Anesthesia preoperative medication risk assessment method

Abstract

The invention relates to the technical field of medical care information, in particular to an anesthesia preoperative medication risk assessment method, which comprises the following steps: acquiring preoperative anesthetic dose and operation time of each historical patient and different types of physiological index data of each historical patient in different operation stages; based on the preoperative anesthetic dosage and the operation time of each historical patient, the change condition of different types of physiological index data of each historical patient in different operation stages is analyzed, and risk weights generated by anesthetic medication for different types of physiological indexes are determined; and based on the risk weight, constructing an anesthetic drug risk assessment model, and performing real-time anesthetic drug risk assessment on the patient by using the constructed anesthetic drug risk assessment model. According to the method, the risk weights generated by the anesthetic drugs for different types of physiological indexes are determined in a self-adaptive manner, and the anesthetic drug risk assessment model is constructed based on the risk weights so as to perform anesthetic drug risk assessment, so that the risk assessment accuracy is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of medical care information technology, and in particular to a method for assessing the risk of medication before anesthesia. Background Art

[0002] Some surgeries require the patient to be anesthetized before the operation. Since different patients may have some chronic diseases, such as hypertension, diabetes, heart disease, liver and kidney dysfunction, etc., there may be some risks during the anesthesia process. Therefore, in order to ensure the safety of the patient's anesthetic medication, the patient needs to be assessed before the operation. This can assist the anesthesiologist in identifying the patient's high-risk factors and taking corresponding preventive measures, such as adjusting drug use, intensive intraoperative monitoring, and preparing emergency drugs.

[0003] Existing medication risk assessment methods typically collect data on multiple physiological parameters from patients before or after surgery and then integrate these data to assess medication risk. However, in existing medication risk assessment methods, all physiological parameter data are typically assigned an equal contribution. Because different physiological parameters have varying degrees of correlation with medication risk, this can lead to an inability to accurately assess their actual impact, resulting in inaccurate anesthetic risk assessment results. Summary of the Invention

[0004] In order to solve the technical problem in the prior art that the anesthetic medication risk assessment results are not accurate due to the equal contribution of all physiological parameter data, the purpose of the present invention is to provide a method for pre-anesthetic medication risk assessment. The technical solution adopted is as follows: In a first aspect, the present invention provides a method for risk assessment of pre-anesthetic medication, comprising the following steps: Obtain the preoperative anesthesia dose and operation time of each historical patient as well as different types of physiological index data of each historical patient at different stages of the operation; Based on the preoperative anesthesia dose and operation time of each historical patient, the changes in different types of physiological indicators of each historical patient at different surgical stages are analyzed to determine the risk weights of anesthetic drugs on different types of physiological indicators; Based on the risk weights, an anesthetic medication risk assessment model is constructed, and the constructed anesthetic medication risk assessment model is used to perform real-time anesthetic medication risk assessment on patients.

[0005] In conjunction with the first aspect above, in some possible implementations, determining the risk weights of anesthetic drugs on different types of physiological indicators includes: Based on the changes in physiological indicator data of the target type corresponding to each historical patient during the intraoperative and postoperative stages, and combined with the preoperative anesthetic dose and operation time of each historical patient, an anesthetic drug impact index is determined. The anesthetic drug impact index reflects the impact of anesthetic drugs on the patient's postoperative recovery; According to the changes in physiological indicator data of the target type corresponding to each historical patient in the preoperative stage and the intraoperative stage, and the correlation between the changes in physiological indicator data of the target type corresponding to each historical patient in the preoperative stage and the intraoperative stage, a preoperative abnormality impact index is determined, wherein the preoperative abnormality impact index reflects the impact of the patient's preoperative physiological indicator abnormality on the intraoperative physiological indicator abnormality; Based on the anesthetic drug impact index and the preoperative abnormality impact index, the risk weight of the anesthetic drug on the physiological index of the target type is determined.

[0006] In conjunction with the first aspect above, in some possible implementations, determining the anesthetic medication impact indicator includes: Determine the postoperative recovery status indicator of each historical patient based on the changes in physiological indicator data of the target type corresponding to each historical patient in the postoperative stage; Combined with the operation time of each historical patient, the correlation between the postoperative recovery status indicators and preoperative anesthetic doses of each historical patient was analyzed to determine the initial anesthetic drug impact indicators; According to the fluctuation of physiological index data of target type corresponding to each historical patient during the intraoperative stage, and combined with the preoperative anesthesia dose of each historical patient, the correction coefficient of the anesthetic medication impact index is determined; The anesthetic medication influence index correction coefficient is used to correct the initial anesthetic medication influence index to obtain a corrected final anesthetic medication influence index.

[0007] In conjunction with the first aspect above, in some possible implementations, determining the postoperative recovery status indicator of each historical patient includes: Determine abnormal points that exceed the normal range in the physiological indicator data of the target type corresponding to each historical patient in the postoperative period; Determining an abnormal value of the abnormal point according to data fluctuations at the abnormal point in the physiological indicator data of the target type; Performing straight line fitting on the outlier values of all the outliers to obtain a first fitting straight line; Performing straight line fitting on the physiological indicator data of the target type corresponding to each historical patient in the postoperative stage to obtain a second fitting straight line; The postoperative recovery status index of each historical patient is determined based on the difference between the slope of the first fitting straight line and the slope of the second fitting straight line, and the difference between each indicator value in the physiological indicator data of the target type corresponding to each historical patient in the postoperative stage and the standard indicator value.

[0008] In conjunction with the foregoing first aspect, in some possible implementations, determining the outlier value of the outlier point includes: Determine a reference extreme value point for the abnormal point; if the abnormal point is higher than the normal range, the reference extreme value point is a minimum value point closest to 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 value point is a maximum value point closest to the abnormal point in the physiological indicator data of the target type; Determining the absolute value of the difference between the abnormal point and its reference extreme point, and the time difference between the abnormal point and its reference extreme point; A ratio of the absolute value of the difference to the time difference is determined as an outlier value of the outlier point.

[0009] In conjunction with the first aspect above, in some possible implementations, determining the initial anesthetic medication impact indicator includes: With the operation time as the horizontal axis and the postoperative recovery status index as the vertical axis, curve fitting is performed on the postoperative recovery status index of each historical patient to obtain a first fitting curve; With the operation time as the horizontal axis and the preoperative anesthetic dose as the vertical axis, a curve fitting is performed on the preoperative anesthetic dose of each historical patient to obtain a second fitting curve; A mean square error between the first fitting curve and the second fitting curve is determined, and the mean square error is determined as an initial anesthetic medication impact index.

