Method, system and terminal for evaluating surgical anesthesia quality
By obtaining physiological monitoring data and anesthesia drug use records of surgical patients, and evaluating the quality of anesthesia, the problems of lag and limitations of anesthesia quality evaluation in traditional methods are solved, and real-time and objective anesthesia quality monitoring and optimization suggestions are achieved.
Patent Information
- Application Number
- CN202411296293.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-18
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-09-18
AI Technical Summary
The traditional method of evaluation of anesthesia quality relies on the experience of the anesthesiologist and postoperative patient feedback, and cannot fully reflect the real-time status during the anesthesia process, resulting in lag and limitations in the evaluation.
By obtaining physiological monitoring data of surgical patients, including respiratory rate and oxygen saturation, combined with anesthetic drug use records, physiological stability and depth of anesthesia assessment, anesthesia quality scores are calculated, and a detailed anesthesia quality feedback report is generated.
Real-time physiological status monitoring of the surgical anesthesia process is realized, which reduces the evaluation lag, improves the objectivity and timeliness of the anesthesia quality, and provides optimization suggestions to improve the safety and effectiveness of the surgical procedure.
Smart Images

Figure CN118824576B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of anesthesia quality evaluation, and in particular to a method, system and terminal for evaluating surgical anesthesia quality. Background Art
[0002] During surgery, the evaluation of anesthesia quality is crucial to ensure patient safety and surgical success. Anesthesia-related physiological data, such as electroencephalogram (EEG), electrocardiogram (ECG), respiratory rate, and blood oxygen saturation, are collected in real time through a variety of sensors and data analysis. The collected data is transmitted to the processing unit, and advanced data analysis technology is used to comprehensively evaluate various parameters during the anesthesia process. Combined with the anesthetic dose, the pharmacokinetic model of anesthetic drugs, and the individual characteristics of the patient, a comprehensive anesthesia quality evaluation report is generated. Finally, based on the evaluation results, targeted suggestions and adjustment measures are provided to optimize the anesthesia effect and improve the safety of the operation. However, traditional anesthesia quality evaluation methods mainly rely on the experience of anesthesiologists and feedback from postoperative patients, and often cannot fully reflect the real-time status of the anesthesia process, resulting in a certain lag and limitation in the evaluation of the anesthesia effect. Summary of the invention
[0003] Based on this, it is necessary for the present invention to provide a method, system and terminal for evaluating the quality of surgical anesthesia to solve at least one of the above technical problems.
[0004] To achieve the above object, a method for evaluating the quality of surgical anesthesia comprises the following steps:
[0005] Step S1: Acquire the physiological monitoring data of the surgical patient, and perform respiratory rate and blood oxygen saturation analysis on the physiological monitoring data of the surgical patient to obtain the respiratory rate data and blood oxygen saturation data of the surgical patient; perform physiological stability evaluation and analysis based on the respiratory rate data and blood oxygen saturation data of the surgical patient to obtain a physiological stability evaluation factor of the surgical patient;
[0006] Step S2: Acquire the anesthetic drug use record data of the surgical patient, and perform anesthesia depth monitoring on the surgical patient's physiological monitoring data based on the anesthetic drug use record data to obtain the surgical patient's physiological anesthesia depth data; perform an anesthesia safety assessment analysis on the surgical patient's physiological anesthesia depth data to obtain the surgical patient's anesthesia depth safety assessment factor;
[0007] Step S3: performing physiological response status evaluation and analysis on the physiological monitoring data of the surgical patient to obtain the physiological response status data of the surgical patient; performing surgical anesthesia quality evaluation and calculation on the physiological response status data of the surgical patient based on the physiological stability evaluation factor of the surgical patient and the anesthesia depth safety evaluation factor of the surgical patient to obtain the anesthesia quality score of the surgical patient;
[0008] Step S4: Perform an anesthesia quality feedback analysis based on the anesthesia quality score of the surgical patient to generate an anesthesia quality feedback evaluation report for the surgical patient.
[0009] Further, step S1 includes the following steps:
[0010] Step S11: Acquiring physiological monitoring data of surgical patients;
[0011] Step S12: demodulating and filtering the respiratory signal in the physiological monitoring data of the surgical patient to obtain smoothed data of the respiratory signal of the surgical patient;
[0012] Step S13: performing respiratory signal spectrum conversion processing on the smoothed data of the surgical patient's respiratory signal to generate a respiratory signal spectrum diagram of the surgical patient; performing respiratory frequency statistical analysis on the respiratory signal spectrum diagram of the surgical patient to obtain respiratory frequency data of the surgical patient;
[0013] Step S14: performing blood oxygen saturation analysis on the physiological monitoring data of the surgical patient to obtain blood oxygen saturation data of the surgical patient;
[0014] Step S15: Perform physiological stability assessment analysis based on the surgical patient's respiratory rate data and the surgical patient's blood oxygen saturation data to obtain a physiological stability assessment factor for the surgical patient.
[0015] Further, step S14 includes the following steps:
[0016] Step S141: extracting blood oxygen spectrum signals from the physiological monitoring data of the surgical patient to obtain blood oxygen spectrum signal data of the surgical patient;
[0017] Step S142: performing blood oxygen saturation-related wavelength separation processing on the blood oxygen spectrum signal data of the surgical patient to obtain the blood oxygen saturation-related signal wavelength region of the surgical patient;
[0018] Step S143: performing spectral signal intensity characteristic analysis on the wavelength region of the signal related to the blood oxygen saturation of the surgical patient to obtain blood oxygen spectral signal intensity data of the surgical patient;
[0019] Step S144: performing pulse fluctuation calibration processing on the blood oxygen spectrum signal data of the surgical patient based on the blood oxygen spectrum signal intensity data of the surgical patient to obtain calibration optimization data of the blood oxygen spectrum signal of the surgical patient;
[0020] Step S145: performing blood oxygen saturation evaluation and analysis on the calibration and optimization data of the blood oxygen spectrum signal of the surgical patient to obtain the blood oxygen saturation data of the surgical patient.
[0021] Further, step S144 includes the following steps:
[0022] Performing time series characteristic analysis on the blood oxygen spectrum signal intensity data of surgical patients to obtain the time series characteristic data of the blood oxygen spectrum intensity of surgical patients;
[0023] Analyze the variation law of the blood oxygen spectrum intensity of surgical patients based on the time series characteristic data of the blood oxygen spectrum intensity, and obtain the variation law data of the blood oxygen spectrum intensity of surgical patients;
[0024] Based on the blood oxygen spectrum intensity change law data of surgical patients, the pulse fluctuation dynamic change curve analysis is performed on the blood oxygen spectrum signal data of surgical patients to generate the pulse fluctuation dynamic change curve of the blood oxygen signal of surgical patients;
[0025] The pulse fluctuation change drift area of the dynamic change curve of the blood oxygen signal pulse fluctuation of the surgical patient is monitored to obtain the pulse fluctuation change drift area in the blood oxygen pulse change curve of the surgical patient; the signal drift compensation analysis is performed on the pulse fluctuation change drift area in the blood oxygen pulse change curve of the surgical patient to obtain the blood oxygen pulse fluctuation signal drift compensation coefficient of the surgical patient;
[0026] According to the drift compensation coefficient of the blood oxygen pulse fluctuation signal of the surgical patient, the corresponding blood oxygen spectrum signal drift data part in the blood oxygen spectrum signal data of the surgical patient is subjected to signal drift compensation calibration processing to obtain the calibration optimization data of the blood oxygen spectrum signal of the surgical patient.
[0027] Further, step S15 includes the following steps:
[0028] Step S151: performing respiratory rhythm fluctuation analysis on the respiratory frequency data of the surgical patient to obtain respiratory rhythm fluctuation pattern data of the surgical patient;
[0029] Step S152: performing blood oxygen fluctuation coordinated change analysis on the blood oxygen saturation data of the surgical patient based on the respiratory rhythmic fluctuation pattern data of the surgical patient to generate respiratory-blood oxygen fluctuation coordinated effect change data of the surgical patient;
[0030] Step S153: dividing the respiratory-blood oxygen fluctuation synergistic effect change data of the surgical patient into time periods, and obtaining the respiratory-blood oxygen fluctuation synergistic change data of the surgical patient in different time periods;
[0031] Step S154: performing cross-time period fluctuation change comparison processing on the respiratory-blood oxygen fluctuation coordinated change data of the surgical patients in different time periods, so as to obtain the physiological fluctuation change trend data of the surgical patients between different time periods;
[0032] Step S155: Perform physiological stability assessment analysis on the physiological fluctuation change trend data of surgical patients in different time periods to obtain a physiological stability assessment factor for surgical patients.
[0033] Further, step S2 includes the following steps:
[0034] Step S21: Acquire the anesthetic drug use record data of the surgical patient;
[0035] Step S22: performing a time series distribution analysis of the anesthetic drug usage record data of the surgical patients to obtain a time series distribution of the anesthetic drug dosage usage of the surgical patients;
[0036] Step S23: performing a dynamic change trend analysis of physiological response of the surgical patient's physiological monitoring data based on the time series distribution of the surgical patient's anesthetic drug dosage, and obtaining dynamic change trend data of physiological response of the surgical patient's anesthetic drug usage;
[0037] Step S24: performing drug use-physiological response prediction analysis on the dynamic change trend data of the physiological response of the surgical patients to the use of anesthetic drugs, so as to obtain the physiological response data of the surgical patients under different anesthetic drug dosages; performing anesthesia depth estimation processing on the physiological response data of the surgical patients under different anesthetic drug dosages, so as to obtain the physiological anesthesia depth data of the surgical patients;
[0038] Step S25: Perform an anesthesia safety assessment analysis on the physiological anesthesia depth data of the surgical patient to obtain an anesthesia depth safety assessment factor for the surgical patient.
[0039] Further, step S25 includes the following steps:
[0040] Step S251: performing fluctuation amplitude analysis on the physiological anesthesia depth data of the surgical patient to obtain the fluctuation amplitude data of the physiological anesthesia depth of the surgical patient;
[0041] Step S252: performing physiological emergency response evaluation and analysis on the physiological anesthesia depth data of the surgical patient based on the fluctuation amplitude data of the physiological anesthesia depth of the surgical patient, and obtaining the physiological emergency response processing efficiency of the physiological anesthesia depth of the surgical patient when the physiological anesthesia depth is abnormal;
[0042] Step S253: Quantitatively analyzing the safety level of the physiological emergency response processing efficiency of the surgical patient's physiological anesthesia depth when the patient suddenly experiences physiological abnormalities, so as to obtain the physiological safety level of the surgical patient's anesthesia depth;
[0043] Step S254: Perform an anesthesia safety assessment analysis on the physiological safety level of the anesthesia depth of the surgical patient to obtain an anesthesia depth safety assessment factor for the surgical patient.
