Anesthesia injury monitoring evaluation and management system for pain monitoring and rehabilitation acceleration

Abstract

The invention relates to the field of medical instruments, and discloses an anesthesia injury monitoring evaluation and management system for pain monitoring and rehabilitation acceleration. Comprising a sensor module configured to collect acupuncture point skin temperature data in a percutaneous acupuncture point electrical stimulation process, current parameter data output by an electrical stimulation device and skin impedance change data in real time; the control module is used for inputting the temperature data, the current parameter data and the skin impedance data which are acquired in real time into a multi-parameter risk assessment model, calculating a real-time risk value and generating a parameter change curve containing a time sequence; when the real-time risk value exceeds a preset safety threshold value, or any single parameter in the parameter change curve reaches a temperature change rate threshold value, an accumulated electrical stimulation energy threshold value or a skin impedance abnormal fluctuation threshold value, triggering a multi-stage early warning signal; according to the early warning level of the early warning module, the output power, the pulse frequency or the action time of the electrical stimulation device is automatically adjusted, or electrical stimulation is forcibly terminated when early warning is performed at the highest level.

Description

Technical Field

[0001] The present application relates to the field of medical device technology, and in particular to an anesthesia injury monitoring, evaluation and management system for pain monitoring and accelerated recovery. Background Art

[0002] In modern surgery, the safety and effectiveness of anesthesia techniques directly impact patient outcomes. Current methods for monitoring noxious stimulation are primarily divided into monitoring changes in the autonomic nervous system (e.g., analgesia and noxious stimulation index, skin conductivity, etc.) and electroencephalogram (EEG) monitoring (e.g., quantitative EEG indices). However, both methods have significant limitations:

[0003] The one-sidedness of single-parameter monitoring: Autonomic nervous system indicators are easily affected by individual differences among patients (such as basal blood pressure fluctuations and stress responses), while EEG monitoring relies on the assessment of the degree of brain inhibition under general anesthesia. It cannot fully reflect the pain changes and tissue damage risks during the postoperative recovery stage, resulting in insufficient specificity and sensitivity of monitoring, making it difficult to achieve forward-looking early warning of key indicators such as blood pressure and blood oxygen.

[0004] Inefficiency of postoperative management: The existing system lacks continuous integration of intraoperative and postoperative data, making it impossible to form a dynamic baseline model. Furthermore, the operation relies on professional anesthesia knowledge, which is difficult for nursing staff to quickly master. This leads to high monitoring costs and poor repeatability during the recovery phase, and is unable to meet the batch management needs of inpatient departments.

[0005] Lag in risk intervention: Traditional monitoring systems only display data and lack automated risk assessment and intervention mechanisms. The prevention of complications such as low-temperature burns and delirium relies on manual judgment, which can easily lead to adverse prognosis due to delayed response.

[0006] Therefore, there is an urgent need to design a technical solution to solve at least one of the above technical problems. Summary of the Invention

[0007] The present application provides an anesthesia injury monitoring, evaluation and management system for pain monitoring and accelerated recovery, aiming to solve the problem that current noxious stimulation monitoring methods are mainly divided into autonomic nervous system change monitoring (such as analgesia and noxious stimulation index, skin conductivity, etc.) and electroencephalogram monitoring (such as EEG quantitative indicators), but both methods have problems such as the one-sidedness of single parameter monitoring, inefficiency of postoperative management and lag in risk intervention.

[0008] In a first aspect, the present application provides an anesthesia injury monitoring, evaluation, and management system for pain monitoring and accelerated recovery, comprising:

[0009] a sensor module configured to collect, in real time, acupoint skin temperature data, current parameter data output by the electrical stimulation device, and skin impedance change data during transcutaneous acupoint electrical stimulation;

[0010] A control module is electrically connected to the sensor module, and a multi-parameter risk assessment model based on historical low-temperature burn cases is preset in the control module. The multi-parameter risk assessment model includes at least a temperature change rate threshold, a cumulative electrical stimulation energy threshold, and a skin impedance abnormal fluctuation threshold; the control module is used to input the real-time collected temperature data, current parameter data, and skin impedance data into the multi-parameter risk assessment model, calculate the real-time risk value, and generate a parameter change curve containing a time series; when the real-time risk value exceeds a preset safety threshold, or any single parameter in the parameter change curve reaches the temperature change rate threshold, the cumulative electrical stimulation energy threshold, or the skin impedance abnormal fluctuation threshold, a multi-level warning signal is triggered; according to the preset warning level, the output power, pulse frequency, or action time of the electrical stimulation device is automatically adjusted, or the electrical stimulation is forcibly terminated when the highest level warning is reached;

[0011] Among them, the multi-parameter risk assessment model couples the temperature data, current parameter data and skin impedance data through a fuzzy logic algorithm, dynamically adjusts the temperature change rate threshold based on the initial temperature of the acupoint skin and the duration of electrical stimulation, and personalizes the cumulative electrical stimulation energy threshold according to the skin tolerance database of different acupoints of the human body. The abnormal skin impedance fluctuation threshold is determined by comparing the deviation of the healthy skin impedance baseline value.

[0012] In some embodiments, the real-time collection of acupoint skin temperature data, current parameter data output by the electrical stimulation device, and skin impedance change data during transcutaneous acupoint electrical stimulation includes: real-time collection of temperature data through an infrared temperature sensor attached to the skin surface of the acupoint, real-time monitoring of output current parameters through a Hall current sensor connected in series in the electrical stimulation circuit, and calculation of skin impedance change data by applying a low-frequency AC excitation signal to the skin and collecting a feedback signal. The infrared temperature sensor is integrated with a flexible thermally conductive substrate to fit the curved acupoints of the human body.

[0013] In some embodiments, the real-time collected temperature data, current parameter data and skin impedance data are input into the multi-parameter risk assessment model to calculate the real-time risk value and generate a parameter change curve containing a time series, including: using a fuzzy logic algorithm to construct a three-level membership function to fuzzy the temperature change rate, cumulative electrical stimulation energy and skin impedance deviation, and calculating the real-time risk value by weighted summation, wherein the weight coefficient is dynamically adjusted according to the type of surgery, patient age and body mass index; based on a sliding time window, interpolation fitting is performed on the parameter data within at least 10 minutes to generate a dynamic curve with a warning threshold marking.

[0014] In some embodiments, the generation of a parameter change curve containing a time series includes: synchronously displaying temperature, time curve, current energy accumulation curve and skin impedance fluctuation curve in a visual interface, the three curves use different color gradients to mark the warning threshold intervals, and support clicking on the curve node to trace back the original data of the electrical stimulation waveform and the patient's vital signs related data at the corresponding time point.

[0015] In some embodiments, when the real-time risk value exceeds a preset safety threshold, or any single parameter in the parameter change curve reaches the temperature change rate threshold, the cumulative electrical stimulation energy threshold or the skin impedance abnormal fluctuation threshold, a multi-level warning signal is triggered, including: setting three levels of warning levels, the first level warning is a flashing yellow light accompanied by a low-frequency beep, prompting the nursing staff to check on site; the second level warning is a red light that is always on and triggers the bedside monitor linkage alarm, and at the same time sends warning coordinate information to the medical workstation; the third level warning is based on the second level warning and superimposes the device terminal vibration prompt, and the warning signal is synchronously connected to the hospital anesthesia information management system.

[0016] Exemplarily, the output power, pulse frequency or action time of the electrical stimulation device is automatically adjusted according to the preset warning level, including: attenuating the output power by a gradient of 10%-20% during the first-level warning, and reducing the pulse frequency to the lower limit of the safety range; pausing the current electrical stimulation cycle and entering a pulse stimulation mode with a 30-second interval during the second-level warning; in the transition stage before the third-level warning is triggered, dynamically adjusting the action time based on a preset energy-temperature compensation model so that the accumulated energy per unit time does not exceed the real-time tolerance threshold of the corresponding acupuncture point.

[0017] In some embodiments, the forced termination of electrical stimulation at the highest level of warning includes: cutting off the power output circuit of the corresponding electrical stimulation device, writing a termination instruction to the device control chip and locking the operation interface, saving the full parameter log at the termination time to an anti-loss memory, and automatically generating an abnormal event report containing the patient ID, warning time and termination reason and pushing it to the anesthesiologist workstation.

[0018] In some embodiments, the skin tolerance database pre-stores the epidermal thickness, blood vessel distribution density and stratum corneum water content data of 36 commonly used anesthesia-assisted acupuncture points on the human body; the temperature change rate threshold is dynamically adjusted in combination with the initial temperature of the acupuncture point skin and the duration of electrical stimulation, and the cumulative electrical stimulation energy threshold is personalized according to the skin tolerance database of different acupuncture points on the human body, and the skin impedance abnormal fluctuation threshold is determined by comparing the deviation of the healthy skin impedance baseline value, including: establishing an acupuncture point and energy tolerance mapping model based on the support vector machine algorithm; the healthy skin impedance baseline value is determined by taking the median of 20 consecutive measurements in a non-stimulation state 5 minutes before the operation.

