Restless legs symptom intelligent monitoring and relief system, method, device and storage medium
Through intelligent monitoring and relief system, dynamic frequency domain feature analysis and individualized treatment, the convenience and immediate feedback of patients with restless leg syndrome diagnosis and non-drug treatment in adolescents and other patients was solved, and personalized and efficient treatment effects were achieved. , significantly improves the quality of life of patients.
Patent Information
- Application Number
- CN202410912681.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-09
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-07-09
AI Technical Summary
The prior art is difficult to achieve accurate diagnosis and non-pharmaceutical treatment of restless leg syndrome in patients such as adolescents, especially in terms of immediate feedback on equipment convenience and treatment effects.
An intelligent monitoring and relief method for restless leg symptoms is adopted. By obtaining continuous physiological signals, dynamic frequency domain feature extraction and in-depth analysis are carried out, classification similarity sequence is generated, classification weight is dynamically adjusted, and acupoints are stimulated using infrared light irradiation and electrical pulses. Perform individualized treatment.
It realizes intelligent evaluation and monitoring, provides a personalized, efficient and easy-to-use treatment experience, integrates closed-loop instant feedback technology, ensures the optimal balance between treatment effect and comfort, and significantly improves the quality of life of patients such as teenagers.
Smart Images

Figure CN118452839B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of medical equipment, and in particular to a system, method, device and storage medium for intelligent monitoring and relief of restless legs symptoms. Background Art
[0002] Restless Legs Syndrome (RLS) is a neurological sensorimotor disorder that generally affects the quality of life. It is characterized by indescribable leg discomfort and desire to move, which is especially aggravated during resting moments, seriously affecting patients' nighttime rest and daytime function. RLS affects a wide range of people worldwide, and is more common in women and the elderly. Currently, although there are a variety of treatments, including physical therapy and lifestyle adjustments, non-drug interventions for specific groups such as adolescents and pregnant women still face challenges, especially in terms of symptom quantification, device convenience, and immediate feedback on treatment effects.
[0003] Specifically, existing solutions fail to adequately address the following key requirements:
[0004] Difficulties in accurate diagnosis for adolescents and other patients: The lack of simple and effective tools to quantify leg discomfort before seeking medical treatment increases the difficulty of diagnosing RLS in adolescents and other patients.
[0005] Equipment gap for non-drug therapies: For people who prefer non-drug treatments, there is a lack of home-use, wearable, and lightweight physical therapy devices on the market.
[0006] Lack of feedback mechanism: Although physical therapy has potential, most programs do not integrate a closed-loop feedback system, making it difficult to adjust in real time to adapt to individual changes and maximize treatment effects. Summary of the invention
[0007] In order to achieve the above-mentioned purpose and other advantages according to the present invention, the first object of the present invention is to provide a method for intelligent monitoring and relief of restless legs symptoms, comprising the following steps:
[0008] Acquire the captured continuous physiological signals;
[0009] Process continuous physiological signals and divide them into discrete time frames;
[0010] Performing dynamic frequency domain feature extraction on each frame of an event sequence of a preset duration;
[0011] Perform in-depth analysis on the dynamic frequency domain features extracted from each frame to generate a classification similarity sequence containing time series information;
[0012] Dynamically adjusting the classification weight of each frame according to the mutual relationship and overall trend of each frame within the classification similarity sequence;
[0013] If the frequency of restless legs events exceeds a threshold, infrared light irradiation and / or electrical pulse stimulation of acupoints are applied until the frequency of restless legs events decreases.
[0014] Furthermore, the step of processing the continuous physiological signal includes:
[0015] The continuous physiological signals are subjected to bandpass filtering, principal component extraction and Hilbert-Huang transform.
[0016] Furthermore, the step of performing dynamic frequency domain feature extraction on each frame of the event sequence of a preset duration includes:
[0017] Fourier synchronous squeezing transform technology is used to extract the dynamic frequency domain features of each frame.
[0018] Furthermore, the step of performing in-depth analysis on the dynamic frequency domain features extracted from each frame includes:
[0019] A bidirectional long short-term memory network model is used to perform in-depth analysis of the dynamic frequency domain features extracted from each frame.
[0020] Furthermore, the step of using the bidirectional long short-term memory network model to deeply analyze the dynamic frequency domain features extracted from each frame includes:
[0021] Considering the past and future context information of the time series, the feature vector of each frame is assigned a similarity score with the predefined category, and a classification similarity sequence containing time series information is generated.
[0022] Furthermore, the predefined categories include restless legs events and sleep interruption events, and the durations of the restless legs events and the sleep interruption events are different.
[0023] Furthermore, the sleep interruption events include apnea, snoring, and non-specific limb movements during awakenings; the restless legs event is not accompanied by a decrease in tissue oxygen saturation, the apnea is also accompanied by a decrease in tissue oxygen saturation, the snoring is not necessarily accompanied by a decrease in tissue oxygen saturation, and its vibration characteristics are different from the movement pattern of the restless legs event.
[0024] Furthermore, the step of dynamically adjusting the classification weight of each frame according to the mutual relationship and overall trend of each frame within the classification similarity sequence includes:
[0025] A multi-head attention mechanism is used to dynamically adjust the classification weight of each frame according to the mutual relationship and overall trend of each frame within the classification similarity sequence.
