Method for analyzing dosage of anesthetic drugs during surgery based on three high-risk population groups

Abstract

This invention discloses a dosage analysis method for anesthetic drugs during surgery in patients with hypertension, hyperlipidemia, and hyperglycemia. This method integrates multi-source heterogeneous health data from the patient over the past five years to construct a personalized, structured health record. During anesthesia induction, based on the patient's individualized pharmacokinetic model and assessed drug interaction risks, it calculates and recommends precisely adjusted induction doses. During anesthesia maintenance, it innovatively decodes specific EEG signals to establish a dynamic mapping relationship between neurophysiological characteristics and pharmacokinetics. Based on EEG characteristics reflecting drug sensitivity and pain perception, it automatically and in real-time adjusts the predicted concentration of the target drug, achieving closed-loop precise control based on direct feedback from the central nervous system. The system automatically identifies all medications used by the patient, generates a drug interaction risk assessment report using a massive knowledge base, and dynamically updates the risk level and sends warnings during surgery based on real-time vital signs.

Description

Technical Field

[0001] This invention relates to the field of anesthetic drug dosage analysis technology, specifically a method for dosage analysis of anesthetic drugs during surgery in individuals with hypertension, hyperlipidemia, and diabetes. Background Technology

[0002] Precise dosage control of anesthetic drugs is crucial for ensuring surgical safety and anesthesia quality. For patients with hypertension, diabetes, and hyperlipidemia (collectively known as the "three highs") and other underlying conditions, their pathophysiological state is complex, and their responses to anesthetic drugs vary greatly, often resulting in significant alterations in pharmacokinetics and pharmacodynamics. This poses a significant challenge to traditional anesthesia protocols based on population average parameters, leading to a marked increase in the risks of drastic intraoperative hemodynamic fluctuations, excessively deep or shallow anesthesia, delayed recovery, and perioperative complications. Current clinical practice for these patients faces significant limitations in several key aspects of anesthesia management: Patients with hypertension, hyperlipidemia, and hyperglycemia often require long-term use of multiple medications for underlying disease management, such as beta-blockers, angiotensin-converting enzyme inhibitors, metformin, statins, and antiplatelet drugs. These drugs may interact with anesthetic drugs in complex pharmacokinetic (e.g., competing for metabolic enzymes) and pharmacodynamic (e.g., synergistic inhibition of circulation) interactions, significantly altering the expected effects and adverse reaction profiles of anesthetic drugs. Current risk assessment methods largely rely on static verification of medication lists during pre-anesthesia visits, lacking an intelligent system capable of integrating massive drug interaction knowledge bases, pharmacogenomics data, and clinical adverse event reports in real time, and dynamically and personally grading risks based on the patient's specific physiological state (e.g., liver and kidney function). This is especially true during surgical procedures, where the risk assessment is not fully assessed based on the patient's actual condition. The ability to dynamically track vital signs (such as sudden bradycardia and hypotension), assess the actual clinical impact of identified interaction risks, and provide timely warnings means that risk management remains merely a theoretical concept before surgery, making it difficult to translate into proactive intraoperative prevention and control measures. Furthermore, for complications such as severe hypotension, hypertensive crisis, and arrhythmia that are common in patients with hypertension, hyperlipidemia, and diabetes during surgery, the current clinical model generally only initiates identification and treatment procedures after the event occurs, which lacks foresight. Because the detailed medical history of each patient, the extent of target organ damage, real-time surgical stage information, and massive historical complication data are not fully utilized to build predictive models, it is impossible to assess the probability of complications before they occur. This increases decision-making pressure and the risk of delays in emergency situations, which is detrimental to the patient's perioperative safety. Summary of the Invention

[0003] The purpose of this invention is to provide a dosage analysis method for anesthetic drugs during surgery in patients with hypertension, hyperlipidemia, and hyperglycemia, in order to solve the problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a method for dose analysis of anesthetic drugs during surgery in individuals with hypertension, hyperlipidemia, and hyperglycemia, comprising the following steps: S1. Integrate all of the patient's medical records from the past five years to build a personal health record, and simultaneously enter the key examination data for this preoperative procedure; S2. Establish the dynamic relationship between neurophysiological activity and pharmacokinetics through EEG signal decoding, and adjust the predicted concentration of the target drug in real time according to specific EEG characteristics; S3. Automatically identify all medications used by the patient, generate a drug interaction risk assessment report based on multi-source data, dynamically update the risk level during the operation and push out early warnings and treatment suggestions; S4. Calculate individualized anesthesia depth and circulatory management target parameters by considering both surgical and physiological factors; S5. During the anesthesia induction phase, the dosage of induction drugs is calculated based on individualized pharmacokinetics. During the anesthesia maintenance phase, fully automated closed-loop anesthesia control is achieved by receiving monitoring data in real time at high frequency. S6. Through multidimensional physiological field signal acquisition and analysis, high-accuracy prediction of adverse events such as hypotension can be achieved. S7. Predict the probability of complications based on historical case data, and automatically generate personalized treatment plans for high-risk complications; S8. Real-time intraoperative correction of individualized pharmacokinetics, combined with analgesia database to generate personalized multimodal analgesia plans; S9. Postoperatively, automatically design multimodal analgesia programs, assess the risk of nonsteroidal anti-inflammatory drug use, and provide early warning and automatic intervention for opioid-related respiratory depression in high-risk patients. S10. An anesthesia quality report is automatically generated after each anesthesia. The pharmacokinetic model parameters, dose recommendation algorithm and risk assessment model weights are automatically fine-tuned by comparing the actual clinical results with the system prediction results. S11. Regularly analyze newly added cases to optimize algorithms and contingency plans, and generate knowledge update reports to push to physicians.

[0005] Preferably, step S1 specifically includes the following steps: A11. The system automatically collects and records the patient's demographic information, past medical history, surgical anesthesia history, and drug allergy history; A12. Focus on structured recording of the underlying disease course, current medication regimen, recent control level, and extent of target organ damage for hypertension, diabetes, and hyperlipidemia; A13. The system acquires key preoperative examination data, specifically including: The ambulatory blood pressure monitoring report three months before surgery, including mean blood pressure, blood pressure variability, and nocturnal blood pressure drop rate, is used to assess the diurnal rhythm of blood pressure. Recent glycated hemoglobin, fasting blood glucose, postprandial blood glucose test results, and continuous blood glucose monitoring data are used to assess the level and variability of glycemic control. A complete blood lipid test report, including total cholesterol, triglycerides, high-density lipoprotein cholesterol, and low-density lipoprotein cholesterol; The results of liver and kidney function tests, electrolyte tests, coagulation function tests, electrocardiograms, echocardiograms, carotid ultrasound, and lower extremity vascular ultrasound are used to comprehensively assess organ function and vascular status. A14. Automatically connect to and integrate multi-source heterogeneous data, wherein the multi-source heterogeneous data specifically includes: The hospital's internal electronic medical record system allows access to all of the patient's inpatient and outpatient records. A regional health information platform to obtain patients' medical treatment information from other medical institutions within the region; A database of wearable devices authorized by patients, synchronizing long-term home vital sign monitoring data; A15. Perform time-series alignment, structured processing, and fusion analysis on all medical records, examination and test reports, and medication records of the patient within the past five years; A16. Construct a personalized and standardized health data file containing health information throughout the entire life cycle, and automatically synchronize and enter all key examination data before this operation.

