Rehabilitation nursing risk early warning system, fatigue risk early warning method, equipment and medium

Abstract

The invention provides a risk early warning system for rehabilitation nursing, a fatigue risk early warning method, equipment and a medium. The method comprises the following steps: synchronously acquiring a three-axis acceleration signal and a surface electromyogram signal of a target muscle of a patient during rehabilitation nursing; carrying out filtering processing on the surface electromyographic signals according to frequency spectrum characteristics of the three-axis acceleration signals so as to suppress artifacts generated by macroscopic movement of limbs, and obtaining preprocessed electromyographic signals; determining a median frequency sequence of the preprocessed electromyographic signals and an approximate entropy sequence of amplitude envelope in a continuously sliding time window; constructing a risk index of the muscle fatigue state according to a collaborative change relation between the median frequency sequence and the approximate entropy sequence; and generating a fatigue risk early warning report of the patient during rehabilitation nursing by combining the risk index with a preset fatigue risk threshold. By adopting the scheme of the invention, a normal physiological fatigue process and an abnormal neuromuscular decompensation state can be discriminated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of rehabilitation nursing, and more particularly, to a risk early warning system for rehabilitation nursing, a fatigue risk early warning method, an equipment and a medium. BACKGROUND

[0002] Rehabilitation nursing is a process of converting the patient's dysfunction state into a quantifiable, traceable and optimized functional output system through standardized assessment, modular intervention, data-driven regulation and closed-loop management, so as to realize the paradigm shift from experience-based decision-making to precise regulation. In this process, how to effectively manage training-related risks such as muscle overwork, secondary injury and cardiovascular overload is the core challenge to ensure the safety and effectiveness of rehabilitation. Among them, the accurate early warning of muscle fatigue risk is particularly crucial.

[0003] Traditional fatigue monitoring methods mostly rely on isolated judgment or linear combination of a single or a few characteristics such as electromyogram frequency spectrum and amplitude, which is difficult to analyze the complex coupling relationship and dynamic pattern of multi-dimensional physiological signals in the fatigue evolution process. For example, traditional methods often attribute single changes such as muscle activation decline and frequency spectrum shift to routine physical exertion, but cannot identify the potential injury risk or neural muscle control strategy decompensation when these changes are accompanied by abnormal patterns such as muscle coordination disorder and electromyogram-mechanical output efficiency decoupling. Therefore, how to distinguish between normal physiological fatigue process and abnormal neural muscle decompensation state has become a problem faced by the industry. SUMMARY

[0004] The present application provides a risk early warning system for rehabilitation nursing, a fatigue risk early warning method, an equipment and a medium, which can distinguish between normal physiological fatigue process and abnormal neural muscle decompensation state.

[0005] In a first aspect, the present application provides a fatigue risk early warning method for early warning of fatigue risk during rehabilitation nursing of a user, which comprises the following steps: synchronously collecting three-axis acceleration signals and surface electromyogram signals of a target muscle of a patient during rehabilitation nursing; filtering the surface electromyogram signals according to the frequency spectrum characteristics of the three-axis acceleration signals to suppress artifacts generated by limb macro-movement, to obtain pre-processed electromyogram signals; determining a median frequency sequence and an approximate entropy sequence of the amplitude envelope of the pre-processed electromyogram signals within a continuously sliding time window; constructing a risk index of muscle fatigue state according to the synergistic change relationship between the median frequency sequence and the approximate entropy sequence; generating a fatigue risk early warning report of the patient during rehabilitation nursing by combining the risk index with a pre-set fatigue risk threshold.

[0006] In some embodiments, the sEMG signal is filtered according to spectral features of the triaxial acceleration signal to suppress artifacts caused by limb macro-movements, to obtain a pre-processed sEMG signal, specifically comprising: extracting reference noise features representing limb macro-movement patterns from the triaxial acceleration signal; constructing an adaptive filter for filtering out motion artifacts based on the reference noise features; processing the sEMG signal through the adaptive filter to suppress artifacts caused by limb macro-movements, to obtain a pre-processed sEMG signal.

[0007] In some embodiments, the median frequency sequence and the approximate entropy sequence of the pre-processed sEMG signal are determined within a continuously sliding time window, specifically comprising: pre-setting a continuously sliding time window; dividing the pre-processed sEMG signal into consecutive signal segments through the time window; determining the median frequency of each signal segment, to obtain a median frequency sequence of the pre-processed sEMG signal; extracting the amplitude envelope of each signal segment and calculating the approximate entropy of the corresponding amplitude envelope, to obtain an approximate entropy sequence of the amplitude envelope.

