Wearable anesthesia depth monitoring equipment and monitoring method thereof

Abstract

The invention discloses wearable anesthesia depth monitoring equipment and a monitoring method thereof, and relates to the technical field of anesthesia monitoring, and the method comprises the following steps: collecting electroencephalogram signals, oxyhemoglobin saturation, integrated heart rate and skin conductance signals of a user through a head-mounted module and a wrist-strap module, and combining physiological feature information and operation feature information to obtain a monitoring result of the depth of anesthesia; and sending the data to a cloud server, and configuring an anesthesia monitoring precision coefficient. And according to the precision coefficient, performing anesthesia depth identification by using the multi-modal physiological signal, generating an anesthesia depth monitoring result, and displaying the result in real time. The technical problems that existing anesthesia depth monitoring equipment depends on a single signal, is insufficient in accuracy and real-time performance, is poor in equipment portability and cannot adapt to the multi-scene requirement of a resource-limited environment are solved, and the purposes that multi-modal physiological signal collection and personalized monitoring precision configuration are achieved, and the monitoring precision of the anesthesia depth is greatly improved are achieved. The accuracy, the real-time performance and the portability of anesthesia depth monitoring are improved, and the technical effects of multi-scene application requirements are met.

Description

Technical Field

[0001] The present invention relates to the technical field of anesthesia monitoring, and in particular to a wearable anesthesia depth monitoring device and a monitoring method thereof. Background Art

[0002] In clinical anesthesia management, accurate monitoring of anesthesia depth is crucial to ensure patient safety. Existing anesthesia monitoring equipment mainly relies on a single EEG signal (such as the bispectral index, BIS). Although it can assess the patient's state of consciousness, it has a single function and relies on fixed installation. The equipment is large, costly, and complex to operate, and requires special consumables (such as disposable electrodes). These limitations make it difficult for traditional equipment to meet the needs of short-term surgery, local anesthesia, and primary care scenarios with limited resources. In addition, single signal monitoring cannot fully reflect the patient's physiological state and is easily interfered by artifacts, affecting the accuracy of monitoring. Summary of the invention

[0003] The present application provides a wearable anesthesia depth monitoring device and a monitoring method thereof, which are used to solve the technical problems that existing anesthesia depth monitoring devices rely on a single signal, lack accuracy and real-time performance, have poor portability, and cannot adapt to the multi-scenario requirements of resource-constrained environments.

[0004] In view of the above problems, the present application provides a wearable anesthesia depth monitoring device and a monitoring method thereof.

[0005] In a first aspect, the present application provides a wearable anesthesia depth monitoring device, the device comprising a head-mounted module, a wristband module and an anesthesia depth monitoring system, the system comprising: a physiological signal monitoring unit, for performing EEG signal monitoring, blood oxygen saturation monitoring, integrated heart rate monitoring and skin conductance monitoring on a user wearing the device through the head-mounted module and the wristband module, and obtaining EEG signals, blood oxygen saturation, integrated heart rate and skin conductance, wherein the head-mounted module and the wristband module are respectively configured with an EEG sensor, a blood oxygen saturation sensor, an integrated heart rate sensor and a skin conductance sensor; a feature information acquisition unit; A unit for acquiring the physiological characteristic information and surgical characteristic information of the user; an anesthesia monitoring accuracy configuration unit for sending the EEG signal, blood oxygen saturation, integrated heart rate, skin conductance, physiological characteristic information and surgical characteristic information to the cloud server, and configuring an anesthesia monitoring accuracy coefficient for monitoring the anesthesia depth of the user according to the physiological characteristic information and surgical characteristic information; an anesthesia depth identification unit for identifying the anesthesia depth according to the EEG signal, blood oxygen saturation, integrated heart rate and skin conductance according to the anesthesia monitoring accuracy coefficient, obtaining and receiving anesthesia depth monitoring results, and displaying the anesthesia depth monitoring results.

[0006] In a second aspect, the present application provides a wearable anesthesia depth monitoring method, the method comprising: performing EEG signal monitoring, blood oxygen saturation monitoring, integrated heart rate monitoring and skin conductance monitoring on a user wearing the device through a head-mounted module and a wristband module, and obtaining EEG signals, blood oxygen saturation, integrated heart rate and skin conductance, wherein the head-mounted module and the wristband module are respectively configured with EEG sensors, blood oxygen saturation sensors, integrated heart rate sensors and skin conductance sensors; obtaining physiological characteristic information and surgical characteristic information of the user; sending the EEG signals, blood oxygen saturation, integrated heart rate, skin conductance, physiological characteristic information and surgical characteristic information to a cloud server, and configuring an anesthesia monitoring accuracy coefficient for anesthesia depth monitoring of the user according to the physiological characteristic information and surgical characteristic information; according to the anesthesia monitoring accuracy coefficient, identifying the anesthesia depth according to the EEG signals, blood oxygen saturation, integrated heart rate and skin conductance, obtaining and receiving anesthesia depth monitoring results, and displaying the anesthesia depth monitoring results.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The wearable anesthesia depth monitoring device and the monitoring method thereof provided in the embodiments of the present application relate to the field of anesthesia monitoring technology. Multimodal signals such as EEG, blood oxygen saturation, heart rate, and skin conductance are collected through head-mounted and wristband modules, and the anesthesia monitoring accuracy coefficient is configured in combination with physiological and surgical characteristic information. The cloud server and intelligent algorithm are used to identify the depth of anesthesia, and accurate monitoring results are generated and displayed in real time to meet the needs of multiple scenarios. The technical problems that the existing anesthesia depth monitoring equipment relies on a single signal, lacks accuracy and real-time performance, and has poor portability and cannot adapt to the multi-scenario requirements of resource-constrained environments are solved. The accuracy, real-time performance and portability of anesthesia depth monitoring are improved through multi-modal physiological signal collection and personalized monitoring accuracy configuration, and the technical effect of meeting the application needs of multiple scenarios is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A structural schematic diagram of an anesthesia depth monitoring system of a wearable anesthesia depth monitoring device is provided for this application;