[0044] Further, step S3 includes the following steps:
[0045] Step S31: performing signal amplitude variation characteristic analysis on the corresponding physiological monitoring signal in the physiological monitoring data of the surgical patient to obtain abnormal characteristic data of amplitude fluctuation of the physiological signal of the surgical patient;
[0046] Step S32: Based on the abnormal amplitude fluctuation characteristic data of the surgical patient's physiological signal, a dynamic stress response model is performed on the corresponding physiological monitoring signal in the surgical patient's physiological monitoring data to obtain a dynamic stress response model of the abnormal amplitude fluctuation of the surgical patient's physiological signal;
[0047] Step S33: performing physiological response status evaluation and analysis on the dynamic model of stress response to abnormal amplitude of physiological signals of surgical patients to obtain physiological response status data of surgical patients;
[0048] Step S34: Perform surgical anesthesia quality evaluation calculation on the surgical patient's physiological response status data based on the surgical patient's physiological stability evaluation factor and the surgical patient's anesthesia depth safety evaluation factor to obtain the surgical patient's anesthesia quality score.
[0049] Furthermore, the present invention also provides a system for evaluating the quality of surgical anesthesia, which is used to perform the method for evaluating the quality of surgical anesthesia as described above. The system for evaluating the quality of surgical anesthesia includes:
[0050] The physiological stability assessment module is used to obtain the physiological monitoring data of the surgical patient, and to perform respiratory rate and blood oxygen saturation analysis on the physiological monitoring data of the surgical patient, so as to obtain the respiratory rate data and blood oxygen saturation data of the surgical patient; perform physiological stability assessment and analysis based on the respiratory rate data and blood oxygen saturation data of the surgical patient, so as to obtain the physiological stability assessment factor of the surgical patient;
[0051] The anesthesia depth safety assessment module is used to obtain the anesthetic drug use record data of the surgical patient, and perform anesthesia depth monitoring on the surgical patient's physiological monitoring data based on the anesthetic drug use record data of the surgical patient to obtain the surgical patient's physiological anesthesia depth data; perform an anesthesia safety assessment and analysis on the surgical patient's physiological anesthesia depth data, thereby obtaining the surgical patient's anesthesia depth safety assessment factor;
[0052] The surgical anesthesia quality scoring module is used to evaluate and analyze the physiological response status of the surgical patient's physiological monitoring data to obtain the surgical patient's physiological response status data; based on the surgical patient's physiological stability evaluation factor and the surgical patient's anesthesia depth safety evaluation factor, the surgical patient's physiological response status data is evaluated and calculated to obtain the surgical patient's anesthesia quality score;
[0053] The surgical anesthesia quality feedback evaluation module is used to perform anesthesia quality feedback analysis based on the surgical patient anesthesia quality score to generate a surgical patient anesthesia quality feedback evaluation report.
[0054] Furthermore, the present invention also provides a terminal, comprising a processor, a memory, and a computer control unit stored in the memory and executable on the processor, for executing the method for evaluating surgical anesthesia quality as described above.
[0055] Beneficial effects of the present invention:
[0056] 1. Compared with the prior art, the method for evaluating the quality of surgical anesthesia proposed in the present invention has the beneficial effect that obtaining the physiological monitoring data of surgical patients is the starting point of the entire monitoring process, which provides a basic understanding of the patient's health status. This step includes collecting real-time data from various physiological monitoring devices. These data include electrocardiogram (ECG), respiratory signals, blood oxygen spectrum signals, body temperature and other key indicators. By efficiently collecting these data, a comprehensive view of the patient's real-time physiological state can be obtained. The accuracy and timeliness of the data are crucial for monitoring the patient's status during the entire operation, and can help identify potential risks, make timely adjustments, and ensure the safety and stability of the patient during the operation. By performing respiratory frequency statistical analysis on the respiratory signals in the physiological monitoring data of surgical patients, the patient's respiratory frequency data can be accurately calculated, and then it can be understood whether the patient's respiratory rhythm and frequency are within the normal range. This information is of great significance for evaluating respiratory function and monitoring physiological stability during surgery, and can help doctors make timely adjustments and optimize respiratory management during surgery, thereby providing basic data guarantee for subsequent processing. By analyzing the blood oxygen saturation of the physiological monitoring data of surgical patients, the patient's blood oxygen level can be accurately reflected. Normal blood oxygen saturation is crucial to ensure the oxygen supply of tissues and organs. By analyzing the blood oxygen saturation data, it can help identify hypoxemia or other oxygenation problems, which is critical for evaluating the patient's respiratory efficiency and cardiopulmonary function during surgery, thereby providing data support for the subsequent processing process. At the same time, by evaluating and analyzing the physiological stability of surgical patients based on the respiratory rate data and the blood oxygen saturation data of surgical patients, the patient's overall physiological state can be comprehensively evaluated. This step combines the two key indicators of respiratory rate and blood oxygen saturation. By analyzing their changing trends and current values, a comprehensive physiological stability evaluation factor can be obtained. This factor reflects the patient's physiological stability during surgery, including the ability to breathe and oxygenate. By evaluating physiological stability, it can be determined whether it is necessary to adjust the surgical strategy or perform additional intervention to maintain the patient's physiological balance. This comprehensive evaluation can effectively reduce surgical risks, thereby being able to comprehensively monitor the real-time physiological state of surgical patients during anesthesia. Secondly, by obtaining the record data of anesthetic drug use in surgical patients, these records include information such as drug type, dosage, administration time and frequency. This data set provides an important basis for evaluating the effect of anesthesia and can reflect the implementation and changing trends of anesthesia management. Accurately recording drug use helps to ensure the rationality of anesthetic dosage and avoid overdose or underdose of drugs. At the same time, it can provide detailed reference data for subsequent analysis. The comprehensive acquisition and recording of this data can enhance the controllability of the anesthesia process and help medical staff adjust anesthesia strategies in a timely manner to improve the safety of the surgical process and the comfort of patients.By monitoring and estimating the depth of anesthesia based on the corresponding physiological monitoring data of surgical patients based on the anesthetic drug use record data of surgical patients, the depth of anesthesia of surgical patients throughout the operation can be evaluated. This process involves using physiological data to estimate the actual impact of anesthesia on patients. Accurate estimation of the depth of anesthesia is crucial to ensure that patients maintain an appropriate state of anesthesia during surgery. Too shallow anesthesia will cause discomfort or pain to patients, while too deep anesthesia will increase surgical risks. By accurately estimating the depth of anesthesia, the anesthetic dose can be adjusted to achieve the best anesthetic effect, improve the safety of surgery and the quality of postoperative recovery of patients, thereby providing basic data guarantee for subsequent safety assessment of surgical procedures. In addition, anesthesia safety assessment and analysis of the physiological anesthesia depth data of surgical patients is also performed to evaluate the safety of the anesthesia process. This analysis involves evaluating whether the depth of anesthesia is within a safe range and whether there is a risk of over-anesthesia or under-anesthesia. The anesthesia safety assessment factor is a comprehensive indicator that reflects the degree of match between the depth of anesthesia and the patient's physiological state. Through this analysis, medical staff can monitor the anesthesia process in real time to ensure that the anesthetic dose and depth are always maintained at a safe level. Then, by evaluating and analyzing the physiological response status of the corresponding physiological monitoring signals in the physiological monitoring data of the surgical patient, the patient's physiological response status data can be generated. These data provide a detailed picture of the patient's physiological response during the operation, helping to understand the patient's overall physiological state and specific physiological problems. This evaluation can provide a scientific basis for further clinical decision-making, such as whether the surgical anesthesia plan needs to be adjusted. In addition, by evaluating and calculating the surgical anesthesia quality based on the surgical patient's physiological stability evaluation factor and the surgical patient's anesthesia depth safety evaluation factor, a comprehensive anesthesia quality score can be obtained. This score comprehensively considers the patient's physiological stability and the safety of the anesthesia depth, and provides a quantitative evaluation of the surgical anesthesia quality. This score helps the medical team to objectively evaluate the effectiveness and timeliness of the anesthesia quality, thereby identifying potential improvement points, improving the anesthesia quality, and providing a basis for improvement for future surgical anesthesia practices, thereby reducing the lag and limitations of the anesthesia quality effect evaluation process. Finally, by performing anesthesia quality feedback analysis based on the specific size of the surgical patient's anesthesia quality score, a detailed anesthesia quality feedback evaluation report can be analyzed and generated. This report summarizes the key data and evaluation results of the anesthesia process and provides a comprehensive review and analysis of anesthesia quality. The anesthesia quality feedback report includes not only anesthesia quality evaluation effects, patient responses, and stability data, but also improvement suggestions and future optimization plans.Through this feedback, problems in the surgical anesthesia process can be identified, the strengths and weaknesses of anesthesia management can be understood, and measures can be taken to improve anesthesia practice. The generated reports can provide valuable reference information, help optimize the surgical anesthesia process, improve the overall quality of surgical anesthesia, and achieve higher safety and effectiveness in future operations.
[0057] 2. The system for evaluating the quality of surgical anesthesia proposed in the present invention is generally composed of a physiological stability assessment module, an anesthesia depth safety assessment module, a surgical anesthesia quality scoring module and a surgical anesthesia quality feedback assessment module. It can implement any method for evaluating the quality of surgical anesthesia described in the present invention, and is used to combine the operations between computer programs running on each module to implement the method for evaluating the quality of surgical anesthesia. The internal structures of the system cooperate with each other, which can greatly reduce duplication of work and manpower investment, and can quickly and effectively provide a more accurate and efficient process for evaluating the quality of surgical anesthesia, thereby simplifying the operating procedures of the system for evaluating the quality of surgical anesthesia. BRIEF DESCRIPTION OF THE DRAWINGS
[0058] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:
[0059] Figure 1 A schematic flow chart of the steps of the method for evaluating surgical anesthesia quality of the present invention;
[0060] Figure 2 for Figure 1 Detailed step flow diagram of step S1;
[0061] Figure 3 for Figure 2 Detailed step flow chart of step S14 in FIG. DETAILED DESCRIPTION
[0062] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.
[0063] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different network and / or processor methods and / or microcontroller methods.
[0064] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.