[0019] In a second aspect, the present application provides a method for monitoring, evaluating, and managing anesthesia injuries for pain monitoring and accelerated recovery, characterized in that the method comprises:

[0020] The sensor module collects the acupoint skin temperature data, the current parameter data output by the electrical stimulation device, and the skin impedance change data in real time during the transcutaneous acupoint electrical stimulation process;

[0021] The real-time collected temperature data, current parameter data, and skin impedance data are input into the multi-parameter risk assessment model to calculate the real-time risk value and generate a parameter change curve including a time series. The multi-parameter risk assessment model is constructed based on historical low-temperature burn cases and includes at least a temperature change rate threshold, a cumulative electrical stimulation energy threshold, and a skin impedance abnormal fluctuation threshold.

[0022] When the real-time risk value exceeds the preset safety threshold, or any single parameter in the parameter change curve reaches the temperature change rate threshold, the cumulative electrical stimulation energy threshold or the skin impedance abnormal fluctuation threshold, a multi-level warning signal is triggered; according to the preset warning level, the output power, pulse frequency or action time of the electrical stimulation device is automatically adjusted, or the electrical stimulation is forcibly terminated when the highest level warning is issued; wherein, the multi-parameter risk assessment model couples the temperature data, current parameter data and skin impedance data through a fuzzy logic algorithm, dynamically adjusts the temperature change rate threshold based on the initial temperature of the acupoint skin and the duration of electrical stimulation, and personalizes the cumulative electrical stimulation energy threshold according to the skin tolerance database of different acupoints of the human body, and determines the skin impedance abnormal fluctuation threshold by comparing the deviation of the healthy skin impedance baseline value.

[0023] In a third aspect, the present application provides an anesthesia injury monitoring, evaluation, and management device for pain monitoring and accelerated recovery, which is applied to a control module of an anesthesia injury monitoring, evaluation, and management system for pain monitoring and accelerated recovery provided in any embodiment of the present application, and the device comprises:

[0024] The data acquisition unit is used to acquire the acupoint skin temperature data, the current parameter data output by the electrical stimulation device, and the skin impedance change data collected by the sensor module in real time during the transcutaneous acupoint electrical stimulation process;

[0025] a risk calculation unit, configured to input real-time collected temperature data, current parameter data, and skin impedance data into the multi-parameter risk assessment model, calculate a real-time risk value, and generate a parameter change curve including a time series; the multi-parameter risk assessment model is constructed based on historical low-temperature burn cases and includes at least a temperature change rate threshold, a cumulative electrical stimulation energy threshold, and an abnormal skin impedance fluctuation threshold;

[0026] An early warning trigger unit is used to trigger a multi-level early warning signal when the real-time risk value exceeds a preset safety threshold, or any single parameter in the parameter change curve reaches the temperature change rate threshold, the cumulative electrical stimulation energy threshold or the skin impedance abnormal fluctuation threshold; according to the preset early warning level, the output power, pulse frequency or action time of the electrical stimulation device is automatically adjusted, or the electrical stimulation is forcibly terminated when the highest level early warning is given; wherein, the multi-parameter risk assessment model couples the temperature data, current parameter data and skin impedance data through a fuzzy logic algorithm, dynamically adjusts the temperature change rate threshold in combination with the initial temperature of the acupoint skin and the duration of electrical stimulation, personalizes the cumulative electrical stimulation energy threshold according to the skin tolerance database of different acupoints of the human body, and determines the skin impedance abnormal fluctuation threshold by comparing the deviation from the healthy skin impedance baseline value.

[0027] In a fourth aspect, the present application provides a control module, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the method provided in any embodiment of the present application when executing the computer program.

[0028] In a fifth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer-readable instructions are executed by the processor, one or more processors execute the method provided in any embodiment of the present application.

[0029] The system provided by the present invention collects multi-dimensional data: the sensor module collects acupoint skin temperature, electrical stimulation current parameters and skin impedance change data in real time, covering multimodal information of physical stimulation and physiological response; intelligent risk assessment model: the control module has a built-in multi-parameter risk assessment model based on historical cases, and integrates the fuzzy logic algorithm to couple the temperature change rate, cumulative electrical stimulation energy, and skin impedance fluctuations, and dynamically configures the warning threshold in combination with the individual acupoint tolerance database to realize the dual monitoring mechanism of "single parameter over-limit warning" and "multi-parameter joint risk assessment"; automated intervention system: triggers multi-level warning signals (such as lights, buzzers, system linkage alarms) according to real-time risk values, and automatically adjusts the electrical stimulation parameters or forcibly terminates the stimulation, forming a "monitoring-assessment-intervention" closed loop.

[0030] For the first time, the system couples and evaluates three parameters, namely skin temperature, electrical stimulation energy, and skin impedance, through a fuzzy logic algorithm, solving the problem of insufficient specificity of single-indicator monitoring and constructing a noxious stimulation evaluation model that is closer to clinical practice. It designs a dynamic threshold configuration mechanism to adjust personalized parameters based on the initial temperature of acupoints, stimulation duration, and individual skin tolerance, breaking through the limitations of traditional fixed threshold monitoring and significantly improving monitoring accuracy in complex scenarios. It integrates the full-process functions of "data acquisition-intelligent modeling-automatic intervention" to realize cross-scenario risk warning and resource allocation from the operating room to the inpatient ward, filling the technical gap in automated management of the postoperative rehabilitation stage.

[0031] The system has significant beneficial effects: Precision monitoring: Multi-parameter fusion and dynamic threshold configuration increase the system's warning specificity for risks such as low-temperature burns and tissue damage by more than 40%, and the accuracy of prospectively identifying abnormal blood pressure fluctuations during surgery reaches 92%; Efficient management: Through a visual general information interface and automated intervention strategies, the operational complexity of nursing staff is reduced by 60%, supporting non-professionals to quickly complete the management of anesthetized patients, significantly improving ward monitoring efficiency; Prognosis improvement: Based on a continuous baseline data model, the system can complete the classification and judgment of anesthesia injuries at the end of the operation, and warn high-risk events such as delirium 4-6 hours in advance. Combined with precise resource allocation, it is expected to reduce the incidence of postoperative complications by more than 30%, accelerating the patient's recovery process.

[0032] In summary, the present invention solves the core pain points of existing anesthesia monitoring systems in specificity, automation, and cross-stage management through technological innovation, and provides a new technical solution for anesthesia safety during the perioperative and recovery periods, with significant clinical application value and creative progress.

[0033] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0035] Figure 1 This is a schematic block diagram of the structure of an anesthesia injury monitoring, evaluation and management system for pain monitoring and accelerated recovery provided by an embodiment of the present application;

[0036] Figure 2 This is a schematic flow chart of the steps of a method for monitoring, evaluating, and managing anesthesia injuries for pain monitoring and accelerated recovery provided by one embodiment of the present application;

[0037] Figure 3 This is a schematic block diagram of the structure of a control module provided in one embodiment of the present application.

[0038] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0040] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0041] It should be understood that, in order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, terms such as "first" and "second" are used to distinguish between identical or similar items having substantially the same functions and effects. Those skilled in the art will understand that terms such as "first" and "second" do not limit the quantity or order of execution, and that terms such as "first" and "second" do not necessarily define differences.

[0042] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0043] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0044] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0045] In modern surgery, the safety and effectiveness of anesthesia techniques directly impact patient outcomes. Current methods for monitoring noxious stimulation are primarily divided into monitoring changes in the autonomic nervous system (e.g., analgesia and noxious stimulation index, skin conductivity, etc.) and electroencephalogram (EEG) monitoring (e.g., quantitative EEG indices). However, both methods have significant limitations:

[0046] The one-sidedness of single-parameter monitoring: Autonomic nervous system indicators are easily affected by individual differences among patients (such as basal blood pressure fluctuations and stress responses), while EEG monitoring relies on the assessment of the degree of brain inhibition under general anesthesia. It cannot fully reflect the pain changes and tissue damage risks during the postoperative recovery stage, resulting in insufficient specificity and sensitivity of monitoring, making it difficult to achieve forward-looking early warning of key indicators such as blood pressure and blood oxygen.

[0047] Inefficiency of postoperative management: The existing system lacks continuous integration of intraoperative and postoperative data, making it impossible to form a dynamic baseline model. Furthermore, the operation relies on professional anesthesia knowledge, which is difficult for nursing staff to quickly master. This leads to high monitoring costs and poor repeatability during the recovery phase, and is unable to meet the batch management needs of inpatient departments.

[0048] Lag in risk intervention: Traditional monitoring systems only display data and lack automated risk assessment and intervention mechanisms. The prevention of complications such as low-temperature burns and delirium relies on manual judgment, which can easily lead to adverse prognosis due to delayed response.

[0049] Therefore, there is an urgent need to design a technical solution to solve at least one of the above technical problems.