[0006] Preferably, step S2 specifically includes the following steps: S21. A high-density EEG electrode array is set on the patient's scalp to collect and decode cortical nerve oscillation signals related to drug sensitivity and pain perception in real time. S22. Establish a dynamic mapping relationship between neurophysiological characteristics and key pharmacokinetic parameters; S23. When an increase in the power of a specific frequency band of EEG reflecting drug sensitivity is detected, the predicted value of the propofol effect-room concentration is automatically lowered by 15%; when an increase in the synchronization activity of a specific frequency band of EEG reflecting pain perception is detected, the predicted value of the opioid target concentration is automatically increased by 20%.

[0007] Preferably, step S3 specifically includes the following steps: S31. Identify and list all medications the patient is currently taking, including categories such as antihypertensive drugs, hypoglycemic drugs, lipid-lowering drugs, antiplatelet drugs, and anticoagulants; S32. Real-time retrieval and integration of a comprehensive knowledge base containing massive amounts of drug interaction research literature, clinical adverse anesthetic event reports, and pharmacogenomics data; S33. Based on the patient's medication list and knowledge base information, generate an interactive drug interaction risk assessment report; the risk assessment report details the potential interaction mechanisms, risk levels, clinical evidence levels, and specific prevention and treatment measures. S34. The risk assessment report identifies key interaction risks that require close monitoring for commonly used anesthetic drugs. These key interaction risks specifically include: The combined use of β-blockers and anesthetic drugs (such as remifentanil and propofol) may result in synergistic circulatory depression and bradycardia. The combined use of metformin and iodine-containing contrast agents under certain conditions (such as renal insufficiency) may increase the risk of lactic acidosis. The combined use of statins with anesthetic drugs metabolized by the CYP3A4 enzyme (such as midazolam and fentanyl) may increase the risk of rhabdomyolysis. S35. During anesthesia and surgery, continuously receive real-time vital sign monitoring data of the patient, wherein the real-time vital sign monitoring data includes blood pressure, heart rate, and electrocardiogram; S36. Dynamically analyze real-time vital sign monitoring data, assess the immediate impact of previously identified drug interaction risks, and dynamically adjust the relevant risk levels. S37. When the monitoring data triggers the preset warning conditions, the system automatically pushes the warning information to the anesthesiologist's monitoring interface.

[0008] Preferably, step S4 specifically includes the following steps: S41. Analyze surgery-related information and patient physiological indicators; the surgery-related information includes surgery grade, estimated duration, estimated blood loss, surgical position, and expected changes in body temperature; the patient physiological indicators include cardiopulmonary reserve, cerebral oxygen metabolism rate, and basal metabolic rate. S42. Referencing a large amount of anesthesia record data from similar surgeries in historical data, calculate and set individualized target values ​​for anesthesia depth monitoring for patients, including the target range of the bispectral index, the target value of the entropy index, and the target interval of the anesthesia depth index. S43. Based on the patient's preoperative circulatory status and regulatory capacity, including baseline blood pressure level, duration of hypertension, degree of existing target organ damage, and individualized cerebral blood flow autoregulation curve, set preliminary circulatory management goals. S44. During the operation, the perfusion requirements of each organ during different stages of the operation are calculated in combination with the real-time progress and stage changes of the operation. The initial circulation management target is calculated and dynamically adjusted in real time. The parameters for real-time calculation and dynamic adjustment include: individualized mean arterial pressure target range, allowable fluctuation range of systolic blood pressure, heart rate control zone, stroke volume variability threshold reflecting volume responsiveness, and cardiac output target value.

[0009] Preferably, step S5 specifically includes the following steps: S51. During the anesthesia induction phase, based on the patient's lean body mass, individualized pharmacokinetics, and assessed drug interaction risks, calculate the dose, administration rate, and expected onset time of the anesthesia induction drug, wherein the anesthesia induction drug is propofol, etomidate, rocuronium bromide, or sufentanil. S52. For patients with hypertension, adjust the induction dose of propofol to 70%–85% of the usual dose; for patients with diabetes, adjust the initial dose of opioids to 80%–90% of the usual dose. S53. During the anesthesia maintenance phase, the monitored data is received at a high frequency of every 200 milliseconds, and the infusion parameters of anesthetic drugs and vasoactive drugs are optimized in real time.

[0010] Preferably, step S7 specifically includes the following steps: S71. By analyzing a database containing a large number of historical cases of anesthesia complications, analyze the correlation between individual patient characteristics, surgical type, anesthesia method and the occurrence of complications, and predict the probability of patients experiencing various complications such as severe hypotension, hypertensive crisis, arrhythmia and bronchospasm during surgery. S72. For complications with a predicted probability exceeding a set threshold of 10%, automatically generate personalized treatment plans; The personalized treatment plan includes a list of required medications, dosage calculations, routes of administration, expected effects, and key points for monitoring adverse reactions. It also clearly indicates the recommended starting or loading doses of nitroglycerin, nicardipine, phenylephrine, and amiodarone as emergency medications.

[0011] Preferably, step S8 specifically includes the following steps: S81. During anesthesia, trend data of blood drug concentration, end-tidal anesthetic gas concentration, and bispectral index of electroencephalogram are continuously collected to dynamically correct the individualized pharmacokinetic parameters of the patient, wherein the individualized pharmacokinetic parameters are volume of distribution and clearance rate. S82. The system can predict the blood concentration decay curves of various anesthetic drugs during critical postoperative periods. S83. Evaluate the efficacy, adverse reactions and satisfaction of different analgesia regimens in similar patient populations, and generate personalized multimodal analgesia regimens for current patients, including drug selection, administration mode, dose range, lockout time and background infusion rate.

[0012] Preferably, step S9 specifically includes the following steps: S91. During the postoperative analgesia phase, the system automatically designs a multimodal analgesia regimen that includes epidural block, transversus abdominis plane block, regional nerve block techniques, and combines selective COX-2 inhibitors, acetaminophen, and sustained-release opioids. S92. Before initiating nonsteroidal anti-inflammatory drugs (NSAIDs), the system automatically assesses the patient's renal function, bleeding risk, and gastrointestinal ulcer risk, and automatically prompts patients with renal insufficiency to discontinue or use non-selective NSAIDs with caution. S93. Connecting a smart analgesia pump system that integrates respiratory rate, blood oxygen saturation, end-tidal carbon dioxide, pupil diameter and skin conductance monitoring to patients receiving patient-controlled analgesia. S94. Early detection of respiratory depression characteristics caused by opioids, wherein the respiratory depression characteristics are a gradual decrease in respiratory rate and a decrease in tidal volume, and automatic reduction of background infusion rate by 50% before the respiratory rate falls below a safe threshold, and automatic suspension of infusion and issuance of an alarm when blood oxygen saturation falls below a safe value.