[0065] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for evaluating the quality of surgical anesthesia, the method comprising the following steps:
[0066] Step S1: Acquire the physiological monitoring data of the surgical patient, and perform respiratory rate and blood oxygen saturation analysis on the physiological monitoring data of the surgical patient to obtain the respiratory rate data and blood oxygen saturation data of the surgical patient; perform physiological stability evaluation and analysis based on the respiratory rate data and blood oxygen saturation data of the surgical patient to obtain a physiological stability evaluation factor of the surgical patient;
[0067] Step S2: Acquire the anesthetic drug use record data of the surgical patient, and perform anesthesia depth monitoring on the surgical patient's physiological monitoring data based on the anesthetic drug use record data to obtain the surgical patient's physiological anesthesia depth data; perform an anesthesia safety assessment analysis on the surgical patient's physiological anesthesia depth data to obtain the surgical patient's anesthesia depth safety assessment factor;
[0068] Step S3: performing physiological response status evaluation and analysis on the physiological monitoring data of the surgical patient to obtain the physiological response status data of the surgical patient; performing surgical anesthesia quality evaluation and calculation on the physiological response status data of the surgical patient based on the physiological stability evaluation factor of the surgical patient and the anesthesia depth safety evaluation factor of the surgical patient to obtain the anesthesia quality score of the surgical patient;
[0069] Step S4: Perform an anesthesia quality feedback analysis based on the anesthesia quality score of the surgical patient to generate an anesthesia quality feedback evaluation report for the surgical patient.
[0070] In the embodiment of the present invention, please refer to Figure 1 FIG. 1 is a flow chart of the steps of the method for evaluating the quality of surgical anesthesia according to the present invention. In this example, the method for evaluating the quality of surgical anesthesia includes the following steps:
[0071] Step S1: Acquire the physiological monitoring data of the surgical patient, and perform respiratory rate and blood oxygen saturation analysis on the physiological monitoring data of the surgical patient to obtain the respiratory rate data and blood oxygen saturation data of the surgical patient; perform physiological stability evaluation and analysis based on the respiratory rate data and blood oxygen saturation data of the surgical patient to obtain a physiological stability evaluation factor of the surgical patient;
[0072] In an embodiment of the present invention, real-time physiological data of surgical patients are collected by using corresponding physiological monitoring equipment (such as electrocardiographs, respiratory monitors, and blood oxygen optical monitoring equipment, etc.), wherein these data include key indicators such as electrocardiogram (ECG), respiratory signals, blood oxygen spectrum signals, and body temperature, thereby obtaining physiological monitoring data of surgical patients. At the same time, the respiratory signal in the physiological monitoring data of surgical patients previously monitored is mediated to remove noise in the original signal, and a low-pass filter is used to remove high-frequency noise, and the respiratory signal is smoothed by applying a median filter or a Gaussian filter to reduce random fluctuations in the respiratory signal, and the previously smoothed respiratory signal is converted into a spectrum by using a fast Fourier transform (FFT) to convert the smoothed respiratory signal into a spectrum diagram. The FFT algorithm can convert a time domain signal into a frequency domain signal, and a mathematical statistical method is used to perform a statistical analysis of the respiratory frequency on the frequency domain signal to analyze and extract the main frequency components in the frequency domain signal to calculate the corresponding respiratory frequency value, thereby obtaining the respiratory frequency data of surgical patients. Furthermore, by extracting data related to the blood oxygen spectral signal from the physiological monitoring data of the surgical patient obtained by real-time monitoring, and performing separation processing on the extracted blood oxygen spectral signal data of the surgical patient according to the wavelength associated with blood oxygen saturation, the spectrum analyzer is used to separate the signals of different wavelengths related to blood oxygen saturation, thereby decomposing the spectrum signal into wavelength regions representing blood oxygen saturation. Specifically, the spectrum analyzer will separate the characteristic wavelength range of blood oxygen saturation (e.g., 660 nm and 940 nm) into the wavelength region representing blood oxygen saturation. nm) for signal separation, so that the signal wavelength region related to blood oxygen saturation can be extracted, and at the same time, the spectral intensity in the signal wavelength region obtained by the previous analysis is measured by using a high-precision spectrometer, and the intensity distribution of the blood oxygen spectral signal is further understood, and the time series statistical analysis of the pulse fluctuation of the corresponding surgical patient's blood oxygen spectral signal data is performed by combining the blood oxygen spectral signal intensity obtained by the previous analysis, so as to identify and analyze the periodicity and distribution amplitude of the pulse fluctuation in the blood oxygen spectral signal, and adjust the pulse fluctuation in the blood oxygen spectral signal by using a calibration algorithm to reduce noise interference and errors, and the blood oxygen saturation is evaluated and calculated by the calibration optimization data of the blood oxygen spectral signal obtained after the previous calibration optimization, so as to calculate the actual value of the blood oxygen saturation based on the wavelength intensity ratio of the spectral signal, so as to obtain the blood oxygen saturation data of the surgical patient.Then, by combining the respiratory rate data of surgical patients and the blood oxygen saturation data of surgical patients obtained in the previous analysis, a set evaluation algorithm (such as a linear regression model or a logistic regression model) is used to evaluate and analyze the physiological stability indicators of surgical patients in various time periods. These indicators include heart rate variability (HRV) and blood pressure fluctuations to evaluate the consistency and stability of physiological fluctuations, thereby evaluating and analyzing the corresponding physiological stability assessment factors. These factors reflect the stability of the patient's physiological state during the operation, and finally the physiological stability assessment factors of surgical patients are obtained.
[0073] Step S2: Acquire the anesthetic drug use record data of the surgical patient, and perform anesthesia depth monitoring on the surgical patient's physiological monitoring data based on the anesthetic drug use record data to obtain the surgical patient's physiological anesthesia depth data; perform an anesthesia safety assessment analysis on the surgical patient's physiological anesthesia depth data to obtain the surgical patient's anesthesia depth safety assessment factor;
[0074] In an embodiment of the present invention, by extracting the anesthetic drug use records of surgical patients from the hospital electronic health record system, in a specific implementation, by using a data extraction tool to export relevant records from the database through specified query conditions (such as patient ID, surgery date, anesthetic drug type, etc.), these records include the dosage, administration time and frequency of each anesthetic drug, etc., so as to obtain the anesthetic drug use record data of surgical patients. At the same time, by arranging the anesthetic drug use record data of surgical patients previously collected and obtained according to time series, a statistical analysis method is applied to calculate the dose distribution of each anesthetic drug used during the entire operation. For example, a time series analysis tool (such as the Pandas library in Python or the xts package in R language) is used to group and count the anesthetic drug use record data of surgical patients to analyze the corresponding anesthetic drug usage distribution over time and at each time point, and by combining the anesthetic drug dosage time series distribution obtained by the previous analysis, the corresponding surgical patient physiological monitoring data is statistically analyzed for the dynamic change trend of physiological response. At this stage, the physiological monitoring data (such as heart rate, blood pressure, respiratory rate, etc.) recorded during the operation are compared with the anesthetic drug use record. The recorded data are compared and analyzed, and the effect of changes in anesthetic drug doses on physiological parameters is explored through dynamic analysis methods (such as regression analysis or time series modeling). For example, linear regression analysis is performed using statistical software to detect the dynamic change trend of drug doses on physiological responses. Secondly, predictive modeling technology is used to predict the dynamic change trend of drug doses on physiological responses obtained in the previous analysis to conduct a predictive analysis of drug use-physiological response conditions, so as to predict and analyze the effects of different drug doses on physiological responses. Machine learning algorithms (such as support vector machines, decision trees, random forests, etc.) can be used to establish a predictive model between drug doses and physiological responses, and by training the model, the physiological responses under different anesthetic drug doses can be predicted to obtain the physiological responses of surgical patients under different anesthetic drug doses. The depth of anesthesia is also estimated by analyzing the physiological responses of surgical patients at different doses of anesthetic drugs obtained by previous prediction analysis, so as to estimate the depth level of anesthesia by using an algorithm by analyzing the physiological response data. An anesthesia depth estimation algorithm based on physiological parameters can be used, such as a depth analysis method based on electroencephalogram (EEG) or other physiological signals. In the specific implementation process, a specific physiological monitoring device is used to obtain the patient's physiological parameter data, and then a special depth estimation algorithm (such as Bispectral Index (BIS) algorithm) is used to analyze the corresponding physiological response data, wherein the corresponding calculation formula can be: , where The physiological depth of anesthesia for surgical patients. The dosage of anesthetic drugs is Dosages for anesthetic drugs Physiological EEG data under is the physiological EEG weight coefficient, Dosages for anesthetic drugs The physiological heart rate data below, is the physiological heart rate weight coefficient, is the attenuation coefficient of the effect of the anesthetic drug dosage, Dosages for anesthetic drugs Blood oxygen saturation data, is the blood oxygen saturation weight coefficient, Dosages for anesthetic drugs The mean arterial pressure data under is the arterial pressure weight coefficient to evaluate the patient's anesthesia depth, thereby obtaining the data of the physiological anesthesia depth of the surgical patient. Then, the previously estimated physiological anesthesia depth data of the surgical patient is evaluated and analyzed for anesthesia safety by using corresponding evaluation tools (such as safety evaluation algorithms and safety standards) to evaluate and analyze and check whether the corresponding anesthesia depth is within the safety range, for example, setting safety thresholds and comparing the actual anesthesia depth data with these thresholds to evaluate whether there is a risk of over-anesthesia or under-anesthesia, and generating a safety evaluation report to provide specific safety evaluation factors, wherein the evaluation factors include anesthetic drug concentration, patient consciousness state, stability of anesthesia depth, emergency treatment effect and possible complication risks, etc., and finally the evaluation and analysis obtains the safety evaluation factors of the anesthesia depth of the surgical patient.
