Inertial measurement-based method for monitoring finger activity of anesthetized patient and transmitting signal to central monitoring system
By combining inertial measurement units and signal processing algorithms with Bluetooth Low Energy transmission, the accuracy problem of anesthesia depth monitoring was solved, achieving more precise anesthesia management and improved safety.
Patent Information
- Application Number
- CN202510916647.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-03
- Publication Date
- 2025-10-28
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing anesthesia depth monitoring methods such as BIS monitoring are susceptible to electromagnetic interference in the operating room, cannot accurately assess the neuromuscular function status, and are unable to meet the anesthesia management needs of complex surgeries.
The system uses an inertial measurement unit to collect finger movement data, combines Kalman filtering and support vector machine algorithms for signal processing, and transmits the data to a central monitoring system via Bluetooth Low Energy protocol to achieve real-time monitoring and evaluation of finger activities.
It enables precise management of anesthesia depth, improves surgical safety, reduces the dosage of anesthetic drugs and the incidence of complications, and optimizes the anesthesia management process.
Smart Images
Figure CN120837057A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of patient anesthesia monitoring technology, specifically a method for monitoring finger movements of anesthetized patients based on inertial measurement and transmitting signals to a central monitoring system. Background Technology
[0002] During anesthesia, real-time and accurate monitoring of the patient's physiological state is a core element in ensuring surgical safety and optimizing anesthesia management. During surgery, the patient's physiological functions are significantly altered by the intervention of anesthetic drugs. Excessive anesthesia can lead to serious complications such as respiratory depression and circulatory failure, while insufficient anesthesia can cause intraoperative awareness and motor responses, increasing surgical risks and potentially causing psychological trauma. Therefore, accurate monitoring of the anesthetic state is crucial for maintaining stable vital signs and reducing surgical risks.
[0003] Finger movement, as a key physiological indicator reflecting the depth of anesthesia and neuromuscular function, is closely related to the mechanism of action of anesthetic drugs. Anesthetic drugs achieve their anesthetic effect by inhibiting the central nervous system, and changes in finger movement directly reflect the degree of neuromuscular excitability. When the depth of anesthesia is insufficient, the patient's neuromuscular excitability increases, which may result in involuntary micro-movements of the fingers; as anesthesia deepens, finger movement gradually weakens and eventually disappears. This dynamic change provides anesthesiologists with a direct and reliable basis for real-time adjustment of anesthetic drug dosage.
[0004] Traditional methods for monitoring the depth of anesthesia, such as bispectral index (BIS) monitoring, while widely used in clinical practice, have significant limitations. BIS monitoring relies on the analysis of electroencephalogram (EEG) signals, making it susceptible to strong electromagnetic interference from operating room equipment such as high-frequency electrosurgical units and MRI scanners, leading to signal distortion and affecting monitoring accuracy. Furthermore, BIS only reflects the electrical activity of the cerebral cortex and cannot comprehensively capture subcortical EEG changes, creating blind spots in assessing the effects of anesthetic drugs on deep brain structures. More importantly, these methods cannot directly assess the patient's neuromuscular functional status, failing to meet the demands of precise anesthesia management in complex surgeries. Summary of the Invention
[0005] The purpose of this invention is to provide a method for monitoring finger movements of anesthetized patients and transmitting signals to a central monitoring system based on inertial measurement, so as to solve the problems mentioned in the background art.
[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for monitoring finger movement of anesthetized patients and transmitting signals to a central monitoring system based on inertial measurement, which is based on a monitoring system including an inertial measurement unit, a signal processing module, a wireless transmission module, and a central monitoring system;
[0007] The method includes the following steps:
[0008] Step 1: Use an inertial measurement unit to collect three-dimensional acceleration and angular velocity motion data of the anesthetized patient's fingers;
[0009] Step 2: Perform Kalman filtering and min-max normalization preprocessing on the acquired raw data. The Kalman filtering algorithm is used to denoise the raw data. Kalman filtering can optimally estimate noisy measurement data based on the system's state and observation equations, effectively removing high-frequency noise and baseline drift. In this system, accelerometer and gyroscope measurement data are used as observations. By establishing appropriate state and observation equations, the system state is updated in real time to obtain accurate filtered data. The filtered data is then normalized to eliminate dimensional differences between different sensors, facilitating subsequent feature extraction and analysis.