[0010] In conjunction with the first aspect above, in some possible implementations, determining the correction coefficient of the anesthetic medication impact index includes: Determine the fluctuation of each indicator value in the target type of physiological indicator data corresponding to each historical patient during the intraoperative stage to obtain a fluctuation sequence for each historical patient; determine the abnormal fluctuation value of the physiological indicator of each historical patient based on the distribution of the fluctuations in the fluctuation sequence; With the preoperative anesthesia dose as the horizontal axis and the abnormal fluctuation value of the physiological index as the vertical axis, a straight line is fitted to the abnormal fluctuation value of the physiological index of each historical patient to obtain a third fitting straight line; The slope value of the third fitting straight line is determined as the correction coefficient of the anesthetic medication influence index.

[0011] In conjunction with the first aspect above, in some possible implementations, determining the preoperative abnormal impact indicator includes: Determine the DTW distance value of the physiological indicator data of the target type corresponding to each historical patient in the preoperative stage and the intraoperative stage, and obtain the physiological indicator distance value of each historical patient; Determine the abnormal value of the preoperative indicator of each historical patient according to the change of the physiological indicator data of the target type corresponding to each historical patient in the preoperative stage; Determine the abnormal preoperative index impact parameter of each historical patient based on the abnormal preoperative index value, the abnormal physiological index fluctuation value, and the physiological index distance value; With the abnormal value of the preoperative index as the horizontal axis and the abnormal influencing parameter of the preoperative index as the vertical axis, a straight line fitting is performed on the abnormal influencing parameter of the preoperative index of each historical patient to obtain a fourth fitting straight line; The slope of the fourth fitting straight line is determined as an indicator of preoperative abnormal influence.

[0012] In conjunction with the first aspect above, in some possible implementations, determining abnormal values of preoperative indicators for each historical patient includes: Determine abnormal data points that are outside the normal range in the physiological indicator data of the target type corresponding to each historical patient in the preoperative stage; Determining the abnormality of the abnormal data point based on the fluctuation of the indicator value at the abnormal data point and the density of the abnormal data point; Determine the average value of the fluctuation of each indicator value in the physiological indicator data of the target type corresponding to each historical patient in the preoperative stage to obtain the fluctuation mean; Determine the average value of the abnormality of all abnormal data points to obtain the average abnormality value; The product of the fluctuation mean and the abnormality mean is determined as the preoperative indicator abnormality value of each historical patient.

[0013] In conjunction with the first aspect above, in some possible implementations, determining the risk weight of anesthetic drugs on physiological indicators of target types includes: Determining the product of the anesthetic drug impact index and the preoperative abnormality impact index to obtain an initial risk weight of the anesthetic drug on the physiological index of the target type; Determine the cumulative sum of the initial risk weights of anesthetic drugs on all types of physiological indicators to obtain the cumulative weight; The ratio of the initial risk weight of the anesthetic drug on the physiological index of the target type to the cumulative weight is determined to obtain the risk weight of the anesthetic drug on the physiological index of the target type.

[0014] In a second aspect, the present invention further provides a device for assessing the risk of medication before anesthesia, the device comprising: A data acquisition module is used to obtain the preoperative anesthesia dose and operation time of each historical patient as well as different types of physiological index data of each historical patient at different stages of the operation; The weight acquisition module is used to analyze the changes in different types of physiological indicator data of each historical patient at different surgical stages based on the preoperative anesthetic dose and operation time of each historical patient, and determine the risk weights of anesthetic drugs on different types of physiological indicators; The risk assessment module is used to construct an anesthetic medication risk assessment model based on the risk weights, and use the constructed anesthetic medication risk assessment model to perform real-time anesthetic medication risk assessment on patients.

[0015] In a third aspect, the present invention further provides a pre-anesthesia medication risk assessment system, comprising a memory and a processor. The memory is configured to store executable computer program code, and the processor is configured to retrieve and execute the executable computer program code from the memory, so that the system performs the method of the first aspect or any possible implementation of the first aspect.

[0016] In a fourth aspect, the present invention further provides a computer program product, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0017] In a fifth aspect, the present invention also provides a computer-readable storage medium, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0018] The present invention has the following beneficial effects: the present invention obtains the preoperative anesthetic dose and operation time of each historical patient and different types of physiological indicator data of each historical patient at different stages of the operation; based on the preoperative anesthetic dose and operation time of each historical patient, analyzes the changes in different types of physiological indicator data of each historical patient at different stages of the operation, and determines the risk weights of anesthetic drugs on different types of physiological indicators; based on the risk weights, constructs an anesthetic drug risk assessment model, and uses the constructed anesthetic drug risk assessment model to perform real-time anesthetic drug risk assessment for patients. The present invention adaptively determines the risk weights of anesthetic drugs on different types of physiological indicators by analyzing the changes in different types of physiological indicator data of each historical patient at different stages of the operation in combination with the preoperative anesthetic dose and operation time of each historical patient, and constructs an anesthetic drug risk assessment model based on the risk weights to perform anesthetic drug risk assessment, thereby effectively improving the accuracy of risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 This is a flowchart of the steps of a method for risk assessment of pre-anesthetic medication according to an embodiment of the present invention; Figure 2 A flowchart of the steps for determining the risk weights of anesthetic drugs on different types of physiological indicators according to an embodiment of the present invention; Figure 3 This is a flowchart of the steps for determining an anesthetic medication impact index according to an embodiment of the present invention; Figure 4 This is a flowchart of the steps for determining preoperative abnormality impact indicators according to an embodiment of the present invention; Figure 5 This is a schematic structural diagram of a device for risk assessment of pre-anesthetic medication according to an embodiment of the present invention; Figure 6 The figure is a schematic structural diagram of a pre-anesthesia medication risk assessment system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to clearly illustrate the technical features of this solution, the present invention is described in detail below through specific implementation methods in conjunction with the accompanying drawings.

[0022] Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0023] 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. In addition, 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.

[0024] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0025] It should be noted that the concepts of "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0026] Although operations or steps are described in a particular order in the drawings in the embodiments of the present invention, this should not be understood as requiring that these operations or steps be performed in the particular order shown or in a serial order, or that all of the operations or steps shown be performed to obtain a desired result. In the embodiments of the present invention, these operations or steps may be performed serially; they may also be performed in parallel; or a portion of these operations or steps may be performed.

