Anesthesia patient finger movement monitoring device based on inertia measurement

Abstract

The invention discloses an anesthetic patient finger activity monitoring device based on inertia measurement, and relates to the field of finger activity monitoring, the anesthetic patient finger activity monitoring device comprises a detector, a wiring end of the detector is fixedly connected with a data line, the other end of the data line is fixedly connected with a toggle clip type sensor, the toggle clip type sensor is clamped at a fingertip, and the detector is connected with a power supply. The measuring system comprises a sensor module, a signal processing module, a multi-mode data fusion module, a low-delay data transmission module and an environment adaptation and self-calibration module. By capturing the finger micro-motion signal in real time and being linked with the central monitoring system, the system is used for anesthesia depth dynamic evaluation and intraoperative risk early warning, the defect of motor nerve feedback in traditional anesthesia monitoring is overcome, high-precision finger micro-motion signal monitoring is achieved, sub-millimeter finger motion changes can be accurately captured, and the accuracy and accuracy of anesthesia monitoring are improved. Richer and more accurate original data are provided for anesthesia depth evaluation.

Description

Technical Field

[0001] This invention relates to the field of finger movement monitoring technology, specifically to a device for monitoring finger movement in anesthetized patients based on inertial measurement. Background Technology

[0002] Finger movement monitoring in anesthetized patients refers to the process of tracking, collecting, and analyzing the movement of a patient's fingers in real time during anesthesia using specific devices and techniques. Its main purpose is to provide crucial information for assessing the depth of anesthesia and the patient's physical condition by monitoring the signals generated by finger movements (such as micro-movements, amplitude, and frequency). This allows medical staff to adjust anesthesia strategies promptly, reducing the risk of insufficient or excessive anesthesia and improving surgical safety.

[0003] For example, the "A Finger Orthosis Usage Monitoring System" with publication number CN115670770A includes a finger orthosis usage monitoring device, a cloud server, a rehabilitation doctor's terminal, and a patient's terminal. When the angle of the affected finger joint exceeds a threshold, the alarm module immediately vibrates to remind the patient to adjust the joint's range of motion to a suitable range. The data collected by the finger orthosis usage monitoring device is wirelessly transmitted to the cloud server via an NB-IoT module. After receiving the data, the cloud server compares and analyzes the rehabilitation plan and the actual situation of the patient's use of the finger orthosis, and generates finger orthosis usage suggestions which are sent to the patient's terminal.

[0004] However, existing technologies, such as traditional methods for monitoring the depth of anesthesia, including single electroencephalogram (EEG) monitoring, have blind spots and cannot comprehensively and accurately reflect the patient's anesthetic state. While the subtle movements of the fingers during anesthesia can often directly reflect the body's nervous system's response to anesthetic drugs, current technologies for monitoring finger movements generally suffer from insufficient accuracy. On one hand, existing sensors struggle to accurately capture finger micro-movement signals in the low-frequency range of 0.1-5Hz, failing to meet the needs of monitoring the subtle movements of anesthetized patients. On the other hand, in the complex operating room environment, factors such as high-frequency electromagnetic interference and temperature changes can severely affect the stability and accuracy of sensor signals, leading to data deviations and consequently impacting the accuracy of anesthesia depth assessment, thus failing to provide a reliable basis for anesthesia management. Summary of the Invention

[0005] The purpose of this invention is to provide an inertial measurement-based finger movement monitoring device for anesthetized patients. Through innovative system architecture design and advanced technical solutions, it achieves high-precision monitoring of finger movements, effectively integrates multimodal data to improve the accuracy of anesthesia depth assessment, and has good environmental adaptability and real-time self-calibration function, providing strong support for precise anesthesia management in anesthesia surgery.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a finger movement monitoring device for anesthetized patients based on inertial measurement, comprising a detector, a data cable fixedly connected to the terminal of the detector, a clip-on sensor fixedly connected to the other end of the data cable, the clip-on sensor being clipped onto the fingertip, a limiting plate being snapped onto the bottom of the detector, a support plate being rotatably connected to the inner side of the limiting plate, a movable rod being rotatably connected to one side of the support plate, a hollow cylinder being sleeved on the outer wall of the movable rod, a base plate being rotatably connected to one end of the hollow cylinder, and damping connectors being fixedly installed at the junction of the base plate and the hollow cylinder and at the junction of the movable rod and the support plate;

