Anesthetic gas concentration detection and early warning method

Abstract

The invention provides an anesthetic gas concentration detection and early warning method, and relates to the technical field of medical treatment. The anesthetic gas concentration detection and early warning method specifically comprises the following steps: S1, setting biofeedback equipment; s2, biological feedback signal processing and analysis; s3, performing gas concentration adjustment and biological feedback closed-loop control; s4, implementing a double-layer early warning mechanism; s5, performing predictive early warning and deep nerve regulation and control; s6, anesthetic gas management and non-invasive feedback enhancement; and S7, context awareness and personalized adjustment are carried out. Through signal processing, intelligent closed-loop control, comprehensive multi-dimensional monitoring and personalized dynamic adjustment, the anesthetic gas concentration detection and early warning method has the remarkable advantages in the aspects of ensuring the safety of a patient, improving the anesthetic precision, reducing side effects and achieving efficient management, the anesthetic management process can be optimized, and the anesthetic gas concentration detection and early warning method has the advantages that the anesthetic gas concentration detection and early warning effects are improved. And a solid guarantee is provided for safe operation of the operating room.

Description

Technical Field

[0001] The invention relates to the field of medical technology, and in particular to an anesthetic gas concentration detection and early warning method. Background Art

[0002] Anesthesia is a medical technology that uses drugs to make patients lose their senses, especially pain, so that surgery or other medical procedures can be performed painlessly. Anesthesia can be divided into local anesthesia, which only anesthetizes specific parts of the body. Regional anesthesia, which anesthetizes a larger area, such as spinal anesthesia. General anesthesia, which makes the entire body lose consciousness and sensation, is usually used for more complex and larger operations. In anesthesia, anesthetic gas concentration detection and warning are important measures to ensure patient safety and anesthetic effect during surgery. The main reasons include that too deep anesthesia may cause respiratory depression and cardiovascular instability; while too shallow anesthesia may cause intraoperative awareness, that is, the patient regains partial or full consciousness during the operation and experiences pain. Different patients react differently to anesthetic drugs, which are affected by factors such as age, weight, and health status, so the concentration of anesthetic gases needs to be adjusted in real time. During the operation, the physiological state may change. Timely detection and warning can quickly adjust the anesthesia strategy to ensure patient safety.

[0003] The existing technology mainly detects and warns the concentration of anesthetic gases through the following methods: First, conventional physiological parameter monitoring is one of the commonly used methods. The equipment will detect basic physiological parameters such as heart rate, blood pressure and blood oxygen saturation, and indirectly understand the patient's anesthesia state through the changes in these parameters. Secondly, gas analyzers (such as infrared absorption spectrometers and electrochemical sensors) directly measure the concentration of anesthetic gases and display the results on the monitor for reference by the anesthesiologist. Thirdly, the dosage of anesthetic drugs is usually adjusted manually, and the anesthesiologist makes judgments and adjustments based on the changes in physiological parameters and his own experience. Finally, the early warning system is mostly based on a single-layer early warning mechanism of limit values. When any monitoring parameter exceeds the preset safety range, the device will issue an alarm to remind medical staff to pay attention. In the above-mentioned prior art. First, the real-time performance of these methods is poor, the data collection and transmission speed is slow, and instantaneous response cannot be achieved. Secondly, the accuracy and stability of existing gas analyzers are limited, and they are easily affected by environmental noise and electromagnetic interference, thereby affecting the accuracy of the data. In addition, manual adjustment of the concentration of anesthetic drugs is prone to human errors, low degree of automation, and lack of intelligent regulation. Most of the existing early warning mechanisms are based on simple threshold judgments, lacking complex pattern recognition and predictive analysis, and are unable to warn of potential risks in advance. Finally, traditional methods mainly rely on anesthetic gases, lack multi-dimensional feedback and control methods, are difficult to adjust in a personalized and dynamic manner, and cannot fully adapt to the needs of different surgical scenarios. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an anesthetic gas concentration detection and early warning method, which solves the problems of low accuracy and intelligence in the prior art.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for detecting and warning the concentration of anesthetic gas, specifically comprising the following steps:

