An autonomic nervous function real-time monitoring system and a monitoring method
Wearable devices that integrate multimodal sensors and lightweight AI models solve the problems of convenient, real-time, and continuous monitoring of autonomic nervous function assessment, achieving efficient and accurate autonomic nervous function assessment, suitable for home and daily health management.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHANGHAI DEBINKANG INVESTMENT MANAGEMENT CO LTD
- Filing Date
- 2026-04-30
- Publication Date
- 2026-07-24
AI Technical Summary
Existing methods for assessing autonomic nervous function are complex, time-consuming, and dependent on professionals, making it difficult to achieve convenient, real-time, and continuous monitoring. Furthermore, the equipment is expensive and difficult to popularize.
By integrating PPG, ECG, GSR and accelerometers into wearable devices, combined with lightweight AI models and intelligent guidance modules, multimodal signal fusion and cardiopulmonary coupling analysis are achieved, providing real-time physiological data processing and feedback.
It enables real-time, continuous, and convenient monitoring of autonomic nervous system function, improves the accuracy and universality of assessment, reduces equipment costs, and is suitable for home and daily health management.
Smart Images
Figure CN122440159A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of medical and health monitoring technology, specifically relating to a wearable device and related system capable of real-time monitoring of autonomic nervous system function. This product combines physiological signal sensing technology, signal processing algorithms, and health status assessment models to provide a non-invasive, continuous, in vivo solution for assessing autonomic nervous system function, suitable for various application scenarios such as cardiovascular disease risk warning, mental stress monitoring, and sub-health status assessment. Background Technology
[0002] The autonomic nervous system (ANS), as the body's "automatic control system," is responsible for regulating numerous involuntary physiological functions such as heart rate, blood pressure, respiration, and digestion. Autonomic nervous system dysfunction is closely related to a variety of diseases, including sudden cardiac death, arrhythmias, coronary heart disease, and heart failure—serious cardiovascular diseases. Therefore, accurate assessment of autonomic nervous system function has significant clinical value.
[0003] Currently, the main methods for assessing autonomic nervous system function in clinical practice include: (1) Heart rate variability (HRV) analysis: This method assesses autonomic balance by analyzing the fluctuations in the continuous heart rate interval (RR interval). Time-domain indicators (such as SDNN) and frequency-domain indicators (such as the LF / HF ratio) of HRV can reflect the balance between the sympathetic and parasympathetic nervous systems. However, traditional HRV analysis often requires a long signal recording time (usually at least 5 minutes), and the results are easily affected by respiratory rate, body position, medications, and environmental factors.
[0004] (2) Ewing test: This is a standardized set of tests for autonomic nervous system function, including deep breathing, standing, grip strength and other actions. The autonomic nervous system function is assessed by monitoring the heart rate and blood pressure response to these actions. However, the Ewing test requires the patient's active cooperation and the degree of completion of each action is difficult to standardize, and the results are easily affected by the operator's subjectivity.
[0005] (3) Autonomic neurotransmitter detection: Sympathetic nerve activity is assessed by measuring the concentration of catecholamines such as norepinephrine and epinephrine in blood or urine. This method is invasive and costly, making it difficult to popularize in primary hospitals or routine health monitoring.
[0006] (4) Traditional medical testing equipment: Existing commercial autonomic nervous function testing instruments usually integrate multiple monitoring devices such as electrocardiogram, blood pressure, respiration, and grip strength. They are bulky, complex to operate, require professional personnel to operate, and the examination process takes a long time (traditional diagnosis may take 1.5 hours), which limits their daily application.
