Wearable pain management and rehabilitation equipment with dynamic impedance adaptation
By integrating multiple advanced technologies into wearable pain management devices, the problems of electrode impedance drift and lack of biomarker feedback in existing devices are solved, accurate monitoring and personalized management of pain status are achieved, and the effectiveness and safety of pain management are improved.
Patent Information
- Application Number
- CN202510948426.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-10
- Publication Date
- 2025-09-19
AI Technical Summary
Existing pain management devices have electrode-skin contact impedance drift that leads to inaccurate electrical stimulation dosage, lack closed-loop feedback on pain biomarkers, and the rehabilitation model is disconnected from the physiological state of pain, which can easily cause secondary injuries.
It uses wearable pain management and rehabilitation equipment with dynamic impedance adaptation, integrating millimeter-wave radar, flexible multi-electrode array, multi-frequency bioimpedance detection module, pain biomarker fusion processor, sEMG sensor, thermistor, 9-axis IMU, pain level prediction model, dynamic impedance adaptation engine, nerve stimulation waveform generator and cloud-based pain digital twin system to achieve comprehensive monitoring and management of pain status.
By real-time monitoring and adjustment of nerve stimulation intensity, the accuracy and safety of pain management can be improved, future pain levels can be predicted, management measures can be taken in advance, pain aggravation can be avoided, and personalized and intelligent pain management can be achieved.
Smart Images
Figure CN120661843A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of wearable medical devices, and in particular to a wearable pain management and rehabilitation device with dynamic impedance adaptation. Background Art
[0002] "Pain management devices" refers to a variety of medical devices and technologies used to relieve, control, or treat pain. These devices aim to reduce pain, improve function, and improve quality of life, often in addition to or as an alternative to medication, physical therapy, or surgery.
[0003] The electrode-skin contact impedance drift of current pain management devices leads to inaccurate electrical stimulation dosage, and there is a lack of closed-loop feedback on pain biomarkers (such as electromyography, skin temperature, and HRV). At the same time, the rehabilitation model is disconnected from the physiological state of pain, which can easily cause secondary injuries.
[0004] To this end, we propose a wearable pain management and rehabilitation device with dynamic impedance adaptation. Summary of the Invention
[0005] The present invention mainly solves the technical problems existing in the above-mentioned prior art and provides a wearable pain management and rehabilitation device with dynamic impedance adaptation.
[0006] In order to achieve the above-mentioned objectives, the present invention adopts the following technical solutions: a wearable pain management and rehabilitation device with dynamic impedance adaptation, including a millimeter-wave radar, a flexible multi-electrode array, a multi-frequency bioimpedance detection module, a pain biomarker fusion processor, an sEMG sensor, a thermistor, a 9-axis IMU, a pain level prediction model, a dynamic impedance adaptation engine, a neural stimulation waveform generator and a cloud-based pain digital twin system. The working frequency band of the multi-frequency bioimpedance detection module covers 1kHz-1MHz.
[0007] Preferably, the input ports of the pain biomarker fusion processor are electrically connected to the sEMG sensor, the thermistor and the 9-axis IMU respectively.
[0008] Preferably, the dynamic impedance adaptation engine adjusts the stimulation intensity in real time, and the formula is:
[0009] I stim =I0×[1+α(Z t -Z0)] -1
[0010] Where I0 is the initial stimulation current intensity, α is the tissue attenuation factor, and Z t is the real-time tissue impedance value, and Z0 is the target stimulation current intensity.
[0011] Preferably, the flexible multi-electrode array adopts a fractal topology structure, and the flexible multi-electrode array includes 6 stimulation electrodes, 4 sensing electrodes and an electrode spacing adaptive adjustment mechanism, and the electrode spacing adaptive adjustment mechanism changes the distribution density according to the joint curvature.
[0012] Preferably, the dynamic impedance adaptation engine includes an impedance phase detection unit, a motion artifact compensation unit and a sweat influence model, wherein the impedance phase detection unit is used to measure the capacitive component Z c and the resistive component Z r ,The motion artifact compensation unit eliminates the impedance drift caused by ,motion through IMU data, and the sweat impact model is used to establish ,the impedance-sweat secretion rate mapping table.
[0013] Preferably, the pain level prediction model adopts a three-layer LSTM neural network, and the formula for the input vector is:
[0014] X t =[RMS EMG ,ΔT skin ,EDA slope ,ROM joint ] T
[0015] Among them, RMS EMG is the hidden layer state of the LSTM neural network, ΔT skin Represents the predicted value of pain level at different time points, EDA slope Represents the output layer weight of the LSTM neural network, ROM joint represents the activation function of the LSTM neural network, and T represents the fusion feature of pain biomarkers
[0016] Preferably, the neural stimulation waveform generator supports:
[0017] Transcutaneous electrical nerve stimulation (TENS) mode: frequency adjustable from 2 to 150 Hz;
[0018] Interferential Current Therapy (ICT) mode: carrier 4kHz±10%;
[0019] Neuromuscular Reeducation (NMR) Mode: Triggered synchronously with sEMG signals.