[0075] Step S3: performing physiological response status evaluation and analysis on the physiological monitoring data of the surgical patient to obtain the physiological response status data of the surgical patient; performing surgical anesthesia quality evaluation and calculation on the physiological response status data of the surgical patient based on the physiological stability evaluation factor of the surgical patient and the anesthesia depth safety evaluation factor of the surgical patient to obtain the anesthesia quality score of the surgical patient;
[0076] In an embodiment of the present invention, a high-pass filter is used to preprocess the physiological monitoring signal corresponding to the physiological monitoring data of the surgical patient to remove low-frequency noise and interference, and a short-time Fourier transform (STFT) is applied to decompose the physiological monitoring signal into multiple time-frequency domain components, and the time series data of the signal amplitude is extracted therefrom. Statistical methods, such as standard deviation, root mean square (RMS) and coefficient of variation, are also used to identify abnormal characteristic data of amplitude fluctuation, which can reveal the abnormal fluctuation of the physiological signal of the surgical patient during the operation, and an autoregressive moving average (ARMA) model or a long short-term memory (LSTM) network is selected by combining the abnormal characteristic data of signal amplitude fluctuation obtained by previous analysis to model the corresponding physiological monitoring signal in the physiological monitoring data of the surgical patient, so that the abnormal amplitude characteristic data obtained by previous analysis is input into the autoregressive moving average (ARMA) model or the long short-term memory (LSTM) network, and the dynamic relationship between the signal amplitude fluctuation and the stress response is captured by modeling and analysis, and a dynamic model that can predict the fluctuation of the physiological signal under different stress states is generated by training the model. At the same time, the physiological reaction status of the dynamic model obtained by the previous modeling is evaluated and analyzed, so as to predict the physiological signals collected during the real-time operation by using the model and compare them with the actual monitoring data. The corresponding physiological reaction status is evaluated by calculating the difference between the predicted value and the actual value. The specific operation includes using error analysis tools, such as mean square error (MSE) and mean absolute error (MAE), to quantitatively evaluate the accuracy of the model prediction, so as to obtain the physiological reaction status data of the surgical patient, which shows the physiological stress of the patient during the operation and the physiological abnormal reaction state. Then, by combining the physiological stability evaluation factor of the surgical patient obtained by the previous evaluation and analysis and the anesthesia depth safety evaluation factor of the surgical patient, the corresponding surgical patient physiological reaction status data is evaluated and quantitatively calculated to evaluate the quality of surgical anesthesia, so as to use the weighted scoring calculation formula to combine the above evaluation factors (where the physiological stability evaluation factor includes indicators such as heart rate variability (HRV) and blood pressure fluctuations, and the anesthesia depth safety evaluation factor includes anesthetic drug concentration and patient consciousness state) with the physiological reaction status data to quantitatively calculate the anesthesia quality score, and the numerical value of the evaluation factor is input into the preset scoring calculation formula, for example: , where Scoring the quality of anesthesia for surgical patients, The total number of factors that assess the physiological stability of surgical patients, For the The actual value of the physiological stability assessment factor for surgical patients, For the The weight coefficient of the physiological stability assessment factor of each surgical patient, The total number of factors for safety assessment of the depth of anesthesia in surgical patients, For the The actual value of the safety assessment factor for the depth of anesthesia in surgical patients. For the The weight coefficients of the safety assessment factors of the depth of anesthesia for surgical patients are summarized to obtain the final anesthesia quality score, which is used to judge the overall quality of surgical anesthesia, ensure the physiological stability and anesthesia safety of patients during the operation, and finally quantify and calculate the anesthesia quality score for surgical patients.
[0077] Step S4: Perform an anesthesia quality feedback analysis based on the anesthesia quality score of the surgical patient to generate an anesthesia quality feedback evaluation report for the surgical patient.
[0078] In an embodiment of the present invention, anesthesia quality feedback analysis is performed based on the specific size of the surgical patient's anesthesia quality score obtained by previous quantitative calculation, so as to convert the surgical patient's anesthesia quality score and related analysis results into a detailed anesthesia quality feedback evaluation report. The report content includes the specific numerical value of the anesthesia quality score, the explanation of the evaluation indicators, the key data during the anesthesia process and potential improvement suggestions. In addition, the report should also include a summary of the anesthesia quality evaluation and provide specific improvement suggestions or measures to improve the quality of anesthesia management in future surgeries. The final generated surgical patient anesthesia quality feedback evaluation report will be provided to the medical team for postoperative analysis and improvement of anesthesia techniques and processes.
[0079] Further, step S1 includes the following steps:
[0080] Step S11: Acquiring physiological monitoring data of surgical patients;
[0081] Step S12: demodulating and filtering the respiratory signal in the physiological monitoring data of the surgical patient to obtain smoothed data of the respiratory signal of the surgical patient;
[0082] Step S13: performing respiratory signal spectrum conversion processing on the smoothed data of the surgical patient's respiratory signal to generate a respiratory signal spectrum diagram of the surgical patient; performing respiratory frequency statistical analysis on the respiratory signal spectrum diagram of the surgical patient to obtain respiratory frequency data of the surgical patient;
[0083] Step S14: performing blood oxygen saturation analysis on the physiological monitoring data of the surgical patient to obtain blood oxygen saturation data of the surgical patient;
[0084] Step S15: Perform physiological stability assessment analysis based on the surgical patient's respiratory rate data and the surgical patient's blood oxygen saturation data to obtain a physiological stability assessment factor for the surgical patient.
[0085] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps:
[0086] Step S11: Acquiring physiological monitoring data of surgical patients;
[0087] In an embodiment of the present invention, real-time physiological data of surgical patients are collected by using corresponding physiological monitoring equipment (such as electrocardiographs, respiratory monitors, and blood oxygen optical monitoring equipment, etc.), where these data include key indicators such as electrocardiogram (ECG), respiratory signals, blood oxygen spectral signals, body temperature, etc., and ultimately the physiological monitoring data of surgical patients are obtained.
[0088] Step S12: demodulating and filtering the respiratory signal in the physiological monitoring data of the surgical patient to obtain smoothed data of the respiratory signal of the surgical patient;
[0089] In an embodiment of the present invention, the respiratory signal in the physiological monitoring data of the surgical patient previously monitored is mediated to remove the noise in the original signal, and a low-pass filter is used to remove high-frequency noise. At the same time, the respiratory signal is smoothed by applying a median filter or a Gaussian filter to reduce random fluctuations in the respiratory signal. In specific implementation, appropriate filter parameters (such as the cutoff frequency of the filter and the order of the filter) are selected to ensure that the processed respiratory signal is smooth and has no obvious noise, and finally smoothed data of the surgical patient's respiratory signal is obtained.
[0090] Step S13: performing respiratory signal spectrum conversion processing on the smoothed data of the surgical patient's respiratory signal to generate a respiratory signal spectrum diagram of the surgical patient; performing respiratory frequency statistical analysis on the respiratory signal spectrum diagram of the surgical patient to obtain respiratory frequency data of the surgical patient;
[0091] In an embodiment of the present invention, the smoothed data of the surgical patient's respiratory signal obtained after smoothing is converted into a signal spectrum by using a fast Fourier transform (FFT) to convert the smoothed respiratory signal into a spectrum graph. The FFT algorithm can convert the time domain signal into a frequency domain signal, thereby generating a spectrum graph of the surgical patient's respiratory signal. At the same time, a mathematical statistical method is used to perform a statistical analysis of the respiratory frequency on the surgical patient's respiratory signal spectrum graph to analyze and extract the main frequency components in the spectrum graph to calculate the corresponding respiratory frequency value, and finally obtain the surgical patient's respiratory frequency data by identifying the main peak value and its corresponding frequency in the spectrum graph.
[0092] Step S14: performing blood oxygen saturation analysis on the physiological monitoring data of the surgical patient to obtain blood oxygen saturation data of the surgical patient;
[0093] In the embodiment of the present invention, data related to the blood oxygen spectrum signal is extracted from the physiological monitoring data of the surgical patient obtained by real-time monitoring, and the extracted blood oxygen spectrum signal data of the surgical patient is subjected to the separation processing of the wavelength associated with blood oxygen saturation, so as to use the spectrum analyzer to separate the signals of different wavelengths related to blood oxygen saturation, thereby decomposing the spectrum signal into wavelength regions representing blood oxygen saturation. Specifically, the spectrum analyzer will separate the characteristic wavelength range of blood oxygen saturation (for example, 660 nm and 940 nm) according to the wavelength range of the blood oxygen saturation. nm) for signal separation, so that the signal wavelength region related to blood oxygen saturation can be extracted, and the spectral intensity within the signal wavelength region obtained by the previous analysis is measured by using a high-precision spectrometer, and the intensity distribution of the blood oxygen spectral signal is further understood. At the same time, the corresponding surgical patient blood oxygen spectral signal data is subjected to a time series statistical analysis of the pulse fluctuation by combining the blood oxygen spectral signal intensity obtained by the previous analysis, so as to identify and analyze the periodicity and distribution amplitude of the pulse fluctuation in the blood oxygen spectral signal, and the pulse fluctuation in the blood oxygen spectral signal is adjusted by using a calibration algorithm to reduce noise interference and errors. The blood oxygen saturation is also evaluated and calculated by the calibration and optimization data of the blood oxygen spectral signal obtained after the previous calibration optimization, so as to calculate the actual value of the blood oxygen saturation based on the wavelength intensity ratio of the spectral signal, and finally the surgical patient blood oxygen saturation data is obtained.
[0094] Step S15: Perform physiological stability assessment analysis based on the surgical patient's respiratory rate data and the surgical patient's blood oxygen saturation data to obtain a physiological stability assessment factor for the surgical patient.
[0095] In an embodiment of the present invention, the respiratory rate data of surgical patients and the blood oxygen saturation data of surgical patients obtained by previous analysis are combined with a set evaluation algorithm (such as a linear regression model or a logistic regression model) to evaluate and analyze the physiological stability indicators of surgical patients in various time periods. These indicators include indicators such as heart rate variability (HRV) and blood pressure fluctuations, so as to evaluate and determine the consistency and stability of physiological fluctuations, thereby evaluating and analyzing to obtain corresponding physiological stability evaluation factors. These factors reflect the stability of the patient's physiological state during the operation, and ultimately the physiological stability evaluation factors of surgical patients are obtained.
[0096] Further, step S14 includes the following steps:
[0097] Step S141: extracting blood oxygen spectrum signals from the physiological monitoring data of the surgical patient to obtain blood oxygen spectrum signal data of the surgical patient;
[0098] Step S142: performing blood oxygen saturation-related wavelength separation processing on the blood oxygen spectrum signal data of the surgical patient to obtain the blood oxygen saturation-related signal wavelength region of the surgical patient;
[0099] Step S143: performing spectral signal intensity characteristic analysis on the wavelength region of the signal related to the blood oxygen saturation of the surgical patient to obtain blood oxygen spectral signal intensity data of the surgical patient;
[0100] Step S144: performing pulse fluctuation calibration processing on the blood oxygen spectrum signal data of the surgical patient based on the blood oxygen spectrum signal intensity data of the surgical patient to obtain calibration optimization data of the blood oxygen spectrum signal of the surgical patient;
[0101] Step S145: performing blood oxygen saturation evaluation and analysis on the calibration and optimization data of the blood oxygen spectrum signal of the surgical patient to obtain the blood oxygen saturation data of the surgical patient.