[0027] At the same time, it is understood that the data involved in the technical solutions of the present invention (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions. Unless otherwise defined, all technical and scientific terms used in this invention have the same meanings as those commonly understood by those skilled in the art to which this invention belongs, and all parameters or indicators in the formulas involved in this invention are normalized values to eliminate dimension effects.

[0028] In order to solve the problem that the anesthetic drug risk assessment results are not accurate due to the same contribution of all physiological parameter data, an embodiment of the present invention provides an anesthetic preoperative medication risk assessment method. The method analyzes the changes in the physiological indicator data of the target type of each historical patient at different surgical stages based on the preoperative anesthetic dose and operation time of each historical patient, determines the risk weights of anesthetic drugs on different types of physiological indicators, and constructs an anesthetic drug risk assessment model based on the risk weights to perform anesthetic drug risk assessment, thereby effectively improving the accuracy of anesthesia risk assessment.

[0029] A method for risk assessment of pre-anesthetic medication provided by an embodiment of the present invention will be described in detail below with reference to the accompanying drawings.

[0030] Figure 1 FIG. 1 shows a basic flow chart of a method for risk assessment of pre-anesthetic medication provided by an embodiment of the present invention, such as Figure 1 As shown, the method specifically includes the following steps: Step S100: obtaining the preoperative anesthesia dosage and operation time of each historical patient as well as different types of physiological indicator data of each historical patient at different operation stages.

[0031] Specifically, to build an accurate anesthetic risk assessment model, we first need to leverage the hospital's big data system to obtain historical information on a large number of patients who underwent similar surgeries. This historical information includes preoperative anesthetic doses and surgical durations, as well as various physiological indicator data from different surgical phases. These phases are preoperative, intraoperative, and postoperative. The anesthetics used before surgery can be used to determine the postoperative recovery time, or the postoperative phase. Furthermore, based on the surgical time recorded in the system, the surgical process can be divided into the preoperative, intraoperative, and postoperative phases. These physiological indicator data refer to time-series data obtained by monitoring physiological parameters of historical patients at different surgical phases. These physiological indicators include heart rate, blood pressure, respiratory rate, blood oxygen saturation, and other types of physiological indicators that are affected by anesthetic risk.

[0032] Step S200: Based on the preoperative anesthesia dose and operation time of each historical patient, analyze the changes in different types of physiological indicator data of each historical patient at different operation stages to determine the risk weights of anesthetic drugs on different types of physiological indicators.

[0033] Specifically, in order to construct a patient anesthetic medication risk assessment model based on the historical information of historical patients, it is necessary to determine the physiological condition of the historical patients after surgery in the historical information, and judge the postoperative recovery status of the historical patients based on their physiological condition after surgery. In order to observe the postoperative physical recovery status of historical patients, any physiological indicator among the physiological parameters of historical patients, such as the heart rate of historical patients, is used as a target type of physiological indicator, and the changes in the target type of physiological indicator data in the postoperative period are analyzed. For example, when the difference between all indicator values in the physiological indicator data and the standard value is smaller, it indicates that the historical patient's postoperative recovery is better.

[0034] In order to obtain the impact of anesthetic drugs on the patient's postoperative recovery, based on the operation time of each historical patient, the changing trend of the postoperative recovery status of all historical patients can be analyzed, and the changing trend of the preoperative anesthetic dose of all historical patients can be analyzed. When the consistency of the two changing trends is worse, it means that the preoperative anesthetic drug situation may have an impact on the recovery status of the historical patients; conversely, when the two changing trends are more similar, it indicates that the patient's preoperative drug dosage may have less impact on the patient, that is, the patient may have a certain drug resistance.

[0035] However, there are certain limitations in evaluating the impact of anesthetic drugs based solely on the patient's postoperative recovery status. Due to the independence of patients, their acceptance of anesthetic doses is also different. Therefore, it is necessary to further evaluate the impact of preoperative anesthetic drugs through changes in physiological indicator data during the intraoperative stage. For example, abnormal fluctuations in physiological indicator data of target types of historical patients during anesthesia surgery may indicate that the current anesthetic drug dose may have a more obvious impact on historical patients. Therefore, the changes in physiological indicator data of target types of each historical patient during the intraoperative stage can be used to judge the degree of impact of preoperative medication on intraoperative patients, thereby obtaining a more accurate understanding of the impact of anesthetic drugs on postoperative recovery.

[0036] Considering the physiological indicator data status of the target type of different patients is also a necessary part of the preoperative anesthetic drug risk assessment. Therefore, it is also necessary to analyze the changes in the physiological indicator data of the target type of each historical patient in the preoperative stage, and determine the impact of the abnormal physiological indicators of the target type of historical patients in the preoperative stage on the 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 the target type.

[0037] In the above manner, by analyzing the changes in different types of physiological indicator data of each historical patient at different surgical stages based on the preoperative anesthetic dose and operation time of each historical patient, the risk weights of anesthetic drugs on different types of physiological indicators can be determined.

[0038] Step S300: Based on the risk weights, an anesthetic medication risk assessment model is constructed, and the constructed anesthetic medication risk assessment model is used to perform real-time anesthetic medication risk assessment on patients.

[0039] Specifically, based on the risk weights of anesthetic drugs for different types of physiological indicators determined above, an anesthetic drug risk assessment model is constructed using different types of physiological indicator data. For example, a multimodal gated spatiotemporal network (MGST-Net) can be used as an anesthetic drug risk assessment model. The input layer of the multimodal gated spatiotemporal network is used to input different types of physiological indicator data. The dynamic gated fusion module in the network is used to adjust the risk weights of different types of physiological indicator data. The spatiotemporal joint analysis layer in the network uses time-dependent modeling and spatial association mining to ultimately output the anesthetic drug risk assessment results.

[0040] When a real-time patient's preoperative anesthetic medication needs to be assessed, different types of physiological indicator data are obtained for the real-time patient during the preoperative period and input into the anesthetic medication risk assessment model. The anesthetic medication risk assessment model then outputs an anesthetic medication risk assessment result for the real-time patient, which is then provided to the anesthesiologist for reference. Based on this anesthetic medication risk assessment result and other monitoring data from the real-time patient, the anesthesiologist determines the real-time anesthetic medication risk assessment result for the real-time patient. Based on the final anesthetic medication risk assessment result determined by the anesthesiologist, the anesthesiologist can explain the potential anesthetic risks and the impact of preoperative medications to the patient, ensure informed consent, and adjust the type, dosage, or route of administration of the anesthetic medication accordingly. For example, if the patient's preoperative medication risk is high, the anesthesiologist can reduce the preoperative anesthetic dose based on the patient's specific condition and develop an anesthesia risk management plan that identifies possible emergency and preventive measures to address potential adverse reactions or complications.