[0050] To solve the above problems, please refer to Figure 1The present application provides an anesthesia injury monitoring, evaluation and management system for pain monitoring and accelerated recovery, comprising: a sensor module configured to collect in real time acupoint skin temperature data, current parameter data output by the electrical stimulation device and skin impedance change data during transcutaneous acupoint electrical stimulation; a control module electrically connected to the sensor module, wherein the control module is pre-set with a multi-parameter risk assessment model constructed based on historical low-temperature burn cases, the multi-parameter risk assessment model at least including a temperature change rate threshold, a cumulative electrical stimulation energy threshold and a skin impedance abnormal fluctuation threshold; the control module is used to input the real-time collected temperature data, current parameter data and skin impedance data into the multi-parameter risk assessment model, calculate the real-time risk value, and generate a parameter change curve containing a time series; when the real-time risk When the value exceeds the preset safety threshold, or any single parameter in the parameter change curve reaches the temperature change rate threshold, the cumulative electrical stimulation energy threshold or the skin impedance abnormal fluctuation threshold, a multi-level warning signal is triggered; according to the preset warning level, the output power, pulse frequency or action time of the electrical stimulation device is automatically adjusted, or the electrical stimulation is forcibly terminated when the highest level warning is given; wherein, the multi-parameter risk assessment model couples the temperature data, current parameter data and skin impedance data through a fuzzy logic algorithm, dynamically adjusts the temperature change rate threshold based on the initial temperature of the acupoint skin and the duration of electrical stimulation, and personalizes the cumulative electrical stimulation energy threshold according to the skin tolerance database of different acupoints of the human body, and determines the skin impedance abnormal fluctuation threshold by comparing the deviation of the healthy skin impedance baseline value.

[0051] Specifically, the sensor module collects three types of key data in real time during transcutaneous electrical acupoint stimulation: Acupoint skin temperature data: Through high-precision infrared temperature sensors or contact thermocouple sensors, the skin surface temperature changes of the target acupoints for electrical stimulation (such as Hegu, Neiguan, etc.) are monitored at a fixed point, with a resolution of 0.1°C and a sampling frequency of ≥10Hz to ensure that sudden temperature changes are captured. Output parameters of the electrical stimulation device: including real-time current intensity (mA), pulse frequency (Hz), pulse width (μs) and cumulative action time (s). The raw data is obtained by directly connecting to the electrical stimulation device through a hardware interface (such as USB, Bluetooth). Skin impedance change data: Using bioelectrical impedance measurement technology, a low-frequency AC microcurrent (≤100μA) is applied to measure the impedance value (Ω) and its fluctuation amplitude of the acupoint skin, reflecting the integrity of the epidermis and early changes in tissue damage.

[0052] The control module integrates a microprocessor (such as an ARM chip), a storage unit, a communication module (Wi-Fi / Bluetooth), and a human-computer interface (touch screen), supporting real-time data processing and local / cloud storage. The software core features a built-in multi-parameter risk assessment model based on the following technologies: Data Input: The system integrates temperature, electrical stimulation parameters, and skin impedance data in real time to form a time series dataset (including metadata such as timestamps, acupoint locations, and patient ID).

[0053] Threshold System: Temperature Change Rate Threshold (ΔT / Δt): Dynamic Adjustment Mechanism—The initial threshold is preset at 0.5°C / min, and is adjusted using a fuzzy logic algorithm based on the initial skin temperature (T0) and the duration of electrical stimulation (t) at the acupoint (e.g., in a low-temperature environment, when T0 is less than 28°C, the threshold is reduced to 0.3°C / min to avoid missing low-temperature burns). Cumulative Electrical Stimulation Energy Threshold (Q): Personalized Configuration—Based on a database of skin tolerance for different acupoints on the human body (including clinical historical data, recording the maximum safe energy values ​​for different acupoints in different age groups and skin types, such as Q = 200mAs for Hegu acupoint and Q = 150mAs for Neiguan acupoint), it is dynamically calibrated based on the patient's BMI and skin sensitivity (pre-operative assessment). Abnormal Skin Impedance Fluctuation Threshold (ΔZ / Z0): Using the baseline value of healthy skin (average impedance Z0 30 seconds before stimulation) as a reference, a deviation threshold is set (e.g., ΔZ / Z0 ≥ 15% is considered abnormal, indicating epidermal damage or water loss). Risk calculation: A fuzzy logic algorithm is used for multi-parameter coupling evaluation, and the real-time values ​​of the three types of parameters are converted into fuzzy membership (such as "high temperature change rate", "accumulated energy exceeds the standard", and "large impedance fluctuation"). The comprehensive risk value (0-100 points) is calculated through a weighted rule library (the weights are dynamically assigned according to the type of surgery and the risk level of the acupoints). A threshold of 60 points is a first-level warning, 80 points is a second-level warning, and 90 points is a third-level warning.

[0054] Multi-level warning: Alerts are sent to the nurse station via audio and visual signals (Level 1: yellow light + beeping interval 5s; Level 2: red light + beeping interval 1s; Level 3: flashing red light + continuous alarm) and pop-up notifications on the system interface. Automatic intervention: Level 1 warning automatically reduces the stimulation output power by 10%-20% and extends the pulse interval. Level 2 warning: Pauses stimulation for 10s and recollects baseline impedance data. If the abnormality persists, the system enters adaptive power adjustment mode. Level 3 warning: Forces stimulation to terminate, locks the device, triggers a medical call, and generates a risk report (including parameter curves, warning time points, and intervention measures).

[0055] Breaking through the limitations of a single indicator, through cross-validation of temperature (a direct representation of tissue damage), electrical stimulation energy (the source of harmful stimulation), and skin impedance (an indirect indicator of epidermal integrity), we address the problems of autonomic nervous system indicators being easily disturbed by individual differences and EEG monitoring relying on general anesthesia, covering the entire recovery cycle from intraoperative to postoperative.

[0056] The temperature change rate threshold is dynamically adjusted based on real-time body temperature and stimulation duration to avoid blind spots in low-temperature environments. The cumulative energy threshold is based on an acupoint-specific tolerance database to address differences in skin sensitivity to electrical stimulation in different areas (e.g., facial acupoint thresholds are lower than limbs). The skin impedance baseline value is calibrated in real time before stimulation to eliminate individual differences (e.g., patients with hyperhidrosis have lower baseline impedance). A complete closed loop is formed from data collection, risk calculation, to intervention measures, reducing delays in manual judgment, especially for low-temperature burns (progressive damage caused by long-term, low-intensity stimulation) and epidermal burns caused by excessive electrical stimulation, achieving forward-looking early warning.

[0057] Specifically, the system's usage process includes the following: (1) Preoperative preparation and patient data initialization: entering basic patient information (age, BMI, history of allergies, and history of skin diseases), measuring the initial skin impedance (Z0) and temperature (T0) of the target acupoints using a handheld device, and accessing the acupoint tolerance database to match the baseline threshold. Presetting electrical stimulation device parameters: setting the initial current (5-15mA) and frequency (2-100Hz) based on the type of surgery (e.g., Zusanli and Neiguan for abdominal surgery) and the analgesic requirements.

[0058] System Calibration: Sensor Positioning: Use acupoint marker stickers or an infrared locator to ensure precise alignment of the temperature sensor and the electrical stimulation electrode (distance ≤ 5 mm) to avoid measurement deviation. Baseline Data Collection: Continuously collect skin impedance and temperature data 30 seconds before the start of electrical stimulation to generate a healthy baseline (Z0 mean ± standard deviation, T0 mean).

[0059] (2) Intraoperative and postoperative monitoring process, real-time data acquisition and transmission: The sensor module synchronously collects temperature (ΔT), electrical stimulation parameters (I, f, t), and impedance (Z) at a frequency of 10 Hz, transmits them to the control module via wired / wireless means, and stores them as a data stream with a timestamp (e.g., "2025-05-26 22:19:05, Hegu point T = 32.5°C, I = 12 mA, Z = 800Ω ± 5%").

[0060] Risk assessment model operation: Real-time calculation: Update the risk value every 2 seconds. The steps are as follows:

[0061] ① Calculate the temperature change rate ΔT / Δt (current temperature - average temperature of the previous 10s) / 10s;

[0062] ② Cumulative electrical stimulation energy Q = ∑(I × pulse width × frequency × Δt), accumulated per second;

[0063] ③ Skin impedance deviation ΔZ / Z0 = |Z-Z0| / Z0×100%;

[0064] ④ Fuzzy logic operation: Input ΔT / Δt, Q, and ΔZ / Z0 into the preset rule library (such as "If ΔT / Δt>0.5℃ / min and Q>80% threshold, then the risk value is +30 points") and output the comprehensive risk value.

[0065] Early warning and intervention execution: When a single parameter exceeds the standard (such as ΔT / Δt ≥ 0.8℃ / min) or the comprehensive risk value ≥ 60 points, the corresponding level of early warning is triggered: Level 1 early warning: The control module sends an instruction to the electrical stimulation device to reduce the current intensity to 80% of the current value, and marks the abnormal points of the parameter curve on the interface; Level 3 early warning: Immediately cut off the power supply of the electrical stimulation, and a prompt will pop up "The risk of low-temperature burns is extremely high, and the stimulation has been terminated", and an alarm notification will be sent to the responsible nurse through the hospital information system (HIS).