[0010] Figure 2 A flow chart of a wearable anesthesia depth monitoring method is provided for this application.

[0011] Description of reference numerals:

[0012] A physiological signal monitoring unit 11, a characteristic information acquiring unit 12, an anesthesia monitoring accuracy configuration unit 13, and an anesthesia depth identification unit 14. DETAILED DESCRIPTION

[0013] The present application provides a wearable anesthesia depth monitoring device and a monitoring method thereof, so as to solve the technical problems that the anesthesia depth monitoring devices in the prior art rely on a single signal, lack accuracy and real-time performance, have poor portability, and cannot adapt to the multi-scenario requirements of resource-constrained environments.

[0014] Embodiment 1, as Figure 1 As shown, the present application provides a wearable anesthesia depth monitoring device, the device includes a head-mounted module, a wristband module and an anesthesia depth monitoring system, the system includes:

[0015] The physiological signal monitoring unit 11 is used to monitor the EEG signals, blood oxygen saturation, integrated heart rate and skin conductance of the user wearing the device through the head-mounted module and the wrist-band module, and obtain the EEG signals, blood oxygen saturation, integrated heart rate and skin conductance, wherein the head-mounted module and the wrist-band module are respectively configured with an EEG sensor, a blood oxygen saturation sensor, an integrated heart rate sensor and a skin conductance sensor.

[0016] Furthermore, the physiological signal monitoring unit 11 is further configured to perform the following steps:

[0017] P11: Through the head-mounted module and wristband module, the user wearing the device is monitored for EEG signals, blood oxygen saturation, integrated heart rate and skin conductance to obtain original EEG signals, original blood oxygen saturation, original integrated heart rate and original skin conductance; P12: The original EEG signals, original blood oxygen saturation, original integrated heart rate and original skin conductance are pre-processed with noise filtering to obtain EEG sensors, blood oxygen saturation sensors, integrated heart rate sensors and skin conductance sensors.

[0018] It should be understood that the physiological signal monitoring unit 11 of the present application performs real-time monitoring of multimodal physiological signals of the user of the wearable device through a head-mounted module and a wrist-mounted module, including monitoring of electroencephalogram (EEG), blood oxygen saturation (SpO2), integrated heart rate (ECG) and skin conductance (EDA). Among them, the head-mounted module integrates an electroencephalogram sensor and a blood oxygen saturation sensor to collect the user's brain neural activity and the dynamic changes of oxygen content in the blood; the wrist-mounted module is equipped with an integrated heart rate sensor and a skin conductance sensor to reflect the user's circulatory system status and skin conductivity changes, which are closely related to the user's autonomic nervous system and emotional state.

[0019] Specifically, the original signals of the user are first collected through the sensors of the head-mounted module and the wrist-mounted module. The EEG sensor and blood oxygen saturation sensor integrated in the head-mounted module record the user's brain electrical activity and the oxygen saturation in the blood, respectively. The EEG signal (EEG) can directly reflect the state of brain nerve activity and is an important indicator for the assessment of anesthesia depth; the blood oxygen saturation (SpO2) is used to monitor the blood oxygen carrying capacity and reflect the patient's circulatory system condition. At the same time, the heart rate sensor and skin conductance sensor in the wrist-mounted module collect the user's heart rate and skin conductance (EDA) signals respectively. The former reflects the state of the circulatory system through the electrophysiological activity of the heart, and the latter reflects the response of the autonomic nervous system to external stimuli. Through these sensor arrays, the device can simultaneously collect the original data of EEG signals, blood oxygen saturation, integrated heart rate and skin conductance. However, these raw data may contain noise, such as muscle artifacts, motion interference or the influence of ambient light on the signal, and further processing is required to ensure the signal quality.

