Intelligent anesthesia depth monitoring system and method

Abstract

The invention discloses an intelligent anesthesia depth monitoring system and method, and relates to the technical field of medical anesthesia, and the method is characterized in that through real-time data acquisition of an ultrasonic system and an electromyography instrument, nerve surrounding tissue data of shoulder and arm parts are accurately acquired. And inputting data of tissues around nerves into a real-time anesthesia depth calculation formula to calculate a real-time anesthesia depth Dreal, carrying out preliminary comparison on the real-time anesthesia depth Dreal and a target anesthesia depth Dtarget to obtain an anesthesia depth difference degree D, and evaluating a current anesthesia injection effect in real time. And based on the preliminary evaluation result, executing an anesthetic injection rate adjustment mechanism, and dynamically adjusting the anesthetic injection rate Radj (t) at the current time t to ensure that the anesthetic amount is accurately adjusted along with the change of the physiological state of the patient. Through the real-time dynamic adjustment mechanism, the anesthetic dosage control flexibility is improved, and continuous and stable anesthesia depth of a patient is ensured.

Description

Technical Field

[0001] The present invention relates to the field of medical anesthesia technology, and in particular to an intelligent anesthesia depth monitoring system and method. Background Art

[0002] During the anesthesia process, precise control of the depth of anesthesia is crucial to the success of the operation and the safety of the patient. The intelligent anesthesia monitoring system collects the patient's physiological data, such as brain waves, electromyographic signals, local tissue metabolism, etc., and combines algorithms to monitor and adjust the depth of anesthesia in real time. In this monitoring method, ultrasound-guided neuroanesthesia monitoring is particularly suitable for nerve block anesthesia. Through real-time imaging and physiological signal analysis, it assists anesthesiologists in performing precise local anesthesia operations to ensure the appropriate depth of anesthesia during surgery.

[0003] At present, in the existing local anesthesia process, anesthesiologists rely on personal experience to judge the depth of anesthesia, especially for ultrasound-guided nerve block anesthesia. Although the position of the anesthetic needle can be monitored by imaging, it is difficult to accurately judge the diffusion of the anesthetic around the nerve and the inhibitory effect on the nerve. In addition, traditional anesthesia monitoring methods cannot reflect the changes in the patient's nerve function in real time, and it is difficult to accurately adjust the dose of anesthetics. This may lead to insufficient anesthesia, intraoperative pain for the patient, or too deep anesthesia, causing side effects from drug overdose. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an intelligent anesthesia depth monitoring system and method, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented by the following technical scheme: comprising the following steps:

[0006] S1. Before the patient undergoes surgery, the patient's basic physiological data is collected through medical equipment, and the initial anesthetic dose Dinit is calculated and output based on the collected basic physiological data through the initial anesthetic dose algorithm formula;

[0007] S2. Then, the echo image of the shoulder nerve is collected through the ultrasound system, and the data of the tissue around the nerve is analyzed through the algorithm to accurately enter the area around the brachial plexus nerve, and then a precise local injection is performed according to the initial anesthetic dose Dinit. During the injection process, the electromyography detector is used to detect the nerve electrical activity data in real time;

[0008] S3. Collect superconducting data and combine it with the change rate of neural electrical activity data to calculate and output the real-time anesthesia depth Dreal, and perform difference calculation between the anesthesia depth Dreal and the target anesthesia depth Dtargt to obtain the anesthesia depth difference △D, and perform a preliminary evaluation and analysis of the current anesthesia injection situation based on the output result of the anesthesia depth difference △D;

[0009] S4. Based on the preliminary evaluation results, the anesthetic injection rate adjustment mechanism is executed to calculate and output the anesthetic injection rate Radj(t) at the current time t, and the anesthetic injection rate is dynamically adjusted;

[0010] S5. After the adjustment of the anesthetic injection rate adjustment mechanism, the patient's anesthesia metabolism data is collected in real time and input into the comprehensive anesthesia depth evaluation formula to calculate and output the real-time comprehensive anesthesia depth Dfinal(t), and then calculate and output the anesthesia threshold TD;

[0011] S6. Perform secondary comparative evaluation on the obtained comprehensive anesthesia depth Dfinal(t) and the anesthesia threshold TD, deeply monitor and evaluate the anesthesia effect, and generate prompt information based on the evaluation results.

[0012] Preferably, S1 includes S11 and S12;

[0013] S11. Before shoulder joint surgery, use medical equipment to collect basic physiological data of the patient, including electromyograph and near-infrared spectrometer;

[0014] Basic physiological data include skin galvanic response EMG, local tissue oxygen saturation StO2 and neural potential asynchrony index NAPI;

[0015] The galvanic skin response EMG and the neural potential asynchrony index NAPI were collected by electromyograph;

[0016] Local tissue oxygen saturation StO2 was collected by near-infrared spectrometer;

[0017] S12, constructing an initial anesthetic dose algorithm formula, and then inputting the basic physiological data of the patient obtained before the operation into the initial anesthetic dose algorithm formula to calculate and output the initial anesthetic dose Dinit;

[0018] The initial anesthetic dose Dinit is calculated by the following initial anesthetic dose algorithm formula;

[0019]

[0020] Wherein, k1 represents the drug adjustment coefficient, W represents the patient's weight, A represents the patient's age, and exp represents the exponential function.

[0021] Preferably, S2 includes S21 and S22;

[0022] S21. After obtaining the initial anesthetic dose Dinit, the anesthesiologist uses an ultrasonic imager to accurately locate the brachial plexus nerve, assists the anesthetic needle in inserting into the correct position, performs anesthesia injection according to the obtained initial anesthetic dose Dinit, and collects ultrasound data through the ultrasonic imager;

[0023] Ultrasound data included nerve echogenicity (NES) and perineurial tissue thickness (NTS);

[0024] S22. During the re-injection, the electromyography is used to monitor and collect the neural electrical activity data in real time. The neural electrical activity data include the skin electrical response EMG and the nerve potential asynchronous index NAPI. The changes before and after anesthesia are calculated to obtain the skin electrical response change rate △EMG and the nerve potential asynchronous change rate △NAPI.