[0007] In summary, existing technologies suffer from the following main drawbacks: complex operation, long processing time, reliance on professional personnel, difficulty in achieving continuous dynamic monitoring, and high cost hindering widespread adoption. Therefore, the market urgently needs a device capable of convenient, real-time, and continuous monitoring of autonomic nervous system function to meet the demands of daily health management and early disease warning. Summary of the Invention
[0008] To address the technical deficiencies of existing technologies, the purpose of this invention is to provide a real-time monitoring system for autonomic nervous function, comprising: Signal processing and feature extraction module 2 is used to preprocess the physiological signals acquired by physiological signal acquisition module 1 to obtain real-time physiological data; The data communication and display module 4 is used to transmit the data and / or evaluation results processed by the monitoring system to a display device or a back-end system; Its characteristic is that it further includes at least: The intelligent guidance and feedback module 5 is used to guide the user to perform a standardized short test. The intelligent guidance and feedback module 5 includes a miniature vibration motor and / or a voice prompt unit, which is used to issue the prompt information in a vibration manner and / or voice prompt to guide the user to perform the standardized short test. The autonomic nervous system function analysis module 3 is used to analyze the real-time physiological data in real time through a lightweight AI model to determine whether there is a tendency for autonomic nervous system dysfunction. The physiological signal acquisition module 1 is a wearable device that is placed on the user's wrist or earlobe. The physiological signal acquisition module 1 integrates a PPG sensor for monitoring heart rate, a GSR sensor, and an accelerometer.
[0009] According to another aspect of the present invention, a real-time monitoring method for the above-mentioned real-time monitoring system of autonomic nervous function is also provided, characterized by comprising the following steps: i. Guide users through standardized breathing exercises using vibration and / or screen animations; ii. Collect the user's physiological signals during step i; iii. Use AI algorithms to calculate the user's cardiopulmonary coupling strength index to determine whether the user's autonomic nervous system has a tendency to be dysfunctional; iv. If a sustained increase in sympathetic nerve excitation is detected, health advice will be sent to the user via vibration and / or voice prompts.
[0010] Preferably, step i includes any one or more of the following steps: - Uses rhythmic vibrations to guide users through long inhale and short exhale training; - Use rhythmic vibrations to guide users through short inhales and long exhales.
[0011] Preferably, the following steps are included before step i: - Acquire the user's spontaneous breathing ability data through physiological signal acquisition module 1.
[0012] Preferably, in step iii, the user's cardiopulmonary follow-up response index is also calculated.
[0013] Preferably, the physiological signal acquisition module 1: - Collect PPG and ECG signals from the wrist or earlobe to extract heart rate and heart rate variability (HRV); - Monitor skin conductivity levels using GSR sensors to reflect sympathetic nerve activity; - Monitoring body activity and posture using accelerometers for motion compensation.
[0014] Preferably, the signal processing and feature extraction module 2 performs filtering and noise reduction preprocessing on the physiological signal and obtains one or more of the following real-time physiological data: - Heartbeat cycle; - Calculate the time-domain and frequency-domain metrics of HRV; - Extract feature data of skin electrical conductance signals.
[0015] Compared with the prior art, the present invention has the following significant advantages: 1. Real-time and continuous: It breaks through the limitations of traditional detection methods that can only be measured at specific points in time and under static conditions, and realizes long-term, dynamic and continuous monitoring of autonomic nerve function. It helps to capture transient or daily activity-related fluctuations in autonomic nerve function and provides more comprehensive data support for health early warning.
[0016] 2. Convenience and Universality: The product adopts a wearable device form factor, which is small in size, comfortable to wear, and easy to operate, requiring no professional medical personnel to use. This allows autonomic nervous system function assessment to extend from professional medical scenarios to everyday environments such as homes and offices, greatly expanding its application scope.
[0017] 3. Rapid Assessment and High Accuracy: By introducing multimodal signal fusion and cardiopulmonary coupling analysis under intelligent respiratory guidance, reliable assessment results can be obtained in a short time. Combined with AI algorithms, the limitations of single physiological parameter analysis are reduced, improving the accuracy and robustness of the assessment.
[0018] 4. Proactive health management: The device's real-time feedback and early warning functions enable users to understand changes in their autonomic nervous system state in a timely manner and take intervention measures (such as rest, relaxation training, or medical consultation) after receiving abnormal prompts, thereby realizing the transformation from passive treatment to proactive prevention.
[0019] 5. Cost-effectiveness: The sensors used in this invention (such as PPG and ECG) are mature and low-cost electronic components, which helps to reduce the overall cost of the device, making the product more competitive in price and promoting its popularization among ordinary consumers.