[0020] Next, the collected raw signal is pre-processed to filter out noise to obtain a clean physiological signal. Exemplarily, for electroencephalogram (EEG) signals, the device uses bandpass filtering technology to retain the frequency band of 0.5Hz to 45Hz, and combines the independent component analysis (ICA) algorithm to separate artifact signals such as eye movement, electromyography, and power frequency noise to ensure that the extracted signal can accurately reflect the brain's neural activity. For blood oxygen saturation (SpO2), photoplethysmography (PPG) technology is used to remove high-frequency noise through low-pass filtering, and the signal amplitude is normalized to eliminate the interference of ambient light changes and user actions on the data. In the processing of heart rate signals (ECG), the baseline drift is first removed by high-pass filtering, and then the R-wave detection algorithm is used to identify the characteristic peaks in the ECG signal, and the noise pseudo-peaks are eliminated to ensure the accuracy of the heart rate calculation. For skin conductance (EDA), low-frequency filtering is used to separate background conductance and instantaneous conductance changes, where background conductance reflects long-term physiological status and instantaneous conductance changes are closely related to the rapid response of the autonomic nervous system. Preprocessing can effectively improve signal quality, provide accurate input for the device's intelligent algorithm module, and ensure the reliability and accuracy of the device in multiple scenarios.

[0021] The characteristic information acquisition unit 12 is used to acquire the physiological characteristic information and surgical characteristic information of the user.

[0022] Furthermore, the feature information acquisition unit 12 is further configured to perform the following steps:

[0023] P21: Collecting the physiological characteristic information of the user according to multiple physiological characteristic categories; P22: Collecting the operation time length and the operation difficulty level as the operation characteristic information.

[0024] Optionally, the core function of the characteristic information acquisition unit 12 of the present application is to comprehensively collect the user's physiological characteristic information and characteristic information related to the surgery as an important input for subsequent anesthesia depth monitoring and analysis. The work of this unit is divided into the following two steps:

[0025] The first step is to collect the user's physiological characteristic information according to multiple physiological characteristic categories. Physiological characteristic information refers to basic parameters directly related to the user's individual status, including but not limited to age, gender, weight, height, and basal metabolic rate (BMR). This information provides the algorithm model with an individualized reference for the patient to ensure the personalization and accuracy of the anesthesia depth monitoring results. For example, age and weight affect the metabolic rate and distribution volume of anesthetic drugs, while gender differences may be related to the sensitivity of physiological responses. In addition, the unit will dynamically collect some physiological status indicators of the patient before surgery, such as heart rate variability (HRV) and blood pressure levels. These indicators reflect the state of the patient's autonomic nervous system and help assess their tolerance to anesthesia. By collecting physiological characteristic information in a classified manner, the comprehensiveness and applicability of the data can be ensured, providing accurate physiological basic data for the intelligent algorithm module.

[0026] The second step is to collect surgical feature information, including the length of the operation and the level of surgical difficulty. The length of the operation refers to the estimated or actual duration of the operation. This information can help predict the maintenance time and dosage adjustment strategy of anesthetic drugs. The difficulty level of the operation is graded according to the complexity of the operation, the degree of trauma, and the requirements for the depth of anesthesia (such as mild, moderate, and severe). This information directly determines the regulation target of the depth of anesthesia. For example, high-difficulty operations may require a deeper depth of anesthesia to ensure the patient's complete unconsciousness while reducing intraoperative stress reactions. The accurate collection of these surgical feature information can not only optimize the equipment's assessment of the patient's current state, but also form the overall input variables of the surgical scene in the intelligent algorithm, making the monitoring results more practical.

[0027] Through the above two steps, the characteristic information acquisition unit 12 integrates the physiological characteristic information and the surgical characteristic information into multi-dimensional input parameters, providing comprehensive support for the subsequent anesthesia depth recognition module of the device. This systematic collection method of characteristic information not only improves the flexibility and adaptability of the monitoring equipment, but also significantly improves the accuracy and clinical guidance value of anesthesia monitoring results through personalized and situational data support.

[0028] The anesthesia monitoring accuracy configuration unit 13 is used to send the EEG signal, blood oxygen saturation, integrated heart rate, skin conductance, physiological characteristic information and surgical characteristic information to the cloud server, and configure the anesthesia monitoring accuracy coefficient for monitoring the anesthesia depth of the user according to the physiological characteristic information and surgical characteristic information.

[0029] Furthermore, the anesthesia monitoring accuracy configuration unit 13 is further configured to perform the following steps:

[0030] P31: Construct an anesthesia monitoring accuracy configurator; P32: Input the physiological characteristic information and surgical characteristic information into the anesthesia monitoring accuracy configurator, and output the anesthesia monitoring accuracy coefficient.

[0031] Specifically, the core task of the anesthesia monitoring accuracy configuration unit 13 of the present application is to send the collected multimodal physiological signals, physiological characteristic information and surgical characteristic information to the cloud server, construct and calculate the accuracy coefficient of anesthesia monitoring, thereby ensuring the accuracy and personalization of anesthesia depth monitoring.

[0032] First, build an anesthesia monitoring accuracy configurator. The anesthesia monitoring accuracy configurator is a core tool based on cloud computing and algorithm models that can dynamically analyze the user's personalized parameters. Specifically, the configurator uses a preset machine learning algorithm or neural network model, combined with multi-dimensional input parameters (including physiological characteristic information and surgical characteristic information) to quantitatively model the accuracy requirements of anesthesia monitoring. For example, the configurator adjusts the real-time and sensitivity of anesthesia depth monitoring based on surgical characteristic information (such as the length of the operation and the level of difficulty), and optimizes the personalized parameter weights of the model based on the user's physiological characteristic information (such as age, weight, and basal metabolic rate). In this way, the configurator can generate exclusive anesthesia monitoring configuration plans for different users and surgical scenarios to ensure that the monitoring accuracy meets actual needs.