[0102] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 2 Detailed step flow diagram of step S14 in the embodiment, step S14 includes the following steps:
[0103] Step S141: extracting blood oxygen spectrum signals from the physiological monitoring data of the surgical patient to obtain blood oxygen spectrum signal data of the surgical patient;
[0104] In an embodiment of the present invention, by extracting data related to the blood oxygen spectrum signal from the physiological monitoring data of the surgical patient previously obtained by real-time monitoring, the corresponding blood oxygen spectrum signal data can be obtained by using a special optical monitoring device (including an optical sensor and a photodetector, etc.), wherein the optical sensor emits infrared light and red light through the patient's skin and tissue, the light is absorbed by the tissue and reflected back to the sensor, the sensor receives light intensity signals of different wavelengths, and converts these light intensity signals into electrical signals using a photodetector, and then uses a digital-to-analog converter to convert these electrical signals into digital signals, and finally obtains the blood oxygen spectrum signal data of the surgical patient.
[0105] Step S142: performing blood oxygen saturation-related wavelength separation processing on the blood oxygen spectrum signal data of the surgical patient to obtain the blood oxygen saturation-related signal wavelength region of the surgical patient;
[0106] In an embodiment of the present invention, the extracted blood oxygen spectral signal data of the surgical patient is subjected to separation processing of the wavelengths associated with blood oxygen saturation, so that the spectrum signal is separated into wavelength regions representing blood oxygen saturation by using a spectrum analyzer. Specifically, the spectrum analyzer performs signal separation according to the characteristic wavelength range of blood oxygen saturation (for example, 660 nm and 940 nm). Through this separation processing, the signal wavelength regions associated with blood oxygen saturation can be extracted. These regions will be screened and marked, and finally the signal wavelength regions associated with the blood oxygen saturation of the surgical patient will be obtained.
[0107] Step S143: performing spectral signal intensity characteristic analysis on the wavelength region of the signal related to the blood oxygen saturation of the surgical patient to obtain blood oxygen spectral signal intensity data of the surgical patient;
[0108] In an embodiment of the present invention, a high-precision spectrometer is used to measure the spectral intensity within the wavelength region of the surgical patient's blood oxygen saturation-related signal obtained previously by analysis, and these spectral intensity data are processed using statistical analysis software to analyze the characteristics of the signal intensity, including indicators such as the mean value and standard deviation of the intensity. These spectral intensity characteristic data are used to further understand the intensity distribution of the blood oxygen spectral signal, and ultimately obtain the surgical patient's blood oxygen spectral signal intensity data.
[0109] Step S144: performing pulse fluctuation calibration processing on the blood oxygen spectrum signal data of the surgical patient based on the blood oxygen spectrum signal intensity data of the surgical patient to obtain calibration optimization data of the blood oxygen spectrum signal of the surgical patient;
[0110] In an embodiment of the present invention, a time series statistical analysis of pulse fluctuations is performed on the corresponding blood oxygen spectrum signal data of surgical patients in combination with the blood oxygen spectrum signal intensity data obtained by previous analysis, so as to identify and analyze the periodicity and distribution amplitude of the pulse fluctuations in the blood oxygen spectrum signal, and adjust the pulse fluctuations in the signal by using a calibration algorithm to reduce noise interference and errors. The calibration algorithm can be adjusted based on the historical data of the signal, and the value of the drift part in the blood oxygen spectrum signal is adjusted by filtering and adjusting parameters to make it conform to the normal range, and finally the calibration optimization data of the blood oxygen spectrum signal of surgical patients is obtained.
[0111] Step S145: performing blood oxygen saturation evaluation and analysis on the calibration and optimization data of the blood oxygen spectrum signal of the surgical patient to obtain the blood oxygen saturation data of the surgical patient.
[0112] In an embodiment of the present invention, the blood oxygen saturation is evaluated and calculated by using the calibration and optimization data of the surgical patient's blood oxygen spectral signal obtained after previous calibration and optimization, so as to calculate the blood oxygen saturation based on the wavelength intensity ratio of the spectral signal. During the calculation process, the optimized signal data needs to be compared with the standard model of blood oxygen saturation to obtain the actual value of the blood oxygen saturation, and finally the blood oxygen saturation data of the surgical patient is obtained.
[0113] Further, step S144 includes the following steps:
[0114] Performing time series characteristic analysis on the blood oxygen spectrum signal intensity data of surgical patients to obtain the time series characteristic data of the blood oxygen spectrum intensity of surgical patients;
[0115] In an embodiment of the present invention, by using a time series analysis tool, such as the Pandas library in Python, time series features in the blood oxygen spectral signal intensity data of surgical patients, such as statistical characteristics such as mean, variance, peak, valley, etc., are extracted, and finally the time series feature data of the blood oxygen spectral intensity of surgical patients are obtained.
[0116] Preferably, the spectral intensity variation law analysis is performed on the time series characteristic data of the blood oxygen spectrum intensity of the surgical patient to obtain the blood oxygen spectrum intensity variation law data of the surgical patient;
[0117] In an embodiment of the present invention, frequency domain analysis methods such as Fourier transform are used to perform spectrum analysis on the previously analyzed time series characteristic data of the blood oxygen spectrum intensity of surgical patients to identify periodic changes and frequency components in the signal, and linear regression or curve fitting technology is applied to perform statistical analysis on the changing laws of the time series characteristic data of the blood oxygen spectrum intensity of surgical patients to extract the changing laws of the spectrum intensity, such as the rising or falling trend of the blood oxygen signal, and by comparing the spectrum intensity data of different time periods, the changing trend of the blood oxygen spectrum during the operation is analyzed, and finally the changing law data of the blood oxygen spectrum intensity of surgical patients is obtained.
[0118] Preferably, a pulse fluctuation dynamic change curve analysis is performed on the blood oxygen spectrum signal data of the surgical patient based on the blood oxygen spectrum intensity change law data of the surgical patient to generate a pulse fluctuation dynamic change curve of the blood oxygen signal of the surgical patient;
[0119] In an embodiment of the present invention, a pulse fluctuation change curve is plotted for the corresponding blood oxygen spectrum signal data of the surgical patient in combination with the blood oxygen spectrum intensity change law data obtained by previous analysis, and the spectral intensity change law data obtained in the above steps are used to apply a time domain analysis method, such as autocorrelation function analysis, to model the dynamic change curve of the pulse fluctuation of the blood oxygen spectrum signal, and by using tools such as the signal processing toolbox in MATLAB, the blood oxygen spectrum signal data is subjected to a dynamic curve fitting of the pulse fluctuation, and finally a dynamic change curve of the pulse fluctuation of the blood oxygen signal of the surgical patient is generated, which reflects the real-time change characteristics of the blood oxygen signal during the operation.
[0120] Preferably, the pulse fluctuation change drift area of the surgical patient's blood oxygen pulse signal pulse fluctuation dynamic change curve is monitored to obtain the pulse fluctuation change drift area within the surgical patient's blood oxygen pulse change curve; the pulse fluctuation change drift area within the surgical patient's blood oxygen pulse change curve is analyzed for signal drift compensation to obtain the surgical patient's blood oxygen pulse fluctuation signal drift compensation coefficient;
[0121] In an embodiment of the present invention, by identifying and determining key feature points in the dynamic change curve of the pulse fluctuation of the blood oxygen signal of the surgical patient, such as peak values and valley values, and by calculating the change range between these feature points to identify the drift area of the pulse fluctuation, image processing software or data analysis tools, such as MATLAB or Python's Matplotlib library, are used to mark these drift areas, and record related drift parameters and area information, thereby obtaining the pulse fluctuation change drift area in the blood oxygen pulse change curve of the surgical patient. At the same time, by using the previously identified pulse fluctuation change drift area to apply a signal processing algorithm, such as a model-based compensation algorithm, the pulse fluctuation change is compensated for signal drift, so as to construct a mathematical model, analyze the characteristics of the drift area, and calculate the drift compensation coefficient. The least squares method or other optimization algorithms can be used to determine the compensation coefficient, for example: , is the drift compensation coefficient, and is the time range of integration, is the integral time variable parameter, For in time The original pulse fluctuation signal at For in time The model predicts the fluctuation signal at For in time The pulse fluctuation signal at the location affects the weight parameter, thereby recording the compensation coefficient of each drift area, and finally obtaining the drift compensation coefficient of the blood oxygen pulse fluctuation signal of the surgical patient.
[0122] Preferably, a signal drift compensation calibration process is performed on a corresponding blood oxygen spectrum signal drift data portion in the blood oxygen spectrum signal data of the surgical patient according to the drift compensation coefficient of the blood oxygen pulse fluctuation signal of the surgical patient to obtain calibration optimization data of the blood oxygen spectrum signal of the surgical patient.
[0123] In an embodiment of the present invention, the drift compensation coefficient of the blood oxygen pulse fluctuation signal of the surgical patient obtained by previous quantitative calculation is combined to perform signal drift compensation calibration on the corresponding blood oxygen spectrum signal drift data part in the blood oxygen spectrum signal data of the surgical patient, so as to use the previously obtained compensation coefficient to calibrate the drift part in the blood oxygen spectrum signal data of the surgical patient, and adopt a compensation algorithm, such as a weighted average method or a linear correction method, to adjust the value of the drift part in the blood oxygen spectrum signal to make it conform to the normal range, and finally obtain the surgical patient's blood oxygen spectrum signal calibration optimization data, which can more accurately reflect the patient's true blood oxygen status.
[0124] Further, step S15 includes the following steps:
[0125] Step S151: performing respiratory rhythm fluctuation analysis on the respiratory frequency data of the surgical patient to obtain respiratory rhythm fluctuation pattern data of the surgical patient;
[0126] In an embodiment of the present invention, the respiratory frequency data of surgical patients obtained by previous statistical analysis are analyzed and processed by using frequency domain analysis tools (such as fast Fourier transform (FFT)). This process includes decomposing the respiratory frequency data of surgical patients into different frequency components to identify specific rhythmic fluctuation patterns. For example, fluctuations in the frequency range of 0.1 Hz to 0.4 Hz are identified and extracted. These frequency ranges are usually related to respiratory rhythms, and the fluctuation pattern data of these frequency components are subjected to time series analysis. Finally, the respiratory rhythmic fluctuation pattern data of surgical patients are obtained by analysis. This data includes the amplitude, periodicity and change trend of the fluctuations, and is stored in a database for subsequent analysis.