[0025] The specific algorithm formula of the skin electrical response change rate △EMG is: Where, EMG represents the skin electrical response at time t before surgery, A EMG(t) It represents the skin electrical response at time t during the operation;

[0026] The specific algorithm formula of the asynchronous change rate of neural potential △NAPI is:

[0027] Where A NAPI(t) It represents the asynchrony index of the neural potential at time t during the surgical process.

[0028] Preferably, S3 includes S31, S32 and S33;

[0029] S31, based on the acquired ultrasound data, the skin electrical response change rate △EMG and the nerve potential asynchronous change rate △NAPI, input them into the anesthesia depth calculation formula, calculate and output the real-time anesthesia depth Dreal, and analyze the immediate effect of the anesthetic on the nerves;

[0030] The real-time anesthesia depth Dreal is calculated and output by the following anesthesia depth calculation formula;

[0031]

[0032] Where Dreal(t) represents the real-time anesthesia depth at time t, exp represents the exponential function,

[0033] (NES·NTS·△EMG-β·△NAPI) represents the influence of nerve and physiological signals on the depth of anesthesia, α represents the regulation coefficient of the influence of nerve and physiological signals on the depth of anesthesia, and β represents the regulation coefficient of the asynchronous change rate of nerve potential.

[0034] Preferably, S32, setting a target anesthesia depth Dtarget based on individual differences of patients, the target anesthesia depth Dtarget is calculated and output by the following formula: Dtarget=f(S, P, M, C), where f represents an adjustment function, S represents the complexity of the surgical type, which is initially set by the user, P represents individual parameters of the patient, including age, weight, liver and kidney function, and cardiopulmonary function, and C represents the type of anesthetic used;

[0035] Then, the obtained target anesthesia depth Dtarget is subtracted from the real-time anesthesia depth Dreal(t) at time t to obtain the anesthesia depth difference △D. The anesthesia depth difference △D algorithm formula is: △D = Dtarget-Dreal(t);

[0036] S33, based on the output result of the anesthesia depth difference △D, a preliminary evaluation of the anesthesia depth is performed, and the specific evaluation contents are as follows;

[0037] When the anesthesia depth difference △D≥0.5, it means that the anesthesia injection volume is insufficient, and the anesthetic injection rate adjustment mechanism is automatically executed;

[0038] When -0.3<anesthesia depth difference △D<0.5, it means that the anesthesia is normal, and the current anesthesia depth is continued;

[0039] When the anesthesia depth difference △D≤-0.3, it means that the anesthesia injection volume is overloaded, and the anesthetic injection rate adjustment mechanism is automatically executed.

[0040] Preferably, S4 includes S41;

[0041] S41. When the anesthetic injection volume is initially assessed to be insufficient or overloaded, the anesthetic injection rate adjustment mechanism is automatically executed. The anesthetic injection rate adjustment mechanism performs a comprehensive calculation based on the acquired target anesthesia depth Dtarget and the real-time anesthesia depth Dreal(t) at time t to output the anesthetic injection rate Radj(t) at the current time t, and adjusts the anesthetic injection rate.

[0042] The anesthetic injection rate Radj(t) at the current time t is calculated and output by the following algorithm formula;

[0043]

[0044] Where Rbase represents the basic anesthetic injection rate, γ represents the adjustment coefficient of the anesthesia depth difference △D, δ represents the feedback coefficient, which is used to smooth the injection rate change, d represents a small variable, dDreal(t) represents the small variable of the real-time anesthesia depth, and dt represents the time small variable.

[0045] Preferably, S5 includes S51 and S52;

[0046] S51. After the anesthetic injection rate adjustment mechanism is adjusted, the patient's anesthetic metabolic data is collected in real time through a blood drug concentration analyzer, near infrared spectroscopy NIRS technology, electromyograph and microcirculation monitoring equipment. The anesthetic metabolic data includes anesthetic metabolic changes Cm(t) and local metabolic recovery index LMI;

[0047] The anesthetic metabolic change Cm(t) and the local metabolic recovery index LMI are calculated and obtained using the following parameters and algorithms;

[0048] Cm(t)=C0·exp -kt ;

[0049] LMI = f(O2, BF, NCV);

[0050] In the formula, C0 represents the initial anesthetic concentration, k represents the elimination rate constant of the drug, f represents the adjustment function, O2 represents the local tissue oxygen saturation, which is obtained by NIRS, BF represents the local blood flow velocity, which is obtained by microcirculation monitoring equipment, and NCV represents the nerve conduction velocity, which is obtained by electromyograph;

[0051] Then, based on the acquired anesthesia metabolism data and the real-time anesthesia depth Dreal(t) at time t, the data is input into the comprehensive anesthesia depth evaluation formula to calculate and output the real-time comprehensive anesthesia depth Dfinal(t);

[0052] The real-time comprehensive anesthesia depth Dfinal(t) is calculated and output by the following comprehensive anesthesia depth evaluation formula;

[0053] Dfinal(t)=w1·Dreal(t)+w2·f(Cm(t),LMI);

[0054] Wherein, Dfinal(t) represents the real-time comprehensive anesthesia depth at time t, w1 represents the weight value of the real-time anesthesia depth, w2 represents the weight value of the anesthesia metabolism data, and w1+w2=1, and the specific value is set by the user.

[0055] Preferably, S52, based on the acquired target anesthesia depth Dtarget, combined with individual differences of patients and the type of surgery, calculate and output an anesthesia threshold TD;

[0056] The anesthesia threshold TD is calculated and output by the following algorithm formula;

[0057] TD=Dtarget·(1+f(W, A, S, Tm));

[0058] Where Tm represents the drug metabolism time constant.