[0013] Preferably, step S10 specifically includes the following steps: S101. After each anesthesia session, the system automatically generates a structured anesthesia quality report. This report fully records all time-series data from the start of anesthesia induction to 24 hours post-surgery, including continuous vital signs, records of all medications used, adverse events that occurred, treatment measures taken, and the final clinical outcome. S102. Perform automated comparative analysis between the actual clinical results of this anesthesia and the various predictions made during the operation. The various predictions include the complication risk prediction in step S7 and the pharmacokinetic simulation results in step S8. S103. Adjust the core parameters and logic, specifically including: parameters of individualized pharmacokinetics, dosage recommendation algorithms for various drugs, and weights of risk assessment models; S11 specifically includes the following steps: S111. The system performs in-depth analysis of accumulated clinical data at fixed intervals, and performs batch analysis of all newly added anesthesia cases every week. It identifies new drug interaction risk factors, the correlation between patient physiological characteristics and complications from the population data, and optimizes the original drug dosage calculation formula and the updated complication management plan library. S113. On a quarterly basis, integrate recent analytical results with external guidelines to generate a knowledge update report and proactively push new clinically significant drug interactions, optimized individualized dosage adjustment plans, and suggested new or improved intraoperative monitoring indicators to anesthesiologists. S114. Save all learning processes, parameter adjustment records, and data iteration versions to the medical record system.

[0014] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure.

[0015] Compared with existing technologies, the beneficial effects of this invention are as follows: By integrating multi-source heterogeneous health data of patients over the past five years to construct a comprehensive personal health record, and combining it with an individualized pharmacokinetic model, the system can calculate and recommend precisely adjusted induction doses for patients with hypertension and diabetes during the anesthesia induction phase; by establishing a dynamic mapping relationship between neurophysiological characteristics and pharmacokinetics through high-density EEG monitoring, the system can adjust the predicted concentration of the target drug in real time and automatically based on specific EEG signals reflecting drug sensitivity or pain perception (such as changes in power in the Gamma and Theta bands) (e.g., reducing propofol effect-site concentration by 15% and increasing opioid concentration by 20%); based on the regulation of direct biofeedback from the central nervous system, it breaks through the traditional model that relies on vital signs and experience, realizing a qualitative change from group-based experience-based medication to individualized precise regulation, significantly improving the accuracy and safety of anesthesia; The system automatically identifies all patient medications and generates a targeted risk assessment report before surgery based on a massive drug interaction knowledge base. It specifically warns of high-risk interactions between commonly used medications (such as beta-blockers, metformin, and statins) and anesthetic drugs for patients with hypertension, hyperlipidemia, and diabetes. Instead of a static assessment, the system continuously receives vital sign data during surgery, dynamically analyzes the immediate impact of identified risks, and adjusts risk levels in real time. When a preset threshold is reached, it automatically sends warnings and treatment suggestions to the anesthesiologist. Based on historical complication data, the system predicts the probability of patients experiencing severe hypotension and other complications during surgery and automatically generates personalized treatment plans, including specific emergency medications and dosages, for high-risk complications. This proactive security system, from preoperative warnings to dynamic intraoperative monitoring and real-time plan preparation, transforms risk management from passive response to proactive prevention and rapid response, greatly enhancing the ability to handle complex situations and emergencies. Attached Figure Description

[0016] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0017] Figure 1 This is a schematic diagram illustrating all the method steps of the present invention; Figure 2 This is a schematic diagram illustrating the process of constructing a personalized health record for patients with hypertension, hyperlipidemia, and hyperglycemia based on surgery according to the present invention. Figure 3This is a schematic diagram of the anesthetic drug interaction risk assessment and dynamic early warning process for surgery in patients with hypertension, hyperlipidemia, and hyperglycemia according to the present invention; Figure 4 This is a schematic diagram illustrating the process of continuous optimization of postoperative analgesia and anesthesia quality for patients with hypertension, hyperlipidemia, and hyperglycemia based on the present invention. Detailed Implementation

[0018] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses consistent with some aspects of this disclosure as detailed in the appended claims.

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0020] Example 1: See Figures 1 to 4As shown in the embodiment of the present invention, the method for dose analysis of anesthetic drugs during surgery in patients with hypertension, hyperlipidemia, and hyperglycemia includes the following steps: S1, integrating all medical records of the patient over the past five years to construct a personal health record, and simultaneously entering key preoperative examination data; S2, establishing a dynamic relationship between neurophysiological activity and pharmacokinetics through EEG signal decoding, and adjusting the predicted concentration of the target drug in real time according to specific EEG characteristics; S3, automatically identifying all medications used by the patient, generating a drug interaction risk assessment report based on multi-source data, dynamically updating the risk level during surgery, and pushing early warnings and treatment suggestions; S4, calculating individualized anesthesia depth and circulatory management target parameters by comprehensively considering surgical and physiological factors; S5, calculating the induction drug dose based on individualized pharmacokinetics during the anesthesia induction phase, and achieving fully automated closed-loop anesthesia during the anesthesia maintenance phase by receiving monitoring data in real time at high frequency. Control measures include: S6. Accurately predicting adverse events such as hypotension through multidimensional physiological field signal acquisition and analysis; S7. Predicting complication probabilities based on historical case data and automatically generating personalized treatment plans for high-risk complications; S8. Real-time intraoperative correction of individualized pharmacokinetics and generation of personalized multimodal analgesia protocols in conjunction with an analgesia database; S9. Automatically designing multimodal analgesia protocols postoperatively, assessing the risks of nonsteroidal anti-inflammatory drug use, and providing early warning and automatic intervention for opioid-related respiratory depression in high-risk patients; S10. Automatically generating an anesthesia quality report after each anesthesia session, and automatically fine-tuning pharmacokinetic model parameters, dosage recommendation algorithms, and risk assessment model weights by comparing actual clinical results with system prediction results; S11. Regularly analyzing new cases to optimize algorithms and plans, generating knowledge update reports and pushing them to physicians. A comprehensive intelligent anesthesia management system for surgery in patients with hypertension, diabetes, and hyperlipidemia has been developed, achieving closed-loop management from preoperative assessment and intraoperative control to postoperative analgesia and continuous improvement. By dynamically linking EEG signals with pharmacokinetic models, real-time dose adjustment based on direct feedback from the central nervous system is realized, improving the precision and individualization of anesthesia. Automated drug interaction risk assessment and complication early warning mechanisms significantly improve anesthesia safety, especially for patients with hypertension, diabetes, and hyperlipidemia who have complex comorbidities. The system's continuous learning and knowledge updating functions ensure that the anesthesia protocol can keep pace with the times and continuously improve clinical quality.