[0127] Step S152: performing blood oxygen fluctuation coordinated change analysis on the blood oxygen saturation data of the surgical patient based on the respiratory rhythmic fluctuation pattern data of the surgical patient to generate respiratory-blood oxygen fluctuation coordinated effect change data of the surgical patient;
[0128] In an embodiment of the present invention, a coordinated change analysis of blood oxygen fluctuations is performed on the corresponding blood oxygen saturation data of surgical patients by combining the respiratory rhythmic fluctuation pattern data of surgical patients obtained in the previous analysis, so as to align the corresponding respiratory rate data with the blood oxygen saturation data, ensure that the two data sets have the same timestamp, and use coordinated analysis tools, such as correlation coefficient calculation or regression analysis, to analyze the fluctuation synergy effect between the two sets of data. For example, the correlation between respiratory rate fluctuations and blood oxygen saturation fluctuations is calculated to determine their temporal consistency and change trend. Through these analyses, the respiratory-blood oxygen fluctuation synergy effect change data of surgical patients are finally generated, which reveals the coordinated fluctuations of respiratory rate and blood oxygen saturation in different time periods.
[0129] Step S153: dividing the respiratory-blood oxygen fluctuation synergistic effect change data of the surgical patient into time periods, and obtaining the respiratory-blood oxygen fluctuation synergistic change data of the surgical patient in different time periods;
[0130] In an embodiment of the present invention, the respiratory-blood oxygen fluctuation synergistic effect change data of surgical patients obtained by previous analysis are divided into time periods to divide the corresponding synergistic effect change data into several time periods, such as one hour or every 15 minutes as a time period, and the respiratory-blood oxygen fluctuation synergistic effect change data are grouped according to the time period, and the average value or median value in the time period is used to calculate the respiratory-blood oxygen fluctuation synergistic effect data of each time period. For example, the data is counted according to the time period into the average synergistic effect value in the time period, and the fluctuation data of each time period is recorded, and finally the respiratory-blood oxygen fluctuation synergistic effect change data of surgical patients in different time periods are obtained.
[0131] Step S154: performing cross-time period fluctuation change comparison processing on the respiratory-blood oxygen fluctuation coordinated change data of the surgical patients in different time periods, so as to obtain the physiological fluctuation change trend data of the surgical patients between different time periods;
[0132] In an embodiment of the present invention, by using corresponding statistical analysis tools, such as time series analysis or variance analysis, the respiratory-blood oxygen fluctuation coordinated change data of surgical patients between different time periods are compared. For example, the fluctuation amplitude difference and trend change between each time period are calculated, the change trend of the data is displayed through a chart, and these fluctuation change trends are further analyzed to identify significant differences between time periods. Finally, the physiological fluctuation change trend data of surgical patients between different time periods are obtained, and these data reveal the evolution trend of physiological fluctuations over time during the operation.
[0133] Step S155: Perform physiological stability assessment analysis on the physiological fluctuation change trend data of surgical patients in different time periods to obtain a physiological stability assessment factor for surgical patients.
[0134] In an embodiment of the present invention, a physiological stability evaluation and analysis is performed on the previously analyzed data of the changing trends of the physiological fluctuations of surgical patients between different time periods, so as to evaluate and calculate the physiological stability indicators of each time period. These indicators include indicators such as heart rate variability (HRV) and blood pressure fluctuations, so as to evaluate and determine the consistency and stability of the physiological fluctuations. For example, the standard deviation of the physiological fluctuation data in each time period is calculated, and its changing trend over time is evaluated, and these indicators are compared with the set normal range or threshold value, so as to evaluate and analyze and obtain the corresponding physiological stability evaluation factors, which reflect the stability of the patient's physiological state during the operation, and finally obtain the physiological stability evaluation factors of the surgical patient.
[0135] Further, step S2 includes the following steps:
[0136] Step S21: Acquire the anesthetic drug use record data of the surgical patient;
[0137] In an embodiment of the present invention, the anesthetic drug usage records of surgical patients are extracted from the hospital electronic health record system. In a specific implementation, relevant records are exported from the database through the use of a data extraction tool through specified query conditions (such as patient ID, surgery date, anesthetic drug type, etc.). These records include the dosage, administration time and frequency of each anesthetic drug. The data extraction tool should support processing large amounts of data and ensure data integrity and accuracy, such as using the SQL query language to operate the database, or using the API interface to obtain data from the health information system, and finally obtain the anesthetic drug usage record data of surgical patients.
[0138] Step S22: performing a time series distribution analysis of the anesthetic drug usage record data of the surgical patients to obtain a time series distribution of the anesthetic drug dosage usage of the surgical patients;
[0139] In an embodiment of the present invention, the previously collected and acquired record data on the use of anesthetic drugs for surgical patients are sorted according to a time series, and a statistical analysis method is applied to calculate the dose distribution of each anesthetic drug used during the entire operation. For example, a time series analysis tool (such as the Pandas library in Python or the xts package in R language) is used to group and count the record data on the use of anesthetic drugs for surgical patients to analyze the distribution of the use of the corresponding anesthetic drugs over time and at each time point. This analysis can reveal the peak and trough periods of drug use, as well as the change pattern of dose over time, and ultimately obtain the time series distribution of anesthetic drug doses for surgical patients.
[0140] Step S23: performing a dynamic change trend analysis of physiological response of the surgical patient's physiological monitoring data based on the time series distribution of the surgical patient's anesthetic drug dosage, and obtaining dynamic change trend data of physiological response of the surgical patient's anesthetic drug usage;
[0141] In an embodiment of the present invention, a statistical analysis of the dynamic change trend of physiological response of the corresponding physiological monitoring data of surgical patients is performed by combining the time-series distribution of anesthetic drug dosage used by surgical patients obtained in the previous analysis. In this stage, the physiological monitoring data recorded during the operation (such as heart rate, blood pressure, respiratory rate, etc.) are compared and analyzed with the data recorded for anesthetic drug use, and dynamic analysis methods (such as regression analysis or time series modeling) are used to explore the impact of anesthetic drug dosage changes on physiological parameters. For example, linear regression analysis is performed using statistical software to detect the impact trend of drug dosage on physiological response, and the results are visualized as a change trend graph to facilitate further analysis and decision-making, and finally the dynamic change trend data of physiological response of surgical patients using anesthetic drugs is obtained.
[0142] Step S24: performing drug use-physiological response prediction analysis on the dynamic change trend data of the physiological response of the surgical patients to the use of anesthetic drugs, so as to obtain the physiological response data of the surgical patients under different anesthetic drug dosages; performing anesthesia depth estimation processing on the physiological response data of the surgical patients under different anesthetic drug dosages, so as to obtain the physiological anesthesia depth data of the surgical patients;
[0143] In an embodiment of the present invention, a predictive modeling technique is used to perform a predictive analysis of the drug usage-physiological response status on the dynamic change trend data of the physiological response to anesthetic drug use of surgical patients obtained by previous analysis, so as to predict and analyze the effects of different drug doses on physiological responses. A machine learning algorithm (such as a support vector machine, a decision tree, a random forest, etc.) can be used to establish a predictive model between drug dose and physiological response, and by training the model, the physiological response status under different anesthetic drug doses can be predicted. During the model training process, the known drug dose and physiological response data need to be divided into a training set and a test set, the prediction accuracy of the model needs to be evaluated, and the trained model is used to perform predictive analysis on new data, thereby obtaining the physiological response data of surgical patients under different anesthetic drug doses. At the same time, the depth of anesthesia is estimated by analyzing the physiological response data of surgical patients at different doses of anesthetic drugs obtained by previous prediction analysis, so as to estimate the depth level of anesthesia by using an algorithm through analyzing the physiological response data. An anesthetic depth estimation algorithm based on physiological parameters can be used, such as a depth analysis method based on electroencephalogram (EEG) or other physiological signals. In the specific implementation process, a specific physiological monitoring device is used to obtain the patient's physiological parameter data, and then a special depth estimation algorithm (such as the Bispectral Index (BIS) algorithm) is used to analyze the corresponding physiological response data. The calculation formula can be: , where The physiological depth of anesthesia for surgical patients. The dosage of anesthetic drugs is Dosages for anesthetic drugs Physiological EEG data under is the physiological EEG weight coefficient, Dosages for anesthetic drugs The physiological heart rate data below, is the physiological heart rate weight coefficient, is the attenuation coefficient of the effect of the anesthetic drug dosage, Dosages for anesthetic drugs Blood oxygen saturation data, is the blood oxygen saturation weight coefficient, Dosages for anesthetic drugs The mean arterial pressure data under is the arterial pressure weight coefficient to evaluate the patient's anesthesia depth and ultimately obtain the physiological anesthesia depth data of the surgical patient.
[0144] Step S25: Perform an anesthesia safety assessment analysis on the physiological anesthesia depth data of the surgical patient to obtain an anesthesia depth safety assessment factor for the surgical patient.
[0145] In an embodiment of the present invention, an evaluation and analysis of the safety of anesthesia is performed on the previously estimated physiological anesthesia depth data of surgical patients by using corresponding evaluation tools (such as safety evaluation algorithms and safety standards) to evaluate and analyze and check whether the corresponding anesthesia depth is within a safe range. For example, safety thresholds are set and the actual anesthesia depth data are compared with these thresholds to evaluate whether there is a risk of over-anesthesia or under-anesthesia, and a safety evaluation report is generated to provide specific safety evaluation factors, wherein the evaluation factors include anesthetic drug concentration, patient consciousness state, stability of anesthesia depth, emergency treatment effects and possible complications, etc., so as to demonstrate the safety performance during anesthesia and ensure anesthesia safety during surgery. Finally, an evaluation and analysis is performed to obtain a safety evaluation factor for the anesthesia depth of surgical patients.
[0146] Further, step S25 includes the following steps:
[0147] Step S251: performing fluctuation amplitude analysis on the physiological anesthesia depth data of the surgical patient to obtain the fluctuation amplitude data of the physiological anesthesia depth of the surgical patient;
[0148] In an embodiment of the present invention, a signal processing tool is used to perform high-pass filtering on the physiological anesthesia depth data of surgical patients obtained by previous analysis to remove low-frequency noise, and the fluctuation amplitude of the data is calculated by using a time domain analysis method, which includes calculating the standard deviation or root mean square (RMS) value of the signal to reflect the fluctuation of the anesthesia depth. The specific operation includes dividing the continuous anesthesia depth data into a number of time windows, and then calculating the difference between the maximum and minimum values of the anesthesia depth in each window. This difference value is used as the fluctuation amplitude data of the anesthesia depth to reflect the fluctuation of the anesthesia depth during the operation, and finally the fluctuation amplitude data of the physiological anesthesia depth of surgical patients is obtained.
