An electroacupuncture terminal that reduces interference with electrocardiogram monitoring

By using an intelligent ECG signal processing module and opto-isolated output circuit, combined with deep learning and high-frequency anti-interference shielding, the problems of ECG monitoring interference and arrhythmia in traditional electroacupuncture devices during the perioperative period are solved, thus achieving the safety and stability of electroacupuncture treatment.

CN123058744APending Publication Date: 2026-11-10GUANGZHOU HOSPITAL OF TRADITIONAL CHINESE MEDICINE
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202611165463.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-03
Publication Date
2026-11-10

AI Technical Summary

Technical Problem

Traditional electroacupuncture devices pose risks of interference with electrocardiogram monitoring, fixed arrhythmias, and insufficient tolerance to external electromagnetic interference during the perioperative period, which seriously affect clinical safety.

Method used

It employs an intelligent ECG signal processing module, integrating a deep learning inference unit and a pulse artifact suppression unit, to accurately predict the onset of the T wave, limit the safety window, and avoid vulnerable periods. Combined with an opto-isolated output circuit and a high-frequency anti-interference shielding structure, it forms a closed-loop control.

Benefits of technology

It effectively eliminates interference artifacts in electrocardiogram monitoring, prevents arrhythmias, ensures the safety and stability of electroacupuncture treatment, and adapts to the complex perioperative environment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123058744A_ABST
    Figure CN123058744A_ABST
Patent Text Reader

Abstract

This invention relates to the technical field of medical devices, and in particular to an electroacupuncture terminal for reducing interference in electrocardiogram (ECG) monitoring, comprising: an intelligent ECG signal processing module, a gating logic control module, a pulse generation module, and an opto-isolated output circuit; its safety window is strictly limited to the absolute refractory period of the ventricle, with the accurately predicted T-wave initiation as the shut-off point, never intruding into the vulnerable period; the pulse is only delivered in the ST segment isoelectric range, actively avoiding QRS waves and T waves, eliminating interference artifacts at the source; the intelligent ECG signal processing module has a built-in pulse artifact suppression unit, which can actively eliminate the interference of its own pulse on the ECG analysis circuit, prevent gating logic disorder, and form a stable closed-loop control; using a deep learning inference unit, it can still accurately detect R waves and predict T-wave initiation even in the event of arrhythmia or waveform variations, achieving a truly individualized, dynamically accurate safety window.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the technical field of medical devices, and in particular to an electroacupuncture terminal that reduces interference with electrocardiogram monitoring. Background Technology

[0002] Electroacupuncture, a medical technique combining traditional acupuncture with modern electrical stimulation, is increasingly widely used in the perioperative period. Examples include an electroacupuncture treatment system based on acupuncture point impedance disclosed in patent application CN107233664B, and an electroacupuncture system, its electroacupuncture needle, and terminal controller disclosed in patent application CN103170058B. Its applications include preoperative sedation, intraoperative analgesia, reducing anesthetic drug dosage, and preventing postoperative nausea and vomiting. In clinical practice, the electroacupuncture device outputs pulsed currents of specific frequency and intensity to the body through the needle handle inserted into the acupuncture point to stimulate Qi and regulate physiological functions. However, in the complex operating room environment, traditional electroacupuncture devices and existing electroacupuncture systems still face several interconnected and insurmountable technical bottlenecks, severely restricting their safe application in the perioperative period.

[0003] First, interference with ECG monitoring is a significant issue. The milliampere-level pulsed current output by the electroacupuncture device is conducted to the ECG monitoring electrodes on the body surface via the body's volumetric conductivity effect. Because electroacupuncture pulses typically have high-frequency and high-voltage characteristics, they create high-amplitude common-mode or differential-mode interference in the ECG signal acquisition circuit after being applied to the body, ultimately manifesting as dense, spike-like artifacts on the ECG waveform. These artifacts are sufficient to mask the true QRS complex and ST segment morphology, leading to frequent false alarms from the ECG monitor. This severely interferes with the anesthesiologist's accurate assessment of the patient's cardiac electrical activity and myocardial ischemia, posing a significant clinical safety hazard.

[0004] Secondly, there is a fixed risk of inducing cardiac arrhythmias. The output pulse frequency of traditional electroacupuncture devices is usually an independently set fixed value, completely detached from the heart's inherent sinus rhythm and cardiac cycle. This means that strong electroacupuncture stimulation pulses may randomly fall during the ventricular repolarization process, especially during the vulnerable period of the ventricle. According to the principles of electrophysiology, applying additional electrical stimulation during the vulnerable period can easily induce ventricular tachycardia or even ventricular fibrillation, which is particularly dangerous for perioperative patients with organic heart disease, electrolyte imbalance, or unstable cardiac electrical activity.