[0006] S1. Biofeedback Equipment Setup

[0007] Electroencephalograms are used to monitor the electrical activity of the brain to determine the depth of anesthesia of patients. Electromyograms are used to monitor muscle reactions to help assess the patient's response to external stimuli. Galvanic skin response is used to monitor changes in skin conductance to reflect the patient's pain or stress response. Before surgery, patients are given the above monitoring equipment to ensure the stability and accuracy of data collection.

[0008] S2. Biofeedback Signal Processing and Analysis

[0009] Physiological signals are collected simultaneously through multi-channel equipment, and the data are transmitted to the central processing unit at a high sampling rate. Low-pass filters are used to process biological signals to filter out environmental noise and electromagnetic interference to ensure data accuracy. Complex signals are decomposed into multiple frequency bands through wavelet transform of time-frequency analysis to capture physiological information in different frequency bands. Machine learning or deep learning algorithms are used to perform pattern recognition on pre-processed biological signals to decode characteristic signals representing anesthesia depth or pain response. Based on a large amount of surgical data, the threshold of biofeedback is set;

[0010] S3. Gas concentration regulation and biofeedback closed-loop control

[0011] Establish a closed-loop control system, connect the biofeedback signal with the anesthetic gas concentration control system to form a closed-loop control. The system adjusts the anesthetic gas concentration in real time according to the patient's physiological response to ensure that the depth of anesthesia is maintained within a reasonable range. Design an adaptive adjustment algorithm to automatically adjust the anesthetic gas concentration according to the individual differences, weight, and age of the patient. The algorithm can analyze the biofeedback signal in real time and provide an automated adjustment strategy. By connecting to the control interface of the intelligent anesthesia machine, the system can dynamically adjust the flow and concentration of the anesthetic gas.

[0012] S4. Implementation of the two-tier early warning mechanism

[0013] A multi-level early warning mechanism is set up based on the biofeedback signal. According to the abnormal physiological feedback of the patient, the operating room is equipped with an external gas monitoring sensor to detect the environmental concentration of anesthetic gas in real time to prevent gas leakage or equipment failure. If the environmental gas concentration exceeds the normal range, the system automatically issues an independent environmental warning to remind medical staff to check the equipment to avoid accidents.

[0014] S5. Predictive warning and deep neural regulation

[0015] Based on historical surgical data, the deep learning model LSTM is used to train the complex relationship between anesthetic gas concentration and biofeedback to build a prediction model. The system continuously collects new data during surgery, self-learns and dynamically updates the model to enhance prediction accuracy. During surgery, the model can predict possible changes in anesthesia depth in advance and generate trend graphs. The system issues warnings in advance based on trend graphs to prevent patients from waking up during surgery or being too deeply anesthetized. For complex surgeries or high-risk patients, the system can combine neuroregulatory equipment to reduce patients' response to pain while maintaining a low anesthetic gas concentration. Combining neuroregulation with anesthetic gas management can reduce the side effects of gas concentration and ensure patient safety.

[0016] S6. Anesthetic Gas Management and Non-Invasive Feedback Enhancement

[0017] Low-concentration anesthetic gas supply combined with non-invasive interventions can reduce gas concentration requirements and side effects;

[0018] S7. Situational awareness and personalized adjustment

[0019] It senses environmental changes and surgical progress in the operating room, and adjusts the concentration of anesthetic gas and the parameters of biofeedback linkage control in real time based on these factors to ensure personalized and dynamic adjustment of the anesthesia effect.

[0020] Preferably, in the setting of the biofeedback device in step S1, the EEG electrodes should be attached to the scalp, the EMG electrodes should be attached to the major muscle groups, and the biofeedback device should be calibrated before anesthesia begins to ensure that it can effectively collect signals under anesthesia.