[0026] Furthermore, the step of dynamically adjusting the classification weight of each frame by using the multi-head attention mechanism according to the mutual relationship and overall trend of each frame within the classification similarity sequence includes:
[0027] Determining whether the probability of a sleep interruption event in the classification similarity sequence exceeds a threshold;
[0028] If the probability of the sleep interruption event exceeds a threshold, blood oxygen saturation measurement is initiated;
[0029] The measured blood oxygen saturation value is used to confirm whether an oxygen depletion event has occurred and to determine the event category.
[0030] Furthermore, if the frequency of restless legs events exceeds a threshold, applying infrared light irradiation and / or electric pulse stimulation to acupoints until the frequency of restless legs events decreases comprises:
[0031] If the frequency of restless legs events exceeds the threshold, the intensity of the near-infrared light is controlled to increase in a step-by-step manner until the frequency of restless legs events increases and the intensity of the near-infrared light is controlled to decrease accordingly;
[0032] If the frequency of restless legs events exceeds the threshold, electric pulse stimulation of the acupoints will be initiated, and the stimulation intensity will be adjusted individually.
[0033] Furthermore, the step of controlling the intensity of the near-infrared light to increase stepwise comprises:
[0034] Control the intensity of near-infrared light to preset steps Incremental;
[0035] Obtain the negative feedback curve of light intensity and the reduction of restless legs event frequency:
[0036] ;
[0037] in, The time of the restless legs event that has occurred. For the intervention time, under continuous intervention, is a steady state;
[0038] In the pre-assessment Under certain circumstances, the intensity of near-infrared light can be controlled in a faster step Increase gradually, shorten the expected intervention time, suppress the frequency of restless legs events to the inflection point as soon as possible, and continue subsequent irradiation at a steady intensity.
[0039] Furthermore, the step of starting electrical pulse stimulation of acupoints and achieving individualized adjustment of stimulation intensity includes:
[0040] Control the intensity of electrical pulse stimulation to preset steps Incremental;
[0041] Obtain the negative feedback curve of the intensity of electrical pulse stimulation and the reduction of the frequency of restless legs events:
[0042] ;
[0043] The protection threshold is compared with the electrical pulse stimulation inflection point;
[0044] If the electrical pulse stimulation inflection point is higher than the protection threshold, electrical pulse stimulation is performed at the intensity of the protection threshold;
[0045] If the electrical pulse stimulation inflection point is not higher than the protection threshold, electrical pulse stimulation is performed at the intensity of the electrical pulse stimulation inflection point.
[0046] Furthermore, if the frequency of restless legs events exceeds a threshold, applying infrared light irradiation and / or electric pulse stimulation to acupoints until the frequency of restless legs events decreases further comprises:
[0047] When both the electrical pulse stimulation and the near-infrared light stimulation are activated, it is determined whether the patient has entered a stable state;
[0048] If so, the electric pulse stimulation is controlled to stop and the near-infrared light stimulation is controlled to continue.
[0049] Furthermore, the step of starting the electrical pulse stimulation of the acupoints and achieving individualized adjustment of the stimulation intensity also includes:
[0050] Start the electrodes in sequence, using the preset time as the time window to obtain high frequency feedback;
[0051] For each electrode, the rate of decrease of restless legs events of the same intensity By comparing and obtaining stimulation feedback diagrams, the degree to which acupoints deviate from expectations is estimated to determine the optimal electrode combination, thus ensuring the most accurate acupoint positioning with minimal power consumption.
[0052] The second object of the present invention is to provide an electronic device, comprising: a memory on which a program code is stored; a processor connected to the memory and implementing the above method when the program code is executed by the processor.
[0053] A third object of the present invention is to provide a computer-readable storage medium having program instructions stored thereon, wherein the program instructions implement the above method when executed.
[0054] The fourth object of the present invention is to provide a restless legs symptom intelligent monitoring and relief system, which implements the above method, including a lower limb intelligent wearable device for providing pressure therapy, a three-axis acceleration sensor, a near-infrared light source, a photodiode, and a main controller, wherein the three-axis acceleration sensor, the near-infrared light source, and the photodiode are integrated on the lower limb intelligent wearable device; wherein,
[0055] The three-axis acceleration sensor is used to capture continuous physiological signals;
[0056] The near-infrared light source is used to measure blood oxygen saturation when the probability of a sleep interruption event in a classification similarity sequence exceeds a threshold;
[0057] The photodiode is used to exert the therapeutic effect of near-infrared light;
[0058] The main controller is used to process continuous physiological signals and divide them into discrete time frames, perform dynamic frequency domain feature extraction on each frame of an event sequence of preset duration, perform in-depth analysis on the dynamic frequency domain features extracted from each frame, generate a classification similarity sequence containing time series information, dynamically adjust the classification weight of each frame according to the mutual relationship and overall trend of each frame within the classification similarity sequence, and if the frequency of restless legs events exceeds a threshold, apply infrared light irradiation and / or electric pulses to stimulate acupuncture points until the frequency of restless legs events decreases.
