Monitoring methods and equipment

By acquiring the previous and current segments of physiological signals from the monitoring device and performing recursive processing in conjunction with the model state, the problem of insufficient effectiveness of monitoring information in existing technologies is solved, and more reliable monitoring information output is achieved.

CN117642115BActive Publication Date: 2026-11-17SHENZHEN MINDRAY BIO MEDICAL ELECTRONICS CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202180100550.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-11-30
Publication Date
2026-11-17
Estimated Expiration
2041-11-30

AI Technical Summary

Technical Problem

The artificial intelligence models of existing monitoring devices can only capture the features of current data fragments and lack the use of historical data, resulting in insufficient effectiveness of monitoring information.

Method used

By acquiring the previous and current physiological signal segments and combining them with the previous model state, the data is input into the monitoring model to output the current analysis results and model state, thus achieving recursive information processing.

Benefits of technology

It improves the effectiveness of monitoring information by combining historical and current information to provide more reliable and effective monitoring information.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117642115B_ABST
    Figure CN117642115B_ABST
Patent Text Reader

Abstract

A monitoring method and device (100) are disclosed. The monitoring method includes: acquiring physiological signals, including a previous physiological signal segment and a current physiological signal segment, wherein the previous physiological signal segment corresponds to a previous analysis result and a previous model state output by a monitoring model (S301); inputting the previous model state and the current physiological signal segment into a monitoring model to output the current analysis result and the current model state corresponding to the current physiological signal segment (S302); and outputting monitoring information based on the previous analysis result and the current analysis result (S303). Since the output monitoring information depends not only on the current physiological signal but also on historical physiological signals, the effectiveness of the monitoring information is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of medical device technology, specifically to a monitoring method and device. Background Technology

[0002] Monitoring equipment can provide medical staff with monitoring data representing the patient's vital signs, enabling clinicians to grasp changes in the patient's condition more comprehensively, intuitively, and promptly. This provides an important basis for formulating treatment plans and carrying out emergency treatments, thereby achieving the best treatment results. Therefore, it is widely used in hospital intensive care units (ICUs), coronary care units (CCUs), anesthesia and operating rooms, and related clinical departments.

[0003] With the rapid development of artificial intelligence (AI) technology, deep neural network-based AI models have been gradually applied to monitoring equipment. Existing AI models for monitoring equipment typically divide continuous data into isolated data segments and process them using a segment analysis model. This means that the model is trained using isolated data segments, and there is no information transfer between prediction processes; it can only capture the features contained in the current data segment. However, in clinical applications, monitoring equipment needs to capture not only the features contained in the current data segment but also the features contained in historical data. Taking atrial fibrillation detection as an example, it is necessary not only to identify whether the current data segment contains F waves but also to analyze historical data to determine whether the current electrocardiographic rhythm is normal. Therefore, the effectiveness of the monitoring information output by existing AI-based monitoring equipment needs to be improved. Invention Overview

[0005] Technical issues

[0006] This invention mainly provides a monitoring method and device to improve the effectiveness of monitoring information output by the monitoring device.

[0007] Solution to the problem

[0008] Technical solutions

[0009] According to the first aspect, one embodiment provides a monitoring method, comprising:

[0010] Acquire physiological signals, which include the previous physiological signal segment and the current physiological signal segment, wherein the previous physiological signal segment corresponds to the previous analysis result and the previous model state output by the monitoring model;

[0011] Input the previous model state and the current physiological signal segment into the monitoring model to output the current analysis result and the current model state corresponding to the current physiological signal segment;

[0012] Based on the previous and current analysis results, monitoring information is output.

[0013] According to a second aspect, one embodiment provides a monitoring device, comprising:

[0014] Signal acquisition circuit, used to acquire physiological signals;

[0015] Output device, used to output monitoring information;

[0016] A processor for executing the monitoring method described in any of the embodiments herein.

[0017] According to a third aspect, one embodiment provides a computer-readable storage medium including a program that can be executed by a processor to implement the monitoring method described in any of the embodiments herein.