[0008] In some embodiments, the risk index of muscle fatigue state is constructed according to the synergistic change relationship between the median frequency sequence and the approximate entropy sequence, specifically comprising: setting the time window length for synergistic change analysis, and then extracting the data segment within the latest time window from the median frequency sequence and the approximate entropy sequence; determining the quantification index of the synergistic change relationship between the median frequency sequence and the approximate entropy sequence based on the extracted data segment; mapping the quantification index as the risk index of muscle fatigue state.

[0009] In some embodiments, the fatigue risk early warning report of the patient during rehabilitation care is generated by combining the risk index with a pre-set fatigue risk threshold, specifically comprising: pre-setting the fatigue risk threshold of the patient during rehabilitation care; determining the fatigue risk level of the patient by combining the risk index with the pre-set fatigue risk threshold; generating a structured report containing early warning information as the fatigue risk early warning report according to the fatigue risk level.

[0010] In some embodiments, the target muscle refers to the main acting muscle group selected as the fatigue monitoring object according to the rehabilitation care action mode.

[0011] In some embodiments, the surface electromyography signal refers to an electrophysiological signal generated by target muscle motor unit activity.

[0012] In a second aspect, the present application provides a risk early warning system for rehabilitation nursing, comprising a fatigue risk early warning unit, the fatigue risk early warning unit comprising: In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the fatigue risk early warning method when executing the computer program.

[0013] In a fourth aspect, the present application provides a computer readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the steps of the fatigue risk early warning method.

[0014] The technical scheme provided by the embodiments of the present application has the following beneficial effects: The rehabilitation nursing risk early warning system, the fatigue risk early warning method, the equipment and the medium provided by the application, first, the three-axis acceleration and the surface electromyogram signal are synchronously collected, and the frequency spectrum characteristics of the acceleration signal are used to filter the original electromyogram signal, the purpose is to inhibit the pseudo-trace interference introduced by the macroscopic movement of the limb from the source, and to provide high-quality, reflecting pure neuromuscular activity electrophysiological data basis for subsequent accurate feature extraction; This step is to ensure that the signal-to-noise ratio of the extracted feature and the physiological correlation is the physical prerequisite; Subsequently, in the continuous sliding time window, the median frequency sequence and the approximate entropy sequence of the amplitude envelope of the electromyogram signal are determined in parallel; The amplitude fluctuation mode of the surface electromyogram signal is converted from the time domain waveform to the quantifiable nonlinear complexity index; The process obtains a complexity change sequence evolving with time by calculating the approximate entropy of the amplitude envelope in each sliding time window, so as to convert the abstract pattern disorder degree into a specific, traceable mathematical sequence; The present scheme provides a key dimension for describing the stability and predictability of neuromuscular control strategy: in normal physiological fatigue, due to the synchronization of motor unit recruitment, the amplitude envelope often presents regularity enhancement and complexity reduction; While in the abnormal decompensation state (such as pain inhibition or compensatory muscle interference), the control command becomes chaotic, which may cause unexpected fluctuations or abnormal rise of the complexity of the amplitude envelope; Further, a risk index is constructed according to the cooperative change relationship between the median frequency sequence and the approximate entropy sequence, the core of which is to design a mathematical model (such as a fusion function based on correlation coefficient, phase synchronism, or trend deviation measurement) to quantify the dynamic correlation pattern of the two key features on the time axis; This process can mathematically distinguish and quantitatively express the two essentially different states of the decrease of the median frequency accompanied by the synchronous decrease of the approximate entropy (typical physiological fatigue) and the decrease of the median frequency but the abnormal fluctuation or rise of the approximate entropy (potential decompensation) through a comprehensive index; Finally, by comparing the calculated dynamic risk index with the preset threshold, an early warning report is generated; In summary, the scheme can distinguish between normal physiological fatigue process and abnormal neuromuscular decompensation state. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 is a flowchart of a fatigue risk early warning method according to some embodiments of the application; Figure 2 is a flowchart of determining the preprocessed electromyogram signal according to some embodiments of the application; Figure 3 is a flowchart of determining the median frequency according to some embodiments of the application; Figure 4 is a structural diagram of a fatigue risk early warning unit according to some embodiments of the application; Figure 5is an internal structure diagram of a computer device for implementing a fatigue risk early warning method according to some embodiments of the present application. DETAILED DESCRIPTION

[0016] In order to better understand the technical solutions in the present embodiment, the technical solutions in the present embodiment will be described in detail below in combination with the accompanying drawings and specific embodiments.

[0017] Reference Figure 1 The figure is a flowchart of a fatigue risk early warning method according to some embodiments of the present application, which mainly includes the following steps: In step 101, three-axis acceleration signals and surface electromyography signals of target muscles of a patient during rehabilitation nursing are synchronously collected.