[0059] Compared with the prior art, the present invention has the following beneficial effects:
[0060] The present invention provides a system, method, device and storage medium for intelligent monitoring and relief of restless legs symptoms, integrating advanced closed-loop instant feedback technology to provide patients with a personalized, efficient and easy-to-use treatment experience. The advantages of the system and method include:
[0061] Intelligent assessment and monitoring: Biosensor technology is used to accurately quantify leg discomfort, solving diagnostic problems for adolescents and other patients, while continuously monitoring the treatment progress to provide an objective basis for efficacy evaluation.
[0062] Closed-loop feedback-driven physical therapy: Integrates wearable, lightweight compression devices, near-infrared light modules and related acupoint electrical stimulation modules, automatically adjusts treatment intensity and mode by real-time monitoring of user feedback, ensuring the optimal balance between treatment effect and comfort.
[0063] Personalized treatment plan: Combined with cloud data analysis, the system can develop personalized treatment plans based on the patient's specific symptoms, reactions and lifestyle habits, support remote monitoring and adjustment, and improve treatment flexibility and effectiveness.
[0064] The system provided by the present invention will fill the gap in this field of the market, especially providing a safe and effective non-drug treatment option for special groups such as adolescents and pregnant women, significantly improving their quality of life. Through intelligent and personalized treatment plans, it can effectively relieve RLS symptoms and reduce the pain of patients, while providing valuable quantitative data support for healthcare providers and researchers, promoting scientific progress in the management of restless legs syndrome.
[0065] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and implement it according to the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention in conjunction with the accompanying drawings. The specific implementation of the present invention is given in detail by the following embodiments and their accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0066] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:
[0067] Figure 1 This is a schematic diagram of the lower limb smart wearable device of Example 1;
[0068] Figure 2 This is a flow chart of the method for intelligent monitoring and relief of restless legs symptoms according to Example 2;
[0069] Figure 3 Schematic diagram of RLS waveform and other waveforms;
[0070] Figure 4 It is a flowchart for judging RLS events at multiple time scales;
[0071] Figure 5 for Figure 4 Input diagram in ;
[0072] Figure 6 for Figure 4 Schematic diagram of Hilbert-Huang transform results;
[0073] Figure 7 for Figure 4 Schematic diagram of FSST results in;
[0074] Figure 8 It is a flow chart for switching the near infrared light mode;
[0075] Fig. 9 Schematic diagram of the initial use and later individualized RLS infrared light adjustment trajectory;
[0076] Fig.10 This is a schematic diagram of the relationship between light intensity and intervention onset time;
[0077] Fig.11 This is a flow chart of acupoint stimulation control;
[0078] Fig.12 Schematic diagram of optimized control for acupoint stimulation;
[0079] Fig.13 is a schematic diagram of an electronic device of Example 3;
[0080] Fig.14 This is a schematic diagram of the storage medium of Example 4. DETAILED DESCRIPTION
[0081] The present invention is further described below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. It should be noted that, under the premise of no conflict, the embodiments or technical features described below can be arbitrarily combined to form a new embodiment.
[0082] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.
[0083] The figure numbers in this application are only used to distinguish the various steps in the scheme, and are not used to limit the execution order of the various steps. The specific execution order is subject to the description in the specification.
[0084] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. Example 1
[0085] A restless legs symptom intelligent monitoring and relief system, the system architecture is divided into two core modules: monitoring and intervention relief, aiming to efficiently identify and relieve restless legs syndrome (RLS) symptoms. The system includes a lower limb intelligent wearable device for providing pressure treatment, a three-axis acceleration sensor, a near-infrared light source, a photodiode, and a main controller. The three-axis acceleration sensor, the near-infrared light source, and the photodiode are integrated on the lower limb intelligent wearable device; wherein,
[0086] The three-axis acceleration sensor is used to capture continuous physiological signals;
[0087] In this embodiment, the monitoring module integrates a highly sensitive three-axis acceleration sensor, which is designed to accurately capture RLS and other related physiological events (such as abnormal breathing) in a low-energy environment.
[0088] The near-infrared light source is used to measure blood oxygen saturation when the probability of a sleep interruption event in a classification similarity sequence exceeds a threshold;
[0089] The photodiode is used to exert the therapeutic effect of near-infrared light;
[0090] The near-infrared light source in this embodiment has the dual functions of monitoring and intervention. In the monitoring mode, the dual-wavelength technology is used to non-invasively measure the blood oxygen saturation and hemoglobin level of the muscle, providing real-time physiological parameters for assessing the condition; when switching to the intervention relief mode, the photodiode is closed, and the therapeutic effect of the near-infrared light is exerted, while data collection is suspended to save energy.
[0091] This embodiment uses a combination of a three-axis accelerometer and an optical sensor to accurately judge RLS. The monitoring module combines a three-axis accelerometer with advanced optical sensor technology to achieve high-precision identification of restless legs syndrome (RLS) events, while effectively distinguishing other sleep interruptions such as sleep apnea, snoring, and non-specific limb movements during wakefulness. RLS events usually last about 5 seconds, and the average duration of sleep apnea is 20 seconds, accompanied by a significant decrease in tissue oxygen saturation. Snoring events usually last for a shorter period of time (about 5 seconds), are not necessarily accompanied by oxygen depletion, and the vibration characteristics are significantly different from the RLS movement pattern.