[0010] Step 3: Extract time-domain, frequency-domain, and time-frequency-domain feature parameters. The time-domain features include root mean square, peak value, mean, and standard deviation. The frequency-domain features are obtained through fast Fourier transform and power spectral density analysis. The time-frequency-domain features are extracted through wavelet transform.
[0011] Step 4: Train the extracted features using the Support Vector Machine (SVM) algorithm to establish a finger movement pattern recognition model. SVM is chosen as the classifier due to its good performance in small-sample, non-linear classification problems. First, collect a large amount of sample data on patients' finger movements under different depths of anesthesia and extract features from them. Then, divide these sample data into training and testing sets. Use the training set to train the SVM model, adjusting the model parameters to achieve optimal performance. Finally, use the testing set to validate the trained model and evaluate its accuracy, recall, and other performance metrics. In practical applications, after extracting features from real-time collected finger movement data, inputting it into the trained SVM model allows for the identification of the patient's finger movement patterns, thereby inferring the patient's depth of anesthesia and neuromuscular function.
[0012] Step 5: Transmit the processed feature data to the central monitoring system via Bluetooth Low Energy (BLE). BLE offers advantages such as low power consumption, low cost, and stable short-range communication, making it suitable for use in medical devices. Its operating frequency band is 2.4GHz, which helps avoid interference with other medical devices to some extent. In this system, the BLE module is responsible for transmitting the finger movement feature data processed by the signal processing module to the central monitoring system.
[0013] Step Six: The central monitoring system stores and graphically displays the received data, and assesses the depth of anesthesia in conjunction with the patient's physiological parameters, triggering an alarm when abnormalities occur.
[0014] Preferably, in step one, the inertial measurement unit is worn as follows: a medical-grade flexible silicone ring is used as a carrier, and a multi-axis inertial measurement unit integrating a three-axis accelerometer and a three-axis gyroscope is embedded inside the ring, in close contact with the finger. A high-sensitivity module integrating a three-axis accelerometer and a three-axis gyroscope is selected, which can capture the weak motion signals of the anesthetized patient's finger in real time, meeting the monitoring needs of low-amplitude movements during surgery. The use of a medical-grade flexible silicone ring ensures good biocompatibility and fits the finger well. The sensor embedded inside the ring is in close contact with the skin, avoiding measurement deviations caused by patient movement during surgery. The calibration process uses a multi-point calibration method, collecting more than 5 sets of data from different postures and combining them with least squares fitting to eliminate sensor bias and scaling factor errors, ensuring the accuracy of the raw data and laying the foundation for subsequent signal processing.
[0015] Preferably, step one also includes a calibration method for the inertial measurement unit, which involves acquiring at least five sets of sensor data at different attitudes while the unit is stationary, and eliminating zero bias and scaling factor errors through least squares fitting. The specific steps are as follows:
[0016] 1. Have the patient keep the finger wearing the inertial measurement unit 1 still and collect at least 5 sets of accelerometer and gyroscope data in different postures.
[0017] 2. Preprocess the collected data to remove outliers and noise.
[0018] 3. Based on the measurement principles of accelerometers and gyroscopes, establish a mathematical model, substitute the collected data into the model, and solve for the calibration parameters, including zero bias and scaling factor, using the least squares method.
[0019] The obtained calibration parameters are stored in the memory of the inertial measurement unit 1. During subsequent data acquisition, these calibration parameters are used to calibrate the measurement data in real time.
[0020] Preferably, in step five, the wireless transmission module uses the Bluetooth Low Energy protocol for data transmission. The wireless transmission module dynamically adjusts its transmission power through signal strength monitoring. The BLE module integrates a signal strength monitoring function to monitor the Received Signal Strength Indicator (RSSI) in real time. When the RSSI value is lower than a set threshold, it indicates a weak signal, which may affect the stability of data transmission. In this case, the BLE module automatically adjusts its transmission power to increase the signal strength and ensure stable data transmission.
