical patient during the intraoperative stage, and in combination with the preoperative anesthetic dose for each historical patient, the correction coefficient for the anesthetic drug influence index was determined. Using the aforementioned correction coefficient for the anesthetic drug impact index, the initial anesthetic drug impact index is corrected to obtain the corrected final anesthetic drug impact index. Determine the postoperative recovery status indicators for each patient's history, including: Identify abnormal points in the physiological indicators of the target type for each historical patient that exceed the normal range during the postoperative stage; Based on the data fluctuations at the abnormal points in the physiological indicator data of the target type, the abnormal values ​​of the abnormal points are determined; A first fitted line is obtained by fitting a straight line to the outlier values ​​of all the aforementioned outlier points. Linear fitting was performed on the physiological index data of the target type corresponding to each historical patient at the postoperative stage to obtain the second fitted line; Based on the difference between the slope of the first fitted line and the slope of the second fitted line, and the difference between each indicator value and the standard indicator value in the physiological indicator data of the target type corresponding to each historical patient in the postoperative stage, the postoperative recovery status indicators of each historical patient are determined.

2. The method for preoperative anesthesia medication risk assessment according to claim 1, characterized in that, Determining the outlier values ​​of the outlier points includes: Determine a reference extreme point for the abnormal point. If the abnormal point is higher than the normal range, the reference extreme point is the nearest minimum point before the abnormal point in the physiological indicator data of the target type. If the abnormal point is lower than the normal range, the reference extreme point is the nearest maximum point before the abnormal point in the physiological indicator data of the target type. Determine the absolute value of the difference between the outlier and its reference extreme point, and the time difference between the outlier and its reference extreme point; The ratio of the absolute value of the difference to the time difference is determined as the outlier value of the outlier point.

3. The method for preoperative anesthesia medication risk assessment according to claim 1, characterized in that, Determine initial indicators of the impact of anesthetic drugs, including: Using the operation time as the horizontal axis and the postoperative recovery status index as the vertical axis, curve fitting was performed on the postoperative recovery status index of each historical patient to obtain the first fitted curve. Using the operation time as the horizontal axis and the preoperative anesthesia dose as the vertical axis, a curve was fitted to the preoperative anesthesia dose of each historical patient to obtain the second fitted curve. The mean square error of the first and second fitted curves is determined, and the mean square error is used as the initial anesthetic drug effect index.

4. The method for preoperative anesthesia medication risk assessment according to claim 1, characterized in that, Determine the correction coefficients for the influencing indicators of anesthetic drugs, including: Determine the volatility of each indicator value in the physiological indicator data of the target type for each historical patient during the intraoperative stage, and obtain the volatility sequence for each historical patient; based on the distribution of volatility in the volatility sequence, determine the abnormal volatility value of the physiological indicator for each historical patient. Using the preoperative anesthetic dose as the x-axis and the abnormal fluctuation value of physiological indicators as the y-axis, a linear fit was performed on the abnormal fluctuation value of physiological indicators of each historical patient to obtain the third fitted line. The slope of the third fitted straight line is determined as the correction coefficient for the anesthetic drug influence index.

5. The method for preoperative anesthesia medication risk assessment according to claim 4, characterized in that, Identify preoperative abnormality indicators, including: Determine the DTW distance value of the physiological index data of the target type for each historical patient in the preoperative and intraoperative stages, and obtain the physiological index distance value for each historical patient; Based on the changes in physiological indicators of the target type for each historical patient during the preoperative stage, abnormal values ​​of preoperative indicators for each historical patient were determined. Based on the abnormal values ​​of preoperative indicators, abnormal fluctuation values ​​of physiological indicators, and distance values ​​of physiological indicators, the parameters affecting the abnormal preoperative indicators of each historical patient were determined. Using the abnormal values ​​of preoperative indicators on the x-axis and the parameters affecting the abnormal preoperative indicators on the y-axis, a linear fit was performed on the parameters affecting the abnormal preoperative indicators of each historical patient to obtain the fourth fitted line. The slope of the fourth fitted line was determined as an indicator of preoperative abnormality.

6. The method for preoperative anesthesia medication risk assessment according to claim 5, characterized in that, Identify abnormal preoperative markers for each historical patient, including: Identify abnormal data points that exceed the normal range in the physiological indicators of the target type for each historical patient during the preoperative stage; The degree of abnormality of the abnormal data points is determined based on the fluctuation of the indicator values ​​at the abnormal data points and the density of the abnormal data points. The average value of the fluctuation of each indicator in the physiological indicator data of the target type for each historical patient in the preoperative stage is determined to obtain the mean fluctuation value. Determine the average anomaly score of all the aforementioned outlier data points to obtain the mean anomaly score; The product of the mean volatility and the mean abnormality is determined as the preoperative abnormality value for each historical patient.

7. The method for preoperative anesthesia medication risk assessment according to claim 1, characterized in that, Determine the risk weights of anesthetic drugs on target physiological indicators, including: The product of the anesthetic drug effect index and the preoperative abnormal effect index is determined to obtain the initial risk weight of the anesthetic drug on the physiological indicators of the target type. The sum of the initial risk weights of the effects of anesthetic drugs on all types of physiological indicators is determined to obtain the cumulative weights; The ratio of the initial risk weight to the cumulative weight of the anesthetic drug on the physiological indicators of the target type is determined to obtain the risk weight of the anesthetic drug on the physiological indicators of the target type.

Images