[0041] The above-mentioned preoperative anesthesia medication risk assessment method provided in this embodiment analyzes the changes in the physiological indicator data of the target type of each historical patient at different surgical stages based on the preoperative anesthesia dose and operation time of each historical patient, adaptively determines the risk weights of anesthetic drugs on different types of physiological indicators, and constructs an anesthetic drug risk assessment model based on the risk weights to perform anesthetic drug risk assessment, thereby effectively improving the accuracy of risk assessment.

[0042] Furthermore, in some possible implementations, such as Figure 2 As shown, the above step S200 determines the risk weights of anesthetic drugs on different types of physiological indicators, which may specifically include the following steps S201-S203: S201: Determine an anesthetic medication impact index based on changes in physiological indicator data of target types corresponding to each historical patient during the intraoperative and postoperative stages, combined with the preoperative anesthetic dose and operation time of each historical patient. The anesthetic medication impact index reflects the impact of anesthetic medication on the patient's postoperative recovery; S202: Determine a preoperative abnormality impact index based on changes in physiological indicator data of target types corresponding to each historical patient during the preoperative and intraoperative stages, and a correlation between changes in physiological indicator data of target types corresponding to each historical patient during the preoperative and intraoperative stages. The preoperative abnormality impact index reflects the impact of the patient's preoperative physiological indicator abnormality on the intraoperative physiological indicator abnormality. S203: Based on the anesthetic medication impact index and the preoperative abnormality impact index, determine the risk weight of the anesthetic medication on the physiological index of the target type.

[0043] In this embodiment, there will be a certain amount of recovery time after the patient undergoes surgery under anesthesia, and during the recovery period, the various physiological index data will gradually return to the normal range. Taking heart rate as an example, the normal range of heart rate for normal adults is 60-100 beats / minute. The heart rate of the patient will rise after surgery, and the difference between the heart rate and the normal range will become smaller and smaller as the recovery time progresses. For the target type of physiological index data, by analyzing the situation where the physiological index data exceeds the normal range and the distance between each index value in the physiological index data and the baseline value, it is possible to assist in evaluating the patient's postoperative recovery. Furthermore, in order to obtain the impact of anesthetic drugs on the patient's postoperative recovery, the relationship between the changing trend of the postoperative recovery of each historical patient and the changing trend of their preoperative anesthetic dose is analyzed. When the relationship between the two changes is relatively consistent, it indicates that the historical patient's preoperative medication has little effect on the patient. Therefore, the anesthetic drug impact index can be determined to reflect the impact of anesthetic drugs on the postoperative recovery of historical patients. At the same time, abnormal fluctuations in various types of patient indicator data during the operation may indicate that the current dose of anesthetic drugs will have a more obvious impact on the patient. Therefore, by monitoring the abnormal changes in various types of physiological indicator data during the operation, we can further judge the impact of preoperative medication on intraoperative patients.

[0044] Abnormal conditions of various types of physiological indicators of patients in the preoperative stage may mean that the patient's reaction after anesthesia will be more sensitive. Therefore, it is necessary to analyze the abnormal conditions of various types of physiological indicators of historical patients in the preoperative stage. At the same time, combined with the abnormal conditions of various types of physiological indicators of historical patients in the intraoperative stage, as well as the correlation between the changes in the physiological indicator data of the target types corresponding to the preoperative and intraoperative stages of historical patients, determine the preoperative abnormality impact index to reflect the impact of the abnormal preoperative physiological indicators of historical patients on the abnormal intraoperative physiological indicators.

[0045] Furthermore, based on the anesthetic drug impact index and the preoperative abnormal impact index, the risk weight of anesthetic drugs on various types of physiological indicators is determined. When the anesthetic drug impact index and the preoperative abnormal impact index are larger, the higher the risk level of anesthetic drugs on the corresponding type of physiological indicators, the larger the corresponding risk weight should be. In this embodiment, the product value of the anesthetic drug impact index and the preoperative abnormal impact index is determined, and the product value is used as the initial risk weight of anesthetic drugs on the target type of physiological indicators. The initial risk weights generated by anesthetic drugs on all different types of physiological indicators are accumulated to obtain the accumulated weight, the ratio of the initial risk weight to the accumulated weight is calculated, and the ratio is used as the final risk weight of anesthetic drugs on all different types of physiological indicators.

[0046] Furthermore, in some possible implementations, such as Figure 3 As shown, the above step S201 determines the anesthetic medication impact index, which may specifically include the following steps S2011-S2014: S2011: determining a postoperative recovery status indicator for each historical patient based on changes in physiological indicator data of a target type corresponding to each historical patient in the postoperative stage; S2012: Combined with the operation time of each historical patient, the correlation between the postoperative recovery status indicators and preoperative anesthetic dose of each historical patient was analyzed to determine the initial anesthetic drug impact indicators; S2013: Determine the correction coefficient of the anesthetic medication impact index based on the fluctuation of the physiological indicator data 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; S2014: using the anesthetic medication influence index correction coefficient, and correcting the initial anesthetic medication influence index to obtain a corrected final anesthetic medication influence index.

[0047] In this embodiment, after determining each patient's postoperative recovery status indicator, the correlation between the changing trend of each patient's postoperative recovery status indicator and the changing trend of each patient's preoperative anesthetic dose is analyzed in conjunction with each patient's surgical time to determine the initial anesthetic medication impact indicator. Simultaneously, the fluctuation of each patient's target physiological indicator data during the intraoperative period is analyzed to determine the abnormal fluctuation value of each patient's physiological indicator.

[0048] The abnormal fluctuation values of physiological indicators of historical patients with changes in preoperative anesthetic doses were analyzed. When the abnormal fluctuation values of physiological indicators of historical patients gradually increased with the continuous increase of preoperative anesthetic doses, it means that the physiological indicators of patients during the operation stage became more unstable with the continuous increase of anesthetic doses, indicating that anesthetics may cause emergency situations in patients during the operation stage. Therefore, the correction coefficient of the index affecting anesthetic drugs can be determined.