[0021] The wireless transmission module also employs frequency hopping spread spectrum (FHSS) technology and an automatic repeat request (ARQ) mechanism for data transmission. Since various electronic devices exist in the operating room environment, they may interfere with the BLE signal. To avoid interference, FHSS technology is used. The BLE module continuously switches channels within the 2.4 GHz band according to a specific frequency hopping sequence for data transmission. This effectively avoids interference signals generated by other devices, improving the stability of data transmission. An ARQ mechanism ensures the reliability of data transmission. When the receiving end detects a data packet checksum error or fails to receive a data packet, it sends a retransmission request to the sending end. Upon receiving the retransmission request, the sending end retransmits the corresponding data packet until the receiving end receives it correctly.
[0022] Preferably, the data transmission format of the wireless transmission module includes a header consisting of a data packet identifier, length, and checksum; a data area consisting of time-domain / frequency-domain / time-frequency-domain features; and a packet trailer. During data transmission, the sending end packages and sends data according to the designed data transmission format, and the receiving end parses the data packet based on the header information to extract the finger movement feature data. This method effectively improves the reliability of data transmission and reduces the occurrence of data transmission errors.
[0023] Preferably, the central monitoring system is integrated with the hospital's electronic medical record system and hospital information system through a healthcare application adapter to perform associated storage and retrieval of monitoring data and medical record information. Integration with the electronic medical record and hospital information systems via the HL7 interface links monitoring data with patient medical records, supports historical data retrieval and anesthesia protocol effectiveness analysis, provides comprehensive data support for clinical decision-making, and optimizes the treatment process.
[0024] Preferably, the central monitoring system is used to receive, store, display data and assess anesthesia status, and includes a data management unit, a graphics display unit, an anesthesia analysis unit and a system integration interface.
[0025] Preferably, the anesthesia analysis unit of the central monitoring system can assess the depth of anesthesia by combining physiological parameters such as heart rate and blood pressure, and trigger audible and pop-up alarms when abnormalities occur. The system receives finger movement data in real time via the BLE protocol, stores it in a relational database, and displays waveforms and characteristic parameters in a graphical interface, allowing anesthesiologists to intuitively understand the patient's condition. The analysis module can comprehensively assess the depth of anesthesia by combining physiological parameters such as heart rate and blood pressure, and trigger audible and pop-up alarms when data is abnormal, improving the timeliness of anesthesia management.
[0026] Preferably, the signal processing module is used to perform noise reduction, normalization, feature extraction, and activity pattern recognition on the acquired data, and includes a Kalman filter unit, a normalization processing unit, a time-frequency domain feature extraction unit, and a support vector machine classifier.
[0027] Compared with the prior art, the present invention has the following beneficial effects:
[0028] 1. In this invention, the inertial measurement-based finger movement monitoring system for anesthesia patients achieves precise anesthesia management through the integration of multiple technologies. The system integrates a high-sensitivity inertial measurement unit, multi-dimensional signal processing algorithms, low-power wireless transmission protocols, and an intelligent central monitoring system, forming a closed-loop process from data acquisition to anesthesia protocol adjustment. Sensors can capture subtle finger movements, and Kalman filtering and machine learning algorithms improve data reliability; Bluetooth Low Energy transmission combined with frequency hopping spread spectrum technology ensures stable real-time data transmission; the central monitoring system is integrated with the hospital information system to achieve dynamic assessment of anesthesia depth and early warning of complications, thereby improving surgical safety.
[0029] 2. In this invention, the inertial measurement unit is designed to balance accuracy and patient comfort. A high-sensitivity module integrating a triaxial accelerometer and a triaxial gyroscope is selected to capture weak motion signals of the anesthetized patient's fingers in real time, meeting the monitoring needs of low-amplitude movements during surgery. The wearing method uses a medical-grade flexible silicone ring, which has good biocompatibility and fits the finger well. The sensor embedded inside the ring is in close contact with the skin, avoiding measurement deviations caused by patient movement during surgery. The calibration process employs a multi-point calibration method, collecting more than five sets of data from different postures and combining them with least squares fitting to eliminate sensor bias and scaling factor errors, ensuring the accuracy of the raw data and laying the foundation for subsequent signal processing.