[0021] Example 2: Step S1 specifically includes the following steps: A11. The system automatically collects and records the patient's demographic information, past medical history, surgical anesthesia history, and drug allergy history; A12. Focus on structured recording of the underlying disease course, current medication regimen, recent control level, and extent of target organ damage for hypertension, diabetes, and hyperlipidemia; A13. The system acquires key preoperative examination data, specifically including: The ambulatory blood pressure monitoring report three months before surgery, including mean blood pressure, blood pressure variability, and nocturnal blood pressure drop rate, is used to assess the diurnal rhythm of blood pressure. Recent glycated hemoglobin, fasting blood glucose, postprandial blood glucose test results, and continuous blood glucose monitoring data are used to assess the level and variability of glycemic control. A complete blood lipid test report, including total cholesterol, triglycerides, high-density lipoprotein cholesterol, and low-density lipoprotein cholesterol; The results of liver and kidney function tests, electrolyte tests, coagulation function tests, electrocardiograms, echocardiograms, carotid ultrasound, and lower extremity vascular ultrasound are used to comprehensively assess organ function and vascular status. A14. Automatically connect to and integrate multi-source heterogeneous data, wherein the multi-source heterogeneous data specifically includes: The hospital's internal electronic medical record system allows access to all of the patient's inpatient and outpatient records. A regional health information platform to obtain patients' medical treatment information from other medical institutions within the region; A database of wearable devices authorized by patients, synchronizing long-term home vital sign monitoring data; A15. Perform time-series alignment, structured processing, and fusion analysis on all medical records, examination and test reports, and medication records of the patient within the past five years; A16. Construct a personalized and standardized health data file containing health information throughout the entire life cycle, and automatically synchronize and enter all key examination data before this operation; Standardized collection and integration of patients' multi-source heterogeneous health data over the past five years have constructed a comprehensive and structured personal health record, providing a reliable data foundation for precision anesthesia. The records focus on the course of hypertension, hyperlipidemia, and hyperglycemia, medication use, control levels, and target organ damage, ensuring that anesthesia protocols are developed with full consideration of the patient's underlying disease status. Furthermore, the integration of long-term monitoring data from hospitals, regions, and wearable devices provides crucial information for assessing the diurnal rhythms and controlling variability of blood pressure and blood glucose, contributing to the development of more rational intraoperative circulatory and metabolic management strategies.

[0022] Step S2 specifically includes the following steps: S21. A high-density EEG electrode array is set on the patient's scalp to collect and decode cortical nerve oscillation signals related to drug sensitivity and pain perception in real time. S22. Establish a dynamic mapping relationship between neurophysiological characteristics and key pharmacokinetic parameters; S23. When an increase in EEG power in a specific frequency band reflecting drug sensitivity is detected, the predicted value of propofol effect-room concentration is automatically lowered by 15%; when an increase in EEG synchronization activity in a specific frequency band reflecting pain perception is detected, the predicted value of opioid target concentration is automatically increased by 20%. This innovative approach establishes a dynamic mapping relationship between neurophysiological characteristics and key pharmacokinetic parameters, providing new and direct biomarkers for real-time monitoring of anesthesia depth and drug effects. By detecting power changes in specific EEG frequency bands (such as Gamma and Theta), it can quantify the patient's drug sensitivity and pain perception status, thereby enabling automatic and quantitative drug concentration adjustments (such as downregulating propofol by 15% and upregulating opioids by 20%), making anesthesia control more precise and timely.

[0023] Step S3 specifically includes the following steps: S31. Identify and list all medications the patient is currently taking, including categories such as antihypertensive drugs, hypoglycemic drugs, lipid-lowering drugs, antiplatelet drugs, and anticoagulants; S32. Real-time retrieval and integration of a comprehensive knowledge base containing massive amounts of drug interaction research literature, clinical adverse anesthetic event reports, and pharmacogenomics data; S33. Based on the patient's medication list and knowledge base information, generate an interactive drug interaction risk assessment report; the risk assessment report details the potential interaction mechanisms, risk levels, clinical evidence levels, and specific prevention and treatment measures. S34. The risk assessment report identifies key interaction risks that require close monitoring for commonly used anesthetic drugs. These key interaction risks specifically include: The combined use of β-blockers and anesthetic drugs (such as remifentanil and propofol) may result in synergistic circulatory depression and bradycardia. The combined use of metformin and iodine-containing contrast agents under certain conditions (such as renal insufficiency) may increase the risk of lactic acidosis. The combined use of statins with anesthetic drugs metabolized by the CYP3A4 enzyme (such as midazolam and fentanyl) may increase the risk of rhabdomyolysis. S35. During anesthesia and surgery, continuously receive real-time vital sign monitoring data of the patient, wherein the real-time vital sign monitoring data includes blood pressure, heart rate, and electrocardiogram; S36. Dynamically analyze real-time vital sign monitoring data, assess the immediate impact of previously identified drug interaction risks, and dynamically adjust the relevant risk levels. S37. When the monitoring data triggers the preset warning conditions, the system automatically pushes the warning information to the anesthesiologist's monitoring interface. A comprehensive drug interaction risk assessment system based on a massive multi-source knowledge base has been established, which can automatically identify and assess the potential risks of patients' current medications being used in combination with anesthetic drugs. It specifically highlights certain high-risk interactions between commonly used drugs for patients with hypertension, hyperlipidemia, and diabetes and anesthetic drugs, providing key warnings and decision support for anesthesiologists. During surgery, the risk level is dynamically adjusted and automatic warnings are issued based on real-time vital sign monitoring data, realizing dynamic and proactive risk management and enhancing the ability to respond to emergencies.

[0024] Step S4 specifically includes the following steps: S41. Analyze surgery-related information and patient physiological indicators; the surgery-related information includes surgery grade, estimated duration, estimated blood loss, surgical position, and expected changes in body temperature; the patient physiological indicators include cardiopulmonary reserve, cerebral oxygen metabolism rate, and basal metabolic rate. S42. Referencing a large amount of anesthesia record data from similar surgeries in historical data, calculate and set individualized target values ​​for anesthesia depth monitoring for patients, including the target range of the bispectral index, the target value of the entropy index, and the target interval of the anesthesia depth index. S43. Based on the patient's preoperative circulatory status and regulatory capacity, including baseline blood pressure level, duration of hypertension, degree of existing target organ damage, and individualized cerebral blood flow autoregulation curve, set preliminary circulatory management goals. S44. During the operation, the perfusion requirements of each organ during different stages of the operation are calculated in combination with the real-time progress and stage changes of the operation. The initial circulation management target is calculated and dynamically adjusted in real time. The parameters for real-time calculation and dynamic adjustment include: individualized mean arterial pressure target range, allowable fluctuation range of systolic blood pressure, heart rate control zone, stroke volume variability threshold reflecting volume responsiveness, and cardiac output target value. By integrating surgical factors (such as grade, duration, and blood loss) and patient physiological indicators (such as cardiopulmonary function and cerebral oxygen metabolism rate), individualized anesthesia depth and circulatory management target parameters are calculated, realizing the transformation from experience-based anesthesia to goal-oriented anesthesia. During the operation, the circulatory management targets (such as mean arterial pressure, heart rate, and cardiac output) are dynamically adjusted in conjunction with real-time progress, which can better meet the perfusion needs of various organs at different stages of surgery and improve the precision and safety of hemodynamic management.

[0025] Step S5 specifically includes the following steps: S51. During the anesthesia induction phase, based on the patient's lean body mass, individualized pharmacokinetics, and assessed drug interaction risks, calculate the dose, administration rate, and expected onset time of the anesthesia induction drug, wherein the anesthesia induction drug is propofol, etomidate, rocuronium bromide, or sufentanil. S52. For patients with hypertension, adjust the induction dose of propofol to 70%–85% of the usual dose; for patients with diabetes, adjust the initial dose of opioids to 80%–90% of the usual dose. S53. During the maintenance of anesthesia, data is received at a high frequency of every 200 milliseconds, and the infusion parameters of anesthetic drugs and vasoactive drugs are optimized in real time. During the anesthesia induction phase, the precise induction dose is calculated by comprehensively considering the patient's individualized pharmacokinetic characteristics, lean body mass, and drug interaction risks. Specific dose adjustment ratios are provided for patients with hypertension and diabetes (70-85% for propofol and 80-90% for opioids), reflecting the principle of precision medication for specific populations. During the anesthesia maintenance phase, monitoring data is received at a high frequency (e.g., every 200 milliseconds), and the infusion of anesthetic and vasoactive drugs is optimized in real time, achieving fully automated closed-loop control, which helps maintain a more stable depth of anesthesia and circulatory status.