[0018] In specific implementation, an integrated biosignal sensor integrating a three-axis accelerometer and surface electromyography electrodes is used for collection; first, according to the main muscle groups involved in rehabilitation nursing actions, the muscle belly positions of target muscles are determined according to clinical surface electromyography measurement standards and the skin is cleaned; then, the electromyography electrodes of the sensor are attached to the target muscle belly along the muscle fiber direction, and the reference electrode is attached to the adjacent bony landmark; at the same time, the three-axis accelerometer module of the sensor is fixed with the limb part, and the three sensitive axes are roughly aligned with the forward-backward, medial-lateral and superior-inferior directions in anatomy; during collection, the unified clock inside the same hardware device is used for control, and the recording is started at a synchronous sampling frequency; the sampling frequency of the surface electromyography signal is not less than 1000 Hz, and the sampling frequency of the three-axis acceleration signal is usually not less than 100 Hz; the signals are transmitted to the signal processing unit through wired or wireless mode, forming a double-channel raw data stream with strictly aligned time stamps.

[0019] It should be noted that the target muscle in the present application refers to the main acting muscle group selected as the fatigue monitoring object according to the rehabilitation nursing action mode; the three-axis acceleration signal refers to a signal reflecting the change of the acceleration of the limb motion in three-dimensional space with time, and the physical dimension is gravity acceleration, which is mainly used for quantifying the macro motion of the limb; the surface electromyography signal refers to the electrophysiological signal generated by the activity of the motor unit of the target muscle, and the amplitude unit is millivolt, which is the core raw signal for evaluating muscle fatigue; synchronous collection refers to that the electromyography signal and the acceleration signal are recorded at the same time under the same time reference, and the technical key lies in that the two signals share the same sampling clock to ensure time alignment, which is the premise for subsequent motion artifact filtering; the integrated biosignal sensor is a special device in which the electromyography collection front end and the miniature three-axis accelerometer are packaged in the same medical-grade patch.

[0020] In step 102, the surface electromyography signal is filtered according to the spectral feature of the three-axis acceleration signal to suppress the artifact generated by the macro motion of the limb, to obtain the preprocessed electromyography signal.

[0021] In some embodiments, the reference Figure 2 As shown in the figure, the figure is a flowchart for determining the preprocessed electromyography signal according to some embodiments of the present application. The surface electromyography signal is filtered according to the spectral feature of the three-axis acceleration signal to suppress the artifact generated by the macro motion of the limb, to obtain the preprocessed electromyography signal, which can be implemented by the following steps: First, in step 1021, the reference noise feature representing the macro motion mode of the limb is extracted from the three-axis acceleration signal; Then, in step 1022, the adaptive filter for filtering out the motion artifact is constructed based on the reference noise feature; Finally, in step 1023, the surface electromyography signal is processed by the adaptive filter to suppress the artifact generated by the macro motion of the limb, to obtain the preprocessed electromyography signal.

[0022] In a specific implementation, the reference noise feature representing the macro motion mode of the limb extracted from the three-axis acceleration signal can be implemented in the following way, for example: first, the time-stamped three-axis acceleration signal is preprocessed to remove the direct current bias and perform smoothing filtering; then, the first principal component time series obtained by performing principal component analysis on the smoothed three-axis acceleration signal is taken as the reference noise feature. In other embodiments, other methods can also be used to implement it, which is not limited here.

[0023] It should be noted that the reference noise feature in the present application refers to the signal feature extracted from the three-axis acceleration signal for representing the macro motion mode of the limb, which is used as the reference input of the adaptive filter to guide the filtering out of the artifact in the surface electromyography signal generated by the motion.

[0024] In a specific implementation, the adaptive filter for filtering out motion artifacts based on the reference noise feature can be implemented in the following manner, for example: first, determine the filter structure to be a finite-length unit impulse response transversal filter; use the reference noise feature as the reference input sequence of the filter; use the synchronously collected original surface electromyography signal as the desired signal; use a normalized least mean square algorithm as the core adaptive algorithm of the filter, which adjusts the filter weight vector through iteration to minimize the mean square error between the filter output and the desired signal; in the construction process, set an adaptive step parameter for the normalized least mean square algorithm to ensure convergence, and the value of the parameter is normalized according to the power of the reference noise feature or set to an empirical fixed small value; at the same time, set an order for the transversal filter related to the possible duration of motion artifacts, which is pre-set according to the sampling frequency and the typical time delay of artifacts, and the present application does not limit this.