[0030] 3. In this invention, the central monitoring system realizes intelligent management of anesthesia data and sharing of medical information. The system receives finger movement data in real time via the BLE protocol, stores it in a relational database, and displays waveforms and characteristic parameters in a graphical interface, allowing anesthesiologists to intuitively understand the patient's condition. The analysis module can comprehensively assess the depth of anesthesia by combining physiological parameters such as heart rate and blood pressure. When data is abnormal, it triggers audible and pop-up alarms, improving the timeliness of anesthesia management. In addition, the system integrates with electronic medical records and hospital information systems through the HL7 interface, linking monitoring data with patient medical records, supporting historical data queries and anesthesia protocol effect analysis, providing comprehensive data support for clinical decision-making, and optimizing the diagnosis and treatment process. Attached Figure Description
[0031] Figure 1 This is a block diagram of the monitoring system in the method for monitoring finger movements of anesthetized patients and transmitting signals to a central monitoring system based on inertial measurement according to the present invention.
[0032] Figure 2 This is a flowchart of a method for monitoring finger movements of anesthetized patients and transmitting signals to a central monitoring system based on inertial measurement, according to the present invention.
[0033] In the diagram: 1. Inertial Measurement Unit; 2. Signal Processing Module; 3. Wireless Transmission Module; 4. Central Monitoring System. Detailed Implementation
[0034] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0035] Example: Refer to Figure 1-Figure 2 The diagram illustrates a method for monitoring finger movements of anesthetized patients and transmitting signals to a central monitoring system based on inertial measurement. This method is implemented using a monitoring system comprising an inertial measurement unit 1, a signal processing module 2, a wireless transmission module 3, and a central monitoring system 4. These components work collaboratively to achieve real-time, accurate monitoring and management of the finger movements of anesthetized patients. The specific details of each component are as follows:
[0036] 1. Inertial Measurement Unit 1, which is responsible for collecting motion data of the fingers of anesthetized patients.
[0037] (I) Sensor Selection: A multi-axis inertial measurement unit 1 with high sensitivity and low noise characteristics was selected, integrating a three-axis accelerometer and a three-axis gyroscope. The accelerometer can accurately measure the acceleration changes of the finger in all directions, with a measurement range of ±16g and a resolution of up to 0.0001g; the gyroscope is used to measure the rotational angular velocity of the finger, with a measurement range of ±2000 dps and a resolution of 0.0625 dps. These parameters can meet the needs of accurate monitoring of the subtle movements of the fingers of anesthetized patients.
[0038] (II) Wearing Method: To ensure that the inertial measurement unit 1 can stably and accurately collect finger motion data, a customized medical-grade flexible finger ring is used as the wearing carrier. The finger ring is made of biocompatible silicone material, which fits the finger well and will not irritate the patient's skin. The inertial measurement unit 1 is firmly embedded in the inside of the finger ring, allowing it to make close contact with the finger, thereby obtaining accurate motion signals. The design of the finger ring fully considers patient comfort and data acquisition stability, ensuring that even if the patient's finger moves slightly during the operation, it will not affect the relative position of the sensor and the finger, ensuring the continuity and accuracy of data acquisition.
[0039] (III) Calibration Method: Before using Inertial Measurement Unit 1, it needs to be calibrated to eliminate sensor bias and scaling factor errors. A multi-point calibration method is used, where sensor data is collected at multiple different attitudes while the unit is stationary, and calibration parameters are obtained through least-squares fitting. The specific steps are as follows:
[0040] 1. Have the patient keep the finger wearing the inertial measurement unit 1 still and collect at least 5 sets of accelerometer and gyroscope data in different postures.
[0041] 2. Preprocess the collected data to remove outliers and noise.