[0005] Furthermore, there is insufficient tolerance to external electromagnetic interference. High-frequency electrosurgical units and bipolar electrocoagulation devices are frequently used during these procedures. These devices radiate strong electromagnetic energy into the space and can cause conducted interference through power lines and ground wires. The control circuits of traditional electroacupuncture devices are often poorly designed to protect against high-intensity radiofrequency interference, easily leading to malfunctions such as control circuit crashes, parameter drift, or uncontrolled output pulses. This can result in treatment interruptions or, in severe cases, accidental injury to the patient.

[0006] Therefore, there is an urgent need for an electroacupuncture terminal that reduces interference with electrocardiogram monitoring and improves the above-mentioned problems. Summary of the Invention

[0007] To address the aforementioned technical problems, this invention provides an electroacupuncture terminal that strictly limits the safety window to the absolute refractory period of the ventricle, using the accurately predicted T-wave initiation as the closing point, and never intrudes into the vulnerable period; the pulse is only delivered in the ST segment isoelectric range, actively avoiding QRS waves and T waves, eliminating interference artifacts at the source; the ECG signal intelligent processing module has a built-in pulse artifact suppression unit that can actively eliminate the interference of its own pulse on the ECG analysis circuit, prevent gating logic disorder, and form a stable closed-loop control; utilizing a deep learning inference unit, it can still accurately detect R waves and predict T-wave initiation even in the event of arrhythmia or waveform variations, achieving a truly individualized, dynamically accurate safety window to reduce ECG monitoring interference.

[0008] An electroacupuncture terminal for reducing interference with electrocardiogram monitoring according to the present invention includes:

[0009] ECG signal intelligent processing module:

[0010] It is used to receive external electrocardiogram signals and integrates a deep learning inference unit and a pulse artifact suppression unit.

[0011] The deep learning inference unit is equipped with a pre-trained neural network model for real-time analysis of ECG signals and outputs at least the R-wave trigger signal and the predicted T-wave onset signal.

[0012] The pulse artifact suppression unit is used to actively eliminate the interference of pulse artifacts on ECG signal analysis during electroacupuncture pulse delivery;

[0013] Gating logic control module:

[0014] Connected to the ECG signal intelligent processing module, it is used to determine a safe stimulation window within the absolute refractory period of the ventricle based on the R-wave trigger signal and the predicted T-wave onset time signal, and outputs an enable signal only within the safe stimulation window;

[0015] Pulse generation module:

[0016] It is connected to the gated logic control module and generates a low-voltage needle pulse control signal only when the enable signal is received;

[0017] Opto-isolated output circuit:

[0018] Includes high-speed optocouplers and high-voltage boost circuits;

[0019] The low-voltage electroacupuncture pulse control signal is driven by a high-voltage boost circuit after a high-speed optocoupler to generate the electroacupuncture output pulse;

[0020] The power ground of the control motherboard where the pulse generation module is located is electrically isolated from the power ground of the output channel where the high voltage boost circuit is located.

[0021] The safety window is strictly limited to the absolute refractory period of the ventricle, with the precise prediction of the T wave initiation as the closing point, never intruding into the vulnerable period; the pulse is only delivered in the ST segment isoelectric range, actively avoiding the QRS wave and T wave, eliminating interference artifacts at the source; the ECG signal intelligent processing module has a built-in pulse artifact suppression unit, which can actively eliminate the interference of its own pulse on the ECG analysis circuit, prevent gating logic disorder, and form a stable closed-loop control; using a deep learning inference unit, it can still accurately detect the R wave and predict the T wave initiation in the event of arrhythmia and waveform variation, achieving a truly individualized, dynamically accurate safety window.

[0022] Preferably, the safe stimulation window is defined as:

[0023] W S =[T R +Δ t1 ,T R +Δ t2 ];

[0024] Among them, W S For a safe stimulation window, T R At the peak of the R-wave, Δ t1 Set to 50 milliseconds after the R-wave peak, Δ t2 The timing is determined by the predicted T-wave onset signal to ensure that the stimulation pulse terminates strictly before the T-wave.

[0025] Preferably, Δ t2 The value is specifically the predicted T-wave onset time minus a preset safety margin. The safety margin is determined based on the statistical distribution of the model prediction error to ensure that the window does not intrude into the T-wave.