[0149] Step S252: performing physiological emergency response evaluation and analysis on the physiological anesthesia depth data of the surgical patient based on the fluctuation amplitude data of the physiological anesthesia depth of the surgical patient, and obtaining the physiological emergency response processing efficiency of the physiological anesthesia depth of the surgical patient when the physiological anesthesia depth is abnormal;
[0150] In an embodiment of the present invention, the physiological emergency response status of the corresponding surgical patient's physiological anesthesia depth data is evaluated and analyzed by combining the surgical patient's physiological anesthesia depth fluctuation amplitude data obtained in the previous analysis, so as to analyze the response of the anesthesia depth in the case of sudden physiological abnormalities by establishing an emergency response model based on the fluctuation amplitude. The specific implementation includes inputting the fluctuation amplitude data into the model, and the model includes threshold setting and response algorithm. For the anesthesia depth data, when it is detected that the data fluctuation amplitude exceeds the preset threshold, the model will automatically record and analyze the relevant emergency processing time and efficiency, and finally the physiological emergency response processing efficiency of the surgical patient's physiological anesthesia depth in the case of sudden physiological abnormalities, thereby reflecting the emergency response capability of the anesthesia depth in the case of sudden physiological abnormalities.
[0151] Step S253: Quantitatively analyzing the safety level of the physiological emergency response processing efficiency of the surgical patient's physiological anesthesia depth when the patient suddenly experiences physiological abnormalities, so as to obtain the physiological safety level of the surgical patient's anesthesia depth;
[0152] In an embodiment of the present invention, a quantitative analysis method is used to quantify the safety level of the physiological emergency response processing efficiency of the surgical patient's physiological anesthesia depth in the event of sudden physiological abnormalities, so as to analyze the emergency response processing efficiency previously analyzed by using a quantitative analysis method. The specific operations include calculating the time delay and processing effect of the reaction processing efficiency, such as using the mean square error (MSE) to evaluate the deviation of the response time from the expected target, and scoring the processing efficiency by setting a safety level standard to quantify the safety level of the anesthesia depth in emergency situations. This safety level is used to judge the stability and effectiveness of the anesthesia depth, and finally the physiological safety level of the anesthesia depth of the surgical patient is obtained.
[0153] Step S254: Perform an anesthesia safety assessment analysis on the physiological safety level of the anesthesia depth of the surgical patient to obtain an anesthesia depth safety assessment factor for the surgical patient.
[0154] In an embodiment of the present invention, an evaluation and analysis of anesthesia safety is performed on the physiological safety level of the anesthesia depth of surgical patients obtained by previous analysis, and anesthesia safety analysis is performed based on the physiological safety level obtained in step S253 and a comprehensive evaluation method. The specific implementation process includes comparing the physiological safety level data with the historical data, and using a weighted scoring model to calculate the final anesthesia safety evaluation factor. The evaluation factors include anesthetic drug concentration, patient consciousness state, stability of anesthesia depth, emergency treatment effect and possible complication risks, etc., so as to demonstrate the safety performance during anesthesia and finally determine the safety evaluation factor of the anesthesia depth of surgical patients.
[0155] Anesthesia depth safety assessment factors include anesthetic drug concentration and patient consciousness status.
[0156] Further, step S3 includes the following steps:
[0157] Step S31: performing signal amplitude variation characteristic analysis on the corresponding physiological monitoring signal in the physiological monitoring data of the surgical patient to obtain abnormal characteristic data of amplitude fluctuation of the physiological signal of the surgical patient;
[0158] In an embodiment of the present invention, a high-pass filter is used to preprocess the corresponding physiological monitoring signal in the physiological monitoring data of the surgical patient to remove low-frequency noise and interference, and the physiological monitoring signal is decomposed into multiple time-frequency domain components by applying short-time Fourier transform (STFT), from which time series data of signal amplitude are extracted, and statistical methods such as standard deviation, root mean square (RMS) and coefficient of variation are used to calculate the variation characteristics of the signal amplitude. Specifically, the signal amplitude data is segmented, and the amplitude fluctuation range of each segment is calculated to obtain the amplitude variation coefficient of each segment, so as to identify abnormal characteristic data of amplitude fluctuation. These data can reveal the abnormal fluctuation of the physiological signal of the surgical patient during the operation, and finally obtain the abnormal characteristic data of the amplitude fluctuation of the physiological signal of the surgical patient.
[0159] Step S32: Based on the abnormal amplitude fluctuation characteristic data of the surgical patient's physiological signal, a dynamic stress response model is performed on the corresponding physiological monitoring signal in the surgical patient's physiological monitoring data to obtain a dynamic stress response model of the abnormal amplitude fluctuation of the surgical patient's physiological signal;
[0160] In an embodiment of the present invention, an autoregressive moving average (ARMA) model or a long short-term memory (LSTM) network is selected to model the corresponding physiological monitoring signals in the physiological monitoring data of surgical patients in combination with abnormal amplitude fluctuation characteristic data of surgical patients obtained by previous analysis, so that the abnormal amplitude characteristic data obtained by previous analysis is input into the autoregressive moving average (ARMA) model or the long short-term memory (LSTM) network, and the model is analyzed to capture the dynamic relationship between signal amplitude fluctuation and stress response. By training the model, a dynamic model of stress response of abnormal amplitude of physiological signals of surgical patients is finally obtained. The model training process includes data annotation, optimization of model parameters and error analysis, so as to generate a dynamic model that can predict the fluctuation of physiological signals under different stress states.
[0161] Step S33: performing physiological response status evaluation and analysis on the dynamic model of stress response to abnormal amplitude of physiological signals of surgical patients to obtain physiological response status data of surgical patients;
[0162] In an embodiment of the present invention, an evaluation and analysis of the physiological reaction status is performed on the previously modeled dynamic model of the abnormal stress reaction of the physiological signal amplitude of the surgical patient, so that the physiological signals collected during the real-time operation are predicted by using the model and compared with the actual monitoring data. The corresponding physiological reaction status is evaluated by calculating the difference between the predicted value and the actual value. The specific operation includes using error analysis tools, such as mean square error (MSE) and mean absolute error (MAE), to quantitatively evaluate the accuracy of the model prediction, and finally obtain the physiological reaction status data of the surgical patient, which shows the patient's physiological stress condition during the operation and the abnormal physiological reaction state that exists.
[0163] Step S34: Perform surgical anesthesia quality evaluation calculation on the surgical patient's physiological response status data based on the surgical patient's physiological stability evaluation factor and the surgical patient's anesthesia depth safety evaluation factor to obtain the surgical patient's anesthesia quality score.
[0164] In an embodiment of the present invention, the surgical anesthesia quality is evaluated and quantified by combining the surgical patient's physiological stability evaluation factor and the surgical patient's anesthesia depth safety evaluation factor obtained by the previous evaluation and analysis to the corresponding surgical patient's physiological reaction status data, so as to use a weighted scoring calculation formula to combine the above evaluation factors (wherein the physiological stability evaluation factor includes indicators such as heart rate variability (HRV) and blood pressure fluctuation, and the anesthesia depth safety evaluation factor includes anesthetic drug concentration and patient consciousness state) with the physiological reaction status data to quantitatively calculate the anesthesia quality score. The specific implementation includes inputting the numerical value of the evaluation factor into a preset scoring calculation formula, for example: , where Scoring the quality of anesthesia for surgical patients, The total number of factors that assess the physiological stability of surgical patients, For the The actual value of the physiological stability assessment factor for surgical patients, For the The weight coefficient of the physiological stability assessment factor of each surgical patient, The total number of factors for safety assessment of the depth of anesthesia in surgical patients, For the The actual value of the safety assessment factor for the depth of anesthesia in surgical patients. For the The weight coefficients of the safety assessment factors of the depth of anesthesia for surgical patients are summarized to obtain the final anesthesia quality score, which is used to judge the overall quality of surgical anesthesia, ensure the physiological stability and anesthesia safety of patients during the operation, and finally quantify and calculate the anesthesia quality score for surgical patients.
[0165] Furthermore, the present invention also provides a system for evaluating the quality of surgical anesthesia, which is used to perform the method for evaluating the quality of surgical anesthesia as described above. The system for evaluating the quality of surgical anesthesia includes:
[0166] The physiological stability assessment module is used to obtain the physiological monitoring data of the surgical patient, and to perform respiratory rate and blood oxygen saturation analysis on the physiological monitoring data of the surgical patient, so as to obtain the respiratory rate data and blood oxygen saturation data of the surgical patient; perform physiological stability assessment and analysis based on the respiratory rate data and blood oxygen saturation data of the surgical patient, so as to obtain the physiological stability assessment factor of the surgical patient;
[0167] The anesthesia depth safety assessment module is used to obtain the anesthetic drug use record data of the surgical patient, and perform anesthesia depth monitoring on the surgical patient's physiological monitoring data based on the anesthetic drug use record data of the surgical patient to obtain the surgical patient's physiological anesthesia depth data; perform an anesthesia safety assessment and analysis on the surgical patient's physiological anesthesia depth data, thereby obtaining the surgical patient's anesthesia depth safety assessment factor;
[0168] The surgical anesthesia quality scoring module is used to evaluate and analyze the physiological response status of the surgical patient's physiological monitoring data to obtain the surgical patient's physiological response status data; based on the surgical patient's physiological stability evaluation factor and the surgical patient's anesthesia depth safety evaluation factor, the surgical patient's physiological response status data is evaluated and calculated to obtain the surgical patient's anesthesia quality score;
[0169] The surgical anesthesia quality feedback evaluation module is used to perform anesthesia quality feedback analysis based on the surgical patient anesthesia quality score to generate a surgical patient anesthesia quality feedback evaluation report.
[0170] Furthermore, the present invention also provides a terminal, comprising a processor, a memory, and a computer control unit stored in the memory and executable on the processor, for executing the method for evaluating surgical anesthesia quality as described above.
[0171] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.
[0172] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.