[0018] Beneficial effects of the invention

[0019] Beneficial effects

[0020] According to the monitoring method and device of the above embodiments, physiological signals are acquired, including previous physiological signal segments and current physiological signal segments, wherein the previous physiological signal segment corresponds to the previous analysis result and the previous model state output by the monitoring model; the previous model state and the current physiological signal segment are input into the monitoring model to output the current analysis result and the current model state corresponding to the current physiological signal segment; and monitoring information is output based on the previous analysis result and the current analysis result. Since the output monitoring information depends not only on the current physiological signal but also on historical physiological signals, the effectiveness of the monitoring information is improved.

[0021] Brief description of the accompanying drawings Attached Figure Description

[0022] Figure 1 This is a schematic diagram of the structure of a monitoring device provided in one embodiment;

[0023] Figure 2 A schematic diagram of the monitoring device provided in another embodiment;

[0024] Figure 3 A flowchart of a monitoring method provided in one embodiment;

[0025] Figure 4 A schematic diagram illustrating the process of outputting monitoring information as provided in one embodiment;

[0026] Figure 5 A schematic diagram of the structure of a monitoring model provided in one embodiment;

[0027] Figure 6 A schematic diagram illustrating the process of outputting monitoring information for another embodiment;

[0028] Figure 7 A schematic diagram of the monitoring model provided in another embodiment;

[0029] Figure 8 This is a schematic diagram of the structure of a monitoring device provided in one embodiment.

[0030] Invention Embodiments

[0031] Embodiments of the present invention

[0032] The present invention will now be described in further detail with reference to specific embodiments and accompanying drawings. Similar elements in different embodiments are referred to by associated similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of this application. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to this application are not shown or described in the specification. This is to avoid obscuring the core parts of this application with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0033] Furthermore, the features, operations, or characteristics described in the specification can be combined in any suitable manner to form various embodiments. At the same time, the steps or actions in the method description can be rearranged or adjusted in a manner obvious to those skilled in the art. Therefore, the various orders in the specification and drawings are only for the clear description of a particular embodiment and do not imply a necessary order, unless otherwise stated that a particular order must be followed.

[0034] The serial numbers assigned to components in this document, such as "first" and "second," are used only to distinguish the described objects and have no sequential or technical meaning. The terms "connection" and "linkage" used in this application, unless otherwise specified, include both direct and indirect connections (linkages).

[0035] like Figure 1The diagram shows a structural schematic of a monitoring device 100 for multi-parameter monitoring. The monitoring device 100 may have an independent housing. The housing panel may have a sensor interface area, which can integrate multiple sensor interfaces for connection to various external physiological parameter sensor accessories 111. The housing panel may also include a small LCD display area, a display 119, an input interface circuit 122, and an alarm circuit 120 (such as an LED alarm area). The monitoring device 100 may have an external communication and power interface 116 for communicating with and drawing power from the host computer. The monitoring device 100 may also support external parameter modules. A plug-in monitoring device 100 host computer can be formed by inserting parameter modules, serving as part of the monitoring device 100. Alternatively, it can be connected to the host computer via a cable, with the external parameter module serving as an external accessory of the monitoring device 100.