[0026] Preferably, the neural network model deployed within the deep learning inference unit includes:

[0027] An R-wave detection model based on a one-dimensional convolutional neural network is used to scan ECG data streams in real time to identify the peak time of the R-wave.

[0028] The T-wave onset prediction model based on temporal convolutional networks uses current and historical ECG signal features as input to predict the T-wave onset time of the current cardiac cycle.

[0029] Preferably, during the electroacupuncture pulse delivery, the pulse artifact suppression unit modifies the data labeling state of the corresponding time period in the input feature vector of the deep learning inference unit, so that the neural network model automatically ignores the pulse artifact period during time series inference, thereby avoiding misjudging it as an R-wave.

[0030] Preferably, the ECG signal intelligent processing module receives analog ECG signals from the anesthesia monitor via a wired interface or a wireless Bluetooth module.

[0031] Preferably, it also includes a high-frequency anti-interference shielding structure, which specifically consists of an aluminum alloy shielding shell, an output wire, and a ferrite magnetic ring. The ferrite magnetic ring is installed on the output wire, and the output wire adopts a double shielding structure. The circuit board inside the terminal is installed on the aluminum alloy shielding shell, and then the aluminum alloy shielding shell, together with the output wire and the ferrite magnetic ring, prevents the terminal from being interfered with.

[0032] Preferably, the aluminum alloy shielding shell includes an aluminum alloy shielding shell body and an aluminum alloy shielding shell cover. The top of the aluminum alloy shielding shell body is provided with a slide rail, the top of the aluminum alloy shielding shell cover is provided with a slide groove, and the side end of the aluminum alloy shielding shell body is provided with a threaded hole, and the side end of the aluminum alloy shielding shell cover is provided with a locking bolt. The circuit board inside the terminal is installed in the aluminum alloy shielding shell body, and then the aluminum alloy shielding shell cover is slidably installed on the aluminum alloy shielding shell body, so that the aluminum alloy shielding shell body and the aluminum alloy shielding shell cover cooperate to protect the circuit board. Then, the bolt is screwed into the aluminum alloy shielding shell body to lock the aluminum alloy shielding shell body and the aluminum alloy shielding shell cover together.

[0033] Preferably, the deep learning inference unit is deployed in the embedded neural network processor hardware acceleration unit of the terminal.

[0034] Preferably, the electroacupuncture output terminal is used in the perioperative environment and coexists with high-frequency electrosurgical unit and electrocardiogram monitor.

[0035] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0036] 1. The safety window is strictly limited to the absolute refractory period of the ventricle, with the precise prediction of the T wave initiation as the closing point, and will never invade the vulnerable period;

[0037] 2. The pulse is only emitted in the ST segment equipotential segment, actively avoiding QRS waves and T waves, thus eliminating interference artifacts at the source;

[0038] 3. The ECG signal intelligent processing module has a built-in pulse artifact suppression unit, which can actively eliminate the interference of its own pulse on the ECG analysis circuit, prevent the gating logic from being disordered, and form a stable closed-loop control.

[0039] 4. Utilizing deep learning inference units, it can still accurately detect R waves and predict T wave initiation even in cases of arrhythmia and waveform variations, achieving a truly individualized, dynamically accurate safety window. Attached Figure Description

[0040] Figure 1 This is a schematic diagram of the electroacupuncture terminal for reducing interference in electrocardiogram monitoring according to the present invention;

[0041] Figure 2 This is an isometric structural diagram of the aluminum alloy shielding shell of the present invention;

[0042] Figure 3 This is a schematic diagram of the structure of the aluminum alloy shielding shell body of the present invention;

[0043] Figure 4 This is a schematic diagram of the structure of the aluminum alloy shielding shell cover of the present invention;

[0044] Figure 5 This is a schematic diagram of the structure of the aluminum alloy shielding shell of the present invention after it is tightly closed;

[0045] Figure 6 This is a schematic diagram of the output wire and ferrite magnetic ring of the present invention.

[0046] The following are labels in the attached diagram: 1. Output wire; 2. Ferrite ring; 3. Aluminum alloy shielding shell body; 4. Aluminum alloy shielding shell cover. Detailed Implementation

[0047] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. The present invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0048] like Figures 1 to 6 As shown, an electroacupuncture terminal for reducing interference with electrocardiogram monitoring includes:

[0049] ECG signal intelligent processing module:

[0050] It is used to receive external electrocardiogram signals and integrates a deep learning inference unit and a pulse artifact suppression unit.