[0059] Preferably, S6 includes S61;

[0060] S61, performing a secondary comparative evaluation on the obtained anesthesia threshold TD and the real-time comprehensive anesthesia depth Dfinal(t), comprehensively analyzing the adjusted anesthesia depth, and generating relevant prompts based on the secondary comparative evaluation results. The specific evaluation contents are as follows;

[0061] When the real-time comprehensive anesthesia depth Dfinal(t)> anesthesia threshold TD, it means that after the anesthetic injection rate adjustment mechanism is adjusted, the patient's anesthesia depth is in an overload state. At this time, a red prompt is generated through the visual interface to prompt the anesthesiologist to manually adjust and reduce the anesthetic injection rate;

[0062] When the real-time comprehensive anesthesia depth Dfinal(t) = anesthesia threshold TD, it means that after the anesthetic injection rate adjustment mechanism is adjusted, the patient's anesthesia depth is in a normal state, and no prompt needs to be generated for continued monitoring;

[0063] When the real-time comprehensive anesthesia depth Dfinal(t) is less than the anesthesia threshold TD, it means that after the anesthetic injection rate adjustment mechanism is adjusted, the patient's anesthesia depth is insufficient. At this time, a green prompt is generated through the visual interface, prompting the anesthesiologist to manually adjust and increase the anesthetic injection rate.

[0064] An intelligent anesthesia depth monitoring system includes a preoperative analysis module, an anesthesia start module, an anesthesia depth analysis module, an anesthesia dose dynamic adjustment module, a comprehensive anesthesia depth analysis module and a comprehensive anesthesia depth monitoring and evaluation module;

[0065] The preoperative analysis module collects the patient's basic physiological data through medical equipment before the operation, and calculates and outputs the initial anesthetic dose Dinit based on the collected basic physiological data through the initial anesthetic dose algorithm formula;

[0066] The anesthesia initiation module collects echo images of the shoulder nerves through an ultrasound system, and analyzes the data of the tissues surrounding the nerves through algorithms, accurately enters the brachial plexus, and performs precise local injection based on the initial anesthetic dose Dinit, and then detects the nerve electrical activity data through electromyography;

[0067] The anesthesia depth analysis module sets a real-time anesthesia depth calculation formula, inputs the nerve perivascular tissue data and nerve electrical activity data into the anesthesia depth calculation formula, calculates and outputs the real-time anesthesia depth Dreal, and calculates the difference between the anesthesia depth Dreal and the target anesthesia depth Dtargt to obtain the anesthesia depth difference △D. Based on the output result of the anesthesia depth difference △D, a preliminary evaluation and analysis of the current anesthesia injection situation is performed;

[0068] The dynamic adjustment module of the anesthetic dose executes the anesthetic injection rate adjustment mechanism based on the preliminary evaluation results, calculates and outputs the anesthetic injection rate Radj(t) at the current time t, and dynamically adjusts the anesthetic injection rate;

[0069] After the comprehensive anesthesia depth analysis module is adjusted by the anesthetic injection rate adjustment mechanism, it collects the patient's anesthesia metabolism data in real time, inputs it into the comprehensive anesthesia depth evaluation formula, calculates and outputs the real-time comprehensive anesthesia depth Dfinal(t), and then calculates and outputs the anesthesia threshold TD;

[0070] The comprehensive anesthesia depth monitoring and evaluation module conducts a secondary comparative evaluation of the obtained comprehensive anesthesia depth Dfinal(t) and the anesthesia threshold TD, deeply monitors and evaluates the anesthesia effect, and generates prompt information based on the evaluation results.

[0071] The present invention provides an intelligent anesthesia depth monitoring system and method. It has the following beneficial effects:

[0072] (1) This method collects the patient's basic physiological data through medical equipment before surgery, and constructs an initial anesthetic dose algorithm based on the basic physiological data to accurately calculate the initial anesthetic dose Dinit. Compared with the traditional experience-based dose setting, this anesthetic dose setting method based on the patient's individualized physiological data can significantly improve the accuracy of the anesthetic dose, avoid the blindness of the anesthetic dose, and reduce the risk of overdose or underdose of anesthesia, thereby improving the safety of surgery and the comfort of patients.

[0073] (2) This method accurately obtains the data of the nerve perineural tissue in the shoulder and arm area through real-time data collection of the ultrasound system and the electromyograph. Then, by inputting the nerve perineural tissue data into the real-time anesthesia depth calculation formula, the real-time anesthesia depth Dreal is calculated, and a preliminary comparison is made with the target anesthesia depth Dtarget to obtain the anesthesia depth difference △D, and then the current anesthesia injection effect is evaluated in real time. Based on the preliminary evaluation results, the anesthetic injection rate adjustment mechanism is executed to dynamically adjust the anesthetic injection rate Radj(t) at the current time t to ensure that the anesthetic dose is accurately adjusted as the patient's physiological state changes. This real-time dynamic adjustment mechanism improves the flexibility of anesthesia dose control and ensures the continuous stability of the patient's anesthesia depth.

[0074] (3) After dynamically adjusting the anesthetic injection rate, this method calculates the real-time comprehensive anesthesia depth Dfinal(t) by comprehensively evaluating the patient's anesthesia metabolic data, and compares it with the anesthesia threshold TD for a second evaluation. When the evaluation results show that the patient's anesthesia depth exceeds or falls below the threshold, the system will generate corresponding prompt information through a visual interface to guide the anesthesiologist to make adjustments. This process not only strengthens the monitoring of the anesthesia process, but also effectively reduces the workload of the anesthesiologist through intelligent prompts, reduces the risk of anesthesia overload or insufficient during surgery, and improves the safety and efficiency of the surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 A schematic diagram of the steps of an intelligent monitoring method for anesthesia depth according to the present invention;

[0076] Figure 2 The present invention is a flowchart of an intelligent anesthesia depth monitoring system. DETAILED DESCRIPTION

[0077] The following will be combined with the drawings in 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.