[0020] Preferably, the formula for establishing the user pain profile of the cloud-based pain digital twin system is:
[0021] P profile = <Z hist ,T flare ,M rehab >
[0022] Among them, Z histRepresents the user's historical pain record, T flare Represents the user's current pain state, M rehab Real-time data representing pain biomarkers.
[0023] Preferably, the cloud-based pain digital twin system updates the stimulation parameter optimization strategy based on federated learning.
[0024] The present invention provides a wearable pain management and rehabilitation device with dynamic impedance adaptation. It has the following beneficial effects:
[0025] 1. This wearable pain management and rehabilitation device with dynamic impedance adaptation can achieve comprehensive monitoring and management of the user's pain status by setting up millimeter-wave radar, flexible multi-electrode array, multi-frequency bioimpedance detection module, pain biomarker fusion processor, sEMG sensor, thermistor and 9-axis IMU. The millimeter-wave radar is used to monitor the user's movements and position in real time to ensure that the device can fit the user accurately and improve the accuracy of pain management. The flexible multi-electrode array and multi-frequency bioimpedance detection module can detect changes in the user's body's bioimpedance and further analyze the user's physical condition and pain level. The pain biomarker fusion processor can integrate data from the sEMG sensor, thermistor and 9-axis IMU, and extract pain-related biomarkers through complex algorithm analysis to provide more accurate information for pain management.
[0026] 2. This wearable pain management and rehabilitation device with dynamic impedance adaptation, by setting up a pain level prediction model, can predict future pain levels based on the user's biomarker data, thereby taking pain management measures in advance, avoiding pain aggravation, and improving rehabilitation effects. The three-layer LSTM neural network used in the pain level prediction model can extract pain-related features from complex time series data, improving the accuracy and reliability of the prediction.
[0027] 3. This wearable pain management and rehabilitation device with dynamic impedance adaptation is equipped with a dynamic impedance adaptation engine to automatically adjust the nerve stimulation intensity according to the real-time tissue impedance value, ensuring the maximum stimulation effect while reducing unnecessary energy consumption and user discomfort. The impedance phase detection unit in the dynamic impedance adaptation engine can accurately distinguish between capacitive and resistive components, providing more detailed data support for subsequent pain management. The motion artifact compensation unit effectively eliminates the impedance drift caused by user movement by integrating the data of the 9-axis IMU, ensuring the stability and accuracy of the data. The sweat impact model establishes an impedance-sweat secretion rate mapping table based on the impact of user sweat secretion on impedance detection, further improving the accuracy of pain management.
[0028] 4. This wearable pain management and rehabilitation device with dynamic impedance adaptation supports multiple nerve stimulation modes, including transcutaneous electrical nerve stimulation (TENS) mode, interferential current therapy (ICT) mode and neuromuscular reeducation (NMR) mode, by setting a nerve stimulation waveform generator to meet the pain management needs of different users. The TENS mode stimulates nerve fibers through low-frequency electrical pulses to relieve pain. The ICT mode uses carrier frequency modulation to produce deep muscle stimulation, promote blood circulation and muscle relaxation. The NMR mode is triggered synchronously with the user's sEMG signal to achieve more accurate and personalized nerve stimulation, and promote the recovery and remodeling of nerve function.
[0029] 5. This wearable pain management and rehabilitation device with dynamic impedance adaptation can synchronize the user's pain data and device status to the cloud in real time by setting up a cloud-based pain digital twin system, building a user-personalized pain digital twin. The cloud-based pain digital twin system can not only monitor and analyze the user's pain condition in real time, but also continuously optimize stimulation parameters and treatment strategies based on federated learning algorithms to achieve intelligent and personalized pain management. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] Figure 1 This is a device module diagram of the present invention. DETAILED DESCRIPTION
[0031] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are merely illustrative, and those skilled in the art can, without inventive effort, derive other implementation drawings based on the provided drawings.
[0032] The structures, proportions, sizes, etc. illustrated in this specification are intended only to complement the contents disclosed herein and to facilitate understanding and reading by persons familiar with the art. They are not intended to limit the conditions under which the present invention may be implemented and therefore have no substantive technical significance. Any structural modifications, changes in proportions, or adjustments in sizes, without affecting the efficacy and objectives of the present invention, shall still fall within the scope of the technical contents disclosed herein.