[0051] The deep learning inference unit is equipped with a pre-trained neural network model for real-time analysis of ECG signals and outputs at least the R-wave trigger signal and the predicted T-wave onset signal.

[0052] The pulse artifact suppression unit is used to actively eliminate the interference of pulse artifacts on ECG signal analysis during electroacupuncture pulse delivery;

[0053] Gating logic control module:

[0054] Connected to the ECG signal intelligent processing module, it is used to determine a safe stimulation window within the absolute refractory period of the ventricle based on the R-wave trigger signal and the predicted T-wave onset time signal, and outputs an enable signal only within the safe stimulation window;

[0055] Pulse generation module:

[0056] It is connected to the gated logic control module and generates a low-voltage needle pulse control signal only when the enable signal is received;

[0057] Opto-isolated output circuit:

[0058] Includes high-speed optocouplers and high-voltage boost circuits;

[0059] The low-voltage electroacupuncture pulse control signal is driven by a high-voltage boost circuit after a high-speed optocoupler to generate the electroacupuncture output pulse;

[0060] The power ground of the control motherboard where the pulse generation module is located is electrically isolated from the power ground of the output channel where the high voltage boost circuit is located.

[0061] The safe stimulation window is defined as:

[0062] W S =[T R +Δ t1 ,T R +Δ t2 ];

[0063] Among them, W S For a safe stimulation window, T R At the peak of the R-wave, Δ t1 Set to 50 milliseconds after the R-wave peak, Δ t2 The timing is determined by the predicted T-wave onset signal to ensure that the stimulation pulse terminates strictly before the T-wave.

[0064] Δ t2 The value is specifically the predicted T-wave onset time minus a preset safety margin. The safety margin is determined based on the statistical distribution of the model prediction error to ensure that the window does not intrude into the T-wave.

[0065] The neural network models deployed within the deep learning inference unit include:

[0066] An R-wave detection model based on a one-dimensional convolutional neural network is used to scan ECG data streams in real time to identify the peak time of the R-wave.

[0067] The T-wave onset prediction model based on temporal convolutional networks uses current and historical ECG signal features as input to predict the T-wave onset time of the current cardiac cycle.

[0068] During the electroacupuncture pulse delivery, the pulse artifact suppression unit modifies the data labeling state of the corresponding time period in the input feature vector of the deep learning inference unit, so that the neural network model can automatically ignore the pulse artifact period during time series inference, thereby avoiding misjudging it as an R wave.

[0069] The ECG signal intelligent processing module receives analog ECG signals from the anesthesia monitor via a wired interface or a wireless Bluetooth module.

[0070] It also includes a high-frequency anti-interference shielding structure, which specifically consists of an aluminum alloy shielding shell, an output wire 1, and a ferrite magnetic ring 2. The ferrite magnetic ring 2 is installed on the output wire 1, and the output wire 1 adopts a double shielding structure.

[0071] The aluminum alloy shielding shell includes an aluminum alloy shielding shell body 3 and an aluminum alloy shielding shell cover 4. The top of the aluminum alloy shielding shell body 3 is provided with a slide rail, the top of the aluminum alloy shielding shell cover 4 is provided with a slide groove, and the side end of the aluminum alloy shielding shell body 3 is provided with a threaded hole, and the side end of the aluminum alloy shielding shell cover 4 is provided with a locking bolt.

[0072] The deep learning inference unit is deployed in the embedded neural network processor hardware acceleration unit of the terminal;

[0073] The electroacupuncture output terminal is used in the perioperative environment and coexists with high-frequency electrosurgical units and electrocardiogram monitors.

[0074] Example:

[0075] This invention consists of four core modules: an intelligent ECG signal processing module, a gating logic control module, a pulse generation module, and an opto-isolated output circuit. These four modules are connected through precise signal and control flows to form a closed-loop feedback system.

[0076] The intelligent ECG signal processing module is responsible for sensing, analyzing, and making decisions about external signals. At the hardware level, it is based on a microcontroller with an integrated embedded neural network processor, supplemented by a high-precision analog-to-digital converter, a power management unit, and a communication interface. This module receives ECG signals from the "ECG analog output" BNC port of the bedside anesthesia monitor through a wired analog interface with electrostatic protection and common-mode rejection. After buffering, filtering, and gain adjustment, this signal is converted into a digital signal stream by the high-precision analog-to-digital converter at a sampling rate of 500Hz or higher. This digital signal stream is divided into two paths: one path enters the deep learning inference unit for neural network inference; the other path serves as raw data for the subsequent pulse artifact suppression unit for synchronous processing.