[0078] Example 1

[0079] See also Figure 1 The present invention provides an intelligent monitoring method for the depth of anesthesia. To achieve the above purpose, the present invention is implemented by the following technical scheme: comprising the following steps:

[0080] S1. Before the patient undergoes surgery, the patient's basic physiological data is collected through medical equipment, and the initial anesthetic dose Dinit is calculated and output based on the collected basic physiological data through the initial anesthetic dose algorithm formula;

[0081] S2. Then, the echo image of the shoulder nerve is collected through the ultrasound system, and the data of the tissue around the nerve is analyzed through the algorithm to accurately enter the area around the brachial plexus nerve, and then a precise local injection is performed according to the initial anesthetic dose Dinit. During the injection process, the electromyography detector is used to detect the nerve electrical activity data in real time;

[0082] S3. Collect superconducting data and combine it with the change rate of neural electrical activity data to calculate and output the real-time anesthesia depth Dreal, and perform difference calculation between the anesthesia depth Dreal and the target anesthesia depth Dtargt to obtain the anesthesia depth difference △D, and perform a preliminary evaluation and analysis of the current anesthesia injection situation based on the output result of the anesthesia depth difference △D;

[0083] S4. Based on the preliminary evaluation results, the anesthetic injection rate adjustment mechanism is executed to calculate and output the anesthetic injection rate Radj(t) at the current time t, and the anesthetic injection rate is dynamically adjusted;

[0084] S5. After the adjustment of the anesthetic injection rate adjustment mechanism, the patient's anesthesia metabolism data is collected in real time and input into the comprehensive anesthesia depth evaluation formula to calculate and output the real-time comprehensive anesthesia depth Dfinal(t), and then calculate and output the anesthesia threshold TD;

[0085] S6. Perform secondary comparative evaluation on the obtained comprehensive anesthesia depth Dfinal(t) and the anesthesia threshold TD, deeply monitor and evaluate the anesthesia effect, and generate prompt information based on the evaluation results.

[0086] In this embodiment, the method collects the basic physiological data of the patient before surgery, combines the initial anesthesia dose algorithm formula, calculates the individualized initial anesthesia dose Dinit, ensures the accurate setting of the anesthesia dose, and avoids the error of the traditional method that relies on experience to set the dose. Then, the echo image of the shoulder nerve and the data of the surrounding tissue of the nerve are collected by the ultrasound system, and the neural electrical activity data monitored by the electromyography are combined to accurately perform local anesthesia injection, thereby ensuring the accurate delivery of the anesthetic. The application of the real-time anesthesia depth calculation formula dynamically calculates the anesthesia depth Dreal by analyzing the real-time neuroanatomy and electrical activity data, and compares it with the target anesthesia depth Dtarget to generate the anesthesia depth difference △D, which helps to make a preliminary assessment of the current anesthesia state. On this basis, by adjusting the anesthetic injection rate Radj(t), the dynamic optimization control of the anesthesia dose is realized to ensure the continuous stability during the anesthesia process. Further, by collecting anesthesia metabolism data, combined with the comprehensive anesthesia depth evaluation formula, the comprehensive anesthesia depth Dfinal(t) is calculated in real time, and a secondary comparison evaluation is performed with the anesthesia threshold TD, and prompt information is generated by visualization to help the anesthesiologist adjust the injection strategy in time. This method achieves precise control and optimization of anesthesia depth through real-time acquisition, intelligent calculation and dynamic adjustment of multi-dimensional data, thereby improving the stability and safety of the anesthesia effect.

[0087] Example 2

[0088] This embodiment is explained in Example 1, please refer to Figure 1, specifically: S1 includes S11 and S12;

[0089] S11. Before shoulder joint surgery, use medical equipment to collect basic physiological data of the patient, including electromyograph and near-infrared spectrometer;

[0090] Basic physiological data include skin galvanic response EMG, local tissue oxygen saturation StO2 and neural potential asynchrony index NAPI;

[0091] The galvanic skin response EMG and the neural potential asynchrony index NAPI were collected by electromyograph;

[0092] Local tissue oxygen saturation StO2 was collected by near-infrared spectrometer;

[0093] S12, constructing an initial anesthetic dose algorithm formula, and then inputting the basic physiological data of the patient obtained before the operation into the initial anesthetic dose algorithm formula to calculate and output the initial anesthetic dose Dinit;

[0094] The initial anesthetic dose Dinit is calculated by the following initial anesthetic dose algorithm formula;

[0095]

[0096] Wherein, k1 represents the drug adjustment coefficient, W represents the patient's weight, A represents the patient's age, and exp represents the exponential function.

[0097] In this embodiment, the method collects the basic physiological data of the patient through preoperative medical equipment, and these data can fully reflect the individual physiological state of the patient. Then, by inputting these data into the initial anesthesia dose algorithm formula, the system can accurately calculate the initial anesthesia dose Dinit according to individual factors such as the patient's weight and age, avoiding the deficiency of traditional anesthesia in relying on experience for dose setting.

[0098] Example 3

[0099] This embodiment is explained in Example 2. Please refer to Figure 1 , specifically: S2 includes S21 and S22;

[0100] S21. After obtaining the initial anesthetic dose Dinit, the anesthesiologist uses an ultrasonic imager to accurately locate the brachial plexus nerve, assists the anesthetic needle in inserting into the correct position, performs anesthesia injection according to the obtained initial anesthetic dose Dinit, and collects ultrasound data through the ultrasonic imager;

[0101] Ultrasound data included nerve echogenicity (NES) and perineurial tissue thickness (NTS);

[0102] S22. During the re-injection, the electromyography is used to monitor and collect the neural electrical activity data in real time. The neural electrical activity data include the skin electrical response EMG and the nerve potential asynchronous index NAPI. The changes before and after anesthesia are calculated to obtain the skin electrical response change rate △EMG and the nerve potential asynchronous change rate △NAPI.

[0103] The specific algorithm formula of the skin electrical response change rate △EMG is: Where, EMG represents the skin electrical response at time t before surgery, A EMG(t) It represents the skin electrical response at time t during the operation;

[0104] The specific algorithm formula of the asynchronous change rate of neural potential △NAPI is:

[0105] Where A NAPI(t) It represents the asynchrony index of the neural potential at time t during the surgical process.

[0106] In this embodiment, the method uses an ultrasound imager to accurately locate the brachial plexus nerve by the anesthesiologist, assists the anesthetic needle to accurately penetrate the target area, and performs local anesthesia injection according to the initial anesthetic dose Dinit. The nerve echo intensity NES and the nerve perineurial tissue thickness NTS data collected by ultrasound imaging ensure the accurate delivery of anesthetics and improve the safety and efficiency of the operation. The electromyograph monitors the nerve electrical activity data in real time, dynamically collects the skin electrical response EMG and the nerve potential asynchronous index NAPI, and calculates the skin electrical response change rate △EMG and the nerve potential asynchronous change rate △NAPI before and after anesthesia to evaluate the anesthetic effect and the inhibition of nerve function in real time. By combining ultrasound-guided nerve positioning with real-time electrophysiological monitoring, this method not only improves the accuracy of anesthetic injection, but also provides instant feedback on the anesthetic effect. This improvement effectively avoids the problem of insufficient or excessive anesthesia, and improves the safety of patients and the success rate of surgery.