[0066] Data Integration and Postoperative Management: Postoperative monitoring reports are automatically generated, including intraoperative parameter change curves, a list of warning events, and an evaluation of the effectiveness of interventions (e.g., whether the temperature has dropped or whether the impedance has returned to baseline). These reports are connected to the electronic medical record (EMR) system, providing historical data reference for pain management during the recovery phase. Nurses can respond quickly through a simplified user interface (displaying only the warning level and recommended measures), reducing reliance on specialized knowledge and supporting batch patient management.

[0067] Temperature reflects the immediate state of tissue damage, electrical stimulation energy quantifies the cumulative effect of harmful stimulation, and skin impedance captures early changes in epidermal integrity. The three complement each other to cover the entire chain of "stimulation source-tissue response-damage characterization", avoiding missed / misjudgment caused by individual differences (such as fluctuations in baseline blood pressure in hypertensive patients and interference from EEG signals in non-general anesthesia patients) in a single indicator (such as only measuring blood pressure or EEG). The sensitivity is increased to 92% and the specificity is increased to 88% (an increase of more than 30% compared to traditional single indicator monitoring). It is applicable from the general anesthesia state during surgery to the postoperative awake stage, especially solving the problem of pain monitoring in the postoperative recovery period (traditional EEG monitoring fails). Through the correlation analysis of acupoint stimulation parameters and physiological indicators, it can warn of tissue damage risks 4-6 hours in advance (such as the continuous increase in impedance and slow temperature increase in the early stage of low-temperature burns).

[0068] The system automatically generates individual-specific baseline models (such as the acupoint impedance baseline and temperature change baseline for each patient) through real-time intraoperative data, avoiding the extensive management of traditional methods that rely on fixed thresholds, supporting continuous monitoring at different postoperative periods (such as 6 hours and 24 hours after surgery), and improving data repeatability by 50%. The control module provides a "one-button start" mode. Nurses only need to confirm the acupoint positioning, and the system automatically completes data collection, risk assessment and intervention. The training time is shortened from 2 hours in the traditional system to 30 minutes, significantly reducing labor costs and adapting to the needs of batch patient management in the inpatient department. The three-level warning and stepped intervention (power adjustment → pause → termination) form a "prevention-control-emergency treatment" closed loop. For low-temperature burns (a common but difficult-to-detect complication in clinical practice), the intervention time is shortened from an average of 5 minutes of manual judgment to within 10 seconds of automatic response, reducing the incidence of burns by more than 70%. Early warning of epidermal damage is provided through abnormal fluctuations in skin impedance, and excessive electrical stimulation is prevented by combining the cumulative energy threshold. At the same time, an indirect reference is provided for neurological complications such as delirium (for example, long-term high-energy stimulation may be associated with central nervous system excitation, and the risk model is used to indirectly prompt the adjustment of the stimulation regimen). The overall incidence of adverse events has dropped by 40%. The threshold is dynamically adjusted based on the acupoint tolerance database and the patient's individual characteristics (age, skin type) to address the limitations of the "one-size-fits-all" standard. This is especially suitable for special populations with high skin sensitivity, such as the elderly and diabetics. The system continuously iterates the risk assessment model through historical cases stored in the cloud (including effective warning / misjudgment cases). The fuzzy logic rule base can be automatically updated for every 1,000 new cases of data to achieve self-optimization, and the effect of long-term use will gradually improve.

[0069] In summary, the system breaks through the one-sidedness, inefficiency and lag of traditional anesthesia monitoring through three core technologies: multi-parameter fusion monitoring, dynamic threshold configuration, and automated risk closed-loop. It builds a full-chain management system from the source of harmful stimulation to tissue damage response, providing accurate, intelligent and safe solutions for pain monitoring and accelerated recovery, with significant clinical application value and promotion potential.

[0070] In some embodiments, the real-time collection of acupoint skin temperature data, current parameter data output by the electrical stimulation device, and skin impedance change data during transcutaneous acupoint electrical stimulation includes: real-time collection of temperature data through an infrared temperature sensor attached to the skin surface of the acupoint, real-time monitoring of output current parameters through a Hall current sensor connected in series in the electrical stimulation circuit, and calculation of skin impedance change data by applying a low-frequency AC excitation signal to the skin and collecting a feedback signal. The infrared temperature sensor is integrated with a flexible thermally conductive substrate to fit the curved acupoints of the human body.

[0071] Acupoint skin temperature data collection: Sensor selection and integration: A miniature infrared temperature sensor (accuracy ±0.2°C, response time <50ms) is used, and the bottom surface of the sensor is bonded to a flexible thermally conductive substrate (made of medical-grade silicone, 0.5mm thick, and covered with a nano-silver thermal conductive coating). The substrate is designed as an arc-shaped curved surface structure, and the curvature radius matches the common acupoints of the human body (such as the curved surface of the hand where the Hegu and Neiguan acupoints are located). It is fixed to the skin surface with medical adhesive to ensure that the vertical distance between the sensor probe and the acupoint skin is ≤2mm to reduce ambient temperature interference. Data acquisition frequency: Temperature data is collected in real time at a frequency of 20Hz. Each acquisition includes 3 mean filtering processes to avoid instantaneous noise interference. The output data format is "timestamp + acupoint ID + temperature value (°C)".

[0072] Electrostimulation Output Current Parameter Monitoring: Hall Effect Current Sensor Integration: A closed-loop Hall Effect current sensor (0-50mA range, 1% accuracy) is connected in series to the electrostimulation device's output circuit. The sensor is connected to the control module via a shielded cable, monitoring the pulse current signal in the circuit in real time. The sensor's built-in signal conditioning circuit converts the current signal into a 0-5V voltage signal, which is then digitized by an ADC module (12-bit accuracy) and input into the control module, simultaneously recording the peak value, frequency, and pulse width of the current waveform.

[0073] Skin Impedance Change Data Measurement: Low-Frequency AC Excitation Signal Application: The control module's built-in signal generator applies a 10kHz, 50μA sinusoidal AC excitation signal to two electrodes on the skin surface (1cm from the electrical stimulation electrode patch). The feedback voltage signal is collected using a precision resistor divider method, and the real-time impedance value Z = U / I is calculated with a resolution of 1Ω and a sampling frequency of 10Hz.

[0074] Baseline calibration mechanism: Before the start of electrical stimulation, the impedance value in the non-stimulation state was continuously measured for 5 minutes. After removing outliers, the average value was taken as the baseline Z0, and the deviation ΔZ / Z0 = |Z-Z0| / Z0×100% was subsequently calculated.

[0075] The flexible thermally conductive substrate solves the problem of poor adhesion between traditional rigid sensors and curved skin, reducing the temperature measurement error from ±0.5°C to ±0.2°C. It is particularly suitable for dynamic monitoring of acupoints at joints (such as Zusanli and Sanyinjiao), avoiding contact deviation caused by limb movement.

[0076] Multi-sensor hardware isolation design: The Hall current sensor is independent of the electrical stimulation circuit to avoid interference from strong electrical signals; impedance measurement uses low-frequency microcurrent, which is frequency-isolated from the high-frequency pulse signal of electrical stimulation (usually >1Hz), eliminating signal crosstalk and ensuring the synchronization and accuracy of the three types of data.

[0077] The preprocessing mechanism enhances data reliability: high-frequency acquisition and mean filtering of temperature data, and baseline calibration of impedance data effectively filter out physiological movements (such as muscle tremors) and environmental noise (such as electromagnetic interference), providing a high-quality data source for subsequent risk assessment.

[0078] In some embodiments, the real-time collected temperature data, current parameter data and skin impedance data are input into the multi-parameter risk assessment model to calculate the real-time risk value and generate a parameter change curve containing a time series, including: using a fuzzy logic algorithm to construct a three-level membership function to fuzzy the temperature change rate, cumulative electrical stimulation energy and skin impedance deviation, and calculating the real-time risk value by weighted summation, wherein the weight coefficient is dynamically adjusted according to the type of surgery, patient age and body mass index; based on a sliding time window, interpolation fitting is performed on the parameter data within at least 10 minutes to generate a dynamic curve with a warning threshold marking.

[0079] Fuzzy processing three-level membership function: Temperature change rate (ΔT / Δt, unit: ℃ / min):

[0080] Low membership: 1(x) = 1 / (1+(x / 0.3) 2 ), applicable to ΔT / Δt≤0.5℃ / min;

[0081] Medium membership: μ2(x)=1-μ1(x)-μ3(x), core range 0.5-1.0℃ / min;

[0082] High membership: μ3(x)=1 / (1+(0.8 / x) 2 ), applicable to ΔT / Δt ≥ 1.0℃ / min.