[0033] Next, the physiological characteristic information and surgical characteristic information are input into the anesthesia monitoring accuracy configurator to calculate and output the anesthesia monitoring accuracy coefficient. The accuracy coefficient is a dynamically adjusted parameter used to guide the calculation accuracy and algorithm weight distribution of the subsequent anesthesia depth recognition module. For example, for patients with relatively stable physiological states, the accuracy configurator may generate a lower accuracy coefficient, thereby reducing the computational burden of monitoring; while for scenarios with higher surgical difficulty and strict anesthesia requirements, the configurator will output a higher accuracy coefficient to increase the sensitivity and response speed of monitoring. The output of the accuracy configurator not only integrates individual physiological differences, but also fully considers the complexity of surgical scenarios, thereby making anesthesia depth monitoring more adaptable and reliable.

[0034] Through the above steps, the anesthesia monitoring accuracy configuration unit 13 can effectively integrate the individual characteristics and surgical requirements of the patient into the anesthesia depth monitoring system, and generate a personalized monitoring accuracy configuration plan. This design not only improves the application efficiency of the device in different scenarios, but also meets the clinical needs for precision anesthesia management to the greatest extent by dynamically adjusting the monitoring accuracy, and improves the reliability of the monitoring results and the clinical guidance value.

[0035] Furthermore, when constructing the anesthesia monitoring accuracy configurator, the anesthesia monitoring accuracy configuration unit 13 is further used to perform the following steps:

[0036] P31-1: Based on the user's surgical anesthesia history data, collect sample physiological characteristic information sets and sample surgical characteristic information sets; P31-2: According to the anesthetic dosage corresponding to each sample physiological characteristic information and sample surgical characteristic information, label and obtain the sample anesthesia monitoring accuracy set; P31-3: Use the sample physiological characteristic information set, sample surgical characteristic information set and sample anesthesia monitoring accuracy set as supervised training data, use machine learning, and build and train an anesthesia monitoring accuracy configurator.

[0037] In a possible embodiment of the present application, when constructing the anesthesia monitoring accuracy configurator, the anesthesia monitoring accuracy configuration unit 13 performs in-depth analysis and modeling of the user's surgical anesthesia history data to ensure that the configurator can accurately adapt to individual needs.

[0038] Specifically, first, based on the user's surgical anesthesia history data, a sample physiological characteristic information set and a sample surgical characteristic information set are collected. These sample data are derived from actual clinical cases, and contain the user's multidimensional physiological characteristic information (such as age, weight, gender, basal metabolic rate) and surgical characteristic information (such as operation time, operation complexity, intraoperative blood loss, etc.). The sample physiological characteristic information set is used to reflect the individual's physiological response differences to anesthetic drugs, while the sample surgical characteristic information set is directly related to the requirements for anesthesia depth. For example, complex operations often require a deeper degree of anesthesia. These data provide comprehensive input features for subsequent model training.

[0039] Furthermore, based on the physiological characteristic information and surgical characteristic information of each sample, the anesthetic dosage is marked and the sample anesthesia monitoring accuracy set is obtained. The anesthetic dosage is recorded according to the anesthesia plan given by the doctor in the historical data, which can directly reflect the user's sensitivity and tolerance to anesthesia under different conditions. Based on the relationship between the anesthetic dosage and the actual anesthesia depth monitoring results, a corresponding anesthesia monitoring accuracy value is marked for each sample. This accuracy value indicates the sensitivity and response accuracy that the monitoring system needs to achieve under the current characteristic conditions. For example, complex surgical samples with large fluctuations in anesthesia depth will be marked with higher accuracy requirements, while short surgeries or local anesthesia may correspond to lower accuracy requirements.

[0040] Next, the sample physiological characteristic information set, the sample surgical characteristic information set and the sample anesthesia monitoring accuracy set are used as supervised training data, and the machine learning method is used to build and train the anesthesia monitoring accuracy configurator. In this process, supervised learning algorithms (such as support vector machines, random forests or neural networks) are used to model the training data. The input of the model is the physiological characteristics and surgical characteristics of the sample, and the output is the corresponding anesthesia monitoring accuracy value. During the training process, the model parameters are optimized by minimizing the error function so that it can accurately predict the anesthesia monitoring accuracy requirements of new users under different physiological and surgical conditions. In addition, in order to improve the generalization ability of the model, cross-validation and data enhancement techniques are used to ensure that the configurator has good adaptability in different scenarios.

[0041] Through the above steps, the anesthesia monitoring accuracy configurator can dynamically calculate the anesthesia monitoring accuracy coefficient based on the user's individual characteristics and surgical requirements, providing accurate guidance for subsequent anesthesia depth identification. The construction of this configurator combines the technical advantages of user historical data and machine learning to ensure the reliability and intelligence level of the device in multiple scenarios, while greatly improving the accuracy and safety of anesthesia management.

[0042] The anesthesia depth identification unit 14 is used to identify the anesthesia depth according to the anesthesia monitoring accuracy coefficient, the EEG signal, the blood oxygen saturation, the integrated heart rate, and the skin conductance, obtain and receive the anesthesia depth monitoring result, and display the anesthesia depth monitoring result.