[0033] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.
[0034] In the description of the embodiments of the present invention, it should be noted that the terms "center," "upper," "lower," "inner," "outer," and "side" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, or the orientations or positional relationships in which the inventive product is typically placed when in use. These terms are intended solely to facilitate the description of the present invention and to simplify the description, and are not intended to indicate or imply that the devices or components referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and the like are used solely to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0035] In the description of the embodiments of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "disposed," "installed," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in the embodiments of the present invention according to specific circumstances.
[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0037] Example 1: Wearable pain management and rehabilitation device with dynamic impedance adaptation, such as Figure 1 As shown, it includes millimeter-wave radar, flexible multi-electrode array, multi-frequency bioimpedance detection module, pain biomarker fusion processor, sEMG sensor, thermistor, 9-axis IMU, pain level prediction model, dynamic impedance adaptation engine, neural stimulation waveform generator and cloud-based pain digital twin system. The operating frequency band of the multi-frequency bioimpedance detection module covers 1kHz-1MHz. The input port of the pain biomarker fusion processor is electrically connected to the sEMG sensor, thermistor and 9-axis IMU respectively. The dynamic impedance adaptation engine adjusts the stimulation intensity in real time, and its formula is:
[0038] I stim =I0×[1+α(Z t -Z0)] -1
[0039] Where I0 is the initial stimulation current intensity, α is the tissue attenuation factor, and Z tis the real-time tissue impedance value, and Z0 is the target stimulation current intensity. The flexible multi-electrode array adopts a fractal topology structure. The flexible multi-electrode array includes 6 stimulation electrodes, 4 sensing electrodes, and an electrode spacing adaptive adjustment mechanism. The electrode spacing adaptive adjustment mechanism changes the distribution density according to the joint curvature. The dynamic impedance adaptation engine includes an impedance phase detection unit, a motion artifact compensation unit, and a sweat influence model. The impedance phase detection unit is used to measure the capacitive component Z c and the resistive component Z r The motion artifact compensation unit uses IMU data to eliminate impedance drift caused by movement. The sweat impact model is used to establish an impedance-sweat secretion rate mapping table. The pain level prediction model uses a three-layer LSTM neural network. The input vector formula is:
[0040] X t =[RMS EMG ,ΔT skin ,EDA slope ,ROM joint ] T
[0041] Among them, RMS EMG is the hidden layer state of the LSTM neural network, ΔT skin Represents the predicted value of pain level at different time points, EDA slope Represents the output layer weight of the LSTM neural network, ROM joint represents the activation function of the LSTM neural network, and T represents the fused features of pain biomarkers. The nerve stimulation waveform generator supports the following: Transcutaneous Electrical Nerve Stimulation (TENS) mode: frequency adjustable from 2 to 150 Hz; Interferential Current Therapy (ICT) mode: carrier frequency 4 kHz ± 10%; Neuromuscular Reeducation (NMR) mode: triggered synchronously with sEMG signals.
[0042] The formula for establishing a user pain profile in the cloud-based pain digital twin system is:
[0043] P profile = <Z hist ,T flare ,M rehab >
[0044] Among them, Z hist Represents the user's historical pain record, T flare Represents the user's current pain state, M rehabReal-time data representing pain biomarkers. The cloud-based pain digital twin system updates the stimulation parameter optimization strategy based on federated learning. By setting up millimeter-wave radar, flexible multi-electrode array, multi-frequency bioimpedance detection module, pain biomarker fusion processor, sEMG sensor, thermistor and 9-axis IMU, comprehensive monitoring and management of the user's pain status can be achieved. The millimeter-wave radar is used to monitor the user's movements and position in real time to ensure that the device can fit the user accurately and improve the accuracy of pain management. The flexible multi-electrode array and multi-frequency bioimpedance detection module can detect changes in the user's body's bioimpedance and further analyze the user's physical condition and pain level. The pain biomarker fusion processor can integrate data from sEMG sensors, thermistors and 9-axis IMUs, and extract pain-related biomarkers through complex algorithm analysis to provide more accurate information for pain management.
[0045] Example 2: Based on Example 1, Figure 1 As shown in Figure 1, the input ports of the pain biomarker fusion processor are electrically connected to the sEMG sensor, thermistor, and 9-axis IMU. The dynamic impedance adaptation engine adjusts the stimulation intensity in real time, and its formula is:
[0046] I stim =I0×[1+α(Z t -Z0)] -1
[0047] Where I0 is the initial stimulation current intensity, α is the tissue attenuation factor, and Z t is the real-time tissue impedance value, and Z0 is the target stimulation current intensity. By setting up a pain level prediction model, future pain levels can be predicted based on the user's biomarker data, allowing for proactive pain management measures to prevent pain exacerbation and improve recovery outcomes. The three-layer LSTM neural network used in the pain level prediction model can extract pain-related features from complex time series data, improving the accuracy and reliability of predictions.