[0007] The activity detection device also uses a measurement system, including a sensor module, a signal processing module, a multimodal data fusion module, a low-latency data transmission module, and an environmental adaptation and self-calibration module. The sensor module directly collects the micro-motion signals of the fingers, providing the raw data foundation for subsequent data processing and analysis. The signal processing module is used to separate low-frequency micro-motion signals from high-frequency noise, improve signal quality, and suppress operating room frequency band interference. The multimodal data fusion module is used to fuse inertial signals with multiple parameters such as EEG and hemodynamics, extract key micro-motion features, quantify the similarity of micro-motion trajectories, and achieve action classification, providing a basis for assessing anesthesia depth and determining the patient's anesthesia status. The low-latency data transmission module is used to automatically switch frequencies to avoid interference, establish a two-way feedback link with the anesthesia machine, transmit the processed data to the anesthesia machine, and receive feedback information from the anesthesia machine. The environmental adaptation and self-calibration module is used to eliminate initial sensor bias and perform dynamic baseline calibration every minute during the operation.

[0008] Preferably, a blocking plate is fixedly installed at the edge of the upper surface of the limiting plate, and a notch is opened on one side of the hollow cylinder. Multiple limiting blocks are fixedly installed at equal intervals on the side wall of the notch, and a groove is formed between the multiple limiting blocks.

[0009] Preferably, a locking block is fixedly connected to one side of the movable rod by a spring, the shape of the locking block is adapted to the locking groove, a thickening block is fixedly connected to one side of the locking block, and a groove is provided at the junction of the thickening block and the locking block, the shape of the groove is adapted to the limiting block.

[0010] Preferably, a cable bundle is fitted over the outside of the plurality of data lines.

[0011] Preferably, the sensor module is composed of various detectors in the clip-on sensor. The clip-on sensor 6 is a nine-axis inertial sensor, which is composed of an accelerometer, a gyroscope and a magnetometer. By attaching it to the nail, it directly captures low-frequency micro-motion signals of 0.1-5Hz and uses the three sensors to obtain finger activity information.

[0012] Preferably, the signal processing module includes a dual-frequency dynamic filtering algorithm unit and an electromagnetic shielding and temperature compensation unit;

[0013] Dual-frequency dynamic filtering algorithm unit: First, wavelet transform technology is used to separate low-frequency micro-motion signals from high-frequency noise based on the signal frequency characteristics. Then, Kalman filtering algorithm is combined to predict and correct the separated micro-motion signals by constructing a finger activity state space model.

[0014] Electromagnetic shielding and temperature compensation unit: An electromagnetic shielding layer and a temperature sensor are integrated inside the clip-on sensor. The shielding layer suppresses frequency interference generated by various devices in the operating room, while the temperature compensation module monitors changes in ambient temperature in real time and corrects the signal through a preset temperature-signal compensation program. The design of the temperature-signal compensation program includes the following steps:

[0015] S1. Temperature Data Acquisition: The program uses a temperature sensor to collect ambient temperature data in real time, converts the analog signal acquired by the temperature sensor into a digital signal, and transmits it to the microprocessor.

[0016] S2. Compensation Model Construction: During the program development phase, a large number of experiments are conducted to obtain data on the difference between the sensor output signal and the real signal at different temperatures. By repeatedly measuring the response of the clip-on sensor to the same standard signal at different temperatures, the data is recorded and analyzed to obtain the correspondence between temperature and signal deviation. Based on this, a compensation table or function is constructed, and a temperature-signal compensation model is established.

[0017] S3. Compensation Calculation and Correction: A microprocessor is used. The microprocessor substitutes the collected real-time temperature data into the temperature-signal compensation model to calculate the compensation amount that the temperature sensor signal should have at the current temperature. Then, the original signal collected by the clip-on sensor is corrected in real time based on the calculation results.

[0018] S4. Dynamic Adjustment and Optimization: During program operation, the compensation effect is evaluated by comparing the corrected signal with the actual situation and comparing it with data from other reliable monitoring devices that are not affected by temperature. If a deviation in the compensation is found, the compensation model parameters are automatically adjusted.