[0036] The internal circuitry of the monitoring device 100 is housed within a casing, such as... Figure 1As shown, the system includes signal acquisition circuits 112 corresponding to at least two physiological parameters, a front-end signal processing circuit 113, and a main processor 115. The signal acquisition circuits 112 can be selected from ECG circuits, respiration circuits, body temperature circuits, blood oxygenation circuits, non-invasive blood pressure circuits, invasive blood pressure circuits, etc. These signal acquisition circuits 112 are electrically connected to corresponding sensor interfaces for electrical connection to sensor accessories 111 corresponding to different physiological parameters. Their output terminals are coupled to the front-end signal processing circuit 113, and the communication port of the front-end signal processing circuit 113 is coupled to the main processor 115. The main processor 115 is electrically connected to an external communication and power interface 116. The sensor accessories 111 and signal acquisition circuits 112 corresponding to various physiological parameters can use common circuits in the prior art. The front-end signal processing circuit 113 completes the sampling and analog-to-digital conversion of the output signals of the signal acquisition circuits 112 and outputs control signals to control the measurement process of physiological signals. These parameters include, but are not limited to: ECG, respiration, body temperature, blood oxygenation, non-invasive blood pressure, and invasive blood pressure parameters. The front-end signal processing circuit 113 can be implemented using a microcontroller or other semiconductor devices, such as the PHLIPS LPC2136 or ADI ADuC7021 mixed-signal microcontrollers, or an ASIC or FPGA. The front-end signal processing circuit 113 can be powered by an isolated power supply. After simple processing and packaging, the sampled data is sent to the main processor 115 through an isolated communication interface. For example, the front-end signal processing circuit 113 can be coupled to the main processor 115 through an isolated power supply and communication interface 114. The reason for powering the front-end signal processing circuit 113 with an isolated power supply is that the DC / DC power supply is isolated by a transformer, which isolates the patient from the power supply equipment. The main purposes are: 1. Isolating the patient by grounding the application part through the isolation transformer, ensuring sufficiently low leakage current; 2. Preventing the voltage or energy during defibrillation or electrosurgical application from affecting the main control board and other intermediate circuit boards and components (ensuring this through creepage distance and clearance). Of course, the front-end signal processing circuit 113 can also be connected to the main processor 115 via cable 124. The main processor 115 is used to calculate physiological parameters and send the calculation results and waveforms to the host (such as a host with a display, PC, central station, etc.) through the external communication and power interface 116. The main processor 115 can be connected to the external communication and power interface 116 through the cable 125 for communication and / or power supply. The monitoring device 100 may also include a power and battery management circuit 117, which draws power from the host through the external communication and power interface 116 and supplies it to the main processor 115 after processing, such as rectification and filtering. The power and battery management circuit 117 can also monitor, manage and protect the power obtained from the host through the external communication and power interface 116.The external communication and power interface 116 can be one or a combination of Ethernet, Token Ring, Token Bus, and Fiber Distributed Data Interface (FDDI) as the backbone of these three networks; it can also be one or a combination of wireless interfaces such as infrared, Bluetooth, Wi-Fi, and WMTS communication; or it can be one or a combination of wired data connection interfaces such as RS232 and USB. The external communication and power interface 116 can also be one or a combination of wireless and wired data transmission interfaces. The host device can be any computer device such as the host of the monitoring device 100, an electrocardiograph, an ultrasound diagnostic instrument, or a computer, and with the appropriate software installed, it can form a monitoring device 100. The host device can also be a communication device, such as a mobile phone. The monitoring device 100 sends data to a Bluetooth-enabled mobile phone via the Bluetooth interface to achieve remote data transmission. The main processor 115 is also used to detect the physiological signals acquired by the signal acquisition circuit 112 and output alarm information when an abnormality is detected. An alarm circuit 120 and a display 119 can be used as output modules to output alarm information. For example, the generated alarm information can be displayed on the display 119, or an alarm sound can be emitted by the alarm circuit 120 for prompting. The memory 118 can store intermediate and final data of the monitoring device 100, as well as program instructions or code for execution by the main processor 115, etc. If the monitoring device 100 has a blood pressure measurement function, it can also include a pump valve drive circuit 121, which is used to perform inflation or deflation operations under the control of the main processor 115.

[0037] Figure 1 The monitoring device 100 shown is a multi-parameter monitoring device, but it can also be a single physiological parameter monitoring device. Figure 2 The example shown is just one instance; see the above for similar content. Figure 1 The content. It should be noted that... Figure 1 and Figure 2 The structure of the monitoring device shown is for illustrative purposes only; in practice, it may include components that are larger than those shown. Figure 1 or Figure 2 The more or fewer components shown, or having the same Figure 1 or Figure 2 The different configurations shown. Figure 1 and Figure 2 The components shown can be implemented in hardware and / or software. Figure 1 and Figure 2 The monitoring device shown can be used to perform the monitoring method provided in any embodiment of the present invention.