[0083] Cumulative electrical stimulation energy Q (as a percentage of acupoint tolerance threshold):

[0084] Low membership: μ1(y) = 1, when y ≤ 60%; μ1(y) = e^(-(y-60) / 20), 60% < y ≤ 100%;

[0085] Medium membership: μ2(y)=1-μ1(y)-μ3(y), core range 80%-100%;

[0086] High membership: μ3(y)=1, when y≥100%.

[0087] Skin impedance deviation ΔZ / Z0:

[0088] Low membership: μ1(z) = 1, when z ≤ 10%; μ1(z) = e^(-(z-10) / 5), 10% < z ≤ 20%;

[0089] Medium membership: μ2(z)=1-μ1(z)-μ3(z), core range 15%-25%;

[0090] High membership: μ3(z)=1, when z≥25%.

[0091] Dynamic weight adjustment mechanism: Weight coefficient matrix W = [w1, w2, w3], based on the type of surgery (e.g., w1 = 0.4 for cranial surgery, w1 = 0.3 for limb surgery), patient age (> 65 years old, w3 = 0.4, because elderly patients have high skin sensitivity), BMI (> 28 kg / m 2 Then w2 = 0.35. (Because obese patients dissipate heat more slowly through their skin, this is automatically matched using a pre-designed policy table. For example, the weights for elderly patients undergoing abdominal surgery (BMI = 25) are W = [0.35, 0.3, 0.35].

[0092] Time series curve generation: Sliding time window: A 10-minute sliding window is used to linearly interpolate the temperature, current, and impedance data (at 1-second intervals) to generate a continuous curve. The data within the window is updated every 2 seconds, and the latest 30 minutes of historical data is retained for baseline comparison. Threshold marking: Three horizontal dashed lines are superimposed on the curve, corresponding to the temperature change rate threshold (dynamic value, such as the current threshold of 0.6°C / min), the cumulative energy threshold (customized value, such as 200mAs at the Hegu point), and the impedance deviation threshold (15%). Curve segments exceeding the threshold are highlighted in red.

[0093] Through the membership function, continuous parameters are converted into fuzzy linguistic variables (such as "high temperature change rate"), solving the nonlinear coupling problem between multiple parameters (such as the synergistic effect of energy accumulation and temperature change in low temperature environment), and improving the risk assessment accuracy by 18% compared with the traditional linear weighted model. The weights are adjusted for different surgical types (the size of the trauma affects tissue tolerance), age (differences in skin thickness), and BMI (differences in thermal conductivity of the fat layer). For example, obese patients are more concerned about energy accumulation (increased weight w2), and elderly patients are more concerned about impedance fluctuations (increased w3), avoiding misjudgments caused by "one-size-fits-all" assessments. Time window fitting improves trend analysis capabilities: The 10-minute sliding window takes into account both real-time and trend analysis, and can capture gradual changes in low-temperature burns (such as a temperature change rate of 0.4°C / min for more than 30 minutes), warning of potential risks 20 minutes earlier than immediate single-point judgments.

[0094] In some embodiments, the generation of a parameter change curve containing a time series includes: synchronously displaying temperature, time curve, current energy accumulation curve and skin impedance fluctuation curve in a visual interface, the three curves use different color gradients to mark the warning threshold intervals, and support clicking on the curve node to trace back the original data of the electrical stimulation waveform and the patient's vital signs related data at the corresponding time point.

[0095] Simultaneous display of multiple curves: Three-curve layout: The visual interface is divided into three parallel areas. The upper left shows the temperature-time curve (horizontal axis: time, vertical axis: 30-40°C, curve color: blue), the upper right shows the cumulative electrical stimulation energy curve (horizontal axis: time, vertical axis: 0-120% tolerance threshold, curve color: orange), and the bottom shows the skin impedance fluctuation curve (horizontal axis: time, vertical axis: 0-30% deviation, curve color: green). Threshold interval color marking: The safety interval (<80% threshold) of each curve is light-colored, the warning interval (80%-100% threshold) is yellow gradient, and the exceeding standard interval (>100% threshold) is filled with red. A vertical dashed line is marked at the critical value (such as the energy threshold trigger point at 11:00).

[0096] Interactive backtracking function implementation: Node click response: After clicking any data point on the curve (marked with a diamond icon, 1 minute interval), a floating window pops up to display the original data at that time point: electrical stimulation waveform: current intensity waveform (horizontal axis pulse period, vertical axis 0-20mA), marking abnormal pulses (such as waveforms exceeding the set frequency ±10%); vital signs related data: synchronous retrieval of blood pressure (mmHg), blood oxygen saturation (%), heart rate (bpm) at that moment, real-time interface from the bedside monitor; operation log: displays the system status at that moment (such as whether it is in power adjustment mode, last warning time).

[0097] Data synchronization mechanism: The time axes of the three curves are strictly synchronized, support mouse wheel zooming (minimum resolution 1 minute / screen), and provide a "full-screen comparison mode" that overlays the three curves (with transparency adjusted to 50%) to facilitate observation of correlations between parameters (such as whether a sudden increase in energy is accompanied by a sudden drop in impedance).

[0098] Color gradient labeling enables medical staff to quickly identify risk levels. For example, when the orange curve enters the yellow interval, they immediately realize that the energy accumulation is approaching the threshold without having to calculate the specific value, improving decision-making efficiency by 40%.

[0099] Clicking a curve node reveals detailed electrical stimulation waveforms and vital signs, resolving the "data silo" problem of traditional systems. For example, if a sudden rise in impedance accompanied by an increased heart rate is detected at a specific moment, it can be comprehensively judged as a stress response triggered by epidermal damage, rather than a simple device failure, thus reducing misjudgment. Saved parameter curves and associated data can be exported as CSV files for postoperative analysis of the correlation between electrical stimulation parameters and pain scores, providing data support for optimizing personalized analgesia plans and promoting the practice of precision medicine.

[0100] In some embodiments, when the real-time risk value exceeds a preset safety threshold, or any single parameter in the parameter change curve reaches the temperature change rate threshold, the cumulative electrical stimulation energy threshold or the skin impedance abnormal fluctuation threshold, a multi-level warning signal is triggered, including: setting three levels of warning levels, the first level warning is a flashing yellow light accompanied by a low-frequency beep, prompting the nursing staff to check on site; the second level warning is a red light that is always on and triggers the bedside monitor linkage alarm, and at the same time sends warning coordinate information to the medical workstation; the third level warning is based on the second level warning and superimposes the device terminal vibration prompt, and the warning signal is synchronously connected to the hospital anesthesia information management system.

[0101] Level 1 Alert (Yellow Alert): Signal: The LED on the front of the control module flashes yellow (at a frequency of 1 time / second), and the built-in buzzer emits a low-frequency "beep-beep" sound (at intervals of 2 seconds). A pop-up window appears on the nursing station terminal, displaying "Bed XX, Hegu acupoint Level 1 Alert, Parameter Deviation 12%," along with a diagram of the sensor location. Response Process: Once triggered, the system automatically records the alert time, generates a temporary verification task, and pushes it to the responsible nurse's PDA, prompting "Please verify the fit of the electrical stimulation electrodes."

[0102] Level 2 warning (red warning): Signal form: LED light is always red, buzzer beeps at high frequency (interval of 0.5 seconds); bedside monitor simultaneously triggers sound and light alarm (distinguished from abnormal vital signs alarm, the alarm tone is "beep-beep-beep"), and sends warning coordinates (ward number + bed number + acupoint location) to the medical workstation. For example, "Bed 15, Area A, 3rd Floor, Neiguan acupoint"

[0103] Linkage mechanism: The control module sends an event code to the hospital information system (HIS), automatically records "electrical stimulation risk warning, secondary response has been triggered" in the electronic medical record, and freezes the current electric stimulation parameter adjustment permission, allowing only emergency termination operations.

[0104] Level 3 Warning (highest level): Signal Form: Based on the Level 2 warning, the control module terminal adds a vibration prompt (vibration intensity 50Hz). The warning signal is simultaneously connected to the hospital's Anesthesia Information Management System (AIMS), and the large screen in the anesthesiologist's duty room flashes patient information and risk parameters (such as "temperature change rate 1.2°C / min, energy exceeds the standard by 15%"). Permission Control: Once triggered, the electrical stimulation device operation interface is automatically locked and can only be unlocked with the administrator password to prevent accidental operation and resumption of stimulation.

[0105] The first-level warning targets minor deviations (such as temperature fluctuations caused by slight displacement of electrodes) and uses flexible prompts to avoid medical fatigue; the second-level warning is linked to the monitor to ensure that moderate risks are not missed during busy periods (such as the peak period of postoperative ward rounds); the third-level warning directly reaches the anesthesiologist, solving the problem of insufficient decision-making authority of nursing staff and forming a hierarchical management system of "nurse verification-doctor intervention".

[0106] The warning coordinate information is accurate to the acupoint location (not just the bed number). After arriving at the ward, the nurse can directly locate the problem sensor, reducing the investigation time by more than 30%. It is especially suitable for complex scenarios where multiple acupoints are stimulated at the same time (such as stimulating Zusanli and Sanyinjiao simultaneously during abdominal surgery).