[0042] 3. Based on the measurement principles of accelerometers and gyroscopes, establish a mathematical model, substitute the collected data into the model, and solve for the calibration parameters, including zero bias and scaling factor, using the least squares method.
[0043] The obtained calibration parameters are stored in the memory of the inertial measurement unit 1. During subsequent data acquisition, these calibration parameters are used to calibrate the measurement data in real time.
[0044] 2. Signal processing module 2, which performs noise reduction, feature extraction and other processing on the acquired data.
[0045] (a) Data preprocessing.
[0046] 1. Noise Reduction Filtering: The Kalman filter algorithm is used to reduce noise in the original data. The Kalman filter can optimally estimate noisy measurement data based on the system's state and observation equations, effectively removing high-frequency noise and baseline drift. In this system, accelerometer and gyroscope measurement data are used as observations. By establishing appropriate state and observation equations, the system state is updated in real time, thus obtaining accurate filtered data.
[0047] 2. Data Normalization: The filtered data is normalized to map it to the [0,1] interval, eliminating dimensional differences between different sensors and facilitating subsequent feature extraction and analysis. The min-max normalization method is used, and the calculation formula is as follows:
[0048]
[0049] Where x is the original data, x min and x max These are the minimum and maximum values of the data set, x and x', respectively. norm This is the normalized data.
[0050] (II) Feature extraction algorithm.
[0051] 1. Time-domain feature extraction: Calculate the root mean square (RMS) of acceleration and angular velocity. The calculation formula is as follows:
[0052]
[0053] Where N is the number of data points, x i Let be the value of the i-th data point. RMS can reflect the energy level of the signal. In finger activity monitoring, different finger movements usually generate acceleration and angular velocity signals with different RMS values.
[0054] In addition, time-domain features such as peak value, mean, and standard deviation of the signal are extracted. The peak value reflects the maximum amplitude of finger movement, the mean reflects the average level of the signal, and the standard deviation reflects the degree of signal fluctuation. These time-domain features can describe the state of finger movement from different perspectives.
[0055] 2. Frequency Domain Feature Extraction: The time-domain signal is converted into a frequency-domain signal using Fast Fourier Transform (FFT) to analyze its frequency components. The power spectral density (PSD) is calculated, reflecting the energy distribution of the signal at different frequencies. In finger movements, different motion patterns often have specific frequency characteristics. By analyzing the PSD, these characteristic frequencies can be identified, thereby determining the type of finger movement.
[0056] 3. Time-Frequency Domain Feature Extraction: Wavelet transform is used for time-frequency analysis of the signal. Wavelet transform can perform localized analysis of the signal simultaneously in both time and frequency dimensions, making it suitable for processing non-stationary signals, such as signals generated by finger movements. The time-frequency plot of the signal is obtained through wavelet transform, from which time-frequency domain features are extracted, such as the energy distribution of wavelet coefficients and wavelet entropy. These features can more comprehensively reflect the dynamic changes in finger movements.
[0057] (III) Activity Pattern Recognition. A finger activity pattern recognition model was established by training the extracted features using machine learning algorithms. Support Vector Machine (SVM) was chosen as the classifier, as it exhibits good performance in small-sample, non-linear classification problems. First, a large amount of sample data on patients' finger activities under different depths of anesthesia was collected, and features were extracted from these samples. Then, these sample data were divided into training and test sets. The SVM model was trained using the training set, and the model parameters were adjusted to achieve optimal performance. Finally, the trained model was validated using the test set, and its accuracy, recall, and other performance metrics were evaluated. In practical applications, after extracting features from real-time collected finger activity data, the data is input into the trained SVM model to identify the patient's finger activity patterns, thereby inferring the patient's depth of anesthesia and neuromuscular function.
[0058] 3. Wireless transmission module 3, which transmits the processed data to the central monitoring system 4.