[0038] Please refer to Figure 3The monitoring method provided in one embodiment of the present invention may include:

[0039] S301. Acquire physiological signals, which include the previous physiological signal segment and the current physiological signal segment, wherein the previous physiological signal segment corresponds to the previous analysis result and the previous model state output by the monitoring model.

[0040] In this embodiment, physiological signals can be acquired from the patient via a signal acquisition circuit and a sensor accessory. After acquiring the physiological signals, they can be divided into partially overlapping or non-overlapping physiological signal segments. Please refer to... Figure 4 The diagram sequentially shows the partially overlapping preceding physiological signal segment x(n-1), the current physiological signal segment x(n), and the following physiological signal segment x(n+1). This partial overlap means that the physiological signal segments are no longer isolated but interconnected. For example... Figure 4 As shown, each physiological signal segment corresponds to an analysis result and model status output by the monitoring model. It should be noted that the length of each physiological signal segment and the overlap between them can be set as needed. For example, the lengths of the previous and current physiological signal segments can be set based on the lengths required to obtain the previous and current analysis results clinically. In an optional implementation, a sliding window method can be used to obtain physiological signal segments from the physiological signals. The length of the physiological signal segment can be changed by controlling the size of the sliding window.

[0041] The physiological signals in this embodiment include, but are not limited to, electrocardiogram (ECG) signals, blood pressure signals, body temperature signals, blood oxygenation signals, and respiratory signals. When the physiological signal is an ECG signal, the analysis results include: normal rhythm, abnormal rhythm, and invalid data.

[0042] S302. Input the previous model state and the current physiological signal segment into the monitoring model to output the current analysis result and the current model state corresponding to the current physiological signal segment.

[0043] In one optional implementation, after acquiring the physiological signals and before inputting the physiological signal segments into the monitoring model, the physiological signals can be preprocessed. Preprocessing operations can be performed according to the type of physiological signal, and may include signal filtering, lead dropout handling, signal denoising, signal saturation handling, and signal normalization. Signal normalization includes standardizing the sampling rate and resolution of the physiological signals to preset values. For multi-channel physiological signals, the physiological signals of each channel can be arranged according to a clinically accepted arrangement order. Taking ECG signals as an example, the resolution can be uniformly adjusted to 200 Lsb / mV, the sampling rate can be uniformly adjusted to 250 Hz, and the leads can be arranged in the order of I\II\III\aVR\aVL\aVF\V1~V6.

[0044] Please refer to Figure 4 In this embodiment, each call to the monitoring model returns the model state and analysis results for the corresponding physiological signal segment. Upon the next call, the returned model state and new physiological signal segment data are input into the monitoring model to obtain a new model state and analysis results. Through this recursive calling, a monitoring process of any duration or a complete duration can be achieved. It is particularly important to emphasize that in this embodiment, the model state of the monitoring model is not initialized each time new physiological signal segment data is analyzed; instead, the model state returned from the previous analysis is used. Since this model state contains historical information, using it only requires processing data of one physiological signal segment length each time, avoiding the need to significantly increase the data length to be processed each time in order to capture historical information. This effectively reduces resource consumption and facilitates deployment on wearable devices.

[0045] The monitoring model in this embodiment can be pre-trained based on training data. First, a relatively long training data period is selected and divided into partially overlapping data segments. Then, the monitoring model is trained according to the order in which these data segments appeared on the original data. Specifically, a sliding window recursive training method that helps capture both long and short-term features can be used for offline training. During training, the monitoring model first processes all data segments preceding the current data segment to obtain the latest model state, which is then used as the initial model state for training on the current data segment. The loss function is determined based on the prediction results output by the monitoring model and the labels of the training data, thereby updating the parameters of the monitoring model. Then, the updated monitoring model is used to reprocess all data preceding the current data segment. The monitoring model is iteratively trained until the loss function value is less than a preset threshold, resulting in a well-trained monitoring model. The trained monitoring model can then be used according to... Figure 4 The process shown analyzes physiological signal segments.