[0049] The initial anesthetic drug impact index determined above is corrected using the anesthetic drug impact index correction coefficient to obtain a corrected final anesthetic drug impact index. In this embodiment, the product value of the initial anesthetic drug impact index and the anesthetic drug impact index correction coefficient can be determined, and the product value is used as the corrected final anesthetic drug impact index.

[0050] Furthermore, in some possible implementations, the above step S2011 of determining the postoperative recovery status index of each historical patient may specifically include the following steps: Determine abnormal points that exceed the normal range in the physiological indicator data of the target type corresponding to each historical patient in the postoperative period; Determining an abnormal value of the abnormal point according to data fluctuations at the abnormal point in the physiological indicator data of the target type; Performing straight line fitting on the outlier values of all the outliers to obtain a first fitting straight line; Performing straight line fitting on the physiological indicator data of the target type corresponding to each historical patient in the postoperative stage to obtain a second fitting straight line; The postoperative recovery status index of each historical patient is determined based on the difference between the slope of the first fitting straight line and the slope of the second fitting straight line, and the difference between each indicator value in the physiological indicator data of the target type corresponding to each historical patient in the postoperative stage and the standard indicator value.

[0051] In this embodiment, for each historical patient's target physiological indicator data corresponding to the postoperative period, abnormal points in the physiological indicator data that are outside the normal range are identified. Taking heart rate as an example, the normal range for an adult heart rate is 60–100 beats / minute. Therefore, heart rate values outside the 60–100 beats / minute range are identified as abnormal points. A determination is made as to whether each abnormal point is above or below the normal range. Based on the determination result, the closest minimum or maximum point preceding the abnormal point is determined as a reference extreme point. If the abnormal point is above the normal range, the reference extreme point is the closest minimum point preceding the abnormal point. If the abnormal point is below the normal range, the reference extreme point is the closest maximum point preceding the abnormal point. The time difference between each abnormal point and its reference extreme point is determined, and then the ratio of the absolute value of the difference between each abnormal point and its reference extreme point to the time difference is determined. This ratio is then determined as the abnormal value for each abnormal point. The larger the abnormal value is, the more it indicates that the physiological indicator data of the target type of the historical patient has experienced a large fluctuation and the fluctuation range exceeds the normal value.

[0052] Combined with the time of the indicator value in the physiological indicator data, all abnormal values corresponding to each historical patient are linearly fitted to obtain the first fitting straight line and obtain the slope of the first fitting straight line. At the same time, a straight line fitting is performed on the physiological index data of the target type corresponding to each historical patient in the postoperative stage to obtain a second fitting straight line, and the slope of the second fitting straight line is obtained. .

[0053] The slope of the second fitted line The slope of the first fitted straight line Compare and combine the difference between each indicator value in the target type physiological indicator data and the standard indicator value to determine the postoperative recovery status indicator of each historical patient. The larger the value of is, the smaller the slope of the first fitting line is. The smaller the value of , the more the patient's target type physiological indicator data in the postoperative period increases and the fewer cases of exceeding the normal range. Therefore, the better the patient's postoperative recovery is, the larger the corresponding postoperative recovery status indicator is. At the same time, all indicator values in the target type physiological indicator data are compared with the standard indicator value. The smaller the difference between all indicator values and the standard indicator value, the closer the historical patient's target type physiological indicator data in the postoperative period is to the normal situation. Therefore, it indicates that their postoperative recovery is good, and the corresponding postoperative recovery status indicator is larger. Among them, the standard indicator value refers to the reference value of the normal indicator value. The middle value of the normal range of the target type physiological indicator data can be used as the standard indicator value.

[0054] In this embodiment, the postoperative recovery status index of each historical patient is calculated using the following formula: ; Where: Indicates the postoperative recovery status index of each historical patient; The slope of the first fitted straight line representing the physiological indicator data of the target type corresponding to each historical patient in the postoperative period; The slope of the second fitting straight line representing the physiological indicator data of the target type corresponding to each historical patient in the postoperative period; The average value of the absolute value of the difference between all indicator values and the standard indicator values in the physiological indicator data of the target type corresponding to each historical patient in the postoperative period; Represents an infinite decimal greater than 0, used to prevent the denominator from being zero; Represents the hyperbolic tangent function, which is used to normalize values.

[0055] Through the above method, corresponding to each type of physiological indicator data, the postoperative recovery status index of each historical patient can be obtained. The larger the value of the postoperative recovery status index, the more it indicates that the physiological indicator data of the historical patient gradually approaches the normal level after the operation, and the patient's postoperative recovery is better; 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, the impact of the patient's preoperative medication is fed back based on the historical patient's postoperative status.

[0056] Furthermore, in some possible implementations, the above step S2012 of determining the initial anesthetic medication impact index may specifically include the following steps: With the operation time as the horizontal axis and the postoperative recovery status index as the vertical axis, curve fitting is performed on the postoperative recovery status index of each historical patient to obtain a first fitting curve; With the operation time as the horizontal axis and the preoperative anesthetic dose as the vertical axis, a curve fitting is performed on the preoperative anesthetic dose of each historical patient to obtain a second fitting curve; A mean square error between the first fitting curve and the second fitting curve is determined, and the mean square error is determined as an initial anesthetic medication impact index.

[0057] In this embodiment, to understand the impact of anesthetic medication on a patient's postoperative recovery, a curve fitting is performed on the postoperative recovery status indicators of each historical patient, based on the surgical time of each historical patient. This yields a fitted curve for the patient's postoperative recovery status over a period of time, which is recorded as the first fitted curve. Simultaneously, a curve fitting is performed on the preoperative anesthetic dose of each historical patient, based on the surgical time of each historical patient. This yields a fitted curve for the anesthetic dose over a period of time, which is recorded as the second fitted curve.

[0058] To understand the impact of anesthetic medication on postoperative recovery, the mean square error (MSE) between the first and second fitting curves was calculated. This MSE reflects the impact of anesthetic medication on postoperative recovery. A larger MSE value indicates a greater difference between the two fitting curves. Therefore, if the recovery state is poor and the anesthetic dosage is increasing, this indicates that preoperative anesthetic medication may have affected the patient's recovery. A smaller MSE indicates that the recovery state curve and the anesthetic dosage fitting curve have similar trends, indicating that the patient's preoperative medication dosage may have had a smaller impact on the patient, indicating that the patient may have a certain degree of drug tolerance. The MSE between the first and second fitting curves is used as the initial anesthetic medication impact indicator.