[0020] The technical solution provided by this invention can guide users in rehabilitation training by actively guiding them in breathing exercises, effectively controlling users' emotions and other indices, thereby achieving better rehabilitation guidance results. The product's lightweight design offers high flexibility in implementation, acceptable cost, and significant application value. Attached Figure Description
[0021] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 A schematic diagram of the structure of a real-time monitoring system for autonomic nervous function according to a first embodiment of the present invention is shown; and Figure 2 The diagram shows a flowchart of a real-time monitoring method for autonomic nervous function according to a first embodiment of the present invention. Detailed Implementation
[0022] To better illustrate the technical solution of the present invention, the present invention will be further described below with reference to the accompanying drawings.
[0023] refer to Figures 1 to 2 The embodiment described illustrates a real-time monitoring system for autonomic nervous function and a corresponding real-time monitoring method provided according to a preferred embodiment of the present invention. Specifically, the real-time monitoring system for autonomic nervous function includes the following modules: The physiological signal acquisition module 1, in a preferred embodiment, integrates an optical volumetric pulse wave (PPG) sensor, an electrocardiogram (ECG) sensor, a skin conductance response (GSR) sensor, and a triaxial accelerometer. It is preferably used to acquire PPG and ECG signals from the wrist or earlobe for extracting heart rate and heart rate variability (HRV); to monitor skin conductance levels through the GSR sensor to reflect sympathetic nerve activity; and to monitor body activity and posture through the accelerometer for motion compensation, etc.
[0024] The signal processing and feature extraction module 2 is implemented using a microcontroller (MCU) and a digital signal processor (DSP). It preferably performs preprocessing such as filtering and denoising on the original physiological signal, accurately identifies the heartbeat cycle (R wave), calculates the time domain index (such as SDNN, RMSSD) and frequency domain index (LF, HF, LF / HF ratio) of HRV, and extracts the features of skin conductance signal, etc.
[0025] The autonomic nervous system function analysis module 3 is implemented using embedded artificial intelligence (AI) algorithms. It is preferably based on multimodal physiological characteristics (such as HRV features and GSR features) and uses a lightweight AI model (such as a machine learning classifier) to analyze the balance of the autonomic nervous system (sympathetic / parasympathetic nerve activity balance) in real time to identify whether there is a tendency for functional disorder.
[0026] The data communication and display module 4 is preferably implemented using Bluetooth Low Energy (BLE), a miniature display screen, or a mobile APP. It preferably wirelessly transmits the processed data and evaluation results to a smartphone APP or cloud server for further analysis, storage, and visualization. The device itself can also provide simple status feedback through a miniature display screen or LED indicator lights.
[0027] The intelligent guidance and feedback module 5 preferably employs a miniature vibration motor and a voice prompt unit to guide users in performing standardized short tests (such as taking deep breaths according to instructions) to ensure the standardization of data collection and the accuracy of evaluation results; and provides user-friendly reminders when significant abnormalities are detected.
[0028] Furthermore, in a preferred embodiment, the real-time monitoring system for autonomic nervous function provided by the present invention can be implemented through the following approach: the physiological signal acquisition module 1 is a sensor array; the signal processing and feature extraction module 2 is an embedded processor; the autonomic nervous function analysis module 3 preferably employs an AI algorithm; the data communication and display module 4 is a wireless transmission and interactive interface; and the intelligent guidance and feedback module 5 serves to guide users and provide early warnings, etc.
[0029] Further, refer to Figure 2 In the illustrated embodiment, in a preferred embodiment, the workflow of the monitoring method provided by the present invention is as follows: Step 1. Signal Acquisition: After the user puts on the device, the system automatically or upon instruction initiates physiological signal acquisition. Optical sensors and electrodes continuously acquire PPG and ECG signals, while the accelerometer simultaneously records the user's activity status.
[0030] Step 2. Signal Preprocessing and Feature Extraction: The signal processing module performs quality assessment and filtering on the raw signal to remove interference such as motion artifacts. Then, it accurately calculates the heart rate and extracts various feature parameters of HRV (such as SDNN, LF / HF, etc.).