[0059] (I) Wireless Communication Protocol Selection: Bluetooth Low Energy (BLE) protocol is used for data transmission. BLE protocol offers advantages such as low power consumption, low cost, and stable short-range communication, making it suitable for applications in medical devices. Its operating frequency band is 2.4GHz, which helps avoid interference with other medical devices to some extent. In this system, the BLE module is responsible for transmitting the finger movement feature data processed by the signal processing module 2 to the central monitoring system 4. The BLE module supports a data transmission rate of up to 1Mbps, sufficient to meet the real-time transmission requirements of finger movement data. Furthermore, the BLE protocol features automatic connection and reconnection functions; when signal transmission is interrupted, it can automatically attempt to reconnect, ensuring continuous data transmission.
[0060] (II) Data Transmission Format: To ensure the accuracy and integrity of data during transmission, a specific data transmission format is designed. Each data packet is divided into three parts: a header, a data area, and a trailer. The header contains information such as the data packet identifier, data length, and checksum, used to identify the type of data packet and ensure the correctness of data transmission. The data area stores processed finger movement feature data, including time-domain features, frequency-domain features, and time-frequency-domain features. The trailer marks the end of the data packet. During data transmission, the sending end packages and sends the data according to the designed data transmission format, and the receiving end parses the data packet based on the header information to extract the finger movement feature data. This method effectively improves the reliability of data transmission and reduces the occurrence of data transmission errors.
[0061] (III) Guarantee of transmission stability.
[0062] 1. Signal Strength Monitoring: The BLE module integrates signal strength monitoring functionality, which monitors the Received Signal Strength Indicator (RSSI) in real time. When the RSSI value falls below a set threshold, it indicates a weak signal, which may affect the stability of data transmission. In this case, the BLE module automatically adjusts its transmit power to increase the signal strength and ensure stable data transmission.
[0063] 2. Data Retransmission Mechanism: An Automatic Repeat Request (ARQ) mechanism is employed to ensure the reliability of data transmission. When the receiving end detects a data packet checksum error or fails to receive a data packet, it sends a retransmission request to the sending end. Upon receiving the retransmission request, the sending end retransmits the corresponding data packet until the receiving end receives it correctly. This data retransmission mechanism effectively reduces the probability of data loss and errors, ensuring data integrity.
[0064] 3. Interference Avoidance: The presence of various electronic devices in the operating room environment may interfere with the BLE signal. To avoid interference, Frequency Hopping Spread Spectrum (FHSS) technology is employed. The BLE module continuously switches channels within the 2.4GHz band according to a specific frequency hopping sequence for data transmission. This effectively avoids interference signals generated by other devices, improving data transmission stability. Simultaneously, the monitoring equipment is strategically positioned, keeping it as far away as possible from potentially interfering devices such as high-frequency electrosurgical units and MRI machines.
[0065] IV. Central monitoring system 4, which receives, stores, displays, and analyzes data.
[0066] (I) System Functions.
[0067] 1. Data Reception and Storage: The central monitoring system 4 receives finger movement data from the wireless transmission module 3 in real time via a BLE receiver and stores the data in a database. The database uses a relational database, such as MySQL, which can efficiently store and manage large amounts of monitoring data. Data is categorized and stored according to fields such as patient ID and time for easy subsequent data retrieval and analysis.
[0068] 2. Data Display: The received finger movement data is displayed intuitively on the monitoring interface. The interface uses a graphical design and can draw waveforms of signals such as acceleration and angular velocity in real time, while also displaying extracted feature parameter values and identified finger movement patterns. Anesthesiologists can clearly understand the patient's finger movement status through the monitoring interface and promptly detect abnormalities.
[0069] 3. Data Analysis and Alarms: The system performs in-depth analysis of finger movement data stored in the database, combining this data with other physiological parameters such as heart rate, blood pressure, and blood oxygen saturation to comprehensively assess the patient's depth of anesthesia and neuromuscular function. When monitored data exceeds the preset normal range, the system automatically issues an alarm signal, reminding the anesthesiologist to adjust the anesthesia plan promptly. Alarm methods include audible alarms and pop-up alerts, ensuring that anesthesiologists can receive alarm information in a timely manner.
[0070] 4. Historical Data Query and Review: The Central Monitoring System 4 supports the query and review of historical monitoring data. Anesthesiologists can query changes in the patient's finger movement data during surgery based on criteria such as patient ID and operation time, analyze the effectiveness of the anesthesia plan, and provide a reference for subsequent anesthesia management.