[0021] Preferably, in the biofeedback signal processing and analysis in step S2, real-time data transmission is achieved through a low-power Bluetooth or Wi-Fi module to ensure that the data can reach the processing center of the system in a timely manner. The physiological information captured in different frequency bands includes decomposing the electroencephalogram signal into α and β waves of different bands to help determine the depth of anesthesia.

[0022] Preferably, in the step S3, when the patient's pain response is identified to be enhanced in the gas concentration adjustment and biofeedback closed-loop control, the concentration of isoflurane or sevoflurane will be increased, and when it is identified that the anesthesia is too deep, the gas supply will be reduced. The method system not only performs multi-dimensional control based on biofeedback, but also refers to the patient's basic vital signs, blood pressure, and heart rate to more accurately adjust the anesthetic concentration.

[0023] Preferably, during the implementation of the double-layer warning mechanism in step S4, the patient's physiological feedback includes unusual muscle reactions or brain wave changes in the electromyogram, which issues a first-level warning, indicating that the anesthesia effect is insufficient. The method system will notify the anesthesiologist when the warning occurs, and remind medical staff to adjust the anesthesia plan in advance through sound and visual prompts.

[0024] Preferably, the predictive warning and deep neuromodulation in step S5 are combined with neuromodulation equipment including spinal cord electrical stimulation or transcranial magnetic stimulation.

[0025] Preferably, the non-invasive intervention in the anesthetic gas management and non-invasive feedback enhancement in step S6 includes mild electrical stimulation, music therapy, and environmental control.

[0026] Preferably, the environmental changes in the situational awareness and personalized adjustment in step S7 include temperature, humidity, and device status.

[0027] The present invention provides an anesthetic gas concentration detection and early warning method, which has the following beneficial effects:

[0028] The present invention provides an anesthetic gas concentration detection and early warning method. The method of the present invention directly reflects the patient's anesthesia depth and pain response by combining the patient's biofeedback signal brain wave, electromyography, and skin conductance, rather than relying solely on physical detection of anesthetic gas concentration. This multi-dimensional signal acquisition and analysis makes the evaluation of anesthetic effect more comprehensive and accurate. Unlike the traditional method of only monitoring gas concentration, the innovative method can more accurately judge the depth of anesthesia and ensure that the patient's state during surgery is more stable and safe. Secondly, the real-time processing and analysis of biofeedback signals significantly improves the response speed of the system. Through high sampling rate, multi-channel equipment, and filtering and time-frequency analysis technology, the system can effectively eliminate noise and ensure the accuracy of the signal, and use machine learning algorithms to quickly identify and decode characteristic signals representing the depth of anesthesia, which enables the system to make adjustment decisions in a short time, thereby improving real-time performance and reducing the anesthesia risk caused by hysteresis. The introduction of the closed-loop control system of the present invention is another major advantage of the present method. The system can dynamically adjust the concentration of anesthetic gas according to the patient's real-time biofeedback signal to ensure that the depth of anesthesia is always maintained within a reasonable range. Compared with traditional manual adjustment, the closed-loop control system can automatically and accurately perform personalized adjustments, taking into account the individual differences of patients, and ensuring the precise match of anesthetic gas concentration with physiological state, thereby realizing truly personalized anesthesia management. Finally, the multi-level early warning mechanism of the present invention makes the system more forward-looking and safe. The traditional early warning mechanism is based on a simple threshold, while the innovative method combines biofeedback and environmental data to set up a multi-level early warning mechanism and prediction model, which can predict the changing trend of anesthesia depth in advance and issue an early warning. The double warning not only takes into account the patient's biological response, but also pays attention to changes in the surgical environment, reducing the potential incidence of anesthesia accidents. Therefore, the advantages of the method of the present invention in anesthesia management are mainly reflected in the real-time linkage, dynamic adjustment and personalized control of multi-dimensional biological signals, as well as the implementation of a double-layer early warning mechanism, which greatly improves the accuracy and safety of the anesthesia effect. DETAILED DESCRIPTION