[0092] The main controller is used to process continuous physiological signals and divide them into discrete time frames, perform dynamic frequency domain feature extraction on each frame of an event sequence of preset duration, perform in-depth analysis on the dynamic frequency domain features extracted from each frame, generate a classification similarity sequence containing time series information, dynamically adjust the classification weight of each frame according to the mutual relationship and overall trend of each frame within the classification similarity sequence, and if the frequency of restless legs events exceeds a threshold, apply infrared light irradiation and / or electric pulses to stimulate acupuncture points until the frequency of restless legs events decreases.
[0093] In this embodiment, the intervention and relief module combines three clinically proven effective strategies: pressure therapy, low-intensity infrared light therapy, and micro-current stimulation of specific acupoints. Figure 1 As shown in the figure, the intervention measures are implemented through smart compression stockings with integrated sensors. Smart compression stockings are the carriers of light therapy and acupoint stimulation. According to the predicted high-frequency attack period of RLS, sufficient regular electric pulses and infrared light irradiation are applied in advance to preventively reduce the frequency of symptom attacks. This strategy not only follows the recommended treatment of professional guidelines, but also takes into account the requirements of portability and low energy consumption, ensuring the efficiency and user-friendliness of the system.
[0094] For a detailed description of the intelligent monitoring and relief method for restless legs symptoms corresponding to the intelligent monitoring and relief system for restless legs symptoms, reference may be made to the corresponding description in the following method embodiments, which will not be repeated here.
[0095] Aiming at the leg discomfort and activity desire of RLS patients, the present invention integrates RLS monitoring module and intervention relief module to realize three kinds of RLS physical relief (acupoint stimulation, pressure, near-infrared light) recommended by the guidelines, so that RLS symptoms can be alleviated in a targeted manner. Compared with traditional drug treatment and in-hospital physical therapy, the present invention is suitable for teenagers, pregnant women and other people who are inconvenient to take drug treatment, and can be used for home sleep; unlike in-hospital treatment, the present invention starts quickly, is easy to wear, can realize RLS regulation every night, realizes individualized regulation with minimal monitoring burden, and can maximize the comfortable sleep of RLS patients. Example 2
[0096] The intelligent monitoring and relief method for restless legs symptoms corresponding to the intelligent monitoring and relief system for restless legs symptoms provided in Example 1 can be described in detail in the corresponding description in the above system embodiment, and will not be repeated here. Figure 2 , Figure 4 As shown, the method comprises the following steps:
[0097] S1. Acquire the captured continuous physiological signals; specifically, use a three-axis acceleration sensor to capture the continuous physiological signals, such as Figure 5 shown.
[0098] S2. Processing continuous physiological signals and dividing them into discrete time frames (for example, into 2-minute frames each) can present typical waveforms representing the characteristics of RLS, such as Figure 3 shown.
[0099] In some optional embodiments, the step of processing the continuous physiological signal includes:
[0100] The continuous physiological signals are subjected to bandpass filtering, principal component extraction (PCA) and Hilbert-huang transform. The results are as follows Figure 6 shown.
[0101] S3, performing dynamic frequency domain feature extraction on each frame of the event sequence of preset duration;
[0102] In some optional embodiments, the step of performing dynamic frequency domain feature extraction on each frame of the event sequence of a preset duration includes:
[0103] The Fourier Synchro-Squeezing Transform (FSST) technique is used to extract the dynamic frequency domain features of each frame, such as Figure 7As shown, the high-resolution spatiotemporal feature maps hidden in the signal are revealed, providing detailed spectral and time domain information for the identification of restless legs syndrome.
[0104] This embodiment uses the Fourier Synchro-Squeezing Transform (FSST) method, which is mainly used to improve the resolution of the signal in the frequency-time domain (time-frequency analysis). This transform combines the advantages of traditional Fourier transform and time-frequency analysis techniques, especially when dealing with non-stationary signals, such as signals whose frequency components vary with time. In contrast, the Fourier transform reveals the spectral structure of the signal, but cannot provide information about how the frequency varies with time; the short-time Fourier transform (STFT) or wavelet transform can provide the energy distribution of the signal in the time-frequency plane, but may encounter resolution problems in high-frequency areas or signals with frequency crossings. The FSST transform aims to resolve the ambiguity problem in traditional time-frequency analysis and enhance the clarity of the time-frequency representation through the following steps:
[0105] Separating frequency components: First a Fourier transform is performed, then a process called "redistribution" or "squeezing" is used to tightly focus the contribution of each frequency component on the time position where it actually changes. This means a clear time-frequency representation is provided even when frequency components are changing rapidly or overlapping.
[0106] Improved resolution: By redistributing the signal's energy to more precise time-frequency locations, the synchrosqueeze transform significantly improves the resolution of the time-frequency diagram, making it easier to identify and analyze the fine structures and transient phenomena hidden in the signal.
[0107] S4, performing in-depth analysis on the dynamic frequency domain features extracted from each frame to generate a classification similarity sequence containing time series information;
[0108] In some optional embodiments, the step of performing in-depth analysis on the dynamic frequency domain features extracted from each frame includes:
[0109] The bidirectional long short-term memory network (BiLSTM) model is used to perform in-depth analysis of the dynamic frequency domain features extracted from each frame.