[0107] Example 4

[0108] This embodiment is explained in Example 3, please refer to Figure 1 , specifically: S3 includes S31, S32 and S33;

[0109] S31, based on the acquired ultrasound data, the skin electrical response change rate △EMG and the nerve potential asynchronous change rate △NAPI, input them into the anesthesia depth calculation formula, calculate and output the real-time anesthesia depth Dreal, and analyze the immediate effect of the anesthetic on the nerves;

[0110] The real-time anesthesia depth Dreal is calculated and output by the following anesthesia depth calculation formula;

[0111]

[0112] Where Dreal(t) represents the real-time anesthesia depth at time t, exp represents the exponential function,

[0113] (NES·NTS·△EMG-β·△NAPI) represents the influence of nerve and physiological signals on the depth of anesthesia, α represents the regulation coefficient of the influence of nerve and physiological signals on the depth of anesthesia, and β represents the regulation coefficient of the asynchronous change rate of nerve potential.

[0114] S32. Setting the target anesthesia depth Dtarget based on individual differences of the patients. The target anesthesia depth Dtarget is calculated and outputted by the following formula: Dtarget=f(S, P, M, C), where f represents the adjustment function, S represents the complexity of the surgical type, which is initially set by the user, P represents the individualized parameters of the patient, including age, weight, liver and kidney function, and cardiopulmonary function, and C represents the type of anesthetic used;

[0115] Then, the obtained target anesthesia depth Dtarget is subtracted from the real-time anesthesia depth Dreal(t) at time t to obtain the anesthesia depth difference △D. The anesthesia depth difference △D algorithm formula is: △D = Dtarget-Dreal(t);

[0116] S33, based on the output result of the anesthesia depth difference △D, a preliminary evaluation of the anesthesia depth is performed, and the specific evaluation contents are as follows;

[0117] When the anesthesia depth difference △D≥0.5, it means that the anesthesia injection volume is insufficient, and the anesthetic injection rate adjustment mechanism is automatically executed;

[0118] When -0.3<anesthesia depth difference △D<0.5, it means that the anesthesia is normal, and the current anesthesia depth is continued;

[0119] When the anesthesia depth difference △D≤-0.3, it means that the anesthesia injection volume is overloaded, and the anesthetic injection rate adjustment mechanism is automatically executed.

[0120] In this embodiment, the method is based on ultrasound data, skin galvanic response change rate △EMG and nerve potential asynchronous change rate △NAPI, and these data are input into the anesthesia depth calculation formula to calculate the real-time anesthesia depth Dreal(t), and instantly analyze the effect of the anesthetic on the nerves. Then the target anesthesia depth Dtarget is set according to the individual differences of the patient, and the anesthesia depth difference △D is calculated by comparing the real-time anesthesia depth Dreal(t) with the target anesthesia depth Dtarget. Based on this difference, the evaluation is performed. When the anesthesia is insufficient or overloaded, the system automatically adjusts the anesthetic injection rate to ensure that the anesthesia effect always remains within the ideal range. This method realizes the accurate evaluation of the real-time anesthesia depth through multi-parameter fusion, and sets the target anesthesia depth according to the individual situation of the patient to ensure that the anesthesia dose is more in line with the needs of the surgery and the patient. Through the feedback adjustment of the anesthesia depth difference, the system can automatically adjust the injection rate, dynamically optimize the anesthesia dose distribution, reduce the complexity of manual adjustment, and greatly improve the accuracy and flexibility of anesthesia control.

[0121] Example 5

[0122] This embodiment is explained in Example 4. Please refer to Figure 1 , specifically: S4 includes S41;

[0123] S41. When the anesthetic injection volume is initially assessed to be insufficient or overloaded, the anesthetic injection rate adjustment mechanism is automatically executed. The anesthetic injection rate adjustment mechanism performs a comprehensive calculation based on the acquired target anesthesia depth Dtarget and the real-time anesthesia depth Dreal(t) at time t to output the anesthetic injection rate Radj(t) at the current time t, and adjusts the anesthetic injection rate.

[0124] The anesthetic injection rate Radj(t) at the current time t is calculated and output by the following algorithm formula;

[0125]

[0126] Where Rbase represents the basic anesthetic injection rate, γ represents the adjustment coefficient of the anesthesia depth difference △D, δ represents the feedback coefficient, which is used to smooth the injection rate change, d represents a small variable, dDreal(t) represents the small variable of the real-time anesthesia depth, and dt represents the time small variable.

[0127] In this embodiment, the method evaluates whether the anesthetic injection volume is insufficient or overloaded according to the anesthesia depth difference △D, and automatically performs injection rate adjustment. By comprehensively calculating the target anesthesia depth Dtarget and the real-time anesthesia depth Dreal(t), the anesthetic injection rate Radj(t) at the current time t is output. This adjustment mechanism not only considers the basic anesthetic injection rate Rbase, but also ensures that the adjustment process of the injection rate is smooth and effective through the adjustment coefficient of the difference and the smooth feedback coefficient. This method significantly improves the response speed and accuracy of anesthesia management through the automatic adjustment mechanism driven by real-time data. Dynamic injection rate adjustment reduces the risks caused by excessive or insufficient anesthesia, avoids human errors in manual adjustment, and improves the safety and effect during surgery. In addition, the injection rate is smoothly adjusted by the feedback coefficient to ensure the stability of the anesthesia dose adjustment, which not only optimizes the patient's anesthesia experience, but also improves the recovery effect after surgery. This method makes anesthesia management more intelligent and efficient, and provides a more sophisticated and flexible solution for anesthesia control in complex operations.