[0019] Preferably, the multimodal data fusion module includes a multi-parameter synchronous analysis unit and a dynamic template matching algorithm unit.

[0020] Multi-parameter synchronous analysis unit: With the help of data synchronization technology, the time alignment of inertial signals, EEG signals and hemodynamic parameters is achieved. Principal component analysis is used to perform dimensionality reduction on multi-parameter data and extract key features related to finger micro-movements, including micro-movement frequency and amplitude.

[0021] Dynamic template matching algorithm unit: The quaternion dynamic time warp algorithm is used to establish a preset template library of finger micro-movement trajectories. In the actual monitoring process, the real-time collected finger micro-movement trajectory data is quantitatively matched with the preset templates to calculate the similarity between the two.

[0022] Preferably, the low-latency data transmission module includes a dynamic frequency hopping wireless transmission unit and a bidirectional feedback link unit;

[0023] Dynamic frequency hopping wireless transmission unit: Based on the 2.4GHz frequency band, it performs wireless data transmission and adopts dynamic frequency hopping technology. During the transmission process, it automatically switches the operating frequency according to the interference of the surrounding wireless environment. At the same time, it uses Huffman compression technology to compress the transmitted data.

[0024] Two-way feedback link unit: Establishes a two-way feedback link with the anesthesia machine, transmits the processed finger movement data and analysis results to the anesthesia machine, and the anesthesia machine adjusts the anesthetic dosage according to the received information and feeds back the adjusted status information to the sensor module.

[0025] Preferably, the intraoperative dynamic calibration in the environmental adaptation and self-calibration module includes the following:

[0026] When the sensor module is powered on, a zero-bias calibration procedure is automatically executed to calibrate the initial state of the clip-on sensor and eliminate initial deviations caused by manufacturing processes, installation, and other factors. During the operation, a dynamic baseline calibration is performed every 30 minutes to adjust the baseline of the monitoring data in real time according to the current environment and equipment status, compensating for signal drift caused by long-term use and environmental changes.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. In this invention, by capturing finger micro-movement signals in real time and linking them with a central monitoring system, it is used for dynamic assessment of anesthesia depth and intraoperative risk warning. This fills the gap in motor nerve feedback in traditional anesthesia monitoring, achieving high-precision monitoring of finger micro-movement signals. It can accurately capture sub-millimeter-level changes in finger movements, providing richer and more accurate raw data for anesthesia depth assessment. Through multimodal data fusion, it effectively improves the accuracy and comprehensiveness of anesthesia depth assessment, reduces assessment blind spots, lowers the risk of too shallow or too deep anesthesia, and improves surgical safety. The low-delay closed-loop feedback mechanism can adjust the anesthesia strategy in a timely manner based on the finger activity monitoring results, achieving precise anesthesia control, optimizing the anesthesia management process, and possessing strong environmental adaptability. It can work stably in complex operating room environments, and the self-calibration mechanism ensures the long-term accuracy and reliability of the monitoring data.

[0029] 2. In this invention, the clip-on sensor design facilitates quick installation and minimizes damage to the patient's fingertips. The damping connector in the mechanical structure effectively buffers external vibrations, improving detection stability. The rotating connection design of components such as the support plate and movable rod allows the device to be placed in any position without affecting the normal operation, enhancing its applicability. The base plate can be fixed to positions such as hospital beds. Combined with the adjustable mechanical structure, it enables real-time and accurate monitoring of the finger movements of anesthetized patients, providing reliable data support for clinical anesthesia depth assessment. Pressing the thickened block drives the locking block to compress the spring, causing the locking block to disengage from the slot, thus adjusting the position of the movable rod. After releasing, the locking block engages with the corresponding slot under the action of the spring. The groove and the limiting block further enhance the locking stability. The cable bundle sleeve covers multiple data cables for storage and organization, preventing the data cables from becoming tangled. The setting of the blocking plate improves the stability of the detector placement and reduces the risk of detection errors caused by shaking. Attached Figure Description

[0030] Figure 1 This is a three-dimensional structural diagram of one side of an inertial measurement-based finger movement monitoring device for anesthetized patients according to the present invention.

[0031] Figure 2 This is a three-dimensional structural diagram of the other side of the inertial measurement-based finger movement monitoring device for anesthetized patients according to the present invention.