[0031] Step 3. State Analysis and Assessment: The autonomic nervous function analysis module 3 inputs the extracted multidimensional features into a pre-trained lightweight AI model. This model can integrate multiple parameters such as HRV and GSR to output an assessment result of the current autonomic nervous balance state, such as sympathetic nerve activity level, parasympathetic nerve activity level, and balance score. To achieve rapid assessment, the system also introduces cardiopulmonary coupling analysis under intelligent breathing guidance. The device can guide the user to breathe at a specific rhythm (such as long inhalation and short exhalation, short inhalation and long exhalation), and by analyzing the coupling relationship between the respiratory cycle and heart rate fluctuations (such as cardiopulmonary follow-up response index and cardiopulmonary coupling strength), quantitative assessment of autonomic nervous function can be achieved in a short time (such as 1-2 minutes).
[0032] Step 4. Results Output and Feedback: The analysis results are transmitted to a mobile app via Bluetooth, displaying the historical trends of autonomic nervous system function in intuitive formats such as charts. When the system detects an abnormal state that significantly deviates from the normal range (such as excessive sympathetic nerve excitation), it can alert the user via device vibration or app notification.
[0033] Please refer to the above for further details. Figure 1 , Figure 2 As shown in the embodiment, the hardware of this product can be specifically implemented as a wristband or ear clip device. The wristband integrates a PPG sensor (for monitoring heart rate), a GSR sensor, and an accelerometer. The back of the wristband also has contact electrodes for acquiring ECG signals; when the user touches the electrodes with their finger, a circuit is formed, recording the electrocardiogram signal. The device's main control chip uses a low-power microcontroller to handle signal processing and control logic. The evaluation model can be embedded in the device or the raw data or pre-processed features can be transmitted to a mobile app for more complex calculations.
[0034] On the software side, a smartphone app is responsible for receiving, storing, and visualizing data, providing a user-friendly interface. The app can display real-time assessment results of autonomic nervous system function (such as balance scores), historical trend graphs, and manage personalized intelligent breathing training programs. Cloud servers can be used to store longer-term data and leverage more powerful computing resources for in-depth analysis and model optimization.
[0035] In a typical application scenario, the device passively and continuously monitors the background while the user wears it daily. When the user wishes to perform a quick assessment, they can open the app and activate the "Quick Detection" mode. The device will guide the user through approximately two minutes of standardized breathing exercises via vibration and screen animation. The system will collect physiological signals during this process and use a cardiopulmonary coupling analysis algorithm to generate a report containing an autonomic nervous system balance score and a brief interpretation within a short time. If a sustained increase in sympathetic nervous system excitation is detected (potentially related to chronic stress), the system will send health suggestions to the user via the app, such as reminding the user to perform relaxation exercises.
[0036] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a wearable product capable of real-time, non-invasive, and continuous monitoring of autonomic nervous system function. This product aims to achieve the following objectives: 1. Provides a lightweight and comfortable wearable form, suitable for long-term wear.
[0037] 2. Integrates multiple physiological signal sensors to achieve synchronous acquisition of multimodal physiological parameters.
[0038] 3. Advanced signal processing and feature extraction algorithms are used to achieve rapid and accurate assessment of autonomic nervous system function.
[0039] 4. It has a real-time feedback function and can provide early warnings or health advice to users or medical staff based on monitoring results.
[0040] 5. Reduce equipment costs to make it suitable for daily health management scenarios such as homes and communities.
[0041] The core innovation of this invention lies in its integration of multimodal physiological signals and intelligent guided assessment, enabling rapid and accurate assessment of autonomic nervous function. For example: (1) Multi-parameter fusion autonomic nervous system assessment model: Traditional HRV analysis is susceptible to the instability of single physiological signals. This invention innovatively combines HRV analysis with skin conductance response and postural activity information. By fusing multi-dimensional features through algorithms, a more robust assessment model is constructed, which can more accurately distinguish the activity state of the sympathetic and parasympathetic nervous systems and reduce the risk of misjudgment.