[0077] The deep learning inference unit is the core of this module. It loads two trained neural network models that have been quantized by INT8 to accelerate inference in the firmware of the embedded neural network processor.

[0078] The first model is an R-wave detection model based on a one-dimensional convolutional neural network. The network structure consists of multiple alternating one-dimensional convolutional layers, batch normalization layers, activation function layers, and max-pooling layers, finally outputting the classification result through a fully connected layer. It is designed as a sliding window classifier, scanning the input ECG data stream point by point. For each signal segment within the window, the model calculates the probability that it belongs to an "R-wave peak." When the probability exceeds a set threshold (e.g., 0.95) and the refractory period constraint is met (i.e., more than 200 ms since the last detected R-wave), the model immediately outputs a sharp R-wave trigger signal and precisely records the absolute timestamp T of the R-wave peak. R The training dataset for this model includes hundreds of thousands of single-lead ECG recordings from public databases and clinical collections, containing various arrhythmias, noise interference, and waveform variations, ensuring its high sensitivity and specificity under complex conditions.

[0079] The second model is a T-wave initiation prediction model based on temporal convolutional networks. Temporal convolutional networks, by introducing causal convolution, dilated convolution, and residual connections, can efficiently capture extremely long-range temporal dependencies in a sequence in a non-recursive manner. They are also computationally efficient and well-suited for real-time processing. When the R-wave detection model outputs T... R At the instant of the signal, using current and historical ECG characteristics as input, forward inference is used to predict the T wave onset time T. onse For absolute safety, the actual system usage is Δt2 = T. onset With a safety margin of 15ms, the total inference time is controlled within 2ms.

[0080] The pulse artifact suppression unit solves the problem of "iatrogenic self-interference". When the gating logic control module decides to issue a pulse and output an enable signal, the enable signal is simultaneously sent to the pulse artifact suppression unit as a trigger. During the pulse issuance period (defined as a time interval including the pulse duration and its small extensions before and after), this unit does not modify the acquired raw ECG data. Instead, it operates on a mask marker vector that is completely synchronized with the ECG data stream. Each element of this vector corresponds to an ECG sampling point. Normally, it is "0", but during the pulse issuance period, it is set to "1" in real time to indicate "interference". When the deep learning inference unit processes the input feature vector, it reads this mask vector synchronously. Its internal attention mechanism is guided to automatically ignore the time period marked as "1". The calculation of its output probability depends almost entirely on the signal segment that is not disturbed in the context. When the pulse issuance ends, the mask vector returns to "0", and the model immediately resumes normal full signal analysis. This mechanism ingeniously realizes "interference self-identification" and "interference self-immunity", preventing the pulse peak from being mistakenly detected as a new R wave, thereby ensuring the long-term correct operation of the gating logic.

[0081] The gated logic control module receives T R and T onset After the signal, calculate the safety window W. S Control the hardware timer at W S An enable signal is output within the window, which triggers a low-voltage pulse generated by the pulse generation module. This pulse is then driven by a high-speed optocoupler to drive a high-voltage boost circuit, and finally output to the needle electrode via a double-shielded cable.

[0082] The main functions achieved by this invention are:

[0083] 1. The safety window is strictly limited to the absolute refractory period of the ventricle, with the precise prediction of the T wave initiation as the closing point, and will never invade the vulnerable period;

[0084] 2. The pulse is only emitted in the ST segment equipotential segment, actively avoiding QRS waves and T waves, thus eliminating interference artifacts at the source;

[0085] 3. The ECG signal intelligent processing module has a built-in pulse artifact suppression unit, which can actively eliminate the interference of its own pulse on the ECG analysis circuit, prevent the gating logic from being disordered, and form a stable closed-loop control.

[0086] 4. Utilizing deep learning inference units, it can still accurately detect R waves and predict T wave onset even in cases of arrhythmia and waveform variations, achieving a truly individualized, dynamically accurate safety window.