[0059] Furthermore, in some possible implementations, the above step S2013 of determining the correction coefficient of the anesthetic medication impact index may specifically include the following steps: Determine the fluctuation of each indicator value in the physiological indicator data of the target type corresponding to each historical patient during the intraoperative stage, and obtain the fluctuation sequence of each historical patient; Determining abnormal fluctuation values of physiological indicators of each historical patient based on the distribution of fluctuations in the fluctuation sequence; With the preoperative anesthesia dose as the horizontal axis and the abnormal fluctuation value of the physiological index as the vertical axis, a straight line is fitted to the abnormal fluctuation value of the physiological index of each historical patient to obtain a third fitting straight line; The slope value of the third fitting straight line is determined as the correction coefficient of the anesthetic medication influence index.

[0060] In this embodiment, for each historical patient's target type of physiological indicator data during the intraoperative phase, the absolute value of the difference between each indicator value in the physiological indicator data and its previous indicator value is recorded as the fluctuation of each indicator value, thereby obtaining a fluctuation sequence corresponding to all indicator values in the physiological indicator data. The maximum value in the fluctuation sequence is recorded as an abnormal fluctuation point, and the average value of each abnormal fluctuation point and its nearest other abnormal fluctuation points is determined to obtain a first average fluctuation; the average value of all fluctuations between each abnormal fluctuation point and its nearest other abnormal fluctuation points is determined to obtain a second average fluctuation; and the distance between each abnormal fluctuation point and its nearest other abnormal fluctuation points is determined. When the first average fluctuation is larger, the second average fluctuation is smaller, and the value of the interval distance is smaller, it indicates that the abnormal fluctuation points are more dense and the fluctuation values of the data points between the abnormal fluctuation points are smaller, thus indicating that the abnormal fluctuation of the physiological indicator data is more obvious. In this way, the abnormal fluctuation value of the physiological indicator of each historical patient can be determined.

[0061] In this embodiment, the abnormal fluctuation value of the physiological index of each historical patient can be calculated by the following formula: ; Where: Indicates the abnormal fluctuation values of physiological indicators of each historical patient; Indicates the number of abnormal fluctuation points in the fluctuation sequence of the physiological indicator data of the target type corresponding to each historical patient during the intraoperative stage, Indicates the volatility series The first average fluctuation corresponding to the abnormal fluctuation point, , Indicates the volatility series An abnormal fluctuation point, Indicates the volatility sequence with Other abnormal fluctuation points closest to the abnormal fluctuation point; Indicates the volatility series The second average volatility corresponding to the abnormal fluctuation point is obtained by The average value of all fluctuations between an abnormal fluctuation point and its nearest other abnormal fluctuation points is obtained; Indicates the volatility series The distance between an abnormal fluctuation point and its nearest abnormal fluctuation point can be obtained by The absolute value of the difference between the corresponding serial numbers of an abnormal fluctuation point and its nearest other abnormal fluctuation points in the volatility sequence is obtained; Represents an infinite decimal greater than 0, used to prevent the denominator from being zero; Represents the hyperbolic tangent function, which is used to normalize values.

[0062] According to the above method, for the physiological indicator data of the target type, the abnormal fluctuation value of the physiological indicator of each historical patient can be determined. With the preoperative anesthesia dose as the horizontal coordinate and the abnormal fluctuation value of the physiological indicator as the vertical coordinate, a straight line fitting is performed on the abnormal fluctuation value of the physiological indicator of each historical patient to obtain a third fitting straight line. The slope of the third fitting straight line is obtained. The smaller the slope, the more stable the physiological indicator of the target type during the patient's operation is as the anesthesia dose continues to increase, indicating that the anesthetic has a better effect on the patient's condition during the operation; the larger the slope, the more unstable the physiological indicator of the target type during the patient's operation is as the anesthesia dose increases, indicating that the anesthetic may cause an emergency situation during the patient's operation. The slope of the third fitting straight line is taken as the correction coefficient of the anesthetic drug influence index, which is used to correct the initial anesthetic drug influence index, thereby obtaining the corrected final anesthetic drug influence index.

[0063] Furthermore, in some possible implementations, such as Figure 4 As shown, the above step S202 determines the preoperative abnormality impact index, which may specifically include the following steps S2021-S2025: S2021: Determine the DTW distance value of the target type of physiological indicator data corresponding to each historical patient in the preoperative stage and the intraoperative stage, and obtain the physiological indicator distance value of each historical patient; S2022: Determine abnormal values of preoperative indicators for each historical patient based on changes in physiological indicator data of the target type corresponding to each historical patient during the preoperative stage; S2023: Determine the preoperative indicator abnormality impact parameter of each historical patient based on the preoperative indicator abnormal value, the physiological indicator abnormal fluctuation value, and the physiological indicator distance value; S2024: using the abnormal value of the preoperative indicator as the horizontal coordinate and the abnormal influencing parameter of the preoperative indicator as the vertical coordinate, performing a straight line fitting on the abnormal influencing parameter of the preoperative indicator of each historical patient to obtain a fourth fitting straight line; S2025: Determine the slope of the fourth fitting straight line as a preoperative abnormality impact indicator.

[0064] In this embodiment, a preoperative indicator abnormality value is determined for each historical patient based on changes in physiological indicator data of the target type corresponding to each historical patient during the preoperative period. This preoperative indicator abnormality value reflects the preoperative abnormality of the physiological indicator data of the target type. A DTW distance value is determined for each historical patient's physiological indicator data of the target type during the preoperative and intraoperative periods. This DTW distance value reflects the degree of similarity between the physiological indicator data of the target type corresponding to each historical patient during the preoperative and intraoperative periods. The smaller the DTW distance value, the higher the degree of similarity. Based on each historical patient's preoperative indicator abnormality value, physiological indicator abnormal fluctuation value, and physiological indicator distance value, a preoperative indicator abnormality impact parameter is determined for each historical patient. This parameter reflects the degree of influence of preoperative abnormalities in the physiological indicator data of the target type on abnormal fluctuations during surgery. The larger the preoperative indicator abnormality value and physiological indicator abnormal fluctuation value, and the smaller the DTW distance value, the more abnormal the physiological indicator data of the target type before surgery and the similar changes during surgery. Therefore, the greater the influence of the physiological indicator data of the target type before surgery on the abnormal fluctuations during surgery, and the larger the value of the corresponding preoperative indicator abnormality impact parameter.