[0032] Figure 3 This is a schematic diagram showing the disassembled structure of the movable rod and hollow cylinder of the inertial measurement-based finger movement monitoring device for anesthetized patients according to the present invention.

[0033] Figure 4 For the present invention Figure 3 Enlarged structural diagram of section A;

[0034] Figure 5 This is a flowchart of the measurement system for a device for monitoring finger movement in anesthetized patients based on inertial measurement, according to the present invention.

[0035] Figure 6 This is a flowchart of the signal processing module of an inertial measurement-based finger movement monitoring device for anesthetized patients according to the present invention.

[0036] Figure 7 This is a flowchart of the multimodal data fusion module of an inertial measurement-based finger movement monitoring device for anesthetized patients according to the present invention.

[0037] Figure 8 This is a flowchart of the environmental adaptation and self-calibration module of an inertial measurement-based finger movement monitoring device for anesthetized patients according to the present invention.

[0038] In the diagram: 1. Detector; 2. Base plate; 3. Damping connector; 4. Hollow cylinder; 5. Support plate; 6. Limiting plate; 7. Blocking plate; 8. Data cable; 9. Clip-on sensor; 10. Movable rod; 11. Limiting block; 12. Slot; 13. Locking block; 14. Thickened block; 15. Groove; 16. Cable harness. Detailed Implementation

[0039] 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.

[0040] Example 1: Refer to Figure 1 , Figure 2 , Figure 3 and Figure 4 As shown: A finger movement monitoring device for anesthetized patients based on inertial measurement includes a detector 1. A data cable 8 is fixedly connected to the terminal of the detector 1. A clip-on sensor 9 is fixedly connected to the other end of the data cable 8. The clip-on sensor 9 is clipped onto the fingertip. A limit plate 6 is snapped onto the bottom of the detector 1. A support plate 5 is rotatably connected to the inner side of the limit plate 6. A movable rod 10 is rotatably connected to one side of the support plate 5. A hollow cylinder 4 is sleeved on the outer wall of the movable rod 10. A base plate 2 is rotatably connected to one end of the hollow cylinder 4. Damping connectors 3 are fixedly installed at the junction of the base plate 2 and the hollow cylinder 4 and at the junction of the movable rod 10 and the support plate 5.

[0041] In this embodiment, the clip-on sensor 9 is clipped onto the patient's fingertip and connected to the detector 1 via a data cable 8. It uses inertial measurement technology to collect motion data such as acceleration and angular velocity of the finger movement and transmits this data to the detector 1 for processing and analysis. A limiting plate 6, snapped into the bottom of the detector 1, is rotatably connected to a support plate 5. The support plate 5 is sleeved onto a hollow cylinder 4 via a movable rod 10. The other end of the hollow cylinder 4 is rotatably connected to a base plate 2. A damping connector 3 at the junction provides damping force, ensuring that the mechanical structure composed of the support plate 5, movable rod 10, hollow cylinder 4, and base plate 2 maintains a certain degree of freedom of movement while reducing swaying. The stable support detector 1 ensures the accuracy of inertial measurement data during the detection process. The clip-on sensor 9 is designed for quick installation and minimizes damage to the patient's fingertips. The damping connector 3 in the mechanical structure effectively buffers external vibrations and improves detection stability. The rotating connection design of components such as the support plate 5 and the movable rod 10 allows the device to be placed in any position without affecting the normal operation of the surgery, enhancing its applicability. The base plate 2 can be fixed to the hospital bed or other positions. Together with the adjustable mechanical structure, it enables real-time and accurate monitoring of the finger movements of anesthetized patients, providing reliable data support for clinical anesthesia depth assessment.

[0042] Example 2: According to Figure 1 , Figure 2 , Figure 3 and Figure 4 As shown, a blocking plate 7 is fixedly installed at the edge of the upper surface of the limiting plate 6. A notch is opened on one side of the hollow cylinder 4. Multiple limiting blocks 11 are fixedly installed at equal intervals on the side wall of the notch. A slot 12 is formed between the multiple limiting blocks 11. A locking block 13 is fixedly connected to one side of the movable rod 10 by a spring. The shape of the locking block 13 is adapted to the slot 12. A thickening block 14 is fixedly connected to one side of the locking block 13. A groove 15 is opened at the junction of the thickening block 14 and the locking block 13. The shape of the groove 15 is adapted to the limiting block 11. A cable bundle sleeve 16 is sleeved on the outside of the multiple data cables 8.