[0029] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] The embodiment of the present invention provides an anesthetic gas concentration detection and early warning method, which specifically includes the following steps:

[0031] S1. Biofeedback Equipment Setup

[0032] Use electroencephalogram (EEG) to monitor the brain's electrical activity to determine the patient's anesthesia depth, use electromyography (EMG) to monitor muscle reactions to help assess the patient's response to external stimuli, and use galvanic skin response to monitor changes in skin conductance to reflect the patient's pain or stress response. Before surgery, patients should wear the above monitoring equipment to ensure the stability and accuracy of data collection. For example, EEG electrodes should be attached to the scalp, and EMG electrodes should be attached to major muscle groups. Before anesthesia begins, the biofeedback device should be calibrated to ensure that it can effectively collect signals under anesthesia;

[0033] S2. Biofeedback Signal Processing and Analysis

[0034] Physiological signals are collected simultaneously through multi-channel devices, and the data is transmitted to the central processing unit at a high sampling rate. Real-time data transmission is achieved through low-power Bluetooth or Wi-Fi modules to ensure that the data can reach the processing center of the system in a timely manner. Filters (such as high-pass and low-pass filters) are used to process biological signals to filter out environmental noise and electromagnetic interference to ensure data accuracy. Complex signals are decomposed into multiple frequency bands through time-frequency analysis (such as wavelet transform) to capture physiological information in different frequency bands. For example, electroencephalogram signals can be decomposed into different bands (such as α and β waves) to help determine the depth of anesthesia. Machine learning or deep learning algorithms are used to perform pattern recognition on pre-processed biological signals to decode characteristic signals representing the depth of anesthesia or pain response. Based on a large amount of surgical data, the threshold of biofeedback is set. For example, specific frequency changes in electroencephalogram signals can indicate that the patient has entered a state of shallow anesthesia or too deep anesthesia.

[0035] S3. Gas concentration regulation and biofeedback closed-loop control

[0036] Establish a closed-loop control system, connect the biofeedback signal with the anesthetic gas concentration control system to form a closed-loop control. The system adjusts the anesthetic gas concentration in real time according to the patient's physiological response to ensure that the depth of anesthesia is maintained within a reasonable range. Design an adaptive adjustment algorithm to automatically adjust the anesthetic gas concentration according to the individual differences, weight, and age of the patient. The algorithm can analyze the biofeedback signal in real time and provide an automated adjustment strategy. By connecting to the control interface of the intelligent anesthesia machine, the system can dynamically adjust the flow and concentration of the anesthetic gas. For example, when the system recognizes that the patient's pain response is enhanced, it will increase the concentration of isoflurane or sevoflurane. When it recognizes that the anesthesia is too deep, it will reduce the gas supply. The system not only uses biofeedback, but also refers to the patient's basic vital signs (such as blood pressure, heart rate, etc.) for multi-dimensional control to more accurately adjust the anesthetic concentration;

[0037] S4. Implementation of the two-tier early warning mechanism

[0038] A multi-level warning mechanism is set up according to the biofeedback signal. According to the abnormal physiological feedback of the patient, such as unusual muscle reaction or brain wave changes in the electromyogram, a first-level warning (which may indicate insufficient anesthesia effect) will be issued. The system will notify the anesthesiologist when the warning occurs, and remind the medical staff to adjust the anesthesia plan in advance through sound and visual prompts. The operating room is equipped with an external gas monitoring sensor to detect the environmental concentration of anesthetic gas in real time to prevent gas leakage or equipment failure. If the environmental gas concentration exceeds the normal range, the system will automatically issue an independent environmental warning to remind medical staff to check the equipment to avoid accidents.