[0065] In this embodiment, the abnormal impact parameter of the preoperative index of each historical patient can be calculated by the following formula: ; Where: is the abnormal influencing parameter of preoperative indicators of each historical patient; Indicates abnormal values of preoperative indicators for each historical patient; Indicates the abnormal fluctuation values of physiological indicators of each historical patient; Physiological indicator data representing the target type of each historical patient in the preoperative stage Physiological indicator data corresponding to the target type during the intraoperative stage of Distance value, the The value of is usually not zero; Represents the hyperbolic tangent function, which is used to normalize values.

[0066] According to the above method, the abnormal influencing parameters of preoperative indicators of each historical patient can be determined. With the abnormal value of the preoperative indicator as the horizontal coordinate and the abnormal influencing parameters of the preoperative indicator as the vertical coordinate, a straight line fitting is performed on the abnormal influencing parameters of the preoperative indicators of each historical patient to obtain a fourth fitting straight line, and the slope of the fourth fitting straight line is obtained. The larger the slope of the fourth fitting straight line, the higher the degree of abnormality of the physiological indicator data of the target type of the patient before the operation, and the more likely the physiological indicator data will fluctuate abnormally during the intraoperative stage. Therefore, it indicates that the abnormal fluctuation of the physiological indicator data of the target type of the patient during the intraoperative stage is more likely to be caused by preoperative anesthetic drugs.

[0067] Furthermore, in some possible implementations, the above step S2022 of determining abnormal values of preoperative indicators of each historical patient may specifically include the following steps: Determine abnormal data points that are outside the normal range in the physiological indicator data of the target type corresponding to each historical patient in the preoperative stage; Determining the abnormality of the abnormal data point based on the fluctuation of the indicator value at the abnormal data point and the density of the abnormal data point; Determine the average value of the fluctuation of each indicator value in the physiological indicator data of the target type corresponding to each historical patient in the preoperative stage to obtain the fluctuation mean; Determine the average value of the abnormality of all abnormal data points to obtain the average abnormality value; The product of the fluctuation mean and the abnormality mean is determined as the preoperative indicator abnormality value of each historical patient.

[0068] In this embodiment, for the physiological indicator data of the target type corresponding to each historical patient in the preoperative stage, the data points in the physiological indicator data that are outside the normal range are determined, and these data points are recorded as abnormal data points. The average value of the absolute value of the difference between each abnormal data point and its left and right adjacent data points is determined, and the average value is recorded as the fluctuation index. At the same time, the proportion of abnormal data points in the neighborhood of each abnormal data point is determined, and the proportion is recorded as the density of the abnormal data point. The product of the fluctuation index and the abnormal density is determined, and the product is recorded as the abnormality. Furthermore, based on the average fluctuation of all data points in the physiological indicator data and the average abnormality of all abnormal data points, the abnormal value of the preoperative indicator of each historical patient is determined.

[0069] Furthermore, in some possible implementations, in step S300, an anesthetic drug risk assessment model is constructed based on the risk weight, and the constructed anesthetic drug risk assessment model is used to perform an anesthetic drug risk assessment on real-time patients, including the following steps: when it is necessary to evaluate the preoperative anesthesia medication of real-time patients, different types of physiological indicator data of the real-time patients in the preoperative stage are obtained, and 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 physiological indicator characteristics, and the cumulative value of the product of all physiological indicator characteristics and the risk weight of the corresponding type of physiological indicator data, and using the normalization function to normalize the cumulative value, thereby obtaining the anesthetic drug risk assessment result of the real-time patient. The normalization function can be reasonably selected as needed, such as selecting The hyperbolic tangent function normalizes the accumulated value.

[0070] Based on the same inventive concept, the embodiment of the present invention also provides a device for assessing the risk of medication before anesthesia. Figure 5 As shown, the device includes: A data acquisition module is used to obtain the preoperative anesthesia dose and operation time of each historical patient as well as different types of physiological index data of each historical patient at different stages of the operation; The weight acquisition module is used to analyze the changes in different types of physiological indicator data of each historical patient at different surgical stages based on the preoperative anesthetic dose and operation time of each historical patient, and determine the risk weights of anesthetic drugs on different types of physiological indicators; The risk assessment module is used to construct an anesthetic medication risk assessment model based on the risk weights, and use the constructed anesthetic medication risk assessment model to perform real-time anesthetic medication risk assessment on patients.

[0071] It should be noted that the device provided in the above embodiment is only illustrated by 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.

[0072] Based on the same inventive concept, the embodiment of the present invention also provides a pre-anesthesia medication risk assessment system, such as Figure 6 As shown, the system includes: a memory 601, a processor 602, and a 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 execute any one of the pre-anesthesia medication risk assessment methods introduced above.

[0073] In embodiments of the present invention, the system can be divided into functional modules based on the above-described method examples. For example, these modules can correspond to individual functional modules, or two or more functions can be integrated into a single processing module. The integrated modules can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and represents only a logical functional division. In actual implementation, other division methods may be used.

[0074] Based on the same inventive concept, an embodiment of the present invention also provides a computer program product, which includes: computer program code, which, when running on a computer, enables the computer to execute any one of the pre-anesthesia medication risk assessment methods introduced above.

[0075] Based on the same inventive concept, an embodiment of the present invention also provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes any one of the pre-anesthesia medication risk assessment methods introduced above.

[0076] It should be noted that the above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for risk assessment of pre-anesthetic medication, characterized in that: The following steps are involved: Obtain the preoperative anesthesia dose and operation time of each historical patient as well as different types of physiological index data of each historical patient at different stages of the operation; Based on the preoperative anesthesia dose and operation time of each historical patient, the changes in different types of physiological indicators of each historical patient at different surgical stages are analyzed to determine the risk weights of anesthetic drugs on different types of physiological indicators; Based on the risk weights, an anesthetic medication risk assessment model is constructed, and the constructed anesthetic medication risk assessment model is used to perform real-time anesthetic medication risk assessment on patients.