[0046] S303. Output monitoring information based on the previous analysis results and the current analysis results.

[0047] The monitoring information in this embodiment relies on both the current and previous analysis results. Both the current and previous results are not only related to a single physiological signal segment but also to historical information. Therefore, the monitoring information in this embodiment can provide medical personnel with more effective and reliable information.

[0048] The monitoring method provided in this embodiment acquires physiological signals, including a previous physiological signal segment and a current physiological signal segment. The previous physiological signal segment corresponds to the previous analysis result and the previous model state output by the monitoring model. The previous model state and the current physiological signal segment are input into the monitoring model to output the current analysis result and the current model state corresponding to the current physiological signal segment. Based on the previous and current analysis results, monitoring information is output, achieving effective monitoring of the patient. During the monitoring process, a recursive approach is adopted, processing only one physiological signal segment length at a time, effectively reducing resource overhead. The previous model state contains historical data information prior to the current physiological signal segment. The monitoring information obtained based on the current physiological signal segment and the previous model state can fully capture the short-term characteristics of the current physiological signal segment and the long-term characteristics of the historical data, providing more effective and reliable information.

[0049] Based on the above embodiments, the monitoring model will be further described in detail below. Please refer to... Figure 5 In one optional implementation, the monitoring model 50 may include: a first feature extraction module 501, a second feature extraction module 502, and an analysis module 503. The first feature extraction module 501 is used to extract first features from the previous physiological signal segment and the current physiological signal segment; the second feature extraction module 502 is used to extract second features from the current physiological signal segment based on the first features of the current physiological signal segment and the previous model state, and output the current model state; the analysis module 503 is used to output the current analysis result based on the second features of the current physiological signal segment. Optionally, the analysis module 503 can also simultaneously analyze the first and second features to output analysis results, that is, the analysis module 503 can also be used to analyze the first and second features of the current physiological signal segment (e.g., ...) to output the current analysis result. Figure 5 (As shown by the dashed line in the middle), the current analysis result is determined. The first feature is only related to the corresponding physiological signal segment and is used to reflect the short-term local characteristics of the physiological signal; the second feature is determined by the first feature used to reflect the short-term local characteristics and the previous model state used to reflect historical data information, and is used to reflect the long-term global characteristics of the physiological signal. The second feature extraction module 502 can adopt a recursive structure, receiving the first feature output by the first feature extraction module 501 at the current time and the previous model state output by the second feature extraction module 502 at the previous time, and recursively calculating the second feature and the current model state at the current time.

[0050] for Figure 5The monitoring model shown can be trained using the following method: Initialize the model state of the monitoring model, for example, by random initialization. Use the first feature extraction module 501 to extract short-term local features from the current physiological signal segment to obtain the first feature. Input the model state and the first feature into the second feature extraction module 502 to extract long-term features, obtaining the second feature and a new model state. Input the second feature into the analysis module 503 to obtain the analysis result. Compare the analysis result output by the analysis module 503 with a pre-obtained gold standard, and update the model parameters of the monitoring model with the goal of minimizing the error between the two, until the error is less than a preset threshold. Optionally, the monitoring model with updated parameters can also be used to re-process the data from the beginning position to the current time to obtain a new model state, and then process the next physiological signal segment data based on the new model state.

[0051] Please refer to Figure 6 One embodiment provides the use of Figure 5 The diagram shown illustrates the monitoring process of the monitoring model. Figure 6 As shown, the first feature extraction module extracts a first feature f1(n) from the current physiological signal segment x(n), and the second feature extraction module obtains a second feature f2(n) based on the first feature f1(n) and the previous model state s(n-1) output by the second feature extraction module at the previous time step. The analysis module analyzes the second feature f2(n) to obtain the analysis result and then outputs the current monitoring information i(n). In an optional embodiment, the first feature extraction module includes a deep residual convolutional neural network; the second feature extraction module includes a multilayer long short-term memory neural network; and the analysis module includes a fully connected neural network. The local perception characteristic of the deep residual convolutional neural network can be used to extract the short-term local first feature; and the memory characteristic of the multilayer long short-term memory neural network can be used to extract the long-term global second feature.