Claims
1. A method for evaluating the quality of surgical anesthesia, characterized in that: The following steps are involved: Step S1: Acquire the physiological monitoring data of the surgical patient, and perform respiratory rate and blood oxygen saturation analysis on the physiological monitoring data of the surgical patient to obtain the respiratory rate data and blood oxygen saturation data of the surgical patient; A physiological stability assessment analysis is performed based on the respiratory rate data and the blood oxygen saturation data of the surgical patient to obtain a physiological stability assessment factor of the surgical patient; wherein step S1 includes the following steps: Step S11: Acquiring physiological monitoring data of surgical patients; Step S12: demodulating and filtering the respiratory signal in the physiological monitoring data of the surgical patient to obtain smoothed data of the respiratory signal of the surgical patient; Step S13: performing respiratory signal spectrum conversion processing on the smoothed data of the surgical patient's respiratory signal to generate a respiratory signal spectrum diagram of the surgical patient; performing respiratory frequency statistical analysis on the respiratory signal spectrum diagram of the surgical patient to obtain respiratory frequency data of the surgical patient; Step S14: performing blood oxygen saturation analysis on the physiological monitoring data of the surgical patient to obtain blood oxygen saturation data of the surgical patient; wherein step S14 includes the following steps: Step S141: extracting blood oxygen spectrum signals from the physiological monitoring data of the surgical patient to obtain blood oxygen spectrum signal data of the surgical patient; Step S142: performing blood oxygen saturation-related wavelength separation processing on the blood oxygen spectrum signal data of the surgical patient to obtain the blood oxygen saturation-related signal wavelength region of the surgical patient; Step S143: performing spectral signal intensity characteristic analysis on the wavelength region of the signal related to the blood oxygen saturation of the surgical patient to obtain blood oxygen spectral signal intensity data of the surgical patient; Step S144: performing pulse fluctuation calibration processing on the blood oxygen spectrum signal data of the surgical patient based on the blood oxygen spectrum signal intensity data of the surgical patient to obtain calibration optimization data of the blood oxygen spectrum signal of the surgical patient; wherein step S144 includes the following steps: Performing time series characteristic analysis on the blood oxygen spectrum signal intensity data of surgical patients to obtain the time series characteristic data of the blood oxygen spectrum intensity of surgical patients; Analyze the variation law of the blood oxygen spectrum intensity of surgical patients based on the time series characteristic data of the blood oxygen spectrum intensity, and obtain the variation law data of the blood oxygen spectrum intensity of surgical patients; Based on the blood oxygen spectrum intensity change law data of surgical patients, the pulse fluctuation dynamic change curve analysis is performed on the blood oxygen spectrum signal data of surgical patients to generate the pulse fluctuation dynamic change curve of the blood oxygen signal of surgical patients; The pulse fluctuation change drift area of the dynamic change curve of the blood oxygen signal pulse fluctuation of the surgical patient is monitored to obtain the pulse fluctuation change drift area in the blood oxygen pulse change curve of the surgical patient; the signal drift compensation analysis is performed on the pulse fluctuation change drift area in the blood oxygen pulse change curve of the surgical patient to obtain the blood oxygen pulse fluctuation signal drift compensation coefficient of the surgical patient; According to the drift compensation coefficient of the blood oxygen pulse fluctuation signal of the surgical patient, a signal drift compensation calibration process is performed on the corresponding blood oxygen spectrum signal drift data part in the blood oxygen spectrum signal data of the surgical patient to obtain the calibration optimization data of the blood oxygen spectrum signal of the surgical patient; Step S145: performing blood oxygen saturation evaluation and analysis on the calibration and optimization data of the blood oxygen spectrum signal of the surgical patient to obtain the blood oxygen saturation data of the surgical patient; Step S15: performing physiological stability assessment analysis based on the surgical patient's respiratory rate data and the surgical patient's blood oxygen saturation data to obtain a physiological stability assessment factor for the surgical patient; Step S2: Acquire the anesthetic drug use record data of the surgical patient, and perform anesthesia depth monitoring on the surgical patient's physiological monitoring data based on the anesthetic drug use record data to obtain the surgical patient's physiological anesthesia depth data; perform an anesthesia safety assessment analysis on the surgical patient's physiological anesthesia depth data to obtain the surgical patient's anesthesia depth safety assessment factor; Step S3: performing physiological response status evaluation and analysis on the physiological monitoring data of the surgical patient to obtain the physiological response status data of the surgical patient; performing surgical anesthesia quality evaluation and calculation on the physiological response status data of the surgical patient based on the physiological stability evaluation factor of the surgical patient and the anesthesia depth safety evaluation factor of the surgical patient to obtain the anesthesia quality score of the surgical patient; Step S4: Perform an anesthesia quality feedback analysis based on the anesthesia quality score of the surgical patient to generate an anesthesia quality feedback evaluation report for the surgical patient.
2. The method for evaluating surgical anesthesia quality according to claim 1, characterized in that: Step S15 includes the following steps: Step S151: performing respiratory rhythm fluctuation analysis on the respiratory frequency data of the surgical patient to obtain respiratory rhythm fluctuation pattern data of the surgical patient; Step S152: performing blood oxygen fluctuation coordinated change analysis on the blood oxygen saturation data of the surgical patient based on the respiratory rhythmic fluctuation pattern data of the surgical patient to generate respiratory-blood oxygen fluctuation coordinated effect change data of the surgical patient; Step S153: dividing the respiratory-blood oxygen fluctuation synergistic effect change data of the surgical patient into time periods, and obtaining the respiratory-blood oxygen fluctuation synergistic change data of the surgical patient in different time periods; Step S154: performing cross-time period fluctuation change comparison processing on the respiratory-blood oxygen fluctuation coordinated change data of the surgical patients in different time periods, so as to obtain the physiological fluctuation change trend data of the surgical patients between different time periods; Step S155: Perform physiological stability assessment analysis on the physiological fluctuation change trend data of surgical patients in different time periods to obtain a physiological stability assessment factor for surgical patients.
3. The method for evaluating surgical anesthesia quality according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: Acquire the anesthetic drug use record data of the surgical patient; Step S22: performing a time series distribution analysis of the anesthetic drug usage record data of the surgical patients to obtain a time series distribution of the anesthetic drug dosage usage of the surgical patients; Step S23: performing a dynamic change trend analysis of physiological response of the surgical patient's physiological monitoring data based on the time series distribution of the surgical patient's anesthetic drug dosage, and obtaining dynamic change trend data of physiological response of the surgical patient's anesthetic drug usage; Step S24: performing drug use-physiological response prediction analysis on the dynamic change trend data of the physiological response of the surgical patients to the use of anesthetic drugs, so as to obtain the physiological response data of the surgical patients under different anesthetic drug dosages; performing anesthesia depth estimation processing on the physiological response data of the surgical patients under different anesthetic drug dosages, so as to obtain the physiological anesthesia depth data of the surgical patients; Step S25: Perform an anesthesia safety assessment analysis on the physiological anesthesia depth data of the surgical patient to obtain an anesthesia depth safety assessment factor for the surgical patient.
4. The method for evaluating surgical anesthesia quality according to claim 3, characterized in that: Step S25 includes the following steps: Step S251: performing fluctuation amplitude analysis on the physiological anesthesia depth data of the surgical patient to obtain the fluctuation amplitude data of the physiological anesthesia depth of the surgical patient; Step S252: performing physiological emergency response evaluation and analysis on the physiological anesthesia depth data of the surgical patient based on the fluctuation amplitude data of the physiological anesthesia depth of the surgical patient, and obtaining the physiological emergency response processing efficiency of the physiological anesthesia depth of the surgical patient when the physiological anesthesia depth is abnormal; Step S253: Quantitatively analyzing the safety level of the physiological emergency response processing efficiency of the surgical patient's physiological anesthesia depth when the patient suddenly experiences physiological abnormalities, so as to obtain the physiological safety level of the surgical patient's anesthesia depth; Step S254: Perform an anesthesia safety assessment analysis on the physiological safety level of the anesthesia depth of the surgical patient to obtain an anesthesia depth safety assessment factor for the surgical patient.
5. The method for evaluating surgical anesthesia quality according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing signal amplitude variation characteristic analysis on the corresponding physiological monitoring signal in the physiological monitoring data of the surgical patient to obtain abnormal characteristic data of amplitude fluctuation of the physiological signal of the surgical patient; Step S32: Based on the abnormal amplitude fluctuation characteristic data of the surgical patient's physiological signal, a dynamic stress response model is performed on the corresponding physiological monitoring signal in the surgical patient's physiological monitoring data to obtain a dynamic stress response model of the abnormal amplitude fluctuation of the surgical patient's physiological signal; Step S33: performing physiological response status evaluation and analysis on the dynamic model of stress response to abnormal amplitude of physiological signals of surgical patients to obtain physiological response status data of surgical patients; Step S34: Perform surgical anesthesia quality evaluation calculation on the surgical patient's physiological response status data based on the surgical patient's physiological stability evaluation factor and the surgical patient's anesthesia depth safety evaluation factor to obtain the surgical patient's anesthesia quality score.
6. A system for evaluating the quality of surgical anesthesia, characterized in that: For executing the method for evaluating the quality of surgical anesthesia as claimed in claim 1, the system for evaluating the quality of surgical anesthesia comprises: The physiological stability assessment module is used to obtain the physiological monitoring data of the surgical patient, and to perform respiratory rate and blood oxygen saturation analysis on the physiological monitoring data of the surgical patient, so as to obtain the respiratory rate data and blood oxygen saturation data of the surgical patient; perform physiological stability assessment and analysis based on the respiratory rate data and blood oxygen saturation data of the surgical patient, so as to obtain the physiological stability assessment factor of the surgical patient; The anesthesia depth safety assessment module is used to obtain the anesthetic drug use record data of the surgical patient, and perform anesthesia depth monitoring on the surgical patient's physiological monitoring data based on the anesthetic drug use record data of the surgical patient to obtain the surgical patient's physiological anesthesia depth data; perform an anesthesia safety assessment and analysis on the surgical patient's physiological anesthesia depth data, thereby obtaining the surgical patient's anesthesia depth safety assessment factor; The surgical anesthesia quality scoring module is used to evaluate and analyze the physiological response status of the surgical patient's physiological monitoring data to obtain the surgical patient's physiological response status data; based on the surgical patient's physiological stability evaluation factor and the surgical patient's anesthesia depth safety evaluation factor, the surgical patient's physiological response status data is evaluated and calculated to obtain the surgical patient's anesthesia quality score; The surgical anesthesia quality feedback evaluation module is used to perform anesthesia quality feedback analysis based on the surgical patient anesthesia quality score to generate a surgical patient anesthesia quality feedback evaluation report.
7. A terminal, characterized in that: The method comprises a processor, a memory and a computer control unit stored in the memory and operable on the processor, and is used to execute the method for evaluating the quality of surgical anesthesia as claimed in any one of claims 1 to 5.
Citation Information
Cited By
Intelligent evaluation system for anesthesia depth
CN120814791A