[0043] Furthermore, the anesthesia depth identification unit 14 is further configured to perform the following steps:

[0044] P41: Using integrated machine learning to construct an anesthesia depth identifier, wherein the anesthesia depth identifier includes multiple anesthesia depth identification paths; P42: Multiplying the anesthesia monitoring accuracy coefficient by the number of the multiple anesthesia depth identification paths and rounding the result to obtain the number of anesthesia monitoring paths, and randomly selecting at least one anesthesia depth identification path according to the number of anesthesia monitoring paths; P43: Inputting the EEG signal, blood oxygen saturation, integrated heart rate, and skin conductance into the at least one anesthesia depth identification path, identifying at least one anesthesia depth, and calculating the mean to obtain the anesthesia depth monitoring result; P44: Receive the anesthesia depth monitoring result transmitted by the cloud server and display it.

[0045] It should be understood that the anesthesia depth identification unit 14 of the present application is responsible for accurately identifying the user's anesthesia depth based on the collected multimodal physiological signals and the calculated anesthesia monitoring accuracy coefficient, and displaying the monitoring results in real time.

[0046] First, an anesthesia depth identifier is constructed using integrated machine learning technology. The anesthesia depth identifier is a multi-path recognition model that integrates multiple machine learning algorithms (such as support vector machines, random forests, deep neural networks, etc.) to enhance its adaptability to different signal patterns. Each path in the identifier corresponds to an algorithm model or a specific feature processing strategy. For example, the path based on EEG signals may focus on analyzing the frequency characteristics of brain waves, while the path based on blood oxygen saturation may focus on the dynamic changes in oxygenation levels. This integrated architecture not only improves the robustness of the model, but also effectively reduces the recognition error of a single model through multi-path fusion, ensuring the comprehensive accuracy of anesthesia depth assessment.

[0047] Next, according to the anesthesia monitoring accuracy coefficient, the appropriate number of identification paths is dynamically selected. Specifically, the anesthesia monitoring accuracy coefficient is multiplied by the total number of paths in the anesthesia depth identifier and rounded to the integer to obtain the number of anesthesia monitoring paths. Subsequently, the system randomly selects at least one path from multiple identification paths for identification according to this number. The core purpose of this process is to flexibly adjust the allocation of computing resources according to the complexity of monitoring requirements. For example, for high-precision requirements (such as complex surgical scenarios), more paths will be enabled to improve the reliability of identification; for low-precision requirements (such as simple surgery or short-time monitoring), the number of paths will be reduced to optimize the operating efficiency of the equipment.

[0048] Next, the collected EEG signals, blood oxygen saturation, integrated heart rate, and skin conductance data are input into the selected anesthesia depth identification path. Each path independently identifies an anesthesia depth value based on its algorithm characteristics. Subsequently, the identification results of all paths are averaged to calculate the final anesthesia depth monitoring result. This path fusion strategy effectively reduces the possible deviation of a single path by integrating the prediction results of multiple models, thereby improving the robustness and credibility of the monitoring results.

[0049] Finally, the anesthesia depth monitoring results transmitted by the cloud server are received in real time and visualized through the display module of the device. The display content includes the current anesthesia depth value, monitoring trend chart, and important warning information (such as too deep or too shallow anesthesia). The visual interface is intuitive and clear, which makes it easy for medical staff to quickly understand the patient's anesthesia status and make corresponding adjustments.

[0050] Through the above steps, the anesthesia depth recognition unit 14 combines multimodal signal input, integrated machine learning and dynamic path selection to ensure the accuracy and real-time monitoring of anesthesia depth. Its integrated architecture can not only flexibly respond to different surgical scenarios and individual differences of users, but also improve the operating efficiency and result reliability of the equipment through cloud data support and path optimization, providing strong technical support for clinical anesthesia management.

[0051] Furthermore, when the anesthesia depth identification unit 14 adopts integrated machine learning to construct an anesthesia depth identifier, it is also used to perform the following steps:

[0052] P41-1: Based on the user's anesthesia record data, collect a sample EEG signal set, a sample blood oxygen saturation set, a sample integrated heart rate set, a sample skin conductance set, and a sample anesthesia depth set, and combine them to obtain an anesthesia depth monitoring training sample set; P41-2: Divide the anesthesia depth monitoring training sample set to obtain multiple anesthesia depth monitoring training samples; P41-3: Use the multiple anesthesia depth monitoring training samples separately, based on integrated machine learning, to train multiple anesthesia depth recognition paths to obtain an anesthesia depth identifier.

[0053] Optionally, when constructing an anesthesia depth identifier, the anesthesia depth identification unit 14 integrates machine learning methods to perform deep modeling on multimodal signals and historical anesthesia depth records to ensure that the identifier can accurately predict the anesthesia depth.

[0054] Exemplarily, first, based on the user's anesthesia record data, a sample set required for training is collected, including a sample EEG signal set, a sample blood oxygen saturation set, a sample integrated heart rate set, a sample skin conductance set, and a sample anesthesia depth set, which are finally combined to generate an anesthesia depth monitoring training sample set.