[0128] Example 6

[0129] This embodiment is explained in Example 5. Please refer to Figure 1 , specifically: S5 includes S51 and S52;

[0130] S51. After the anesthetic injection rate adjustment mechanism is adjusted, the patient's anesthetic metabolic data is collected in real time through a blood drug concentration analyzer, near infrared spectroscopy NIRS technology, electromyograph and microcirculation monitoring equipment. The anesthetic metabolic data includes anesthetic metabolic changes Cm(t) and local metabolic recovery index LMI;

[0131] The anesthetic metabolic change Cm(t) and the local metabolic recovery index LMI are calculated and obtained using the following parameters and algorithms;

[0132] Cm(t)=C0·exp -kt ;

[0133] LMI = f(O2, BF, NCV);

[0134] In the formula, C0 represents the initial anesthetic concentration, k represents the elimination rate constant of the drug, f represents the adjustment function, O2 represents the local tissue oxygen saturation, which is obtained by NIRS, BF represents the local blood flow velocity, which is obtained by microcirculation monitoring equipment, and NCV represents the nerve conduction velocity, which is obtained by electromyograph;

[0135] Then, based on the acquired anesthesia metabolism data and the real-time anesthesia depth Dreal(t) at time t, the data is input into the comprehensive anesthesia depth evaluation formula to calculate and output the real-time comprehensive anesthesia depth Dfinal(t);

[0136] The real-time comprehensive anesthesia depth Dfinal(t) is calculated and output by the following comprehensive anesthesia depth evaluation formula;

[0137] Dfinal(t)=w1·Dreal(t)+w2·f(Cm(t),LMI);

[0138] Wherein, Dfinal(t) represents the real-time comprehensive anesthesia depth at time t, w1 represents the weight value of the real-time anesthesia depth, w2 represents the weight value of the anesthesia metabolism data, and w1+w2=1, and the specific value is set by the user.

[0139] S52, based on the obtained target anesthesia depth Dtarget, combined with individual differences of patients and the type of surgery, calculate and output an anesthesia threshold TD;

[0140] The anesthesia threshold TD is calculated and output by the following algorithm formula;

[0141] TD=Dtarget·(1+f(W,A,S,Tm));

[0142] Where Tm represents the drug metabolism time constant.

[0143] S6 includes S61;

[0144] S61, performing a secondary comparative evaluation on the obtained anesthesia threshold TD and the real-time comprehensive anesthesia depth Dfinal(t), comprehensively analyzing the adjusted anesthesia depth, and generating relevant prompts based on the secondary comparative evaluation results. The specific evaluation contents are as follows;

[0145] When the real-time comprehensive anesthesia depth Dfinal(t)> anesthesia threshold TD, it means that after the anesthetic injection rate adjustment mechanism is adjusted, the patient's anesthesia depth is in an overload state. At this time, a red prompt is generated through the visual interface to prompt the anesthesiologist to manually adjust and reduce the anesthetic injection rate;

[0146] When the real-time comprehensive anesthesia depth Dfinal(t) = anesthesia threshold TD, it means that after the anesthetic injection rate adjustment mechanism is adjusted, the patient's anesthesia depth is in a normal state, and no prompt needs to be generated for continued monitoring;

[0147] When the real-time comprehensive anesthesia depth Dfinal(t) is less than the anesthesia threshold TD, it means that after the anesthetic injection rate adjustment mechanism is adjusted, the patient's anesthesia depth is insufficient. At this time, a green prompt is generated through the visual interface, prompting the anesthesiologist to manually adjust and increase the anesthetic injection rate.

[0148] In the present embodiment, the method collects the patient's anesthetic metabolic changes Cm(t) and local metabolic recovery index LMI through a blood drug concentration analyzer, a near-infrared spectrum, an electromyograph and a microcirculation monitoring device, and combines these data with the real-time anesthesia depth Dreal(t) through a calculation formula to obtain a comprehensive anesthesia depth Dfinal(t). At the same time, the anesthesia threshold TD is further calculated in combination with individual differences of the patient. The comprehensive anesthesia depth Dfinal(t) is then compared and evaluated with the anesthesia threshold TD for a second time, and the anesthesiologist is prompted by visualization whether it is necessary to manually adjust the anesthetic injection rate to ensure that the patient is always at an appropriate anesthesia depth. This method significantly improves the monitoring and feedback capabilities of the depth of anesthesia by collecting anesthesia metabolic data in real time and combining multiple parameters for dynamic evaluation. Traditional anesthesia methods often lack detailed monitoring of drug metabolism and local nerve recovery, and it is difficult to adjust in real time. However, this method achieves continuous optimization of the depth of anesthesia through multi-dimensional data fusion and algorithm calculation. This improvement not only effectively avoids the problem of anesthesia overload or insufficient, but also provides anesthesiologists with more intuitive and intelligent decision-making support, reduces the uncertainty of human intervention, improves the automation, precision and safety of anesthesia management, and further improves patients' intraoperative experience and postoperative recovery.

[0149] Example 7

[0150] See also Figure 1 and Figure 2 , an intelligent anesthesia depth monitoring system, including a preoperative analysis module, an anesthesia start module, an anesthesia depth analysis module, an anesthesia dose dynamic adjustment module, a comprehensive anesthesia depth analysis module and a comprehensive anesthesia depth monitoring and evaluation module;

[0151] The preoperative analysis module collects the patient's basic physiological data through medical equipment before the operation, and calculates and outputs the initial anesthetic dose Dinit based on the collected basic physiological data through the initial anesthetic dose algorithm formula;

[0152] The anesthesia initiation module collects echo images of the shoulder nerves through an ultrasound system, and analyzes the data of the tissues surrounding the nerves through algorithms, accurately enters the brachial plexus, and performs precise local injection based on the initial anesthetic dose Dinit, and then detects the nerve electrical activity data through electromyography;

[0153] The anesthesia depth analysis module sets a real-time anesthesia depth calculation formula, inputs the nerve perivascular tissue data and nerve electrical activity data into the anesthesia depth calculation formula, calculates and outputs the real-time anesthesia depth Dreal, and calculates the difference between the anesthesia depth Dreal and the target anesthesia depth Dtargt to obtain the anesthesia depth difference △D. Based on the output result of the anesthesia depth difference △D, a preliminary evaluation and analysis of the current anesthesia injection situation is performed;

[0154] The dynamic adjustment module of the anesthetic dose executes the anesthetic injection rate adjustment mechanism based on the preliminary evaluation results, calculates and outputs the anesthetic injection rate Radj(t) at the current time t, and dynamically adjusts the anesthetic injection rate;

[0155] After the comprehensive anesthesia depth analysis module is adjusted by the anesthetic injection rate adjustment mechanism, it collects the patient's anesthesia metabolism data in real time, inputs it into the comprehensive anesthesia depth evaluation formula, calculates and outputs the real-time comprehensive anesthesia depth Dfinal(t), and then calculates and outputs the anesthesia threshold TD;

[0156] The comprehensive anesthesia depth monitoring and evaluation module conducts a secondary comparative evaluation of the obtained comprehensive anesthesia depth Dfinal(t) and the anesthesia threshold TD, deeply monitors and evaluates the anesthesia effect, and generates prompt information based on the evaluation results.