2. A method for risk assessment of pre-anesthesia medication according to claim 1, characterized in that: Determine the risk weights that anesthetic medications impose on different types of physiological variables, including: Based on the changes in physiological indicator data of the target type corresponding to each historical patient during the intraoperative and postoperative stages, and combined with the preoperative anesthetic dose and operation time of each historical patient, an anesthetic drug impact index is determined. The anesthetic drug impact index reflects the impact of anesthetic drugs on the patient's postoperative recovery; According to the changes in physiological indicator data of the target type corresponding to each historical patient in the preoperative stage and the intraoperative stage, and the correlation between the changes in physiological indicator data of the target type corresponding to each historical patient in the preoperative stage and the intraoperative stage, a preoperative abnormality impact index is determined, wherein the preoperative abnormality impact index reflects the impact of the patient's preoperative physiological indicator abnormality on the intraoperative physiological indicator abnormality; Based on the anesthetic drug impact index and the preoperative abnormality impact index, the risk weight of the anesthetic drug on the physiological index of the target type is determined.

3. The method for risk assessment of pre-anesthesia medication according to claim 2, characterized in that: Determine the impact indicators of anesthetic medication, including: Determine the postoperative recovery status indicator of each historical patient based on the changes in physiological indicator data of the target type corresponding to each historical patient in the postoperative stage; Combined with the operation time of each historical patient, the correlation between the postoperative recovery status indicators and preoperative anesthetic doses of each historical patient was analyzed to determine the initial anesthetic drug impact indicators; According to the fluctuation of physiological index data of target type corresponding to each historical patient during the intraoperative stage, and combined with the preoperative anesthesia dose of each historical patient, the correction coefficient of the anesthetic medication impact index is determined; The anesthetic medication influence index correction coefficient is used to correct the initial anesthetic medication influence index to obtain a corrected final anesthetic medication influence index.

4. A method for risk assessment of pre-anesthesia medication according to claim 3, characterized in that: Determine the postoperative recovery status indicators for each historical patient, including: Determine abnormal points that exceed the normal range in the physiological indicator data of the target type corresponding to each historical patient in the postoperative period; Determining an abnormal value of the abnormal point according to data fluctuations at the abnormal point in the physiological indicator data of the target type; Performing straight line fitting on the outlier values of all the outliers to obtain a first fitting straight line; Performing straight line fitting on the physiological indicator data of the target type corresponding to each historical patient in the postoperative stage to obtain a second fitting straight line; The postoperative recovery status index of each historical patient is determined based on the difference between the slope of the first fitting straight line and the slope of the second fitting straight line, and the difference between each indicator value in the physiological indicator data of the target type corresponding to each historical patient in the postoperative stage and the standard indicator value.

5. A method for risk assessment of pre-anesthesia medication according to claim 4, characterized in that: Determining an outlier value of the outlier point includes: Determine a reference extreme value point for the abnormal point; if the abnormal point is higher than the normal range, the reference extreme value point is a minimum value point closest to 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 value point is a maximum value point closest to the abnormal point in the physiological indicator data of the target type; Determining the absolute value of the difference between the abnormal point and its reference extreme point, and the time difference between the abnormal point and its reference extreme point; A ratio of the absolute value of the difference to the time difference is determined as an outlier value of the outlier point.

6. The method for risk assessment of pre-anesthetic medication according to claim 3, characterized in that: Determine initial anesthetic medication impact indicators, including: With the operation time as the horizontal axis and the postoperative recovery status index as the vertical axis, curve fitting is performed on the postoperative recovery status index of each historical patient to obtain a first fitting curve; With the operation time as the horizontal axis and the preoperative anesthetic dose as the vertical axis, a curve fitting is performed on the preoperative anesthetic dose of each historical patient to obtain a second fitting curve; A mean square error between the first fitting curve and the second fitting curve is determined, and the mean square error is determined as an initial anesthetic medication impact index.

7. The method for risk assessment of pre-anesthesia medication according to claim 3, characterized in that: Determine the correction coefficient of the anesthetic drug impact index, including: Determine the fluctuation of each indicator value in the target type of physiological indicator data corresponding to each historical patient during the intraoperative stage to obtain a fluctuation sequence for each historical patient; determine the abnormal fluctuation value of the physiological indicator of each historical patient based on the distribution of the fluctuations in the fluctuation sequence; With the preoperative anesthesia dose as the horizontal axis and the abnormal fluctuation value of the physiological index as the vertical axis, a straight line is fitted to the abnormal fluctuation value of the physiological index of each historical patient to obtain a third fitting straight line; The slope value of the third fitting straight line is determined as the correction coefficient of the anesthetic medication influence index.

8. The method for risk assessment of pre-anesthesia medication according to claim 7, characterized in that: Determine preoperative abnormal impact indicators, including: Determine the DTW distance value of the physiological indicator data of the target type corresponding to each historical patient in the preoperative stage and the intraoperative stage, and obtain the physiological indicator distance value of each historical patient; Determine the abnormal value of the preoperative indicator of each historical patient according to the change of the physiological indicator data of the target type corresponding to each historical patient in the preoperative stage; Determine the abnormal preoperative index impact parameter of each historical patient based on the abnormal preoperative index value, the abnormal physiological index fluctuation value, and the physiological index distance value; With the abnormal value of the preoperative index as the horizontal axis and the abnormal influencing parameter of the preoperative index as the vertical axis, a straight line fitting is performed on the abnormal influencing parameter of the preoperative index of each historical patient to obtain a fourth fitting straight line; The slope of the fourth fitting straight line is determined as an indicator of preoperative abnormal influence.

9. The method for risk assessment of pre-anesthesia medication according to claim 8, characterized in that: Determine abnormal values of preoperative indicators for each historical patient, including: Determine abnormal data points that are outside the normal range in the physiological indicator data of the target type corresponding to each historical patient in the preoperative stage; Determining the abnormality of the abnormal data point based on the fluctuation of the indicator value at the abnormal data point and the density of the abnormal data point; Determine the average value of the fluctuation of each indicator value in the physiological indicator data of the target type corresponding to each historical patient in the preoperative stage to obtain the fluctuation mean; Determine the average value of the abnormality of all abnormal data points to obtain the average abnormality value; The product of the fluctuation mean and the abnormality mean is determined as the preoperative indicator abnormality value of each historical patient.

10. The method for risk assessment of pre-anesthesia medication according to claim 2, characterized in that: Determine the risk weights posed by anesthetic medications to target physiological parameters, including: Determining the product of the anesthetic drug impact index and the preoperative abnormality impact index to obtain an initial risk weight of the anesthetic drug on the physiological index of the target type; Determine the cumulative sum of the initial risk weights of anesthetic drugs on all types of physiological indicators to obtain the cumulative weight; The ratio of the initial risk weight of the anesthetic drug on the physiological index of the target type to the cumulative weight is determined to obtain the risk weight of the anesthetic drug on the physiological index of the target type.

Images