[0026] Step S7 specifically includes the following steps: S71. By analyzing a database containing a large number of historical cases of anesthesia complications, analyze the correlation between individual patient characteristics, surgical type, anesthesia method and the occurrence of complications, and predict the probability of patients experiencing various complications such as severe hypotension, hypertensive crisis, arrhythmia and bronchospasm during surgery. S72. For complications with a predicted probability exceeding a set threshold of 10%, automatically generate personalized treatment plans; The personalized treatment plan includes a list of required medications, dosage calculations, routes of administration, expected effects, and key points for monitoring adverse reactions, and clearly indicates the recommended starting or loading doses of nitroglycerin, nicardipine, phenylephrine, and amiodarone as emergency medications. Based on historical big data on anesthesia complications, it can predict the probability of patients experiencing various complications during surgery, achieving proactive early warning of complications and changing the traditional passive response model. For high-risk complications, it automatically generates personalized treatment plans that include specific emergency drugs, precise dosages, routes of administration, and key monitoring points, providing anesthesiologists with standardized emergency operation guidelines, shortening decision-making and preparation time in critical situations, and improving rescue efficiency.

[0027] Step S8 specifically includes the following steps: S81. During anesthesia, trend data of blood drug concentration, end-tidal anesthetic gas concentration, and bispectral index of electroencephalogram are continuously collected to dynamically correct the individualized pharmacokinetic parameters of the patient, wherein the individualized pharmacokinetic parameters are volume of distribution and clearance rate. S82. The system can predict the blood concentration decay curves of various anesthetic drugs during critical postoperative periods. S83. Evaluate the efficacy, adverse reactions and satisfaction of different analgesia regimens in similar patient populations, and generate personalized multimodal analgesia regimens for current patients, including drug selection, administration mode, dose range, lockout time and background infusion rate. During anesthesia, trend data is continuously collected and individualized pharmacokinetic model parameters (such as volume of distribution and clearance rate) are dynamically adjusted to make drug concentration prediction more closely reflect the patient's real-time physiological state and improve the accuracy of the model. Based on the adjusted model, the postoperative drug concentration decay curve is predicted, and combined with the analysis results of a large analgesia database, a personalized multimodal analgesia plan is generated for the patient, which includes elements such as drug selection, mode, dosage, and lockout time. This achieves seamless connection and precise management from intraoperative anesthesia to postoperative analgesia.

[0028] Step S9 specifically includes the following steps: S91. During the postoperative analgesia phase, the system automatically designs a multimodal analgesia regimen that includes epidural block, transversus abdominis plane block, regional nerve block techniques, and combines selective COX-2 inhibitors, acetaminophen, and sustained-release opioids. S92. Before initiating nonsteroidal anti-inflammatory drugs (NSAIDs), the system automatically assesses the patient's renal function, bleeding risk, and gastrointestinal ulcer risk, and automatically prompts patients with renal insufficiency to discontinue or use non-selective NSAIDs with caution. S93. Connecting a smart analgesia pump system that integrates respiratory rate, blood oxygen saturation, end-tidal carbon dioxide, pupil diameter and skin conductance monitoring to patients receiving patient-controlled analgesia. S94. Early detection of respiratory depression characteristics caused by opioids, wherein the respiratory depression characteristics are a gradual decrease in respiratory rate and a decrease in tidal volume, and automatic reduction of background infusion rate by 50% before respiratory rate falls below a safe threshold, and automatic suspension of infusion and issuance of alarm when blood oxygen saturation falls below a safe value. During the postoperative analgesia phase, the system automatically designs multimodal protocols incorporating various regional nerve block techniques and drug combinations, and automatically assesses the risks of using nonsteroidal anti-inflammatory drugs (NSAIDs) (especially in patients with renal insufficiency). This helps to minimize the risk of adverse drug reactions while improving analgesia efficacy. It connects to an intelligent analgesia pump that integrates multiple physiological parameter monitoring for high-risk patients receiving patient-controlled analgesia (such as diabetic patients), and uses pattern recognition technology to provide early warnings of respiratory depression caused by opioids, enabling automatic intervention (such as reducing the infusion rate or pausing the infusion in advance). This significantly improves the safety of postoperative analgesia and effectively prevents serious adverse respiratory events.

[0029] Specifically, step S10 includes the following steps: S101. After each anesthesia session, the system automatically generates a structured anesthesia quality report. This report fully records all time-series data from the start of anesthesia induction to 24 hours post-surgery, including continuous vital signs, records of all medications used, adverse events that occurred, treatment measures taken, and the final clinical outcome. S102. Perform automated comparative analysis between the actual clinical results of this anesthesia and the various predictions made during the operation. The various predictions include the complication risk prediction in step S7 and the pharmacokinetic simulation results in step S8. S103. Adjust the core parameters and logic, specifically including: parameters of individualized pharmacokinetics, dosage recommendation algorithms for various drugs, and weights of risk assessment models; S11 specifically includes the following steps: S111. The system performs in-depth analysis of accumulated clinical data at fixed intervals, and performs batch analysis of all newly added anesthesia cases every week. It identifies new drug interaction risk factors, the correlation between patient physiological characteristics and complications from the population data, and optimizes the original drug dosage calculation formula and the updated complication management plan library. S113. On a quarterly basis, integrate recent analytical results with external guidelines to generate a knowledge update report and proactively push new clinically significant drug interactions, optimized individualized dosage adjustment plans, and suggested new or improved intraoperative monitoring indicators to anesthesiologists. S114. Save all learning processes, parameter adjustment records, and data iteration versions to the medical record system; By automatically generating structured quality reports after each anesthesia session and comparing actual clinical outcomes with various system predictions (such as complication risk and pharmacokinetic simulations), the system can objectively assess anesthesia quality and performance. Based on the comparative analysis results, the system automatically fine-tunes its core parameters, algorithms, and model weights, forming a closed-loop self-optimization mechanism that allows the system to learn and continuously improve from each clinical practice. Regular (weekly, quarterly) in-depth analysis of new clinical data optimizes calculation formulas, updates treatment plans, integrates the latest guidelines, and generates knowledge update reports that are pushed to physicians, ensuring the timely updating and evolution of the entire system's knowledge and enabling it to adapt to the development and changes in clinical practice. All learning and iteration processes are securely recorded, ensuring the traceability of system development.