[0071] (II) Integration with Existing Healthcare Systems: To achieve the sharing and integration of medical information, the central monitoring system can be integrated with existing hospital information systems, such as Electronic Medical Record (EMR) systems and Hospital Information Systems (HIS). Through standard data interfaces, such as the Healthcare Application Adapter (HL7 interface), finger movement monitoring data can be correlated with other patient medical records, facilitating a comprehensive understanding of the patient's condition by healthcare professionals. During surgery, anesthesiologists can directly view the patient's finger movement monitoring results in the EMR system and simultaneously update information such as anesthesia plan adjustments to the EMR system, providing comprehensive and accurate information support for the patient's diagnosis and treatment.
[0072] In summary, the workflow of this method is as follows:
[0073] 1. Data Acquisition: The inertial measurement unit 1 is tightly worn on the patient's finger to collect motion data such as acceleration and angular velocity of the finger in three-dimensional space in real time.
[0074] 2. Signal preprocessing: Signal processing module 2 performs preprocessing operations such as denoising and filtering on the acquired raw data to improve data quality and reduce the impact of noise interference on subsequent analysis.
[0075] 3. Feature extraction: Extract feature parameters that can effectively reflect the finger activity state from the preprocessed data, such as the peak value and mean value of acceleration, and the rate of change of angular velocity.
[0076] 4. Wireless transmission: The extracted feature parameters are transmitted to the central monitoring system via the wireless transmission module 3 using a specific protocol to ensure the stability and accuracy of data transmission.
[0077] 5. Data Reception and Analysis: The central monitoring system receives the transmitted data and stores, displays, and further analyzes it. Based on the analysis results, anesthesiologists can assess the patient's depth of anesthesia and neuromuscular function, and then adjust the anesthesia plan accordingly.
[0078] A certain number of anesthetized patients were selected as research subjects. Patients were randomly divided into an experimental group and a control group. The experimental group underwent anesthesia monitoring using an inertial measurement-based finger movement monitoring system, while the control group underwent traditional anesthesia monitoring methods. During the surgery, the dosage of anesthetic drugs, operation time, postoperative recovery time, and other indicators were recorded for both groups. Postoperative cognitive function and the occurrence of complications such as nausea and vomiting were also recorded, as shown in the table below.
[0079] Clinical trial data comparison table
[0080]
[0081] Conclusion: The inertial measurement-based finger movement monitoring system for anesthetized patients demonstrates significant advantages in anesthesia management. This system assists anesthesiologists in more precisely adjusting anesthetic drug dosages and optimizing anesthesia management during surgery. It not only reduces the amount of anesthetic drugs used and shortens surgery and recovery time, but also lowers the incidence of postoperative complications such as cognitive impairment, nausea, and vomiting. This provides strong support for improving surgical safety and patient outcomes, and compared to traditional anesthesia monitoring methods, it has higher clinical application value and greater potential for widespread adoption.
[0082] In summary, this inertial measurement-based finger movement monitoring system for anesthesia patients achieves precise anesthesia management through the integration of multiple technologies. The system integrates a high-sensitivity inertial measurement unit, multi-dimensional signal processing algorithms, low-power wireless transmission protocols, and an intelligent central monitoring system, forming a closed-loop process from data acquisition to anesthesia protocol adjustment. Its advantages are: sensors can capture subtle finger movements (accelerometer resolution 0.0001g, gyroscope 0.0625 dps), and the combination of Kalman filtering and machine learning algorithms improves data reliability; Bluetooth Low Energy transmission combined with frequency hopping spread spectrum technology ensures real-time and stable data transmission; the central monitoring system is integrated with the hospital information system to achieve dynamic assessment of anesthesia depth and early warning of complications. Clinical trials have shown that this system can reduce anesthetic drug dosage by 16.7%, shorten recovery time by 28.6%, and significantly improve surgical safety.