[0110] Specifically, the step of using a bidirectional long short-term memory network model to perform in-depth analysis on the dynamic frequency domain features extracted from each frame includes:
[0111] Considering the past and future context information of the time series, the feature vector of each frame is assigned a similarity score with predefined categories (including RLS and other potentially confusing states), generating a classification similarity sequence containing time series information.
[0112] Bidirectional long short-term memory networks are specifically designed to process sequence data, such as text, speech, or time series data. Compared with the standard LSTM network, BiLSTM significantly enhances the model's ability to understand and capture contextual dependencies in the sequence by adding a backpropagation direction. The BiLSTM model works as follows:
[0113] Bidirectional structure: BiLSTM contains two LSTM layers, one for forward propagation and the other for backward propagation. The forward LSTM processes information from the beginning to the end of the sequence and can capture the dependencies from front to back; the backward LSTM, on the contrary, processes information from the end to the beginning of the sequence and is good at capturing the dependencies from back to front. The outputs of these two directions are usually connected or concatenated to provide a comprehensive contextual feature representation for each time step.
[0114] Long-term dependency processing: Like the standard LSTM, BiLSTM also uses cell states to handle long-term dependency problems. The cell state can be regarded as the memory unit of the network, which controls the inflow, storage and outflow of information through a carefully designed gate mechanism (input gate, forget gate and output gate), thereby effectively avoiding the gradient vanishing problem and allowing information to be transmitted in long time series.
[0115] Although BiLSTM is widely used in natural language processing tasks, it is suitable for constrained and physiologically consistent sequence discrimination scenarios due to its excellent ability to understand sequence context.
[0116] In some optional embodiments, the predefined categories include restless legs events and sleep interruption events, and the durations of the restless legs events and the sleep interruption events are different.
[0117] In some optional embodiments, the sleep interruption events include apnea, snoring, and non-specific limb movements during awakenings; the restless legs event is not accompanied by a decrease in tissue oxygen saturation, the apnea is also accompanied by a decrease in tissue oxygen saturation, the snoring is not necessarily accompanied by a decrease in tissue oxygen saturation, and its vibration characteristics are different from the movement pattern of the restless legs event.
[0118] In this embodiment, through step S4, each frame is judged as an independent event based on the frequency domain features and four classifications are performed. However, the occurrence of events actually has physiological logic. For example, if hypopnea or apnea does not occur, there will be no hypoxia. There is a certain causal relationship between them. If the sequence is found to be illogical after the independent event is judged, the classification probability of the independent time frame should be readjusted to integrate the sequence with the largest overall probability, that is, to correct the physiological logic of the sequence.
[0119] S5, dynamically adjusting the classification weight of each frame according to the mutual relationship and overall trend of each frame within the classification similarity sequence;
[0120] In some optional embodiments, the step of dynamically adjusting the classification weight of each frame according to the mutual relationship and overall trend of each frame within the classification similarity sequence includes:
[0121] A multi-head attention mechanism is introduced on the basis of BiLSTM, and the classification weight of each frame is dynamically adjusted according to the mutual relationship and overall trend of each frame in the classification similarity sequence.
[0122] In the current algorithm, 30 attention heads are used to analyze an event sequence lasting up to one hour. The precursor event of oxygen depletion is set as hypopnea or apnea, and the subsequent event of hypopnea or apnea is oxygen depletion. The duration of apnea is longer than 20 seconds, while the duration of oxygen depletion is not less than 10 seconds; snoring events are not necessarily connected to oxygen depletion events, and the duration of snoring does not exceed 10s. It must be separated by other events during the period, and there are no long-term continuous snoring events; the duration of RLS1 events is about 5 seconds, and high-frequency RLS events must be separated by other events. By analyzing the internal structure and logical coherence of the four-category similarity sequence, the accuracy of frame-by-frame classification is optimized to ensure that the final classification decision not only depends on the characteristics of a single frame, but also fully considers the overall rationality and contextual information of the sequence.
[0123] This comprehensive strategy not only improves the accuracy and efficiency of RLS event identification, but also effectively reduces the misjudgment rate, providing solid data support for subsequent timely intervention and treatment.
[0124] The monitoring module combines a three-axis accelerometer and an optical sensor to accurately identify RLS. The monitoring module combines a three-axis accelerometer and advanced optical sensor technology to achieve high-precision identification of restless legs syndrome events, while effectively distinguishing other sleep interruptions.
[0125] In some embodiments, the near-infrared light of the three-axis acceleration sensor adopts a time-sharing energy-saving design. Near-infrared light can measure blood oxygen, which can further improve the accuracy of determining RLS events, and the relevant algorithm can be implemented using a decision tree. Blood oxygen measurement is a simple physical measurement and does not require waveform recognition. Therefore, when an oxygen depletion event occurs (for example, a decrease in blood oxygen saturation ≥4%), the RLS event is excluded; because blood oxygen changes relatively slowly, blood oxygen measurement can be started when suspected apnea or snoring events occur (the overall probability of apnea and snoring in the four categories exceeds the threshold a). The value of a is determined by the decision tree algorithm based on the measured data, with the best oxygen depletion resolution accuracy as the algorithm target. For the vast majority of RLS patients, their oxygen depletion is not obvious, so blood oxygen measurement is a sparse measurement, and the overall energy consumption of intermittent blood oxygen measurement is minimized.