[0043] In this embodiment, the blocking plate 7 on the limiting plate 6 is used to limit the position of the detector 1 on the limiting plate 6, preventing it from accidentally sliding out and ensuring the stable placement of the detector 1. The limiting block 11 and the slot 12 at the notch of the hollow cylinder 4 cooperate with the locking block 13 on the movable rod 10, which is connected by a spring. When it is necessary to adjust the position of the movable rod 10 inside the hollow cylinder 4, pressing the thickened block 14 drives the locking block 13 to compress the spring, causing the locking block 13 to disengage from the slot 12, thereby adjusting the position of the movable rod 10. After being released, the locking block 13 is locked into the corresponding slot 12 under the action of the spring. The groove 15 and the limiting block 11 cooperate to further enhance the locking stability. The cable tie sleeve 16 is fitted onto multiple numbers of The external part of the data cable 8 is used to store and organize the data cable 8, preventing it from becoming tangled. The baffle plate 7 improves the stability of the detector 1 and reduces the risk of detection errors caused by shaking. The adjustment components, such as the locking block 13 and the locking slot 12, allow for flexible adjustment of the position of the movable rod 10 according to actual usage needs, enabling precise adjustment of the height and angle of the detector 1 to meet different usage scenarios. The cable tie 16 can organize the data cable 8, preventing it from becoming tangled and damaged or affecting normal use. At the same time, it keeps the overall device neat and beautiful, and also facilitates storage and carrying of the device, improving the convenience of use and the durability of the device.

[0044] Example 3: According to Figure 5 , Figure 6 , Figure 7 and Figure 8As shown, the activity detection device also uses a measurement system, including a sensor module, a signal processing module, a multimodal data fusion module, a low-latency data transmission module, and an environmental adaptation and self-calibration module. The sensor module directly collects the micro-motion signals of the fingers, providing the raw data basis for subsequent data processing and analysis. The signal processing module is used to separate low-frequency micro-motion signals from high-frequency noise, improve signal quality, and suppress operating room frequency band interference. The multimodal data fusion module is used to fuse inertial signals with multiple parameters such as EEG and hemodynamics, extract key micro-motion features, quantify the similarity of micro-motion trajectories, and achieve action classification, providing a basis for assessing anesthesia depth and determining the patient's anesthesia status. The low-latency data transmission module is used to automatically switch frequencies to avoid interference, establish a two-way feedback link with the anesthesia machine, transmit the processed data to the anesthesia machine, and receive feedback information from the anesthesia machine. The environmental adaptation and self-calibration module is used to eliminate initial sensor bias and perform dynamic baseline calibration every 30 minutes during the operation.

[0045] In this embodiment, the sensor module consists of various detectors in the clip-on sensor 9. The clip-on sensor 9 is a nine-axis inertial sensor, composed of an accelerometer, a gyroscope, and a magnetometer. By attaching it to the fingernail, it directly captures low-frequency micro-motion signals of 0.1-5Hz. Utilizing the coordinated work of the three sensors in acceleration, angular velocity, and magnetic field sensing, it acquires finger movement information. Sensor selection and installation: A high-performance nine-axis inertial sensor is selected, ensuring that its accelerometer sensitivity reaches ±0.01g or higher. The gyroscope and magnetometer also possess high resolution and stability. The sensor is precisely fixed to a flexible substrate with a thickness of <1mm and a weight of <2g using medical-grade flexible adhesive or bonding material. The substrate is then attached to the clip-on sensor 9 to ensure that the sensor fits tightly to the finger without affecting normal finger movement. Fit and stability test: Before actual use, the fit and stability of the sensor are tested. By simulating various activities of the patient's finger, it is observed whether the sensor will shift or fall off. At the same time, professional testing equipment is used to test the signal acquisition accuracy of the sensor under different finger activity states to ensure that its performance meets the design requirements.