[0055] Among them, the sample EEG signal set records the characteristics of EEG activity under different anesthesia depths, such as the increase in the proportion of low-frequency delta waves in deep anesthesia, and the change pattern of alpha waves as consciousness weakens. The sample blood oxygen saturation set captures the dynamic changes in blood oxygenation levels, especially the changing trends related to respiratory regulation during surgery. The sample integrated heart rate set contains dynamic fluctuations in heart rate and its variability (HRV), which reflect the response of the circulatory system to anesthesia. The sample skin conductance set is used to capture the activity characteristics of the user's autonomic nervous system, such as the baseline level of skin conductance and the amplitude of response to environmental stimuli. The sample anesthesia depth set is based on historical record annotations, including the actual anesthesia depth state at different time points as the target variable for training. By integrating the above feature sets, the generated multi-dimensional training samples provide a comprehensive and accurate data foundation for the machine learning model.

[0056] Furthermore, the anesthesia depth monitoring training sample set is divided to generate multiple independent training sample subsets to provide data support for the multi-path model of integrated machine learning. In the division process, a random segmentation method is used to ensure that each subset contains samples at different anesthesia depths to ensure the uniformity and balance of feature distribution. For example, when dividing the data, special attention will be paid to the uniform coverage of samples in deep anesthesia, light anesthesia, and awake states, so as to avoid the performance degradation of the model due to sample bias. In addition, this division strategy improves the generalization ability of the model and its adaptability to new data by providing independent training data for different model paths.

[0057] Next, multiple anesthesia depth monitoring training samples are used to train multiple anesthesia depth recognition paths based on the integrated machine learning method, and finally a complete anesthesia depth identifier is generated. Among them, each recognition path corresponds to an independent machine learning model. For example, the path based on the support vector machine (SVM) model focuses on EEG spectrum feature analysis, while the path based on the random forest (RF) model may be more suitable for processing nonlinear changes in heart rate and blood oxygen. During the training process, each path independently extracts features and optimizes parameters for its data subset, such as using cross-validation to optimize the hyperparameters of the model to ensure the robustness of the model under different data conditions. When integrating multiple paths, a weighted average or voting strategy is used to integrate the prediction results of each path to reduce the impact of a single path error on the final recognition result. Through this multi-path integration method, the identifier can achieve a comprehensive analysis of complex signal patterns and improve the accuracy and stability of anesthesia depth recognition.

[0058] Through the above steps, the anesthesia depth identifier takes advantage of integrated machine learning, combines multimodal physiological signals and rich historical data, and achieves highly accurate anesthesia depth identification capabilities, laying a solid foundation for the reliable application of the device in actual clinical practice, ensuring that the device can provide accurate monitoring results under different users and surgical scenarios.

[0059] In summary, the embodiments of the present application have at least the following technical effects:

[0060] This application collects the user's EEG signals, blood oxygen saturation, integrated heart rate and skin conductance signals through head-mounted modules and wrist-mounted modules, and sends the data to the cloud server in combination with physiological characteristic information and surgical characteristic information, and configures the anesthesia monitoring accuracy coefficient. Based on the accuracy coefficient, multimodal physiological signals are used to identify the depth of anesthesia, generate anesthesia depth monitoring results and display them in real time, providing an accurate and efficient anesthesia depth monitoring solution.

[0061] The technical effect of improving the accuracy, real-time and portability of anesthesia depth monitoring and meeting the application needs of multiple scenarios has been achieved through multi-modal physiological signal acquisition and personalized monitoring accuracy configuration.

[0062] Embodiment 2, based on the same inventive concept as the anesthesia depth monitoring system of the wearable anesthesia depth monitoring device in the aforementioned embodiment, Figure 2 As shown, the present application provides a wearable anesthesia depth monitoring method, and the method in the embodiment of the present application and the system embodiment are based on the same inventive concept. The method includes:

[0063] Through the head-mounted module and the wrist-band module, the EEG signal, blood oxygen saturation, integrated heart rate and skin conductance monitoring are performed on the user wearing the device to obtain the EEG signal, blood oxygen saturation, integrated heart rate and skin conductance, wherein the head-mounted module and the wrist-band module are respectively configured with an EEG sensor, a blood oxygen saturation sensor, an integrated heart rate sensor and a skin conductance sensor; the physiological characteristic information and surgical characteristic information of the user are obtained; the EEG signal, blood oxygen saturation, integrated heart rate, skin conductance, physiological characteristic information and surgical characteristic information are sent to the cloud server, and according to the physiological characteristic information and surgical characteristic information, an anesthesia monitoring accuracy coefficient for monitoring the anesthesia depth of the user is configured; according to the anesthesia monitoring accuracy coefficient, the anesthesia depth is identified according to the EEG signal, blood oxygen saturation, integrated heart rate and skin conductance, and the anesthesia depth monitoring result is obtained and received, and the anesthesia depth monitoring result is displayed.