[0039] S5. Predictive warning and deep neural regulation

[0040] Based on historical surgical data, the deep learning model LSTM is used to train the complex relationship between anesthetic gas concentration and biofeedback to build a prediction model. The system continuously collects new data during surgery, self-learns and dynamically updates the model to enhance prediction accuracy. During surgery, the model can predict possible changes in anesthesia depth in advance and generate trend graphs. The system issues warnings in advance based on trend graphs to prevent patients from waking up during surgery or being too deeply anesthetized. For complex surgeries or high-risk patients, the system can combine neuroregulatory devices (such as spinal cord electrical stimulation or transcranial magnetic stimulation) to reduce patients' response to pain while maintaining a low anesthetic gas concentration. Combining neuroregulation with anesthetic gas management can reduce the side effects of gas concentration and ensure patient safety.

[0041] S6. Anesthetic Gas Management and Non-Invasive Feedback Enhancement

[0042] By supplying low-concentration anesthetic gases, combined with non-invasive interventions (such as mild electrical stimulation, music therapy, and environmental control), the gas concentration requirement can be reduced and side effects can be reduced;

[0043] S7. Situational awareness and personalized adjustment

[0044] It senses environmental changes in the operating room (such as temperature, humidity, equipment status) and the progress of the operation, and adjusts the concentration of anesthetic gas and the parameters of biofeedback linkage control in real time based on these factors to ensure personalized and dynamic adjustment of the anesthesia effect.

[0045] Specifically, in the closed-loop control system of the present invention:

[0046] The system architecture is as follows: the biofeedback acquisition module is responsible for collecting EEG, EMG, and EDA physiological signals. The data processing and analysis module performs signal preprocessing, feature extraction, and real-time analysis. The control decision module makes decisions through adaptive adjustment algorithms. The execution module enables the intelligent anesthesia machine to achieve specific adjustments.

[0047] The specific collection operation is to install EEG and EMG electrodes on the patient's head and muscles, and install EDA sensors on the skin surface, connected to the collection device such as Arduino or Raspberry Pi. The data is transmitted to the central processing unit (CPU) in real time via Wi-Fi or Bluetooth module.

[0048] Among them, real-time data collection and storage:

[0049]

[0050] Data preprocessing:

[0051]

[0052]

[0053] Feature extraction and real-time analysis Time domain and frequency domain feature extraction:

[0054]

[0055]

[0056] Dynamic adjustment algorithm Adaptive adjustment algorithm Reinforcement learning algorithm:

[0057]

[0058]

[0059] Training and Optimizing the Training Process:

[0060]

[0061] Real-time feedback adjustment

[0062] Interface establishment and transmission

[0063] TCP / IP interface: Communication with the intelligent anesthesia machine is achieved through TCP / IP.

[0064] Control command transmission:

[0065]

[0066] Intelligent regulation of anesthetic gas concentration, using PLC to connect to the intelligent anesthesia machine, and achieve communication through MODBUS protocol. Configure the communication parameters between PLC and anesthesia machine, such as baud rate, data bit, stop bit. Connect PLC to the computing device of DQN model.

[0067] Information transmission and parameter adjustment

[0068]

[0069]

[0070] Regular calibration and safety mechanisms

[0071] Real-time monitoring:

[0072]

[0073] Multi-parameter control, integrated biofeedback and vital signs, mixed input of biofeedback and vital signs.

[0074] Signal Fusion:

[0075]

[0076]

[0077] A regulatory strategy that integrates multi-dimensional feedback

[0078] Dynamic parameter adjustment and feedback mechanism Fixed-cycle adjustment and emergency adjustment Regular inspection mechanism:

[0079]

[0080] Emergency incident handling anomaly detection and immediate response:

[0081]

[0082]

[0083] Through the above steps, it is explained how to connect biofeedback with the anesthetic gas concentration control system to form a closed-loop control. The adaptive adjustment algorithm and multi-parameter control mechanism can dynamically and accurately adjust the concentration of anesthetic gas to ensure that the patient's anesthesia depth is maintained within a reasonable range during surgery. This method not only improves the intelligence and automation of anesthesia management, but also enhances the safety and patient comfort during surgery.