[0046] Dual-frequency dynamic filtering algorithm implementation: Using mature signal processing software libraries or writing custom algorithm code, the dual-frequency dynamic filtering algorithm is implemented in a microprocessor or dedicated signal processing chip. First, the acquired raw signal is input into the wavelet transform module. According to the preset frequency threshold, the low-frequency micro-motion signal and high-frequency noise are separated. Then, the low-frequency micro-motion signal is input into the Kalman filter module. By continuously updating the state space model parameters, the signal is optimized to improve the signal-to-noise ratio. Electromagnetic shielding and temperature compensation implementation: In the sensor hardware design, an electromagnetic shielding layer is constructed using metal shielding covers or conductive coatings to effectively isolate the internal circuitry of the sensor from external electromagnetic interference. For the temperature compensation module, a high-precision temperature sensor is selected to monitor the ambient temperature in real time. The temperature data is input into the microprocessor. Through a pre-stored temperature-signal compensation table or function, the signal acquired by the sensor is corrected in real time to eliminate the influence of temperature changes on the signal.

[0047] Multi-parameter synchronous acquisition and analysis: Configure multi-channel data acquisition equipment, connecting inertial sensors, EEG electrodes, and hemodynamic monitoring sensors respectively. Through hardware synchronization circuits or software synchronization algorithms, ensure the time consistency of each parameter data during acquisition. Transmit the acquired multi-parameter data to the data processing unit. Using principal component analysis algorithm, write corresponding calculation programs to extract key features such as micro-movement frequency and amplitude, providing a data foundation for anesthesia depth assessment. Dynamic template matching algorithm application: Utilize a large amount of finger micro-movement trajectory data, and establish a rich preset template library through machine learning or manual annotation. During actual monitoring, the real-time acquired finger micro-movement trajectory data is preprocessed and matched with templates in the preset template library using a quaternion dynamic time warp algorithm. By calculating the matching similarity, determine the type of current finger micro-movement, providing a more detailed reference for anesthesia depth assessment.

[0048] Dynamic frequency hopping wireless transmission is implemented by selecting a wireless communication module that supports dynamic frequency hopping in the 2.4GHz band, such as Bluetooth 5.0 or Wi-Fi, and customizing it. During communication, the signal strength and interference of the surrounding wireless environment are monitored in real time, and the operating frequency is automatically adjusted through an algorithm to avoid frequency conflicts with other devices. At the same time, the Huffman compression algorithm is used to compress the transmitted data, reduce the amount of data transmission, improve transmission efficiency, and ensure that the data latency is ≤10ms. Two-way feedback link construction: Communication interfaces and data processing modules are set in the monitoring module and the anesthesia machine, respectively, to establish a two-way data transmission channel based on wireless or wired communication. The monitoring module sends the processed finger activity data and analysis results to the anesthesia machine in a specific data format. After receiving the data, the anesthesia machine calculates the adjustment values ​​of parameters such as the anesthesia dose according to the preset anesthesia strategy adjustment algorithm, and feeds back the adjusted status information to the monitoring module to achieve closed-loop control.

[0049] Intraoperative Dynamic Calibration Program Development: Startup zero-bias calibration and intraoperative dynamic baseline calibration programs are developed in the monitoring module's microprocessor. Upon startup, the zero-bias calibration program is automatically executed, calculating and eliminating the initial sensor deviation by collecting static data over a period of time. During the surgery, the dynamic baseline calibration program is initiated every 30 minutes, recalculating the baseline value of the monitoring data based on factors such as current ambient temperature and equipment operating status, and performing real-time calibration on subsequently collected data to ensure data accuracy and stability. Calibration Effect Verification and Optimization: In actual use, the calibration effect is verified periodically. By comparing monitoring data before and after calibration, and comparing it with data from other high-precision monitoring devices, the accuracy and effectiveness of the calibration are evaluated. Based on the verification results, the parameters and algorithms in the calibration program are optimized to continuously improve the calibration effect and ensure that the monitoring module can work stably and accurately in various environments.