[0126] Specifically, Figure 8 As shown, the step of dynamically adjusting the classification weight of each frame by using the multi-head attention mechanism according to the relationship and overall trend of each frame within the classification similarity sequence includes:
[0127] Determining whether the probability of a sleep interruption event in the classification similarity sequence exceeds a threshold;
[0128] If the probability of the sleep interruption event exceeds a threshold, and a suspected apnea or snoring event occurs, blood oxygen saturation measurement is initiated;
[0129] The measured blood oxygen saturation value is used to confirm whether an oxygen depletion event has occurred to determine the event type. For example, if the blood oxygen saturation drops by more than the preset value, it is determined that an oxygen depletion event has occurred. At this time, RLS events are excluded, and apnea or snoring events may have occurred; if the blood oxygen saturation does not drop, it is determined that no oxygen depletion event has occurred. At this time, apnea events are excluded, and RLS events or snoring events may have occurred.
[0130] After adjusting the weights, it needs to go through the BiLSTM model, the dropout layer, the fully connected layer, and the SoftMax function. In offline computing, this process is single-threaded. However, in training, this process has negative feedback, which means that the weights will be adjusted according to the training data.
[0131] S6. If the frequency of restless legs events exceeds a threshold, infrared light irradiation and / or electric pulse stimulation of acupoints are applied until the frequency of restless legs events decreases.
[0132] In some optional embodiments, if the frequency of restless legs events exceeds a threshold, applying infrared light irradiation and / or electric pulse stimulation to acupoints until the frequency of restless legs events decreases comprises:
[0133] If the frequency of restless legs events exceeds the threshold, the intensity of the near-infrared light is controlled to increase in a step-by-step manner until the frequency of restless legs events increases and the intensity of the near-infrared light is controlled to decrease accordingly;
[0134] The intensity of near-infrared light intervention is related to the frequency of RLS. If the frequency of RLS is high, the intensity of near-infrared light is increased step by step until the frequency of RLS decreases. The intensity of near-infrared light is reduced accordingly to reduce power consumption and prevent tolerance of physical therapy. For specific patients, the first individualized adjustment process is as follows:
[0135] RLS occurs, controlling the intensity of near-infrared light to preset steps Incremental;
[0136] Obtain the negative feedback curve of light intensity and the frequency of restless legs events, that is:
[0137] ;
[0138] in, is the time of the restless legs event that has occurred, that is, the intervention lag time, For the intervention time, under continuous intervention, is a steady state;
[0139] In individualized measurement, the time lag effect is taken into account in the pre-assessment Under certain circumstances, the intensity of near-infrared light can be controlled in a faster step Increase gradually, shorten the expected intervention time, suppress the frequency of restless legs events to the inflection point as soon as possible, and continue the subsequent irradiation at a steady intensity. Although light has fewer side effects, high-dose irradiation quickly depletes the battery, affecting the intervention throughout the night. Therefore, in the negative feedback stage, middle, It is sufficient to descend to the inflection point, without having to reach the lowest point.
[0140] The trajectory of the first use and subsequent individualized RLS infrared light adjustment is as follows Fig. 9 The relationship between light intensity and intervention onset time is shown in Fig.10 As shown in Figure 3, the intervention onset time is the time when the RLS frequency begins to decline.
[0141] like Fig.11 As shown, if the frequency of restless legs events exceeds the threshold, electric pulse stimulation of the acupoints is initiated, and the stimulation intensity is adjusted individually.
[0142] Acupoint stimulation is similar to near-infrared light intervention. When a high frequency of RLS events is detected, acupoint stimulation is initiated and the intensity of stimulation is adjusted individually. The specific process is as follows:
[0143] Control the intensity of electrical pulse stimulation to preset steps Incremental;
[0144] Obtain the negative feedback curve of the intensity of electrical pulse stimulation and the reduction of the frequency of restless legs events, that is:
[0145] ;
[0146] The higher the stimulus intensity, The shorter it is, the faster the RLS frequency decreases, but there is also an inflection point in the stimulation intensity and the amplitude of the decrease. Since excessive electrical stimulation intensity can easily cause patients to wake up, the protection threshold (the threshold that does not wake up the patient) is compared with the inflection point of electrical pulse stimulation;
[0147] If the electrical pulse stimulation inflection point is higher than the protection threshold, electrical pulse stimulation is performed at the intensity of the protection threshold;
[0148] If the electrical pulse stimulation inflection point is not higher than the protection threshold, electrical pulse stimulation is performed at the intensity of the electrical pulse stimulation inflection point in order to achieve RLS suppression as quickly as possible.
[0149] In some embodiments, if the frequency of restless legs events exceeds a threshold, applying infrared light irradiation and / or electric pulse stimulation to acupoints until the frequency of restless legs events decreases further comprises:
[0150] When both electrical pulse stimulation and near-infrared light stimulation are activated, the total stimulation feedback is , determine whether the patient has entered a stable state;
[0151] If so, the electric pulse stimulation is controlled to stop and the near-infrared light stimulation is controlled to continue.
[0152] Unlike near-infrared light, for the ), that is, when the dose of near-infrared light is sufficient to suppress the restless legs episode, acupoint stimulation is no longer initiated, i.e. Set to 0 to avoid disturbing sleep, while near-infrared light can be used continuously as a non-intrusive measure.