[0084] Deep learning model training of long short-term memory network, data collection, use of multiple biofeedback collection sensors to record the patient's physiological signals in real time.

[0085] Data preprocessing

[0086]

[0087]

[0088] Feature extraction time domain features: mean, variance, skewness, and kurtosis.

[0089] Frequency domain characteristics: power spectral density, frequency bandwidth.

[0090]

[0091]

[0092] Building an LSTM prediction model

[0093] The preprocessed physiological signal data is divided into a training set and a test set. The input is multidimensional time series data, and the output is the anesthesia depth prediction result.

[0094] LSTM model definition

[0095]

[0096]

[0097] Model Training

[0098]

[0099]

[0100] Model evaluation and validation

[0101]

[0102] Warning threshold setting: set multiple warning thresholds according to the prediction results, for example: Level 1 warning: the predicted value is close to the safety range boundary. Level 2 warning: the predicted value exceeds the safety range and the anesthetic concentration needs to be adjusted in time.

[0103] Real-time monitoring and early warning

[0104]

[0105]

[0106] Deep neuromodulation

[0107] For example, a spinal cord stimulator or transcranial magnetic stimulator is connected to a real-time monitoring system through a standard interface (such as USB or wireless connection) and can receive system instructions. Based on the patient's current status and predicted results, control instructions are generated to adjust the device operating parameters.

[0108] Real-time execution:

[0109]

[0110]

[0111] By building a prediction model based on LSTM, the depth of anesthesia can be accurately predicted and monitored in real time in combination with a multi-level early warning mechanism. At the same time, with the help of deep neural control equipment, the patient's physiological state can be adjusted in real time to ensure that anesthesia management during surgery is more intelligent and safe. This method achieves closed-loop control and early warning of anesthesia management through the comprehensive use of deep learning and neural control methods.

[0112] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for detecting and warning anesthetic gas concentration, characterized in that: The specific steps include: S1. Biofeedback Equipment Setup Electroencephalograms are used to monitor the electrical activity of the brain to determine the depth of anesthesia of patients. Electromyograms are used to monitor muscle reactions to help assess the patient's response to external stimuli. Galvanic skin response is used to monitor changes in skin conductance to reflect the patient's pain or stress response. Before surgery, patients are given the above monitoring equipment to ensure the stability and accuracy of data collection. S2. Biofeedback Signal Processing and Analysis Physiological signals are collected simultaneously through multi-channel equipment, and the data are transmitted to the central processing unit at a high sampling rate. Low-pass filters are used to process biological signals to filter out environmental noise and electromagnetic interference to ensure data accuracy. Complex signals are decomposed into multiple frequency bands through wavelet transform of time-frequency analysis to capture physiological information in different frequency bands. Machine learning or deep learning algorithms are used to perform pattern recognition on pre-processed biological signals to decode characteristic signals representing anesthesia depth or pain response. Based on a large amount of surgical data, the threshold of biofeedback is set; S3. Gas concentration regulation and biofeedback closed-loop control Establish a closed-loop control system, connect the biofeedback signal with the anesthetic gas concentration control system to form a closed-loop control. The system adjusts the anesthetic gas concentration in real time according to the patient's physiological response to ensure that the depth of anesthesia is maintained within a reasonable range. Design an adaptive adjustment algorithm to automatically adjust the anesthetic gas concentration according to the individual differences, weight, and age of the patient. The algorithm can analyze the biofeedback signal in real time and provide an automated adjustment strategy. By connecting to the control interface of the intelligent anesthesia machine, the system can dynamically adjust the flow and concentration of the anesthetic gas. S4. Implementation of the two-tier early warning mechanism A multi-level early warning mechanism is set up based on the biofeedback signal. According to the abnormal physiological feedback of the patient, the operating room is equipped with an external gas monitoring sensor to detect the environmental concentration of anesthetic gas in real time to prevent gas leakage or equipment failure. If the environmental gas concentration exceeds the normal range, the system automatically issues an independent environmental warning to remind medical staff to check the equipment to avoid accidents. S5. Predictive warning and deep neural regulation Based on historical surgical data, the deep learning model LSTM is used to train the complex relationship between anesthetic gas concentration and biofeedback to build a prediction model. The system continuously collects new data during surgery, self-learns and dynamically updates the model to enhance prediction accuracy. During surgery, the model can predict possible changes in anesthesia depth in advance and generate trend graphs. The system issues warnings in advance based on trend graphs to prevent patients from waking up during surgery or being too deeply anesthetized. For complex surgeries or high-risk patients, the system can combine neuroregulatory equipment to reduce patients' response to pain while maintaining a low anesthetic gas concentration. Combining neuroregulation with anesthetic gas management can reduce the side effects of gas concentration and ensure patient safety. S6. Anesthetic gas management and non-invasive feedback enhancement Low-concentration anesthetic gas supply combined with non-invasive interventions can reduce gas concentration requirements and side effects; S7. Situational awareness and personalized adjustment It senses environmental changes and surgical progress in the operating room, and adjusts the concentration of anesthetic gas and the parameters of biofeedback linkage control in real time based on these factors to ensure personalized and dynamic adjustment of the anesthesia effect.