[0030] Example 3: Intelligent anesthesia management for an elderly patient with hypertension and diabetes undergoing laparoscopic cholecystectomy: Patient profile: Mr. Zhang, 68 years old, male, height 170cm, weight 80kg, is scheduled to undergo laparoscopic cholecystectomy due to gallstones; the patient has a 10-year history of hypertension, and has been taking amlodipine and bisoprolol for a long time, with blood pressure control being relatively good, but ambulatory blood pressure monitoring shows that his diurnal rhythm has disappeared (non-dipper pattern); he has had type 2 diabetes for 8 years, which is controlled by oral metformin, with a recent glycated hemoglobin of 7.2% and large fluctuations in blood glucose; Before anesthesia, the system integrated all of the patient's medical records from the past 5 years at the hospital and the regional medical platform, and synchronized their recent examination data and long-term monitoring data from wearable devices. The system focused on analyzing the ambulatory blood pressure report, continuous blood glucose monitoring, electrocardiogram (suggesting high voltage in the left ventricle), and carotid ultrasound (suggesting plaque in the right carotid artery), and constructed a structured personal health record, providing a detailed data basis for anesthesia decision-making. Prior to anesthesia induction, the system calculated a precise induction dose based on the patient's lean body mass, individualized pharmacokinetic model, and assessed drug interaction risks. Given the patient's history of hypertension and bisoprolol administration, the system adjusted the recommended induction dose of propofol to 80% of the usual dose. Simultaneously, considering the potential impact of diabetes on pain perception, the initial dose of the opioid sufentanil was adjusted to 85% of the usual dose. During anesthesia induction and maintenance, the system plays a central role. Through high-density EEG monitoring, the system establishes a dynamic relationship between the patient's neurophysiological activity and pharmacokinetics. For example, after administering the initial dose of propofol, the system detects an abnormal increase in power in a specific EEG frequency band reflecting drug sensitivity, and automatically lowers the predicted effect-site concentration of propofol by 15%. During surgical skin incision stimulation, the system captures an increase in EEG signals reflecting pain perception, and then automatically increases the target predicted concentration of remifentanil by 20%, achieving precise dose adjustment based on direct feedback from the central nervous system. The preoperative drug interaction risk assessment report automatically generated by the system specifically warned of the high risk of synergistic circulatory depression and bradycardia between the patient's bisoprolol and anesthetic drugs, and also highlighted the potential risks of metformin in the context of using iodine-containing contrast agents during surgery. During anesthesia induction, when the patient's heart rate dropped from 70 beats / min to 45 beats / min, the system dynamically raised the risk level to extremely high based on real-time vital signs and popped up an alert on the monitoring interface, recommending the administration of atropine 0.3mg and guiding the anesthesiologist to handle the situation promptly. Based on the patient's specific condition, the system comprehensively considered surgical information (laparoscopic surgery, effects of pneumoperitoneum) and the patient's physiological indicators (hypertension, diabetes, non-dipper blood pressure) to set individualized management goals: maintaining the anesthesia depth BIS value at 45-55 and the mean arterial pressure at 75-90 mmHg; during the operation, when the establishment of pneumoperitoneum led to an increase in the patient's stroke volume variability, the system optimized the infusion parameters of vasoactive drugs in real time to maintain stable blood pressure; during the critical dissection phase of the operation, the system dynamically adjusted the lower limit of mean arterial pressure management based on the real-time assessment of the intensity of surgical stimulation to ensure perfusion of vital organs; Based on historical complication data, the system predicted that the patient had an 18% probability of developing severe hypotension during the operation and automatically generated a personalized treatment plan, listing detailed treatment steps including the recommended dose of phenylephrine. During the maintenance of anesthesia, the system also continuously collected data, dynamically corrected the patient's pharmacokinetic parameters, and predicted the concentration decay curve of postoperative analgesics accordingly. As the surgery was nearing its end, the system generated a personalized multimodal analgesia plan for the patient based on the revised pharmacokinetic model and comparison results with a large analgesia database. This plan recommended preoperative ultrasound-guided bilateral transversus abdominis plane block and included a patient-controlled intravenous analgesia pump primarily composed of sufentanil and flurbiprofen. The system automatically assessed the patient's renal function as normal, suggesting the use of this nonsteroidal anti-inflammatory drug (NSAID) regimen, but recommended monitoring of renal function. The analgesia pump was connected to an intelligent system integrating respiratory, blood oxygen, and end-tidal carbon dioxide monitoring. Postoperatively, when the system detected an early, progressively decreasing respiratory rate through pattern recognition, it automatically reduced the background infusion rate of the analgesia pump by 50% before blood oxygen saturation decreased, successfully preventing opioid-related respiratory depression.

[0031] After the anesthesia was completed, the system automatically generated a complete anesthesia quality report and compared the actual intraoperative hypotension events with the predictive model. Based on the analysis results, the system automatically fine-tuned the model parameters used to predict the occurrence time of hypotension events in similar patients. In subsequent periodic system analyses, the newly added case data enabled the system to continuously optimize its algorithm and contingency plan library. For example, a new association between bisoprolol and certain opioids and emergent hypotension in diabetic patients was discovered, and the knowledge base was updated accordingly. This new warning information was pushed to clinicians through the quarterly knowledge update report.

[0032] Example 4: Intelligent anesthesia management for an elderly patient with hyperlipidemia who had been taking statins for a long time undergoing knee replacement surgery; Patient Li, a 72-year-old male, was scheduled for total knee arthroplasty due to severe osteoarthritis. He had a 15-year history of hyperlipidemia and was taking atorvastatin 20mg once daily for lipid-lowering. The system automatically integrated his lipid profile, carotid ultrasound (showing multiple plaques), and long-term medication records during preoperative assessment. In the drug interaction risk assessment, the system highlighted that atorvastatin is metabolized by CYP3A4 and may interact with anesthetic drugs used during surgery (such as fentanyl and midazolam), increasing the risk of rhabdomyolysis. It recommended avoiding the use of drugs metabolized by this enzyme during surgery or strengthening creatine kinase monitoring. Based on this warning, the anesthesiologist selected an alternative analgesia regimen that does not involve cytokinase metabolism. During surgery, the system monitored the patient's vital signs in real time. Considering the significant surgical trauma and blood loss, the target range for mean arterial pressure was set at a relatively high level (80-95). (mmHg) to ensure perfusion of vital organs (especially the brain and kidneys with pre-existing vascular lesions); before the end of the operation, the system predicted the postoperative concentration decay of opioids based on an individualized pharmacokinetic model, and combined with the patient's age and type of surgery, generated a multimodal analgesia regimen based on myofascial release blockade + selective cyclooxygenase-2 inhibitor, and suggested the priority use of acetaminophen to reduce the risk of additive liver and kidney effects that statins may have; postoperatively, the system monitored for the occurrence of no expected severe myalgia or renal dysfunction events, and used this negative result data to optimize the risk assessment model of statins and specific anesthesia regimens.