[0050] The usage and working principle of this device are as follows: First, fix the base plate 2 in a suitable position such as a hospital bed. Adjust the angle between the hollow cylinder 4 and the base plate 2 by rotating the damping connector 3. Then, press the thickened block 14 on the movable rod 10 to disengage the spring of the locking block 13 from the slot 12 at the notch of the hollow cylinder 4. Slide the movable rod 10 along the hollow cylinder 4 to adjust the height. Release the thickened block 14 to allow the locking block 13 to engage with the corresponding slot 12. Simultaneously, the groove 15 engages and is fixed with the limiting block 11. Adjust the angle between the support plate 5 and the movable rod 10 by rotating the damping connector 3. Then, place the detector 1... The bottom is snapped onto the limiting plate 6, and the blocking plate 7 restricts the position of the detector 1 to prevent it from slipping out. The clip-on sensor 9 is clipped onto the patient's fingertip, and the data cable 8 connects the detector 1 and the clip-on sensor 9. Multiple data cables 8 are neatly organized and stored using the cable tie 16. The detector 1 is activated, and the clip-on sensor 9 uses inertial measurement technology to collect data such as the acceleration and angular velocity of finger movements and transmits them to the detector 1 for processing and analysis via the data cable 8. The mechanical structure reduces shaking through the damping connector 3 and stably supports the detector 1, realizing real-time and accurate monitoring of the finger movements of anesthetized patients.

[0051] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A device for monitoring finger movement in anesthetized patients based on inertial measurement, characterized in that: Includes a detector (1), with a data cable (8) fixedly connected to the terminal of the detector (1), and a clip-on sensor (9) fixedly connected to the other end of the data cable (8). The clip-on sensor (9) is clipped to the fingertip. A limit plate (6) is snapped into the bottom of the detector (1). A support plate (5) is rotatably connected to the inner side of the limit plate (6). A movable rod (10) is rotatably connected to one side of the support plate (5). A hollow cylinder (4) is sleeved on the outer wall of the movable rod (10). A base plate (2) is rotatably connected to one end of the hollow cylinder (4). Damping connectors (3) are fixedly installed at the junction of the base plate (2) and the hollow cylinder (4) and at the junction of the movable rod (10) and the support plate (5). The activity detection device also uses a measurement system, including a sensor module, a signal processing module, a multimodal data fusion module, a low-latency data transmission module, and an environmental adaptation and self-calibration module. The sensor module directly collects the micro-motion signals of the fingers, providing the raw data foundation for subsequent data processing and analysis. The signal processing module is used to separate low-frequency micro-motion signals from high-frequency noise, improve signal quality, and suppress operating room frequency interference. The multimodal data fusion module is used to fuse inertial signals with multiple parameters such as EEG and hemodynamics, extract key micro-motion features, quantify the similarity of micro-motion trajectories, and classify movements, providing a basis for assessing anesthesia depth and determining the patient's anesthesia status. The low-latency data transmission module is used to automatically switch frequencies to avoid interference, establish a two-way feedback link with the anesthesia machine, transmit the processed data to the anesthesia machine, and receive feedback information from the anesthesia machine. The environmental adaptation and self-calibration module is used to eliminate initial sensor bias and perform dynamic baseline calibration every 30 minutes during the operation.

2. The inertial measurement-based finger movement monitoring device for anesthetized patients according to claim 1, characterized in that: A blocking plate (7) is fixedly installed at the edge of the upper surface of the limiting plate (6). A notch is opened on one side of the hollow cylinder (4). Multiple limiting blocks (11) are fixedly installed at equal intervals on the side wall of the notch. A slot (12) is formed between the multiple limiting blocks (11).

3. The inertial measurement-based finger movement monitoring device for anesthetized patients according to claim 1, characterized in that: One side of the movable rod (10) is fixedly connected to a locking block (13) by a spring. The shape of the locking block (13) is adapted to the locking groove (12). A thickening block (14) is fixedly connected to one side of the locking block (13). A groove (15) is provided at the junction of the thickening block (14) and the locking block (13). The shape of the groove (15) is adapted to the limiting block (11).

4. The inertial measurement-based finger movement monitoring device for anesthetized patients according to claim 1, characterized in that: A cable bundle sleeve (16) is attached to the outside of the plurality of data lines (8).

5. The inertial measurement-based finger movement monitoring device for anesthetized patients according to claim 1, characterized in that: The sensor module consists of various detectors in the clip-on sensor (9). The clip-on sensor (9) is a nine-axis inertial sensor, which is composed of an accelerometer, a gyroscope, and a magnetometer. It directly captures low-frequency micro-motion signals of 0.1-5Hz by attaching it to the nail plate and uses the three sensors to obtain finger activity information.