[0087] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. An electroacupuncture terminal for reducing interference with electrocardiogram monitoring, characterized in that, include: ECG signal intelligent processing module: It is used to receive external electrocardiogram signals and integrates a deep learning inference unit and a pulse artifact suppression unit. The deep learning inference unit is equipped with a pre-trained neural network model for real-time analysis of ECG signals and outputs at least the R-wave trigger signal and the predicted T-wave onset signal. The pulse artifact suppression unit is used to actively eliminate the interference of pulse artifacts on ECG signal analysis during electroacupuncture pulse delivery; Gating logic control module: Connected to the ECG signal intelligent processing module, it is used to determine a safe stimulation window within the absolute refractory period of the ventricle based on the R-wave trigger signal and the predicted T-wave onset time signal, and outputs an enable signal only within the safe stimulation window; Pulse generation module: It is connected to the gated logic control module and generates a low-voltage needle pulse control signal only when the enable signal is received; Opto-isolated output circuit: Including high-speed optocouplers and high-voltage boost circuits; The low-voltage electroacupuncture pulse control signal is driven by a high-voltage boost circuit after a high-speed optocoupler to generate the electroacupuncture output pulse; The power ground of the control motherboard where the pulse generation module is located is electrically isolated from the power ground of the output channel where the high-voltage boost circuit is located.

2. The electroacupuncture terminal for reducing interference with electrocardiogram monitoring as described in claim 1, characterized in that, The safe stimulation window is defined as: W S =[T R +D t1 ,T R +D t2 ]; Among them, W S For a safe stimulation window, T R At the peak of the R-wave, Δ t1 Set to 50 milliseconds after the R-wave peak, Δ t2 The timing is determined by the predicted T-wave onset signal to ensure that the stimulation pulse terminates strictly before the T-wave.

3. The electroacupuncture terminal for reducing interference with electrocardiogram monitoring as described in claim 2, characterized in that, Δ t2 The value is specifically the predicted T-wave onset time minus a preset safety margin. The safety margin is determined based on the statistical distribution of the model prediction error to ensure that the window does not intrude into the T-wave.

4. The electroacupuncture terminal for reducing interference with electrocardiogram monitoring as described in claim 1, characterized in that, The neural network models deployed within the deep learning inference unit include: An R-wave detection model based on a one-dimensional convolutional neural network is used to scan ECG data streams in real time to identify the peak time of the R-wave. The T-wave onset prediction model based on temporal convolutional networks uses current and historical ECG signal features as input to predict the T-wave onset time of the current cardiac cycle.

5. The electroacupuncture terminal for reducing interference with electrocardiogram monitoring as described in claim 1, characterized in that, During the electroacupuncture pulse delivery, the pulse artifact suppression unit modifies the data labeling state of the corresponding time period in the input feature vector of the deep learning inference unit, so that the neural network model can automatically ignore the pulse artifact period during time series inference, thereby avoiding misjudging it as an R wave.

6. The electroacupuncture terminal for reducing interference with electrocardiogram monitoring as described in claim 1, characterized in that, The ECG signal intelligent processing module receives analog ECG signals from the anesthesia monitor via a wired interface or a wireless Bluetooth module.

7. The electroacupuncture terminal for reducing interference with electrocardiogram monitoring as described in claim 1, characterized in that, It also includes a high-frequency anti-interference shielding structure, which is specifically composed of an aluminum alloy shielding shell, an output wire (1) and a ferrite magnetic ring (2). The ferrite magnetic ring (2) is installed on the output wire (1), and the output wire (1) adopts a double shielding structure.

8. The electroacupuncture terminal for reducing interference with electrocardiogram monitoring as described in claim 7, characterized in that, The aluminum alloy shielding shell includes an aluminum alloy shielding shell body (3) and an aluminum alloy shielding shell cover (4). The top of the aluminum alloy shielding shell body (3) is provided with a slide rail, the top of the aluminum alloy shielding shell cover (4) is provided with a slide groove, and the side end of the aluminum alloy shielding shell body (3) is provided with a threaded hole, and the side end of the aluminum alloy shielding shell cover (4) is provided with a locking bolt.

9. The electroacupuncture terminal for reducing interference with electrocardiogram monitoring as described in claim 1, characterized in that, The deep learning inference unit is deployed in the embedded neural network processor hardware acceleration unit of the terminal.

10. The electroacupuncture terminal for reducing interference with electrocardiogram monitoring as described in claim 1, characterized in that, The electroacupuncture output terminal is used in the perioperative environment and coexists with high-frequency electrosurgical units and electrocardiogram monitors.

Citation Information

Patent Citations

  • Electric needle system and electric needle and terminal controller thereof

    CN103170058B

  • An electroacupuncture therapy system based on acupuncture point impedance

    CN107233664B