[0157] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A method for intelligent monitoring of anesthesia depth, characterized in that: The following steps are involved: S1. Before the patient undergoes surgery, the patient's basic physiological data is collected through medical equipment, and the initial anesthetic dose Dinit is calculated and output based on the collected basic physiological data through the initial anesthetic dose algorithm formula; S2. Then, the echo image of the shoulder nerve is collected through the ultrasound system, and the data of the tissue around the nerve is analyzed through the algorithm to accurately enter the area around the brachial plexus nerve, and then a precise local injection is performed according to the initial anesthetic dose Dinit. During the injection process, the electromyography detector is used to detect the nerve electrical activity data in real time; S3. Collect superconducting data and combine it with the change rate of neural electrical activity data to calculate and output the real-time anesthesia depth Dreal, and perform difference calculation between the anesthesia depth Dreal and the target anesthesia depth Dtargt to obtain the anesthesia depth difference △D, and perform a preliminary evaluation and analysis of the current anesthesia injection situation based on the output result of the anesthesia depth difference △D; S4. Based on the preliminary evaluation results, the anesthetic injection rate adjustment mechanism is executed to calculate and output the anesthetic injection rate Radj(t) at the current time t, and the anesthetic injection rate is dynamically adjusted; S5. After the adjustment of the anesthetic injection rate adjustment mechanism, the patient's anesthesia metabolism data is collected in real time and input into the comprehensive anesthesia depth evaluation formula to calculate and output the real-time comprehensive anesthesia depth Dfinal(t), and then calculate and output the anesthesia threshold TD; S6. Perform secondary comparative evaluation on the obtained comprehensive anesthesia depth Dfinal(t) and the anesthesia threshold TD, deeply monitor and evaluate the anesthesia effect, and generate prompt information based on the evaluation results.

2. The method for intelligently monitoring the depth of anesthesia according to claim 1, characterized in that: Said S1 includes S11 and S12; S11. Before shoulder joint surgery, use medical equipment to collect basic physiological data of the patient, wherein the medical equipment includes an electromyograph and a near-infrared spectrometer; The basic physiological data include skin galvanic response EMG, local tissue oxygen saturation StO2 and neural potential asynchrony index NAPI; S12, constructing an initial anesthetic dose algorithm formula, and then inputting the basic physiological data of the patient obtained before the operation into the initial anesthetic dose algorithm formula to calculate and output the initial anesthetic dose Dinit; The initial anesthetic dose Dinit is calculated by the following initial anesthetic dose algorithm formula; Wherein, k1 represents the drug adjustment coefficient, W represents the patient's weight, A represents the patient's age, and exp represents the exponential function.

3. The method for intelligently monitoring the depth of anesthesia according to claim 2, characterized in that: The S2 includes S21 and S22; S21. After obtaining the initial anesthetic dose Dinit, an ultrasonic imager is used to accurately locate the brachial plexus nerve, assist the anesthetic needle in puncturing the correct site, perform an anesthetic injection according to the obtained initial anesthetic dose Dinit, and collect ultrasonic data through the ultrasonic imager; The ultrasound data include nerve echo intensity NES and nerve perineurial tissue thickness NTS; S22. During the reinjection process, the electromyograph is used to monitor and collect the neural electrical activity data in real time, wherein the neural electrical activity data include the galvanic skin response EMG and the neural potential asynchronous index NAPI, and the changes before and after anesthesia are calculated to obtain the galvanic skin response change rate △EMG and the neural potential asynchronous change rate △NAPI.

4. The method for intelligently monitoring the depth of anesthesia according to claim 3, characterized in that: The S3 includes S31, S32 and S33; S31, based on the acquired ultrasound data, the skin electrical response change rate △EMG and the nerve potential asynchronous change rate △NAPI, input them into the anesthesia depth calculation formula, calculate and output the real-time anesthesia depth Dreal, and analyze the immediate effect of the anesthetic on the nerves; The real-time anesthesia depth Dreal is calculated and output by the following anesthesia depth calculation formula; Where Dreal(t) represents the real-time anesthesia depth at time t, exp represents the exponential function, (NES·NTS·△EMG-β·△NAPI) represents the influence of nerve and physiological signals on the anesthesia depth, α represents the regulation coefficient of the influence of nerve and physiological signals on the anesthesia depth, and β represents the regulation coefficient of the asynchronous change rate of nerve potential.

5. The method for intelligently monitoring the depth of anesthesia according to claim 4, characterized in that: S32, setting a target anesthesia depth Dtarget based on individual differences of patients, wherein the target anesthesia depth Dtarget is calculated and outputted by the following formula: Dtarget=f(S, P, M, C), where f represents an adjustment function, S represents the complexity of the surgical type, which is initially set by the user, P represents an individualized parameter of the patient, and C represents the type of anesthetic used; Then, the obtained target anesthesia depth Dtarget and the real-time anesthesia depth Dreal(t) at time t are used for difference calculation to obtain the anesthesia depth difference △D. The anesthesia depth difference △D algorithm formula is: △D=Dtarget-Dreal(t); S33, based on the output result of the anesthesia depth difference △D, a preliminary evaluation of the anesthesia depth is performed, and the specific evaluation contents are as follows; When the anesthesia depth difference △D≥0.5, it means that the anesthesia injection volume is insufficient, and the anesthetic injection rate adjustment mechanism is automatically executed; When -0.3<anesthesia depth difference △D<0.5, it means that the anesthesia is normal, and the current anesthesia depth is continued; When the anesthesia depth difference △D≤-0.3, it means that the anesthesia injection volume is overloaded, and the anesthetic injection rate adjustment mechanism is automatically executed.