[0048] Example 3: Based on Example 1 and Example 2, Figure 1 As shown in the figure, the flexible multi-electrode array adopts a fractal topology structure. The flexible multi-electrode array includes 6 stimulation electrodes, 4 sensing electrodes, and an electrode spacing adaptive adjustment mechanism. The electrode spacing adaptive adjustment mechanism changes the distribution density according to the joint curvature. The dynamic impedance adaptation engine includes an impedance phase detection unit, a motion artifact compensation unit, and a sweat influence model. The impedance phase detection unit is used to measure the capacitive component Z c and the resistive component Z rThe motion artifact compensation unit eliminates the impedance drift caused by movement through IMU data, and the sweat impact model is used to establish an impedance-sweat secretion rate mapping table. By setting up a dynamic impedance adaptation engine, the nerve stimulation intensity is automatically adjusted according to the real-time tissue impedance value to ensure the maximum stimulation effect, while reducing unnecessary energy consumption and user discomfort. The impedance phase detection unit in the dynamic impedance adaptation engine can accurately distinguish between capacitive and resistive components, providing more detailed data support for subsequent pain management. The motion artifact compensation unit effectively eliminates the impedance drift caused by user movement by integrating the data of the 9-axis IMU, ensuring the stability and accuracy of the data. The sweat impact model establishes an impedance-sweat secretion rate mapping table based on the impact of user sweat secretion on impedance detection, further improving the accuracy of pain management.
[0049] Example 4: Based on Example 1, Example 2 and Example 3, Figure 1 As shown in the figure, the pain level prediction model uses a three-layer LSTM neural network, and the formula for the input vector is:
[0050] X t =[RMS EMG ,ΔT skin ,EDA slope ,ROM joint ] T
[0051] Among them, RMS EMG is the hidden layer state of the LSTM neural network, ΔT skin Represents the predicted value of pain level at different time points, EDA slope Represents the output layer weight of the LSTM neural network, ROM joint represents the activation function of the LSTM neural network, and T represents the fusion feature of pain biomarkers. By setting up a nerve stimulation waveform generator, it supports multiple nerve stimulation modes, including transcutaneous electrical nerve stimulation (TENS), interferential current therapy (ICT), and neuromuscular reeducation (NMR), to meet the pain management needs of different users. The TENS mode stimulates nerve fibers through low-frequency electrical pulses to relieve pain. The ICT mode uses carrier frequency modulation to produce deep muscle stimulation, promote blood circulation and muscle relaxation. The NMR mode is triggered synchronously with the user's sEMG signal, achieving more precise and personalized nerve stimulation, promoting the recovery and remodeling of nerve function.
[0052] Example 5: Based on Example 1, Example 2, Example 3 and Example 4, Figure 1As shown, the nerve stimulation waveform generator supports: transcutaneous electrical nerve stimulation (TENS) mode: frequency adjustable from 2 to 150 Hz; interferential current therapy (ICT) mode: carrier 4 kHz ± 10%; neuromuscular reeducation (NMR) mode: triggered synchronously with sEMG signals.
[0053] The formula for establishing a user pain profile in the cloud-based pain digital twin system is:
[0054] P profile = <Z hist ,T flare ,M rehab >
[0055] Among them, Z hist Represents the user's historical pain record, T flare Represents the user's current pain state, M rehab Real-time data representing pain biomarkers. The cloud-based pain digital twin system updates stimulation parameter optimization strategies based on federated learning. By setting up a cloud-based pain digital twin system, users' pain data and device status can be synchronized to the cloud in real time, building a personalized pain digital twin. The cloud-based pain digital twin system not only monitors and analyzes the user's pain status in real time but also continuously optimizes stimulation parameters and treatment strategies based on federated learning algorithms, achieving intelligent and personalized pain management.