[0033] Example 5: Anesthesia management of an obese patient with hypertension and sleep apnea undergoing bariatric surgery; Patient Wang, a 45-year-old male with a body mass index (BMI) of 38 kg / m², was diagnosed with obesity, severe obstructive sleep apnea (OSA), and hypertension, and was taking valsartan to control his blood pressure. He underwent laparoscopic sleeve gastrectomy. The system integrated his polysomnography report (indicating severe OSA), ambulatory blood pressure monitoring (significantly elevated nocturnal blood pressure), and body fat composition analysis preoperatively. The preoperative risk assessment report specifically emphasized the increased sensitivity of OSA patients to opioids and the risk of airway obstruction and respiratory depression. During anesthesia induction, the system reduced the initial dose of the recommended opioid sufentanil to 70% of the usual dose. Intraoperatively, the system closely monitored the depth of anesthesia using high-density EEG monitoring to avoid delayed awakening due to excessive anesthesia. During pneumoperitoneum establishment and positional changes, the system dynamically increased positive end-expiratory pressure (PEEP) based on the patient's physiological characteristics of obesity, OSA, and hypertension. The system recommends parameters to maintain optimal oxygenation. Postoperatively, the system-generated analgesia protocol is centered on regional nerve blocks (bilateral transverse abdominis plane block + erector spinae plane block), with intravenous analgesia using only the minimum necessary dose of opioids and explicitly prohibiting sedative analgesics. The patient is connected to an intelligent analgesia pump integrated with respiratory monitoring. In the recovery room, by analyzing respiratory waveforms, blood oxygen saturation, and end-tidal carbon dioxide trends, the system automatically reduces the background infusion rate of the analgesia pump before the patient experiences significant respiratory apnea events and issues early warnings of respiratory depression, allowing medical staff to intervene in advance and avoid serious adverse respiratory events. In this case, the system's accurate early warning and automatic intervention functions for high-risk OSA patients were effectively validated, and the relevant data were used to optimize the postoperative analgesia management model for obese patients with OSA.

[0034] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

[0035] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope of this disclosure is indicated by the following claims.

Claims

1. A dosage analysis method for anesthetic drugs during surgery in individuals with hypertension, hyperlipidemia, and hyperglycemia, characterized in that... Includes the following steps: S1. Integrate all of the patient's medical records from the past five years to build a personal health record, and simultaneously enter the key examination data for this preoperative procedure; S2. Establish the dynamic relationship between neurophysiological activity and pharmacokinetics through EEG signal decoding, and adjust the predicted concentration of the target drug in real time according to specific EEG characteristics; S3. Automatically identify all medications used by the patient, generate a drug interaction risk assessment report based on multi-source data, dynamically update the risk level during the operation and push out early warnings and treatment suggestions; S4. Calculate individualized anesthesia depth and circulatory management target parameters by considering both surgical and physiological factors; S5. During the anesthesia induction phase, the dosage of induction drugs is calculated based on individualized pharmacokinetics. During the anesthesia maintenance phase, fully automated closed-loop anesthesia control is achieved by receiving monitoring data in real time at high frequency. S6. Through multidimensional physiological field signal acquisition and analysis, high-accuracy prediction of adverse events such as hypotension can be achieved. S7. Predict the probability of complications based on historical case data, and automatically generate personalized treatment plans for high-risk complications; S8. Real-time intraoperative correction of individualized pharmacokinetics, combined with analgesia database to generate personalized multimodal analgesia plans; S9. Postoperatively, automatically design multimodal analgesia programs, assess the risk of nonsteroidal anti-inflammatory drug use, and provide early warning and automatic intervention for opioid-related respiratory depression in high-risk patients. S10. An anesthesia quality report is automatically generated after each anesthesia. The pharmacokinetic model parameters, dose recommendation algorithm and risk assessment model weights are automatically fine-tuned by comparing the actual clinical results with the system prediction results. S11. Regularly analyze newly added cases to optimize algorithms and contingency plans, and generate knowledge update reports to push to physicians.

2. The dosage analysis method for anesthetic drugs during surgery in patients with hypertension, hyperlipidemia, and hyperglycemia according to claim 1, characterized in that, Step S1 specifically includes the following steps: A11. The system automatically collects and records the patient's demographic information, past medical history, surgical anesthesia history, and drug allergy history; A12. Focus on structured recording of the underlying disease course, current medication regimen, recent control level, and extent of target organ damage for hypertension, diabetes, and hyperlipidemia; A13. The system acquires key preoperative examination data, specifically including: The ambulatory blood pressure monitoring report three months before surgery, including mean blood pressure, blood pressure variability, and nocturnal blood pressure drop rate, is used to assess the diurnal rhythm of blood pressure. Recent glycated hemoglobin, fasting blood glucose, postprandial blood glucose test results, and continuous blood glucose monitoring data are used to assess the level and variability of glycemic control. A complete blood lipid test report, including total cholesterol, triglycerides, high-density lipoprotein cholesterol, and low-density lipoprotein cholesterol; The results of liver and kidney function tests, electrolyte tests, coagulation function tests, electrocardiograms, echocardiograms, carotid ultrasound, and lower extremity vascular ultrasound are used to comprehensively assess organ function and vascular status. A14. Automatically connect to and integrate multi-source heterogeneous data, wherein the multi-source heterogeneous data specifically includes: The hospital's internal electronic medical record system allows access to all of the patient's inpatient and outpatient records. A regional health information platform to obtain patients' medical treatment information from other medical institutions within the region; A database of wearable devices authorized by patients, synchronizing long-term home vital sign monitoring data; A15. Perform time-series alignment, structured processing, and fusion analysis on all medical records, examination and test reports, and medication records of the patient within the past five years; A16. Construct a personalized and standardized health data file containing health information throughout the entire life cycle, and automatically synchronize and enter all key examination data before this operation.

3. The dosage analysis method for anesthetic drugs during surgery in patients with hypertension, hyperlipidemia, and hyperglycemia according to claim 2, characterized in that, Step S2 specifically includes the following steps: S21. A high-density EEG electrode array is set on the patient's scalp to collect and decode cortical nerve oscillation signals related to drug sensitivity and pain perception in real time. S22. Establish a dynamic mapping relationship between neurophysiological characteristics and key pharmacokinetic parameters; S23. When an increase in the power of a specific frequency band of EEG reflecting drug sensitivity is detected, the predicted value of the propofol effect-room concentration is automatically lowered by 15%; when an increase in the synchronization activity of a specific frequency band of EEG reflecting pain perception is detected, the predicted value of the opioid target concentration is automatically increased by 20%.

4. The dosage analysis method for anesthetic drugs during surgery in patients with hypertension, hyperlipidemia, and hyperglycemia according to claim 3, characterized in that, Step S3 specifically includes the following steps: S31. Identify and list all medications the patient is currently taking, including categories such as antihypertensive drugs, hypoglycemic drugs, lipid-lowering drugs, antiplatelet drugs, and anticoagulants; S32. Real-time retrieval and integration of a comprehensive knowledge base containing massive amounts of drug interaction research literature, clinical adverse anesthetic event reports, and pharmacogenomics data; S33. Based on the patient's medication list and knowledge base information, generate an interactive drug interaction risk assessment report; the risk assessment report details the potential interaction mechanisms, risk levels, clinical evidence levels, and specific prevention and treatment measures. S34. The risk assessment report identifies key interaction risks that require close monitoring for commonly used anesthetic drugs. These key interaction risks specifically include: The combined use of β-blockers and anesthetic drugs (such as remifentanil and propofol) may result in synergistic circulatory depression and bradycardia. The combined use of metformin and iodine-containing contrast agents under certain conditions (such as renal insufficiency) may increase the risk of lactic acidosis. The combined use of statins with anesthetic drugs metabolized by the CYP3A4 enzyme (such as midazolam and fentanyl) may increase the risk of rhabdomyolysis. S35. During anesthesia and surgery, continuously receive real-time vital sign monitoring data of the patient, wherein the real-time vital sign monitoring data includes blood pressure, heart rate, and electrocardiogram; S36. Dynamically analyze real-time vital sign monitoring data, assess the immediate impact of previously identified drug interaction risks, and dynamically adjust the relevant risk levels. S37. When the monitoring data triggers the preset warning conditions, the system automatically pushes the warning information to the anesthesiologist's monitoring interface.