[0153] In some optional embodiments, the step of starting electrical pulse stimulation of acupoints and achieving individualized adjustment of stimulation intensity further includes:
[0154] Start the electrodes in sequence, using the preset time as the time window to obtain high frequency feedback;
[0155] like Fig.12 As shown, acupoint stimulation can be achieved by using circular dot electrodes, which are activated sequentially (e.g., clockwise or counterclockwise, both are equivalent) with a time window of 5 seconds to obtain high-frequency stimulation. feedback.
[0156] For each electrode, the rate of decrease of restless legs events of the same intensity By comparison, stimulation feedback diagrams are obtained and the degree of deviation of acupoints from expectations is estimated to determine the optimal electrode combination.
[0157] For each electrode, its intensity is adjusted according to the comparison principle of stimulation threshold and inflection point to ensure the most accurate acupoint positioning with the minimum power consumption. Example 3
[0158] An electronic device, such as Fig.13 As shown, it includes: a memory on which program codes are stored; a processor connected to the memory, and when the program codes are executed by the processor, a method for intelligent monitoring and relief of restless legs symptoms is implemented. For a detailed description of the method, reference can be made to the corresponding description in the above method embodiment, which will not be repeated here. Example 4
[0159] A computer readable storage medium such as Fig.14 As shown, program instructions are stored thereon, and when the program instructions are executed, a method for intelligent monitoring and relief of restless legs symptoms is implemented. For a detailed description of the method, reference may be made to the corresponding description in the above method embodiment, and no further description is given here.
[0160] The number of devices and processing scales described here are used to simplify the description of the present invention. Applications, modifications and variations of the present invention will be obvious to those skilled in the art.
[0161] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and implementation modes. They can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the illustrations shown and described herein.
[0162] The apparatus, electronic device, non-volatile computer storage medium and method provided in the embodiments of this specification correspond to each other, and therefore, the apparatus, electronic device and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, electronic device and non-volatile computer storage medium will not be repeated here.
[0163] Those skilled in the art also know that, in addition to implementing the controller in a purely computer-readable program code, the controller can be made to implement the same function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered as a hardware component, and the devices for implementing various functions included therein can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software units for implementing the method and structures within the hardware component.
[0164] The systems, devices or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. For the convenience of description, the above devices are described separately by functions in various units. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in the same or more software and / or hardware.
[0165] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0166] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0167] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0168] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0169] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0170] The specification may be described in the general context of computer-executable instructions executed by a computer, such as program units. Generally, program units include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program units may be located in local and remote computer storage media, including storage devices.
[0171] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0172] The above description is only an embodiment of this specification and is not intended to limit one or more embodiments of this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of one or more embodiments of this specification.
Claims
1. A computer-readable storage medium, characterized in that: Program instructions are stored thereon, and when the program instructions are executed, a method for intelligent monitoring and relief of restless legs symptoms is implemented, the method comprising the following steps: Acquire the captured continuous physiological signals; Process continuous physiological signals and divide them into discrete time frames; Performing dynamic frequency domain feature extraction on each frame of an event sequence of a preset duration; Perform in-depth analysis on the dynamic frequency domain features extracted from each frame to generate a classification similarity sequence containing time series information; Dynamically adjusting the classification weight of each frame according to the mutual relationship and overall trend of each frame within the classification similarity sequence; If the frequency of restless legs events exceeds a threshold, infrared light irradiation and / or electrical pulse stimulation of acupuncture points are applied until the frequency of restless legs events decreases; The step of deeply analyzing the dynamic frequency domain features extracted from each frame includes: A bidirectional long short-term memory network model is used to deeply analyze the dynamic frequency domain features extracted from each frame; The step of using the bidirectional long short-term memory network model to deeply analyze the dynamic frequency domain features extracted from each frame includes: Considering the past and future context information of the time series at the same time, the feature vector of each frame is assigned a similarity score with the predefined category, and a classification similarity sequence containing time series information is generated; The predefined categories include restless legs events and sleep interruption events, and the durations of the restless legs events and the sleep interruption events are different; The sleep interruption events include apnea, snoring, and non-specific limb movements during awakening; the restless legs events are not accompanied by a decrease in tissue oxygen saturation, the apnea is also accompanied by a decrease in tissue oxygen saturation, the snoring is not necessarily accompanied by a decrease in tissue oxygen saturation, and its vibration characteristics are different from the movement pattern of the restless legs events; The step of dynamically adjusting the classification weight of each frame according to the mutual relationship and overall trend of each frame in the classification similarity sequence includes: A multi-head attention mechanism is used to dynamically adjust the classification weight of each frame according to the mutual relationship and overall trend of each frame within the classification similarity sequence; The step of dynamically adjusting the classification weight of each frame by using the multi-head attention mechanism according to the mutual relationship and overall trend of each frame within the classification similarity sequence includes: Determining whether the probability of a sleep interruption event in the classification similarity sequence exceeds a threshold; If the probability of the sleep interruption event exceeds a threshold, blood oxygen saturation measurement is initiated; The measured blood oxygen saturation value is used to confirm whether an oxygen depletion event has occurred and to determine the event category.