[0052] Based on any of the above embodiments, the monitoring model may further include a third feature extraction module for extracting traditional features of the current physiological signal segment. Taking electrocardiogram (ECG) signals as an example, traditional features include, but are not limited to, the RR interval.

[0053] Please refer to Figure 7Another embodiment of the monitoring model 50 may include: a first feature extraction module 501, a second feature extraction module 502, a third feature extraction module 504, and an analysis module 503. The first feature extraction module 501 is used to extract a first feature of the current physiological signal segment; the second feature extraction module 502 is used to extract a second feature of the current physiological signal segment and output the current model state based on the first feature of the current physiological signal segment and the previous model state; the third feature extraction module 504 is used to extract conventional features of the current physiological signal segment; and the analysis module 503 is used to determine the current analysis result based on the second feature and conventional features of the current physiological signal segment. For example, the second feature and conventional features can be concatenated or added together and then input into the analysis module 503 to determine the current analysis result.

[0054] In another optional implementation, the monitoring model may include a first feature extraction module, a second feature extraction module, a third feature extraction module, and an analysis module. The third feature extraction module is used to extract traditional features of the current physiological signal segment; the first feature extraction module is used to extract a first feature of the current physiological signal segment based on the traditional features and the current physiological signal segment itself; the second feature extraction module is used to extract a second feature of the current physiological signal segment based on the first feature and the previous model state, and output the current model state; the analysis module is used to determine the current analysis result based on the second feature of the current physiological signal segment.

[0055] Alternatively, the analysis module can also be implemented using non-neural networks, such as support vector machines (SVM).

[0056] This invention also provides a monitoring device; please refer to [link to relevant documentation]. Figure 8 As shown. Figure 8 As shown, the monitoring device 80 provided in this embodiment may include: a signal acquisition circuit 801, an output module 802, a memory 803, a processor 804, and a bus 805. The bus 805 is used to connect the various components.

[0057] The signal acquisition circuit 801 acquires physiological signals using a sensor accessory connected to the patient.

[0058] Output module 802 is used to output alarm information;

[0059] The memory 803 stores a computer program, which, when executed by the processor 804, can implement the technical solutions of any of the above method embodiments.

[0060] This document describes various exemplary embodiments with reference to them. However, those skilled in the art will recognize that changes and modifications can be made to the exemplary embodiments without departing from the scope of this document. For example, various operational steps and components for performing operational steps can be implemented in different ways depending on the specific application or considering any number of cost functions associated with the operation of the system (e.g., one or more steps can be deleted, modified, or combined with other steps).

[0061] Furthermore, as those skilled in the art will understand, the principles herein can be reflected in a computer program product on a computer-readable storage medium pre-loaded with computer-readable program code. Any tangible, non-transitory computer-readable storage medium may be used, including magnetic storage devices (hard disks, floppy disks, etc.), optical storage devices (CD-ROMs, DVDs, Blu-ray discs, etc.), flash memory, and / or the like. These computer program instructions may be loaded onto a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to form a machine, such that instructions, which execute on the computer or other programmable data processing apparatus, can generate means to perform a specified function. These computer program instructions may also be stored in a computer-readable storage medium that can instruct the computer or other programmable data processing apparatus to operate in a particular manner, such that instructions stored in the computer-readable storage medium can form an article of manufacture, including means for implementing the specified function. The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to perform a series of operational steps on the computer or other programmable apparatus to produce a computer-implemented process, such that instructions, which execute on the computer or other programmable apparatus, can provide steps for implementing the specified function.