[0083] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A method for monitoring finger movement in anesthetized patients and transmitting signals to a central monitoring system based on inertial measurement, characterized in that, It is based on a monitoring system, including an inertial measurement unit (1), a signal processing module (2), a wireless transmission module (3), and a central monitoring system (4); The method includes the following steps: Step 1: Use an inertial measurement unit (1) to collect three-dimensional acceleration and angular velocity motion data of the anesthetized patient's fingers; Step 2: Perform Kalman filtering for noise reduction and max-min normalization preprocessing on the collected raw data; Step 3: Extract time-domain, frequency-domain, and time-frequency-domain feature parameters. The time-domain features include root mean square, peak value, mean, and standard deviation. The frequency-domain features are obtained through fast Fourier transform and power spectral density analysis. The time-frequency-domain features are extracted through wavelet transform. Step 4: Use the support vector machine algorithm to train the extracted features and establish a finger movement pattern recognition model; Step 5: Transmit the processed feature data to the central monitoring system via Bluetooth Low Energy protocol (4); Step 6: The central monitoring system (4) stores and graphically displays the received data, and assesses the depth of anesthesia in conjunction with the patient's physiological parameters, and alarms when abnormalities occur.
2. The method for monitoring finger movement of anesthetized patients and transmitting signals to a central monitoring system based on inertial measurement, as described in claim 1, is characterized in that... In step one, the inertial measurement unit (1) is worn as follows: a medical-grade flexible silicone ring is used as a carrier, and the multi-axis inertial measurement unit (1) integrating a three-axis accelerometer and a three-axis gyroscope is embedded inside the ring and in close contact with the finger.
3. The method for monitoring finger movement of anesthetized patients and transmitting signals to a central monitoring system based on inertial measurement, as described in claim 1, is characterized in that... Step one also includes a calibration method for the inertial measurement unit (1), which collects at least 5 sets of sensor data in different attitudes in a static state and eliminates zero bias and scaling factor errors by least squares fitting.
4. The method for monitoring finger movement of anesthetized patients and transmitting signals to a central monitoring system based on inertial measurement, as described in claim 1, is characterized in that... In step five, the wireless transmission module (3) uses the Bluetooth Low Energy protocol for data transmission, and the wireless transmission module (3) dynamically adjusts the transmission power by monitoring the signal strength. The wireless transmission module (3) also employs frequency hopping spread spectrum technology and automatic retransmission request mechanism for data transmission.
5. The method for monitoring finger movement of anesthetized patients and transmitting signals to a central monitoring system based on inertial measurement, as described in claim 4, is characterized in that: The data transmission format of the wireless transmission module (3) includes a packet header consisting of a packet identifier, length, and checksum, a data area consisting of time domain, frequency domain, and time-frequency domain features, and a packet tail.
6. The method for monitoring finger movement of anesthetized patients and transmitting signals to a central monitoring system based on inertial measurement, as described in claim 1, is characterized in that: The central monitoring system (4) is integrated with the hospital's electronic medical record system and hospital information system through a healthcare application adapter to perform associated storage and retrieval of monitoring data and medical record information.
7. The method for monitoring finger movement of anesthetized patients and transmitting signals to a central monitoring system based on inertial measurement, as described in claim 1, is characterized in that: The central monitoring system (4) is used to receive, store, display data and assess anesthesia status, and includes a data management unit, a graphic display unit, an anesthesia analysis unit and a system integration interface.
8. The method for monitoring finger movement of anesthetized patients and transmitting signals to a central monitoring system based on inertial measurement, as described in claim 7, is characterized in that: The anesthesia analysis unit of the central monitoring system (4) can assess the depth of anesthesia by combining physiological parameters such as heart rate and blood pressure, and trigger sound and pop-up alarms when abnormalities occur.
9. The method for monitoring finger movement of anesthetized patients and transmitting signals to a central monitoring system based on inertial measurement, as described in claim 1, is characterized in that: The signal processing module (2) is used to denoise, normalize, extract features and identify activity patterns of the collected data, and includes a Kalman filter unit, a normalization processing unit, a time-frequency domain feature extraction unit and a support vector machine classifier.