[0064] Furthermore, the head-mounted module and the wrist-mounted module are used to monitor the EEG signal, blood oxygen saturation, integrated heart rate and skin conductance of the user wearing the device, and obtain the EEG signal, blood oxygen saturation, integrated heart rate and skin conductance, including:

[0065] Through the head-mounted module and the wristband module, the user wearing the device is monitored for EEG signals, blood oxygen saturation, integrated heart rate and skin conductance to obtain original EEG signals, original blood oxygen saturation, original integrated heart rate and original skin conductance; the original EEG signals, original blood oxygen saturation, original integrated heart rate and original skin conductance are pre-processed by noise filtering to obtain EEG sensors, blood oxygen saturation sensors, integrated heart rate sensors and skin conductance sensors.

[0066] Furthermore, obtaining the physiological characteristic information and surgical characteristic information of the user includes:

[0067] The physiological characteristic information of the user is collected according to a plurality of physiological characteristic categories; and the operation time length and the operation difficulty level are collected as the operation characteristic information.

[0068] Further, according to the physiological characteristic information and the surgical characteristic information, an anesthesia monitoring accuracy coefficient for monitoring the anesthesia depth of the user is configured, including:

[0069] Construct an anesthesia monitoring accuracy configurator; input the physiological characteristic information and the surgical characteristic information into the anesthesia monitoring accuracy configurator, and output the anesthesia monitoring accuracy coefficient.

[0070] Furthermore, an anesthesia monitoring accuracy configurator is constructed, including:

[0071] According to the user's surgical anesthesia history data, a sample physiological characteristic information set and a sample surgical characteristic information set are collected; according to the anesthetic dosage corresponding to each sample physiological characteristic information and sample surgical characteristic information, a sample anesthesia monitoring accuracy set is labeled; the sample physiological characteristic information set, the sample surgical characteristic information set and the sample anesthesia monitoring accuracy set are used as supervised training data, and machine learning is used to build and train an anesthesia monitoring accuracy configurator.

[0072] Further, according to the anesthesia monitoring accuracy coefficient, anesthesia depth identification is performed according to the EEG signal, blood oxygen saturation, integrated heart rate, and skin conductance, anesthesia depth monitoring results are obtained and received, and the anesthesia depth monitoring results are displayed, including:

[0073] An anesthesia depth identifier is constructed by using integrated machine learning, wherein the anesthesia depth identifier includes multiple anesthesia depth identification paths; the anesthesia monitoring accuracy coefficient is multiplied by the number of the multiple anesthesia depth identification paths and the result is rounded to obtain the number of anesthesia monitoring paths, and at least one anesthesia depth identification path is randomly selected according to the number of anesthesia monitoring paths; the EEG signal, blood oxygen saturation, integrated heart rate, and skin conductance are input into the at least one anesthesia depth identification path to identify and obtain at least one anesthesia depth, and the mean is calculated to obtain the anesthesia depth monitoring result; the anesthesia depth monitoring result transmitted by the cloud server is received and displayed.

[0074] Furthermore, integrated machine learning is used to construct an anesthesia depth identifier, including: collecting a sample EEG signal set, a sample blood oxygen saturation set, a sample integrated heart rate set, a sample skin conductance set, and a sample anesthesia depth set based on the user's anesthesia record data, and combining them to obtain an anesthesia depth monitoring training sample set; dividing the anesthesia depth monitoring training sample set to obtain multiple anesthesia depth monitoring training samples; and using the multiple anesthesia depth monitoring training samples respectively, based on integrated machine learning, training multiple anesthesia depth identification paths to obtain an anesthesia depth identifier.

[0075] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0076] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0077] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. Wearable anesthesia depth monitoring device, characterized in that: The device comprises a head-mounted module, a wrist-mounted module and an anesthesia depth monitoring system, and the system comprises: A physiological signal monitoring unit, used to monitor EEG signals, blood oxygen saturation, integrated heart rate and skin conductance of a user wearing the device through the head-mounted module and the wrist-band module, and obtain EEG signals, blood oxygen saturation, integrated heart rate and skin conductance, wherein the head-mounted module and the wrist-band module are respectively equipped with an EEG sensor, a blood oxygen saturation sensor, an integrated heart rate sensor and a skin conductance sensor; A characteristic information acquisition unit, used to acquire the physiological characteristic information and surgical characteristic information of the user; an anesthesia monitoring accuracy configuration unit, used to send the EEG signal, blood oxygen saturation, integrated heart rate, skin conductance, physiological characteristic information and surgical characteristic information to a cloud server, and configure an anesthesia monitoring accuracy coefficient for monitoring the anesthesia depth of the user according to the physiological characteristic information and surgical characteristic information; The anesthesia depth identification unit is used to identify the anesthesia depth according to the anesthesia monitoring accuracy coefficient, the electroencephalogram signal, the blood oxygen saturation, the integrated heart rate, and the skin conductance, obtain and receive the anesthesia depth monitoring result, and display the anesthesia depth monitoring result.

2. The wearable anesthesia depth monitoring device according to claim 1, characterized in that: The physiological signal monitoring unit is also used for: Through the head-mounted module and the wristband module, the user wearing the device is monitored for EEG signals, blood oxygen saturation, integrated heart rate and skin conductance, and the original EEG signals, original blood oxygen saturation, original integrated heart rate and original skin conductance are obtained; The original EEG signal, original blood oxygen saturation, original integrated heart rate and original skin conductance are subjected to noise filtering preprocessing to obtain an EEG sensor, a blood oxygen saturation sensor, an integrated heart rate sensor and a skin conductance sensor.