6. The inertial measurement-based finger movement monitoring device for anesthetized patients according to claim 1, characterized in that: The signal processing module includes a dual-frequency dynamic filtering algorithm unit and an electromagnetic shielding and temperature compensation unit. Dual-frequency dynamic filtering algorithm unit: First, wavelet transform technology is used to separate low-frequency micro-motion signals from high-frequency noise based on the signal frequency characteristics. Then, Kalman filtering algorithm is combined to predict and correct the separated micro-motion signals by constructing a finger activity state space model. Electromagnetic shielding and temperature compensation unit: An electromagnetic shielding layer and a temperature sensor are integrated inside the clip-on sensor (9). The shielding layer suppresses frequency interference generated by various devices in the operating room. At the same time, the temperature compensation module monitors changes in ambient temperature in real time and corrects the signal through a preset temperature-signal compensation program. The design of the temperature-signal compensation program includes the following steps: S1. Temperature Data Acquisition: The program uses a temperature sensor to collect ambient temperature data in real time, converts the analog signal acquired by the temperature sensor into a digital signal, and transmits it to the microprocessor. S2. Compensation Model Construction: During the program development phase, a large number of experiments were conducted to obtain the difference data between the output signal of the temperature sensor and the real signal at different temperatures. The response of the clip-on sensor (9) to the same standard signal was measured multiple times at different temperatures. The data was recorded and analyzed to obtain the correspondence between temperature and signal deviation. A compensation table or function was constructed based on this, and a temperature-signal compensation model was established based on these data. S3. Compensation calculation and correction: A microprocessor is used. The microprocessor substitutes the collected real-time temperature data into the temperature-signal compensation model to calculate the compensation amount that the temperature sensor signal should have at the current temperature. Then, the original signal collected by the clip-on sensor (9) is corrected in real time according to the calculation results. S4. Dynamic Adjustment and Optimization: During program operation, the compensation effect is evaluated by comparing the corrected signal with the actual situation and comparing it with data from other reliable monitoring devices that are not affected by temperature. If a deviation in the compensation is found, the compensation model parameters are automatically adjusted.

7. The inertial measurement-based finger movement monitoring device for anesthetized patients according to claim 1, characterized in that: The multimodal data fusion module includes a multi-parameter synchronous analysis unit and a dynamic template matching algorithm unit; Multi-parameter synchronous analysis unit: With the help of data synchronization technology, the time alignment of inertial signals, EEG signals and hemodynamic parameters is achieved. Principal component analysis is used to perform dimensionality reduction on multi-parameter data and extract key features related to finger micro-movements, including micro-movement frequency and amplitude. Dynamic template matching algorithm unit: The quaternion dynamic time warp algorithm is used to establish a preset template library of finger micro-movement trajectories. In the actual monitoring process, the real-time collected finger micro-movement trajectory data is quantitatively matched with the preset templates to calculate the similarity between the two.

8. A device for monitoring finger movement in anesthetized patients based on inertial measurement according to claim 1, characterized in that: The low-latency data transmission module includes a dynamic frequency-hopping wireless transmission unit and a bidirectional feedback link unit; Dynamic frequency hopping wireless transmission unit: Based on the 2.4GHz frequency band, it performs wireless data transmission and adopts dynamic frequency hopping technology. During the transmission process, it automatically switches the operating frequency according to the interference of the surrounding wireless environment. At the same time, it uses Huffman compression technology to compress the transmitted data. Two-way feedback link unit: Establishes a two-way feedback link with the anesthesia machine, transmits the processed finger movement data and analysis results to the anesthesia machine, and the anesthesia machine adjusts the anesthetic dosage according to the received information and feeds back the adjusted status information to the sensor module.

9. A device for monitoring finger movement in anesthetized patients based on inertial measurement according to claim 1, characterized in that: Intraoperative dynamic calibration in the environmental adaptation and self-calibration module includes the following: When the sensor module is powered on, the zero bias calibration procedure is automatically executed to calibrate the initial state of the clip-on sensor (9) and eliminate the initial deviation caused by manufacturing process, installation and other factors. During the operation, dynamic baseline calibration is performed every 30 minutes. The baseline of the monitoring data is adjusted in real time according to the current environment and equipment status to compensate for signal drift caused by long-term use and environmental changes.

Images