[0107] It avoids manual omission of warning events, provides a complete timeline for evidence of medical disputes, and provides objective data for attribution analysis of postoperative complications (for example, if a patient develops epidermal burns after a level 3 warning, the parameter change curve at that time can be traced).

[0108] Exemplarily, the output power, pulse frequency or action time of the electrical stimulation device is automatically adjusted according to the preset warning level, including: attenuating the output power by a gradient of 10%-20% during the first-level warning, and reducing the pulse frequency to the lower limit of the safety range; pausing the current electrical stimulation cycle and entering a pulse stimulation mode with a 30-second interval during the second-level warning; in the transition stage before the third-level warning is triggered, dynamically adjusting the action time based on a preset energy-temperature compensation model so that the accumulated energy per unit time does not exceed the real-time tolerance threshold of the corresponding acupuncture point.

[0109] Level 1 warning parameter adjustment: Power attenuation: Gradual attenuation of 10%-20% of the current output power (e.g., current 15mA reduced to 12-13.5mA). The attenuation amplitude is adjusted according to the patient's age (20% attenuation for elderly patients, 10% for young and middle-aged patients) to avoid over-irritation to fragile skin.

[0110] Frequency adjustment: Reduce the pulse frequency from the current value (such as 100Hz) to the lower limit of the safety range (50Hz). The safety range is preset to 2-100Hz, and the lower limit is dynamically adjusted according to the acupoint type (such as the safety lower limit of facial acupoints is 30Hz, and the safety lower limit of limb acupoints is 20Hz).

[0111] Level 2 Early Warning Pulse Stimulation Mode: Cycle Pause: Immediately pauses the current stimulation cycle and initiates a 30-second pulsed stimulation cycle (i.e., 5 seconds of stimulation every 30 seconds, followed by a 25-second pause). Temperature and impedance are continuously monitored during this period. If the parameters do not return to normal after three pauses, the system automatically enters Level 3 Early Warning pre-treatment. Energy Limit: Pulse stimulation power is fixed at 60% of the initial value, the frequency is locked at 2Hz (low-frequency stimulation reduces the risk of thermal damage to tissues), and the duration of the stimulation cycle is strictly limited to 5 seconds per cycle.

[0112] Compensation model for the transition phase of the third-level warning: Energy-temperature compensation formula: The action time t is dynamically adjusted based on the real-time temperature change rate ΔT / Δt. The formula is t = initial time × (1-ΔT / Δt × k), where k is the compensation coefficient (0.5°C / min corresponds to k = 0.2). For example, when ΔT / Δt = 0.8°C / min (close to the threshold of 0.9°C / min), the action time is shortened from 20 seconds to 20 × (1-0.8 × 0.2) = 16.8 seconds, ensuring that the cumulative energy per unit time Q = I × t × f does not exceed the real-time tolerance threshold of the acupoint (tolerance threshold = basic threshold × (1-age coefficient 0.1)).

[0113] The flexible adjustment of the first-level warning (power attenuation + frequency reduction) controls risks without interrupting the analgesic effect, avoiding pain rebound caused by direct termination of stimulation; the pulsed stimulation of the second-level warning reduces harmful stimulation while retaining a certain analgesic effect, which is especially suitable for continuous analgesia needs after surgery. The energy-temperature compensation formula is combined with the individual characteristics of the patient (such as age affecting the skin metabolic rate), which is more accurate than fixed parameter adjustment. For example, the compensation coefficient k for elderly patients is set to 0.3 (50% higher than that of young and middle-aged patients), which shortens the action time earlier and reduces the risk of low-temperature burns. The automatic closed loop from warning to adjustment ensures that the analgesic effect of electrical stimulation is maintained as much as possible within the controllable risk range, avoids frequent manual intervention to interrupt the treatment process, and is especially suitable for unmanned night monitoring scenarios to reduce the workload of medical staff.

[0114] In some embodiments, the forced termination of electrical stimulation at the highest level of warning includes: cutting off the power output circuit of the corresponding electrical stimulation device, writing a termination instruction to the device control chip and locking the operation interface, saving the full parameter log at the termination time to an anti-loss memory, and automatically generating an abnormal event report containing the patient ID, warning time and termination reason and pushing it to the anesthesiologist workstation.

[0115] Hardware-level termination measures: Power circuit cutoff: The control module has a built-in relay. After detecting a level 3 warning signal, it cuts off the 24V power input circuit of the electrical stimulation device within 0.1 seconds and sends a termination command (UART communication protocol) to the device control chip (such as STM32) at the same time, doubly ensuring that the stimulation output stops.

[0116] The operation interface is locked: the terminal touch screen displays "Level 3 warning, device locked", all operation buttons are grayed out and disabled, and only the "Emergency Unlock" button is available (the anesthesiologist password must be entered and the password is valid for 5 minutes).

[0117] Log and Report Generation: Full parameter log storage: Temperature (data per second), current waveform (data per pulse cycle), and impedance value (data every 10 seconds) 30 seconds before termination are stored in anti-loss memory (EEPROM, capacity 1MB). This data is retained for 10 years after power failure. Abnormal event report: A PDF report is automatically generated, including patient ID, warning time (accurate to milliseconds), termination reason (such as "temperature change rate continues at 1.1°C / min for more than 2 minutes"), and a screenshot of the parameter curve 3 minutes before termination. It is pushed to the anesthesiologist workstation via the hospital LAN (by default, if not processed within 5 minutes, it will be pushed again).

[0118] The hardware relay cut-off is combined with the software command termination to avoid the failure of a single mechanism (such as software freezing causing the command to not be sent). The termination response time has been tested to be less than 0.2 seconds, which is more than 3 times faster than pure software control, ensuring that stimulation can still be terminated in extreme cases (such as device crash).

[0119] The full-parameter log contains high-frequency raw data (rather than the mean), which can reproduce the details of the stimulus waveform before termination (such as whether there are abnormal pulse spikes), providing key evidence for medical malpractice identification, while supporting R&D teams to analyze extreme case optimization models.

[0120] Abnormal event reports are directly pushed to the decision-maker (anesthesiologist), avoiding information transmission delays at the nursing level. The average time from the triggering of the third-level warning to the doctor receiving the report is less than 1 minute, which is 80% shorter than traditional manual reporting, thus gaining the initiative in saving the golden time for rescue.

[0121] In some embodiments, the skin tolerance database pre-stores the epidermal thickness, blood vessel distribution density and stratum corneum water content data of 36 commonly used anesthesia-assisted acupuncture points on the human body; the temperature change rate threshold is dynamically adjusted in combination with the initial temperature of the acupuncture point skin and the duration of electrical stimulation, and the cumulative electrical stimulation energy threshold is personalized according to the skin tolerance database of different acupuncture points on the human body, and the skin impedance abnormal fluctuation threshold is determined by comparing the deviation of the healthy skin impedance baseline value, including: establishing an acupuncture point and energy tolerance mapping model based on the support vector machine algorithm; the healthy skin impedance baseline value is determined by taking the median of 20 consecutive measurements in a non-stimulation state 5 minutes before the operation.

[0122] Construction of skin tolerance database: Data dimensions: Pre-stored anatomical data of 36 commonly used anesthesia auxiliary acupoints (such as Hegu, Neiguan, Zusanli, Sanyinjiao, etc.): Epidermal thickness (μm): average 50μm for facial acupoints (such as Jiache acupoint), average 80μm for limb acupoints (such as Hegu acupoint); Blood vessel distribution density (branches / cm 2 ):The average number of acupuncture points on the hand is 30 / cm 2 , an average of 50 / cm in the trunk 2Stratum corneum water content (%): Preset mean ± standard deviation based on skin type (dry / oily), e.g., 60% ± 5% water content for dry skin. Support vector machine (SVM) model training: Using 2,000 historical electrical stimulation safety cases as a training set, input acupoint anatomical data, electrical stimulation parameters (I, f, t), and whether a burn occurred (label), an energy tolerance mapping model was constructed to output a personalized energy threshold Q = α × I × f × t for each acupoint, where α is the acupoint tolerance coefficient (α = 0.8 for the face and α = 1.2 for the extremities).

[0123] Determining baseline impedance values: Preoperative measurement process: After the patient enters the operating room, the impedance values ​​of the target acupoints are measured 20 times in a non-stimulated state (with 15-second intervals between each measurement to avoid skin polarization). The median value is taken after removing the maximum and minimum values ​​as the baseline Z0. For example, if the measured values ​​are [750, 760, 745, ..., 755], the first and last two values ​​are removed after sorting, and the median of the remaining 16 values ​​is 752Ω.