2. A computer-readable storage medium according to claim 1, characterized in that: The step of processing the continuous physiological signal comprises: The continuous physiological signals are subjected to bandpass filtering, principal component extraction and Hilbert-Huang transform.
3. A computer-readable storage medium according to claim 1, characterized in that: The step of performing dynamic frequency domain feature extraction on each frame of the event sequence of preset duration comprises: Fourier synchronous squeezing transform technology is used to extract the dynamic frequency domain features of each frame.
4. A computer-readable storage medium according to claim 1, characterized in that: If the frequency of restless legs events exceeds a threshold, applying infrared light irradiation and / or electric pulse stimulation to acupoints until the frequency of restless legs events decreases comprises: If the frequency of restless legs events exceeds the threshold, the intensity of the near-infrared light is controlled to increase in a step-by-step manner until the frequency of restless legs events increases and the intensity of the near-infrared light is controlled to decrease accordingly; If the frequency of restless legs events exceeds the threshold, electric pulse stimulation of the acupoints will be initiated, and the stimulation intensity will be adjusted individually.
5. A computer-readable storage medium according to claim 4, characterized in that: The step of controlling the intensity of the near-infrared light to increase stepwise comprises: Control the intensity of near-infrared light to preset steps Incremental; Obtain the negative feedback curve of light intensity and the reduction of restless legs event frequency: , in, The time of the restless legs event that has occurred. For the intervention time, under continuous intervention, is a steady state; In the pre-assessment Under certain circumstances, the intensity of near-infrared light can be controlled in a faster step Increase gradually, shorten the expected intervention time, suppress the frequency of restless legs events to the inflection point as soon as possible, and continue subsequent irradiation at a steady intensity.
6. A computer-readable storage medium according to claim 5, characterized in that: The steps of starting electrical pulse stimulation of acupoints and achieving individualized adjustment of stimulation intensity include: Control the intensity of electrical pulse stimulation to preset steps Incremental; Obtain the negative feedback curve of the intensity of electrical pulse stimulation and the reduction of the frequency of restless legs events: , The protection threshold is compared with the electrical pulse stimulation inflection point; If the electrical pulse stimulation inflection point is higher than the protection threshold, electrical pulse stimulation is performed at the intensity of the protection threshold; If the electrical pulse stimulation inflection point is not higher than the protection threshold, electrical pulse stimulation is performed at the intensity of the electrical pulse stimulation inflection point.
7. A computer-readable storage medium according to claim 6, characterized in that: If the frequency of restless legs events exceeds a threshold, applying infrared light irradiation and / or electric pulse stimulation to acupoints until the frequency of restless legs events decreases, the step further includes: When both the electrical pulse stimulation and the near-infrared light stimulation are activated, it is determined whether the patient has entered a stable state; If so, the electric pulse stimulation is controlled to stop and the near-infrared light stimulation is controlled to continue.
8. A computer-readable storage medium according to claim 6, characterized in that: The step of starting electrical pulse stimulation on acupoints and adjusting the stimulation intensity individually also includes: Start the electrodes in sequence, using the preset time as the time window to obtain high frequency feedback; For each electrode, the rate of decrease of restless legs events of the same intensity By comparing and obtaining stimulation feedback diagrams, the degree to which acupoints deviate from expectations is estimated to determine the optimal electrode combination, thus ensuring the most accurate acupoint positioning with minimal power consumption.
9. An electronic device, characterized in that: include: A memory, wherein the memory comprises a computer-readable storage medium according to any one of claims 1 to 8; A processor is connected to the memory, and when the program code in the memory is executed by the processor, the intelligent monitoring and relief method for restless legs symptoms is implemented.
10. An intelligent monitoring and relief system for restless legs symptoms, comprising the electronic device according to claim 9, characterized in that: It includes a lower limb intelligent wearable device for providing pressure therapy, a three-axis acceleration sensor, a near-infrared light source, a photodiode, and a main controller, wherein the three-axis acceleration sensor, the near-infrared light source, and the photodiode are integrated on the lower limb intelligent wearable device; wherein, The three-axis acceleration sensor is used to capture continuous physiological signals; The near-infrared light source is used to measure blood oxygen saturation when the probability of a sleep interruption event in a classification similarity sequence exceeds a threshold; The photodiode is used to exert the therapeutic effect of near-infrared light; The main controller is used to process continuous physiological signals and divide them into discrete time frames, perform dynamic frequency domain feature extraction on each frame of an event sequence of preset duration, perform in-depth analysis on the dynamic frequency domain features extracted from each frame, generate a classification similarity sequence containing time series information, dynamically adjust the classification weight of each frame according to the mutual relationship and overall trend of each frame within the classification similarity sequence, and if the frequency of restless legs events exceeds a threshold, apply infrared light irradiation and / or electric pulses to stimulate acupuncture points until the frequency of restless legs events decreases.
Citation Information
Patent Citations
Emotion recognition method based on convolutional recurrent neural network and multi-head self-attention
CN115238731A
Multi-scale feature fusion sleep staging method, device and equipment and storage medium
CN115251838A
Wireless radio frequency signal-based non-contact living state monitoring method and system
CN115474901A
Sleep staging analysis system and method based on time self-attention and dynamic graph convolution
CN116072265A
Apparatus and method for generating prediction result for TCR using artificial intelligence technology
KR102558549B1