5. The dosage analysis method for anesthetic drugs during surgery in patients with hypertension, hyperlipidemia, and hyperglycemia according to claim 4, characterized in that, Step S4 specifically includes the following steps: S41. Analyze surgery-related information and patient physiological indicators; the surgery-related information includes surgery grade, estimated duration, estimated blood loss, surgical position, and expected changes in body temperature; the patient physiological indicators include cardiopulmonary reserve, cerebral oxygen metabolism rate, and basal metabolic rate. S42. Referencing a large amount of anesthesia record data from similar surgeries in historical data, calculate and set individualized target values ​​for anesthesia depth monitoring for patients, including the target range of the bispectral index, the target value of the entropy index, and the target interval of the anesthesia depth index. S43. Based on the patient's preoperative circulatory status and regulatory capacity, including baseline blood pressure level, duration of hypertension, degree of existing target organ damage, and individualized cerebral blood flow autoregulation curve, set preliminary circulatory management goals. S44. During the operation, the perfusion requirements of each organ during different stages of the operation are calculated in combination with the real-time progress and stage changes of the operation. The initial circulation management target is calculated and dynamically adjusted in real time. The parameters for real-time calculation and dynamic adjustment include: individualized mean arterial pressure target range, allowable fluctuation range of systolic blood pressure, heart rate control zone, stroke volume variability threshold reflecting volume responsiveness, and cardiac output target value.

6. The dosage analysis method for anesthetic drugs during surgery in patients with hypertension, hyperlipidemia, and hyperglycemia according to claim 5, characterized in that, Step S5 specifically includes the following steps: S51. During the anesthesia induction phase, based on the patient's lean body mass, individualized pharmacokinetics, and assessed drug interaction risks, calculate the dose, administration rate, and expected onset time of the anesthesia induction drug, wherein the anesthesia induction drug is propofol, etomidate, rocuronium bromide, or sufentanil. S52. For patients with hypertension, adjust the induction dose of propofol to 70%–85% of the usual dose; for patients with diabetes, adjust the initial dose of opioids to 80%–90% of the usual dose. S53. During the anesthesia maintenance phase, the monitored data is received at a high frequency of every 200 milliseconds, and the infusion parameters of anesthetic drugs and vasoactive drugs are optimized in real time.

7. The dosage analysis method for anesthetic drugs during surgery in patients with hypertension, hyperlipidemia, and hyperglycemia according to claim 6, characterized in that, Step S7 specifically includes the following steps: S71. By analyzing a database containing a large number of historical cases of anesthesia complications, analyze the correlation between individual patient characteristics, surgical type, anesthesia method and the occurrence of complications, and predict the probability of patients experiencing various complications such as severe hypotension, hypertensive crisis, arrhythmia and bronchospasm during surgery. S72. For complications with a predicted probability exceeding a set threshold of 10%, automatically generate personalized treatment plans; The personalized treatment plan includes a list of required medications, dosage calculations, routes of administration, expected effects, and key points for monitoring adverse reactions. It also clearly indicates the recommended starting or loading doses of nitroglycerin, nicardipine, phenylephrine, and amiodarone as emergency medications.

8. The dosage analysis method for anesthetic drugs during surgery in patients with hypertension, hyperlipidemia, and hyperglycemia according to claim 7, characterized in that, Step S8 specifically includes the following steps: S81. During anesthesia, trend data of blood drug concentration, end-tidal anesthetic gas concentration, and bispectral index of electroencephalogram are continuously collected to dynamically correct the individualized pharmacokinetic parameters of the patient, wherein the individualized pharmacokinetic parameters are volume of distribution and clearance rate. S82. The system can predict the blood concentration decay curves of various anesthetic drugs during critical postoperative periods. S83. Evaluate the efficacy, adverse reactions and satisfaction of different analgesia regimens in similar patient populations, and generate personalized multimodal analgesia regimens for current patients, including drug selection, administration mode, dose range, lockout time and background infusion rate.

9. The dosage analysis method for anesthetic drugs during surgery in patients with hypertension, hyperlipidemia, and hyperglycemia according to claim 8, characterized in that, Step S9 specifically includes the following steps: S91. During the postoperative analgesia phase, the system automatically designs a multimodal analgesia regimen that includes epidural block, transversus abdominis plane block, regional nerve block techniques, and combines selective COX-2 inhibitors, acetaminophen, and sustained-release opioids. S92. Before initiating nonsteroidal anti-inflammatory drugs (NSAIDs), the system automatically assesses the patient's renal function, bleeding risk, and gastrointestinal ulcer risk, and automatically prompts patients with renal insufficiency to discontinue or use non-selective NSAIDs with caution. S93. Connecting a smart analgesia pump system that integrates respiratory rate, blood oxygen saturation, end-tidal carbon dioxide, pupil diameter and skin conductance monitoring to patients receiving patient-controlled analgesia. S94. Early detection of respiratory depression characteristics caused by opioids, wherein the respiratory depression characteristics are a gradual decrease in respiratory rate and a decrease in tidal volume, and automatic reduction of background infusion rate by 50% before the respiratory rate falls below a safe threshold, and automatic suspension of infusion and issuance of an alarm when blood oxygen saturation falls below a safe value.

10. The dosage analysis method for anesthetic drugs during surgery in patients with hypertension, hyperlipidemia, and hyperglycemia according to claim 9, characterized in that, Step S10 specifically includes the following steps: S101. After each anesthesia session, the system automatically generates a structured anesthesia quality report. This report fully records all time-series data from the start of anesthesia induction to 24 hours post-surgery, including continuous vital signs, records of all medications used, adverse events that occurred, treatment measures taken, and the final clinical outcome. S102. Perform automated comparative analysis between the actual clinical results of this anesthesia and the various predictions made during the operation. The various predictions include the complication risk prediction in step S7 and the pharmacokinetic simulation results in step S8. S103. Adjust the core parameters and logic, specifically including: parameters of individualized pharmacokinetics, dosage recommendation algorithms for various drugs, and weights of risk assessment models; S11 specifically includes the following steps: S111. The system performs in-depth analysis of accumulated clinical data at fixed intervals, and performs batch analysis of all newly added anesthesia cases every week. It identifies new drug interaction risk factors, the correlation between patient physiological characteristics and complications from the population data, and optimizes the original drug dosage calculation formula and the updated complication management plan library. S113. On a quarterly basis, integrate recent analytical results with external guidelines to generate a knowledge update report and proactively push new clinically significant drug interactions, optimized individualized dosage adjustment plans, and suggested new or improved intraoperative monitoring indicators to anesthesiologists. S114. Save all learning processes, parameter adjustment records, and data iteration versions to the medical record system.

Images