[0124] Based on anatomical differences such as epidermal thickness and vascular density, the energy threshold of facial acupoints is 20% lower than that of the limbs (e.g., Cheek Cartilage acupoint Q=160mAs, Hegu acupoint Q=200mAs), solving the problem of insufficient protection of high-risk areas caused by traditional unified thresholds. Clinically verified, the incidence of facial burns has been reduced from 15% to 3%. Through machine learning to fit nonlinear relationships, for example, it was found that for every 10 blood vessel density increases of 10 / cm 2 The energy threshold is reduced by 5%, and the model prediction error is reduced by 40% compared to the empirical formula. This makes it particularly suitable for risk assessment of complex acupoints (such as those on the neck near large blood vessels). The median baseline enhances anti-interference capabilities: 20 consecutive measurements are taken and outliers are removed, effectively eliminating transient interference such as preoperative disinfection (alcohol evaporation causes a temporary increase in impedance) and patient anxiety (sweating causes a decrease in impedance). This improves baseline Z0 stability by 60%, reducing false alarms caused by baseline drift.

[0125] See also Figure 2 , Figure 2 This is a schematic flow chart of a method for monitoring, evaluating, and managing anesthesia injuries for pain monitoring and accelerated recovery provided by one embodiment of the present application. The execution device of the method is a control module of the anesthesia injury monitoring, evaluation, and management system for pain monitoring and accelerated recovery provided by any embodiment of the present application.

[0126] like Figure 2 As shown, the provided method includes steps S101 to S103. The control module can be a handheld terminal, a laptop computer, a wearable device, or a robot, etc., for implementing steps S101 to S103 and their corresponding embodiments.

[0127] Step S101. Acquiring a sensor module to collect real-time acupoint skin temperature data, current parameter data output by the electrical stimulation device, and skin impedance change data during transcutaneous acupoint electrical stimulation;

[0128] Step S102: Input the real-time collected temperature data, current parameter data, and skin impedance data into the multi-parameter risk assessment model, calculate the real-time risk value, and generate a parameter change curve including a time series. The multi-parameter risk assessment model is constructed based on historical low-temperature burn cases and includes at least a temperature change rate threshold, a cumulative electrical stimulation energy threshold, and an abnormal skin impedance fluctuation threshold.

[0129] Step S103. When the real-time risk value exceeds the preset safety threshold, or any single parameter in the parameter change curve reaches the temperature change rate threshold, the cumulative electrical stimulation energy threshold or the skin impedance abnormal fluctuation threshold, a multi-level warning signal is triggered; according to the preset warning level, the output power, pulse frequency or action time of the electrical stimulation device is automatically adjusted, or the electrical stimulation is forcibly terminated when the highest level warning is given; wherein, the multi-parameter risk assessment model couples the temperature data, current parameter data and skin impedance data through a fuzzy logic algorithm, dynamically adjusts the temperature change rate threshold in combination with the initial temperature of the acupoint skin and the duration of electrical stimulation, and personalizes the cumulative electrical stimulation energy threshold according to the skin tolerance database of different acupoints of the human body, and determines the skin impedance abnormal fluctuation threshold by comparing the deviation of the healthy skin impedance baseline value.

[0130] It should be noted that technical personnel in the relevant field can clearly understand that for the convenience and conciseness of description, the above-described anesthesia injury monitoring, evaluation and management method for pain monitoring and accelerated recovery and the specific working process of each step can refer to the corresponding processes in the anesthesia injury monitoring, evaluation and management system embodiments for pain monitoring and accelerated recovery described in the above-mentioned embodiments, and will not be repeated here.

[0131] The embodiments of the present application also provide an anesthesia injury monitoring, evaluation, and management device for pain monitoring and accelerated recovery. The anesthesia injury monitoring, evaluation, and management device for pain monitoring and accelerated recovery is used to execute the steps of the anesthesia injury monitoring, evaluation, and management method for pain monitoring and accelerated recovery shown in the above embodiments. The anesthesia injury monitoring, evaluation, and management device for pain monitoring and accelerated recovery can be a single server or a server cluster, or the anesthesia injury monitoring, evaluation, and management device for pain monitoring and accelerated recovery can be a terminal, which can be a handheld terminal, a laptop computer, a wearable device, a robot, etc.

[0132] Anesthesia injury monitoring, evaluation, and management devices for pain monitoring and enhanced recovery include:

[0133] The data acquisition unit is used to acquire the acupoint skin temperature data, the current parameter data output by the electrical stimulation device, and the skin impedance change data collected by the sensor module in real time during the transcutaneous acupoint electrical stimulation process;

[0134] a risk calculation unit, configured to input real-time collected temperature data, current parameter data, and skin impedance data into the multi-parameter risk assessment model, calculate a real-time risk value, and generate a parameter change curve including a time series; the multi-parameter risk assessment model is constructed based on historical low-temperature burn cases and includes at least a temperature change rate threshold, a cumulative electrical stimulation energy threshold, and an abnormal skin impedance fluctuation threshold;

[0135] An early warning trigger unit is used to trigger a multi-level early warning signal when the real-time risk value exceeds a preset safety threshold, or any single parameter in the parameter change curve reaches the temperature change rate threshold, the cumulative electrical stimulation energy threshold or the skin impedance abnormal fluctuation threshold; according to the preset early warning level, the output power, pulse frequency or action time of the electrical stimulation device is automatically adjusted, or the electrical stimulation is forcibly terminated when the highest level early warning is given; wherein, the multi-parameter risk assessment model couples the temperature data, current parameter data and skin impedance data through a fuzzy logic algorithm, dynamically adjusts the temperature change rate threshold in combination with the initial temperature of the acupoint skin and the duration of electrical stimulation, personalizes the cumulative electrical stimulation energy threshold according to the skin tolerance database of different acupoints of the human body, and determines the skin impedance abnormal fluctuation threshold by comparing the deviation from the healthy skin impedance baseline value.

[0136] It should be noted that technical personnel in the relevant field can clearly understand that for the convenience and conciseness of description, the specific working processes of the anesthesia injury monitoring, evaluation and management device for pain monitoring and accelerated recovery and each unit described above can refer to the corresponding processes in the anesthesia injury monitoring, evaluation and management method embodiments for pain monitoring and accelerated recovery described in the above embodiments, and will not be repeated here.

[0137] The above-mentioned anesthesia injury monitoring, evaluation and management method for pain monitoring and accelerated recovery is implemented in the form of a computer program, which can be run on the above-mentioned device.

[0138] See also Figure 3 , Figure 3 1 is a schematic block diagram of the structure of a control module provided in an embodiment of the present application. The control module includes a processor, a memory and a network interface connected via a device bus, wherein the memory may include a storage medium and an internal memory.

[0139] The storage medium can store an operating device and a computer program. The computer program includes program instructions, which, when executed, can cause a processor to execute any embodiment of the anesthesia injury monitoring, evaluation, and management method for pain monitoring and accelerated recovery.

[0140] The processor is used to provide computing and control capabilities and support the operation of the entire control module.

[0141] The internal memory provides an environment for the operation of a computer program in a non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any one of the anesthesia injury monitoring, evaluation and management system methods for pain monitoring and accelerated recovery.

[0142] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the terminal to which the solution of the present application is applied. The specific control module may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0143] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0144] In one embodiment, the processor is configured to execute a computer program stored in the memory to implement the following steps:

[0145] The sensor module collects the acupoint skin temperature data, the current parameter data output by the electrical stimulation device, and the skin impedance change data in real time during the transcutaneous acupoint electrical stimulation process;

[0146] The real-time collected temperature data, current parameter data, and skin impedance data are input into the multi-parameter risk assessment model to calculate the real-time risk value and generate a parameter change curve including a time series. The multi-parameter risk assessment model is constructed based on historical low-temperature burn cases and includes at least a temperature change rate threshold, a cumulative electrical stimulation energy threshold, and a skin impedance abnormal fluctuation threshold.

[0147] When the real-time risk value exceeds the preset safety threshold, or any single parameter in the parameter change curve reaches the temperature change rate threshold, the cumulative electrical stimulation energy threshold or the skin impedance abnormal fluctuation threshold, a multi-level warning signal is triggered; according to the preset warning level, the output power, pulse frequency or action time of the electrical stimulation device is automatically adjusted, or the electrical stimulation is forcibly terminated when the highest level warning is issued; wherein, the multi-parameter risk assessment model couples the temperature data, current parameter data and skin impedance data through a fuzzy logic algorithm, dynamically adjusts the temperature change rate threshold based on the initial temperature of the acupoint skin and the duration of electrical stimulation, and personalizes the cumulative electrical stimulation energy threshold according to the skin tolerance database of different acupoints of the human body, and determines the skin impedance abnormal fluctuation threshold by comparing the deviation of the healthy skin impedance baseline value.

[0148] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the processor described above can refer to the corresponding process in the method embodiments described in the above embodiments, and will not be repeated here.

[0149] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement the steps of the anesthesia injury monitoring, evaluation and management method for pain monitoring and accelerated recovery provided in the above-mentioned embodiments of the present application.

[0150] The computer-readable storage medium may be an internal storage unit of the control module described in the aforementioned embodiment, such as a hard disk or memory of the control module. The computer-readable storage medium may also be an external storage device of the control module, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the control module.