[0056] The operating principle of this invention is that non-contact vital sign monitoring is performed using millimeter-wave radar, and a flexible multi-electrode array contacts the user's skin to achieve precise electrical stimulation therapy. A multi-frequency bioimpedance detection module detects tissue impedance in real time, providing data support for the dynamic impedance adaptation engine. A pain biomarker fusion processor integrates data from sEMG sensors, thermistors, and a 9-axis IMU to provide input for a pain level prediction model. The dynamic impedance adaptation engine adjusts stimulation intensity based on real-time tissue impedance to maximize therapeutic efficacy. The fractal topology of the flexible multi-electrode array enables it to adapt to varying joint curvatures, ensuring effective delivery of electrical stimulation. An adaptive electrode spacing adjustment mechanism further enhances the device's adaptability, ensuring optimal therapeutic efficacy across different body regions. The impedance phase detection unit, motion artifact compensation unit, and sweat impact model work together to reduce the impact of external factors on impedance detection and improve treatment accuracy. The pain level prediction model utilizes a three-layer LSTM neural network that accurately predicts pain levels, providing the basis for personalized treatment plans. The neurostimulation waveform generator supports multiple treatment modes to meet the pain management needs of diverse users. The cloud-based pain digital twin system creates a user pain profile and continuously optimizes stimulation parameters based on federated learning, enabling remote monitoring and treatment plan adjustments. In short, by integrating multiple advanced technologies, the device enables precise pain management and rehabilitation treatment, providing users with an efficient and personalized pain management solution.
[0057] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.
Claims
1. Wearable pain management and rehabilitation device with dynamic impedance adaptation, characterized by: It includes millimeter-wave radar, flexible multi-electrode array, multi-frequency bioimpedance detection module, pain biomarker fusion processor, sEMG sensor, thermistor, 9-axis IMU, pain level prediction model, dynamic impedance adaptation engine, nerve stimulation waveform generator and cloud-based pain digital twin system. The working frequency band of the multi-frequency bioimpedance detection module covers 1kHz-1MHz.
2. The wearable pain management and rehabilitation device with dynamic impedance adaptation according to claim 1, characterized in that: The input ports of the pain biomarker fusion processor are electrically connected to the sEMG sensor, the thermistor and the 9-axis IMU respectively.
3. The wearable pain management and rehabilitation device with dynamic impedance adaptation according to claim 1, characterized in that: The dynamic impedance adaptation engine adjusts the stimulation intensity in real time, and the formula is: AND stim =I0×[1+α(Z t -Z0)] -1 Where I0 is the initial stimulation current intensity, α is the tissue attenuation factor, and Z t is the real-time tissue impedance value, and Z0 is the target stimulation current intensity.
4. The wearable pain management and rehabilitation device with dynamic impedance adaptation according to claim 1, characterized in that: The flexible multi-electrode array adopts a fractal topology structure and includes 6 stimulation electrodes, 4 sensing electrodes and an electrode spacing adaptive adjustment mechanism. The electrode spacing adaptive adjustment mechanism changes the distribution density according to the joint curvature.
5. The wearable pain management and rehabilitation device with dynamic impedance adaptation according to claim 1, characterized in that: The dynamic impedance adaptation engine includes an impedance phase detection unit, a motion artifact compensation unit and a sweat influence model. The impedance phase detection unit is used to measure the capacitive component Z c and the resistive component Z r ,The motion artifact compensation unit eliminates the impedance drift caused by ,motion through IMU data, and the sweat impact model is used to establish ,the impedance-sweat secretion rate mapping table.
6. The wearable pain management and rehabilitation device with dynamic impedance adaptation according to claim 1, characterized in that: The pain level prediction model uses a three-layer LSTM neural network, and the formula for the input vector is: X t =[RMS EMG ,ΔT skin ,EDA slope ,ROM joint ] T Among them, RMS EMG is the hidden layer state of the LSTM neural network, ΔT skin Represents the predicted value of pain level at different time points, EDA slope Represents the output layer weight of the LSTM neural network, ROM joint represents the activation function of the LSTM neural network, and T represents the fusion feature of pain biomarkers.
7. The wearable pain management and rehabilitation device with dynamic impedance adaptation according to claim 1, characterized in that: The Neural Stimulation Waveform Generator supports: Transcutaneous electrical nerve stimulation (TENS) mode: frequency adjustable from 2 to 150 Hz; Interferential Current Therapy (ICT) mode: carrier 4kHz±10%; Neuromuscular Reeducation (NMR) Mode: Triggered synchronously with sEMG signals.
8. The wearable pain management and rehabilitation device with dynamic impedance adaptation according to claim 1, characterized in that: The formula for establishing a user pain profile in the cloud-based pain digital twin system is: P profile =<Z hist ,T flare ,M rehab > Among them, Z hist Represents the user's historical pain record, T flare Represents the user's current pain state, M rehab Real-time data representing pain biomarkers.
9. The wearable pain management and rehabilitation device with dynamic impedance adaptation according to claim 1, characterized in that: The cloud-based pain digital twin system updates the stimulation parameter optimization strategy based on federated learning.