[0062] While the principles herein have been illustrated in various embodiments, numerous modifications to the structure, arrangement, proportions, elements, materials, and components, particularly suited to specific environmental and operational requirements, may be used without departing from the principles and scope of this disclosure. These modifications and other alterations or alterations will be included within the scope of this document.

[0063] The foregoing specific descriptions have been described with reference to various embodiments. However, those skilled in the art will recognize that various modifications and changes can be made without departing from the scope of this disclosure. Therefore, considerations for this disclosure are to be illustrative rather than restrictive, and all such modifications are to be included within its scope. Similarly, advantages, other advantages, and solutions to problems with respect to various embodiments have been described above. However, benefits, advantages, solutions to problems, and any elements that produce these, or make them more explicit, should not be construed as critical, essential, or necessary. The term “comprising” and any other variations thereof as used herein are non-exclusive inclusion, meaning that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed or not part of the process, method, system, article, or apparatus. Furthermore, the term “coupled” and any other variations thereof as used herein refer to physical connections, electrical connections, magnetic connections, optical connections, communication connections, functional connections, and / or any other connections.

[0064] Those skilled in the art will recognize that many changes can be made to the details of the above embodiments without departing from the basic principles of the invention. Therefore, the scope of the invention should be determined according to the following claims.

Claims

1. A monitoring method, characterized in that, include: Acquire physiological signals, which include a previous physiological signal segment and a current physiological signal segment, wherein the previous physiological signal segment is used to input the trained monitoring model to output the previous analysis result and the previous model state corresponding to the previous physiological signal segment; The previous model state and the current physiological signal segment are input into the monitoring model, and the previous model state is used as the initial model state of the monitoring model to output the current analysis result and the current model state corresponding to the current physiological signal segment. Based on the previous analysis results and the current analysis results, monitoring information is output.

2. The method as described in claim 1, characterized in that, The monitoring model includes: a first feature extraction module, a second feature extraction module, and an analysis module; The first feature extraction module is used to extract the first features of the previous physiological signal segment and the current physiological signal segment; The second feature extraction module is used to extract the second feature of the current physiological signal segment and output the current model state based on the first feature of the current physiological signal segment and the previous model state; The analysis module is used to output the current analysis result based on the second feature of the current physiological signal segment.

3. The method as described in claim 2, characterized in that, The analysis module is used to determine the current analysis result based on the first and second features of the current physiological signal segment.

4. The method as described in claim 2, characterized in that, The first feature extraction module includes a deep residual convolutional neural network; The second feature extraction module includes a multi-layer long short-term memory neural network; The analysis module includes a fully connected neural network.

5. The method as described in claim 2, characterized in that, The monitoring model also includes a third feature extraction module, used to extract traditional features of the current physiological signal segment.

6. The method as described in claim 5, characterized in that, The analysis module is used to determine the current analysis result based on the second feature and the traditional feature of the current physiological signal segment.

7. The method as described in claim 5, characterized in that, The first feature extraction module is used to extract a first feature of the current physiological signal segment based on the traditional features of the current physiological signal segment and the current physiological signal segment itself.

8. The method as described in claim 1, characterized in that, The lengths of the previous and current physiological signal segments are set based on the lengths required to obtain the previous and current analysis results clinically.

9. The method as described in claim 1, characterized in that, The physiological signals include electrocardiogram signals, and the current analysis results and the previous analysis results include: normal rhythm, abnormal rhythm and invalid data.

10. The method as described in claim 1, characterized in that, The previous physiological signal segment and the current physiological signal segment partially overlap.

11. A monitoring device, characterized in that, include: Signal acquisition circuit, used to acquire physiological signals; Output device, used to output monitoring information; A processor for performing the monitoring method as described in any one of claims 1-10.

12. A computer-readable storage medium, characterized in that, Includes a program that can be executed by a processor to implement the monitoring method as described in any one of claims 1-10.

Citation Information

Patent Citations

  • EEG-based acceleration of second language learning

    US20110159467A1