6. The method for intelligently monitoring the depth of anesthesia according to claim 1, characterized in that: The S4 includes S41; S41, when it is preliminarily assessed that the anesthetic injection volume is insufficient or overloaded, the anesthetic injection rate adjustment mechanism is automatically executed, wherein the anesthetic injection rate adjustment mechanism performs a comprehensive calculation based on the acquired target anesthesia depth Dtarget and the real-time anesthesia depth Dreal(t) at time t to output the anesthetic injection rate Radj(t) at the current time t, and adjusts the anesthetic injection rate; The anesthetic injection rate Radj(t) at the current time t is calculated and output by the following algorithm formula; Where Rbase represents the basic anesthetic injection rate, γ represents the adjustment coefficient of the anesthesia depth difference △D, δ represents the feedback coefficient, d represents a small variable, dDreal(t) represents the small variable of the real-time anesthesia depth, and dt represents the time small variable.

7. The method for intelligently monitoring the depth of anesthesia according to claim 6, characterized in that: The S5 includes S51 and S52; S51. After the anesthetic injection rate adjustment mechanism is adjusted, the patient's anesthetic metabolism data is collected in real time through a blood drug concentration analyzer, near infrared spectroscopy NIRS technology, electromyograph and microcirculation monitoring equipment, wherein the anesthetic metabolism data includes anesthetic metabolism change Cm(t) and local metabolic recovery index LMI; Then, based on the acquired anesthesia metabolism data and the real-time anesthesia depth Dreal(t) at time t, the data is input into the comprehensive anesthesia depth evaluation formula to calculate and output the real-time comprehensive anesthesia depth Dfinal(t); The real-time comprehensive anesthesia depth Dfinal(t) is calculated and outputted by the following comprehensive anesthesia depth evaluation formula; Dfinal(t)=w1·Dreal(t)+w2·f(Cm(t),LMI); Wherein, Dfinal(t) represents the real-time comprehensive anesthesia depth at time t, w1 represents the weight value of the real-time anesthesia depth, w2 represents the weight value of the anesthesia metabolism data, and w1+w2=1, and the specific value is set by the user.

8. The method for intelligently monitoring the depth of anesthesia according to claim 7, characterized in that: S52, based on the obtained target anesthesia depth Dtarget, combined with individual differences of patients and the type of surgery, calculate and output an anesthesia threshold TD; The anesthesia threshold TD is calculated and output by the following algorithm formula; TD=Dtarget·(1+f(W,A,S,Tm)); Where Tm represents the drug metabolism time constant.

9. The method for intelligently monitoring the depth of anesthesia according to claim 8, characterized in that: The S6 includes S61; S61, performing a secondary comparative evaluation on the obtained anesthesia threshold TD and the real-time comprehensive anesthesia depth Dfinal(t), comprehensively analyzing the adjusted anesthesia depth, and generating relevant prompts based on the secondary comparative evaluation results. The specific evaluation contents are as follows; When the real-time comprehensive anesthesia depth Dfinal(t)> anesthesia threshold TD, it means that after the anesthetic injection rate adjustment mechanism is adjusted, the patient's anesthesia depth is in an overload state. At this time, a red prompt is generated through the visual interface to prompt the anesthesiologist to manually adjust the anesthetic injection rate; When the real-time comprehensive anesthesia depth Dfinal(t) = anesthesia threshold TD, it means that after the anesthetic injection rate adjustment mechanism is adjusted, the patient's anesthesia depth is in a normal state, and no prompt needs to be generated for continued monitoring; When the real-time comprehensive anesthesia depth Dfinal(t) is less than the anesthesia threshold TD, it means that after the anesthetic injection rate adjustment mechanism is adjusted, the patient's anesthesia depth is insufficient. At this time, a green prompt is generated through the visual interface to prompt the anesthesiologist to manually adjust the anesthetic injection rate.

10. An intelligent monitoring system for anesthesia depth, applied to an intelligent monitoring method for anesthesia depth according to any one of claims 1 to 9, characterized in that: It includes preoperative analysis module, anesthesia initiation module, anesthesia depth analysis module, dynamic adjustment module of anesthesia dose, comprehensive anesthesia depth analysis module and comprehensive anesthesia depth monitoring and evaluation module; The preoperative analysis module collects the basic physiological data of the patient through medical equipment before the patient's operation, and calculates and outputs the initial anesthetic dose Dinit according to the collected basic physiological data through the initial anesthetic dose algorithm formula; The anesthesia initiation module collects the echo image of the shoulder nerve through the ultrasound system, and analyzes the data of the tissue around the nerve through the algorithm, accurately enters the brachial plexus, and performs precise local injection according to the initial anesthetic dose Dinit, and then detects the nerve electrical activity data through electromyography; The anesthesia depth analysis module sets a real-time anesthesia depth calculation formula, inputs the nerve perivascular tissue data and the nerve electrical activity data into the anesthesia depth calculation formula, calculates and outputs the real-time anesthesia depth Dreal, and performs difference calculation between the anesthesia depth Dreal and the target anesthesia depth Dtargt to obtain the anesthesia depth difference △D, and performs a preliminary evaluation and analysis of the current anesthesia injection situation based on the output result of the anesthesia depth difference △D; The dynamic adjustment module of the anesthetic dose executes the anesthetic injection rate adjustment mechanism based on the preliminary evaluation result, calculates and outputs the anesthetic injection rate Radj(t) at the current time t, and dynamically adjusts the anesthetic injection rate; The comprehensive anesthesia depth analysis module is adjusted by the anesthetic injection rate adjustment mechanism, collects the patient's anesthesia metabolism data in real time, inputs it into the comprehensive anesthesia depth evaluation formula, calculates and outputs the real-time comprehensive anesthesia depth Dfinal(t), and then calculates and outputs the anesthesia threshold TD; The comprehensive anesthesia depth monitoring and evaluation module performs a secondary comparative evaluation on the obtained comprehensive anesthesia depth Dfinal(t) and the anesthesia threshold TD, deeply monitors and evaluates the anesthesia effect, and generates prompt information based on the evaluation result.

Images