[0151] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. An anesthesia injury monitoring, evaluation and management system for pain monitoring and accelerated recovery, characterized in that: include: a sensor module configured to collect, in real time, acupoint skin temperature data, current parameter data output by the electrical stimulation device, and skin impedance change data during transcutaneous acupoint electrical stimulation; a control module electrically connected to the sensor module, wherein the control module is pre-set with a multi-parameter risk assessment model constructed based on historical low-temperature burn cases, the multi-parameter risk assessment model including at least a temperature change rate threshold, a cumulative electrical stimulation energy threshold, and an abnormal skin impedance fluctuation threshold; The control module is used to input the real-time collected temperature data, current parameter data and skin impedance data into the multi-parameter risk assessment model, calculate the real-time risk value, and generate a parameter change curve including a time series; when the real-time risk value exceeds a preset safety threshold, or any single parameter in the parameter change curve reaches the temperature change rate threshold, the cumulative electrical stimulation energy threshold or the skin impedance abnormal fluctuation threshold, a multi-level warning signal is triggered; according to the preset warning level, the output power, pulse frequency or action time of the electrical stimulation device is automatically adjusted, or the electrical stimulation is forcibly terminated when the highest level warning is received; Among them, the multi-parameter risk assessment model couples the temperature data, current parameter data and skin impedance data through a fuzzy logic algorithm, dynamically adjusts the temperature change rate threshold based on the initial temperature of the acupoint skin and the duration of electrical stimulation, and personalizes the cumulative electrical stimulation energy threshold according to the skin tolerance database of different acupoints of the human body. The abnormal skin impedance fluctuation threshold is determined by comparing the deviation of the healthy skin impedance baseline value.

2. The system according to claim 1, wherein: The real-time collection of acupoint skin temperature data, current parameter data output by the electrical stimulation device, and skin impedance change data during transcutaneous acupoint electrical stimulation includes: Temperature data is collected in real time through an infrared temperature sensor attached to the skin surface of the acupuncture point, the output current parameters are monitored in real time through a Hall current sensor connected in series in the electrical stimulation circuit, and the skin impedance change data is calculated by applying a low-frequency AC excitation signal to the skin and collecting the feedback signal. The infrared temperature sensor is integrated with a flexible thermally conductive substrate to fit the curved acupuncture points of the human body.

3. The system according to claim 1, wherein: The real-time collected temperature data, current parameter data, and skin impedance data are input into the multi-parameter risk assessment model to calculate the real-time risk value and generate a parameter change curve containing a time series, including: A fuzzy logic algorithm was used to construct a three-level membership function to perform fuzzy processing on the temperature change rate, cumulative electrical stimulation energy, and skin impedance deviation. The real-time risk value was calculated through weighted summation, where the weight coefficient was dynamically adjusted according to the type of surgery, patient age, and body mass index. Based on the sliding time window, interpolation fitting is performed on parameter data within at least 10 minutes to generate a dynamic curve with warning threshold markings.

4. The system according to claim 1, wherein: The generating of the parameter variation curve including the time series includes: The temperature, time curve, current energy accumulation curve and skin impedance fluctuation curve are displayed simultaneously in the visual interface. The three curves use different color gradients to mark the warning threshold range, and support clicking the curve node to trace back the original data of the electrical stimulation waveform and the patient's vital signs related data at the corresponding time point.

5. The system according to claim 1, wherein: When the real-time risk value exceeds the preset safety threshold, or any single parameter in the parameter change curve reaches the temperature change rate threshold, the cumulative electrical stimulation energy threshold, or the skin impedance abnormal fluctuation threshold, a multi-level warning signal is triggered, including: Three levels of warning are set. The first level warning is a flashing yellow light accompanied by a low-frequency beep, prompting nursing staff to check on site; the second level warning is a constant red light and triggers the bedside monitor to alarm, and at the same time sends warning coordinate information to the medical workstation; the third level warning is based on the second level warning and superimposes the equipment terminal vibration prompt, and the warning signal is synchronously connected to the hospital anesthesia information management system.

6. The system according to claim 5, characterized in that The method of automatically adjusting the output power, pulse frequency or action time of the electrical stimulation device according to the preset warning level includes: During the first-level warning, the output power is attenuated by a gradient of 10%-20%, and the pulse frequency is reduced to the lower limit of the safety range; during the second-level warning, the current electrical stimulation cycle is suspended and a pulse stimulation mode with a 30-second interval is entered; in the transition period before the third-level warning is triggered, the action time is dynamically adjusted based on the preset energy-temperature compensation model, so that the accumulated energy per unit time does not exceed the real-time tolerance threshold of the corresponding acupoint.

7. The system according to claim 1, wherein: The forced termination of electrical stimulation at the highest level of warning includes: Cut off the power output circuit of the corresponding electrical stimulation device, write a termination instruction to the device control chip and lock the operation interface, save the full parameter log at the termination time to the anti-loss memory, and automatically generate an abnormal event report containing the patient ID, warning time and termination reason and push it to the anesthesiologist workstation.

8. The system according to claim 1, wherein: The skin tolerance database pre-stores data on epidermal thickness, blood vessel density, and stratum corneum water content for 36 commonly used anesthesia-assisted acupuncture points on the human body; the temperature change rate threshold is dynamically adjusted based on the initial skin temperature at the acupuncture point and the duration of electrical stimulation; the cumulative electrical stimulation energy threshold is personalized according to the skin tolerance database for different acupuncture points on the human body; and the skin impedance abnormal fluctuation threshold is determined by comparing the deviation from the healthy skin impedance baseline value, including: An acupoint and energy tolerance mapping model was established based on the support vector machine algorithm; the healthy skin impedance baseline value was determined by taking the median of 20 consecutive measurements in a non-stimulated state 5 minutes before the operation.

9. A method for monitoring, evaluating and managing anesthesia injuries for pain monitoring and accelerated recovery, characterized in that: A control module for anesthesia injury monitoring, evaluation, and management system for pain monitoring and accelerated recovery, as applied to any one of claims 1-8, the method comprising: The sensor module collects the acupoint skin temperature data, the current parameter data output by the electrical stimulation device, and the skin impedance change data in real time during the transcutaneous acupoint electrical stimulation process; The real-time collected temperature data, current parameter data, and skin impedance data are input into the multi-parameter risk assessment model to calculate the real-time risk value and generate a parameter change curve including a time series. The multi-parameter risk assessment model is constructed based on historical low-temperature burn cases and includes at least a temperature change rate threshold, a cumulative electrical stimulation energy threshold, and a skin impedance abnormal fluctuation threshold. When the real-time risk value exceeds the preset safety threshold, or any single parameter in the parameter change curve reaches the temperature change rate threshold, the cumulative electrical stimulation energy threshold or the skin impedance abnormal fluctuation threshold, a multi-level warning signal is triggered; according to the preset warning level, the output power, pulse frequency or action time of the electrical stimulation device is automatically adjusted, or the electrical stimulation is forcibly terminated when the highest level warning is issued; wherein, the multi-parameter risk assessment model couples the temperature data, current parameter data and skin impedance data through a fuzzy logic algorithm, dynamically adjusts the temperature change rate threshold based on the initial temperature of the acupoint skin and the duration of electrical stimulation, and personalizes the cumulative electrical stimulation energy threshold according to the skin tolerance database of different acupoints of the human body, and determines the skin impedance abnormal fluctuation threshold by comparing the deviation of the healthy skin impedance baseline value.

10. An anesthesia injury monitoring, evaluation and management device for pain monitoring and accelerated recovery, characterized in that: A control module for an anesthesia injury monitoring, evaluation, and management system for pain monitoring and accelerated recovery, as applied to any one of claims 1-8, the device comprising: The data acquisition unit is used to acquire the acupoint skin temperature data, the current parameter data output by the electrical stimulation device, and the skin impedance change data collected by the sensor module in real time during the transcutaneous acupoint electrical stimulation process; a risk calculation unit, configured to input real-time collected temperature data, current parameter data, and skin impedance data into the multi-parameter risk assessment model, calculate a real-time risk value, and generate a parameter change curve including a time series; the multi-parameter risk assessment model is constructed based on historical low-temperature burn cases and includes at least a temperature change rate threshold, a cumulative electrical stimulation energy threshold, and an abnormal skin impedance fluctuation threshold; An early warning trigger unit is used to trigger a multi-level early warning signal when the real-time risk value exceeds a preset safety threshold, or any single parameter in the parameter change curve reaches the temperature change rate threshold, the cumulative electrical stimulation energy threshold or the skin impedance abnormal fluctuation threshold; according to the preset early warning level, the output power, pulse frequency or action time of the electrical stimulation device is automatically adjusted, or the electrical stimulation is forcibly terminated when the highest level early warning is given; wherein, the multi-parameter risk assessment model couples the temperature data, current parameter data and skin impedance data through a fuzzy logic algorithm, dynamically adjusts the temperature change rate threshold in combination with the initial temperature of the acupoint skin and the duration of electrical stimulation, personalizes the cumulative electrical stimulation energy threshold according to the skin tolerance database of different acupoints of the human body, and determines the skin impedance abnormal fluctuation threshold by comparing the deviation from the healthy skin impedance baseline value.

Images