[0042] (2) Cardiopulmonary coupling analysis based on intelligent breathing guidance: Due to the limitation that HRV analysis usually requires a long period of resting data, this invention introduces an intelligent breathing test and guidance module. This module first adaptively measures the user's breathing capacity (such as maximum uniform inhalation / exhalation time) and formulates a personalized breathing rhythm (such as long inhalation and short exhalation, short inhalation and long exhalation). Then, the system guides the user to follow this rhythm through voice or vibration. During this period, the system performs spectral analysis and causal analysis on the heart rate signal to calculate the cardiopulmonary follow-up response index and cardiopulmonary coupling strength under specific breathing patterns. These indicators are highly correlated with the balance and activity of the autonomic nervous system and can achieve quantitative assessment of autonomic nervous system function in a short time (such as a breathing training cycle, about 1-2 minutes), which is particularly suitable for daily rapid screening.
[0043] (3) Lightweight embedded AI algorithm: To enable complex autonomic neural function assessment models to run on resource-constrained wearable devices, this invention employs optimized lightweight machine learning algorithms (such as decision trees, random forests, or simple neural networks). The model is trained on the cloud using large-scale clinical data and then deployed to the device to achieve localized real-time data processing, which protects user privacy and reduces device power consumption.
[0044] The specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various modifications or variations within the scope of the claims, which do not affect the essence of the present invention.
Claims
1. A real-time monitoring system for autonomic nervous function, comprising: The signal processing and feature extraction module (2) is used to preprocess the physiological signals acquired by the physiological signal acquisition module (1) to obtain real-time physiological data. The data communication and display module (4) is used to transmit the data and / or evaluation results processed by the monitoring system to the display device or the back-end system; Its characteristic is that it further includes at least: The intelligent guidance and feedback module (5) is used to guide the user to perform a standardized short test. The intelligent guidance and feedback module (5) includes a micro vibration motor and / or a voice prompt unit for issuing the prompt information in a vibration manner and / or voice prompt to guide the user to perform the standardized short test. The autonomic nervous system function analysis module (3) is used to analyze the real-time physiological data in real time through a lightweight AI model to determine whether there is a tendency for autonomic nervous system dysfunction. The physiological signal acquisition module (1) is a wearable device that is placed on the user's wrist or earlobe. The physiological signal acquisition module (1) integrates a PPG sensor (for monitoring heart rate), a GSR sensor, and an accelerometer.
2. A real-time monitoring method for the autonomic nervous function real-time monitoring system according to claim 1, characterized in that, Includes the following steps: i. Guide users through standardized breathing exercises using vibration and / or screen animations; ii. Collect the user's physiological signals during step i; iii. Use AI algorithms to calculate the user's cardiopulmonary coupling strength index to determine whether the user's autonomic nervous system has a tendency to be dysfunctional; iv. If a sustained increase in sympathetic nerve excitation is detected, health advice will be sent to the user via vibration and / or voice prompts.
3. The real-time monitoring method according to claim 2, characterized in that, Step i includes any one or more of the following steps: - Uses rhythmic vibrations to guide users through long inhale and short exhale training; - Use rhythmic vibrations to guide users through short inhales and long exhales.
4. The real-time monitoring method according to claim 3, characterized in that, The following steps are included before step i: - Acquire the user's spontaneous breathing ability data through the physiological signal acquisition module (1).
5. The real-time monitoring method according to any one of claims 2 to 4, characterized in that, In step iii, the user's cardiopulmonary follow-up response index is also calculated.
6. The monitoring system according to claim 1 and / or the real-time monitoring method according to any one of claims 2 to 5, characterized in that, The physiological signal acquisition module (1): - Collect PPG and ECG signals from the wrist or earlobe to extract heart rate and heart rate variability (HRV). - Monitor skin conductivity levels using GSR sensors to reflect sympathetic nerve activity; - Monitoring body activity and posture using accelerometers for motion compensation.
7. The monitoring system and / or real-time monitoring method according to claim 6, characterized in that, The signal processing and feature extraction module (2) performs filtering and noise reduction preprocessing on the physiological signal and obtains one or more of the following real-time physiological data: - Heartbeat cycle; - Calculate the time-domain and frequency-domain metrics of HRV; - Extract feature data of skin electrical conductance signals.