3. The wearable anesthesia depth monitoring device according to claim 1, characterized in that: The feature information acquisition unit is also used for: Collecting physiological characteristic information of the user according to multiple physiological characteristic categories; The length of operation time and the level of difficulty of the operation were collected as surgical characteristic information.

4. The wearable anesthesia depth monitoring device according to claim 1, characterized in that: The anesthesia monitoring accuracy configuration unit is also used for: Build an anesthesia monitoring accuracy configurator; The physiological characteristic information and the surgical characteristic information are input into the anesthesia monitoring accuracy configurator, and the anesthesia monitoring accuracy coefficient is obtained by output.

5. The wearable anesthesia depth monitoring device according to claim 4, characterized in that: When constructing the anesthesia monitoring accuracy configurator, the anesthesia monitoring accuracy configuration unit further includes: Collecting a sample physiological characteristic information set and a sample surgical characteristic information set based on the user's surgical anesthesia history data; According to the anesthetic dosage corresponding to each sample's physiological characteristic information and sample's surgical characteristic information, the sample anesthesia monitoring accuracy set is obtained by annotation; The sample physiological feature information set, the sample surgical feature information set and the sample anesthesia monitoring accuracy set are used as supervised training data, and machine learning is used to construct and train an anesthesia monitoring accuracy configurator.

6. The wearable anesthesia depth monitoring device according to claim 1, characterized in that: The anesthesia depth identification unit is also used for: An anesthesia depth identifier is constructed by using integrated machine learning, wherein the anesthesia depth identifier includes a plurality of anesthesia depth identification paths; The anesthesia monitoring accuracy coefficient is multiplied by the number of the multiple anesthesia depth identification paths and the result is rounded to obtain the number of anesthesia monitoring paths, and at least one anesthesia depth identification path is randomly selected according to the number of anesthesia monitoring paths; Inputting the EEG signal, blood oxygen saturation, integrated heart rate, and skin conductance into at least one anesthesia depth identification path, identifying and obtaining at least one anesthesia depth, and calculating the mean to obtain an anesthesia depth monitoring result; Receive the anesthesia depth monitoring result transmitted by the cloud server and display it.

7. The wearable anesthesia depth monitoring device according to claim 6, characterized in that: When the anesthesia depth identification unit adopts integrated machine learning to construct an anesthesia depth identifier, it also includes: According to the user's anesthesia record data, a sample EEG signal set, a sample blood oxygen saturation set, a sample integrated heart rate set, a sample skin conductance set, and a sample anesthesia depth set are collected, and the anesthesia depth monitoring training sample set is obtained by combining them; Dividing the anesthesia depth monitoring training sample set to obtain a plurality of anesthesia depth monitoring training samples; The plurality of anesthesia depth monitoring training samples are respectively used to train a plurality of anesthesia depth identification paths based on integrated machine learning to obtain an anesthesia depth identifier.

8. A wearable anesthesia depth monitoring method, characterized in that: The method comprises: Through the head-mounted module and the wrist-mounted module, the user of the wearable device is monitored for EEG signals, blood oxygen saturation, integrated heart rate and skin conductance, and the EEG signals, blood oxygen saturation, integrated heart rate and skin conductance are obtained, wherein the head-mounted module and the wrist-mounted module are respectively equipped with an EEG sensor, a blood oxygen saturation sensor, an integrated heart rate sensor and a skin conductance sensor; Acquiring physiological characteristic information and surgical characteristic information of the user; The EEG signal, blood oxygen saturation, integrated heart rate, skin conductance, physiological characteristic information and surgical characteristic information are sent to a cloud server, and an anesthesia monitoring accuracy coefficient for monitoring the anesthesia depth of the user is configured according to the physiological characteristic information and the surgical characteristic information; According to the anesthesia monitoring accuracy coefficient, anesthesia depth identification is performed based on the EEG signal, blood oxygen saturation, integrated heart rate, and skin conductance, and anesthesia depth monitoring results are obtained and received, and the anesthesia depth monitoring results are displayed.

9. The wearable anesthesia depth monitoring method according to claim 8, characterized in that: Through the head-mounted module and the wristband module, the user wearing the device is monitored for EEG signals, blood oxygen saturation, integrated heart rate and skin conductance, and EEG signals, blood oxygen saturation, integrated heart rate and skin conductance are obtained, including: Through the head-mounted module and the wristband module, the user wearing the device is monitored for EEG signals, blood oxygen saturation, integrated heart rate and skin conductance, and the original EEG signals, original blood oxygen saturation, original integrated heart rate and original skin conductance are obtained; The original EEG signal, original blood oxygen saturation, original integrated heart rate and original skin conductance are subjected to noise filtering preprocessing to obtain an EEG sensor, a blood oxygen saturation sensor, an integrated heart rate sensor and a skin conductance sensor.

10. The wearable anesthesia depth monitoring method according to claim 8, characterized in that: Acquiring the user's physiological characteristic information and surgical characteristic information, including: Collecting physiological characteristic information of the user according to multiple physiological characteristic categories; The length of operation time and the level of difficulty of the operation were collected as surgical characteristic information.

Images