2. The anesthetic gas concentration detection and early warning method according to claim 1, characterized in that: In the setting of the biofeedback device in step S1, the EEG electrodes should be attached to the scalp, the EMG electrodes should be attached to the major muscle groups, and the biofeedback device should be calibrated before anesthesia begins to ensure that it can effectively collect signals under anesthesia.

3. The anesthetic gas concentration detection and early warning method according to claim 1 is characterized in that: In the biofeedback signal processing and analysis in step S2, real-time data transmission is achieved through a low-power Bluetooth or Wi-Fi module to ensure that the data can reach the processing center of the system in a timely manner. The physiological information captured in different frequency bands includes decomposing the electroencephalogram signal into α and β waves of different bands to help determine the depth of anesthesia.

4. The anesthetic gas concentration detection and early warning method according to claim 1 is characterized in that: In the step S3 of gas concentration adjustment and biofeedback closed-loop control, when it is recognized that the patient's pain response is enhanced, the concentration of isoflurane or sevoflurane will be increased, and when it is recognized that the anesthesia is too deep, the gas supply will be reduced. The method system not only performs multi-dimensional control based on biofeedback, but also refers to the patient's basic vital signs, blood pressure, and heart rate to more accurately adjust the anesthetic concentration.

5. The anesthetic gas concentration detection and early warning method according to claim 1 is characterized in that: In the implementation of the double-layer warning mechanism in step S4, the patient's physiological feedback includes unusual muscle reactions or brain wave changes in the electromyogram, which issues a first-level warning, indicating that the anesthesia effect is insufficient. The method system will notify the anesthesiologist when the warning occurs, and remind the medical staff to adjust the anesthesia plan in advance through sound and visual prompts.

6. The anesthetic gas concentration detection and early warning method according to claim 1 is characterized in that: The predictive warning and deep neural regulation in step S5 are combined with neural regulation equipment including spinal cord electrical stimulation or transcranial magnetic stimulation.

7. The anesthetic gas concentration detection and early warning method according to claim 1 is characterized in that: The non-invasive intervention in step S6 anesthetic gas management and non-invasive feedback enhancement includes mild electrical stimulation, music therapy, and environmental control.

8. The method for detecting and warning the concentration of anesthetic gas according to claim 1, characterized in that: The environmental changes in the scenario perception and personalized adjustment in step S7 include temperature, humidity, and device status.

Images