[0025] It should be noted that the adaptive filter in the present application refers to a signal processing component that can dynamically adjust its parameters according to the reference noise feature, which functions to estimate and subtract the motion artifact component from the surface electromyography signal, thereby obtaining the electromyography signal after artifact suppression.

[0026] In a specific implementation, the adaptive filter for filtering out motion artifacts based on the reference noise feature can be implemented in the following manner, for example: first, determine the filter structure to be a finite-length unit impulse response transversal filter; use the reference noise feature as the reference input sequence of the filter; use the synchronously collected original surface electromyography signal as the desired signal; use a normalized least mean square algorithm as the core adaptive algorithm of the filter, which adjusts the filter weight vector through iteration to minimize the mean square error between the filter output and the desired signal; in the construction process, set an adaptive step parameter for the normalized least mean square algorithm to ensure convergence, and the value of the parameter is normalized according to the power of the reference noise feature or set to an empirical fixed small value; at the same time, set an order for the transversal filter related to the possible duration of motion artifacts, which is pre-set according to the sampling frequency and the typical time delay of artifacts, and the present application does not limit this.

[0027] It should be noted that the adaptive filter in the present application refers to a signal processing component that can dynamically adjust its parameters according to the reference noise feature, which functions to estimate and subtract the motion artifact component from the surface electromyography signal, thereby obtaining the electromyography signal after artifact suppression.

[0028] In step 103, the median frequency sequence and the approximate entropy sequence of the amplitude envelope of the preprocessed electromyographic signal are determined within a continuously sliding time window.

[0029] In some embodiments, determining the median frequency sequence and the approximate entropy sequence of the amplitude envelope of the preprocessed electromyographic signal within a continuously sliding time window can be achieved by the following steps: Preset the time window for continuous sliding; The preprocessed electromyographic signal is divided into a sliding window using the time window to obtain continuous signal segments. The median frequency of each signal segment is determined, thereby obtaining the median frequency sequence of the preprocessed electromyographic signal; The amplitude envelope of each signal segment is extracted and the approximate entropy of the corresponding amplitude envelope is calculated, thereby obtaining the approximate entropy sequence of the amplitude envelope.

[0030] In practical implementation, a time window length and a sliding step size can be preset based on the non-stationary characteristics of electromyographic signals and the real-time requirements of fatigue monitoring. The window length needs to be long enough to include several muscle activation cycles to stably estimate the signal spectrum, while also being short enough to ensure timely response to changes in fatigue state. Its specific value can be set within a reasonable range based on the main frequency components of the preprocessed electromyographic signal and the actual application scenario. The sliding step size determines the temporal resolution of the feature sequence update, and its value is less than or equal to the window length. It can be preset after balancing computational resources and real-time monitoring requirements. This application does not limit the specific values ​​of the window length and the sliding step size.

[0031] In specific implementation, the preprocessed electromyography (EMG) signal is divided into continuous signal segments by a sliding window through the time window. This can be achieved in the following way: starting from the starting point of the preprocessed EMG signal, signal segments with a length equal to the window length are sequentially extracted at intervals of the sliding step size. Each extraction operation extracts the data points of the corresponding time segment in the preprocessed EMG signal to form a signal segment. Since the sliding step size is less than the window length, there is partial overlap in time between adjacent signal segments. This extraction process is repeated until the signal ends, thereby obtaining a series of temporally continuous and partially overlapping signal segments. In other embodiments, other methods can also be used to determine this, which are not limited here.

[0032] It should be noted that the signal segment mentioned in this application refers to a block of signal data within a continuous time period extracted from the preprocessed electromyographic signal through a sliding time window.

[0033] For specific implementation, refer to Figure 3As shown, the figure is a flow diagram for determining the median frequency according to some embodiments of the present application. The median frequency of each signal segment is determined, and then the median frequency sequence of the preprocessed electromyography signal is obtained. This can be achieved in the following manner, for example: for each signal segment obtained by division, first perform short-time Fourier transform on each signal segment to estimate its power spectral density; then in the frequency domain, integrate the power spectral density from low frequency to high frequency to calculate the cumulative power; the frequency point corresponding to the cumulative power reaching 50% of the total power of the corresponding signal segment is taken as the median frequency of the corresponding signal segment; the above short-time Fourier transform and median frequency finding process is repeatedly performed in time sequence for the continuous signal segments, and all the calculated median frequency values are arranged in time sequence according to the center time of the corresponding signal segment, that is, the median frequency sequence of the preprocessed electromyography signal is obtained.

[0034] It should be noted that the median frequency sequence in the present application refers to time series data formed by arranging the median frequency of each signal segment in time sequence, which is used to represent the trend of the center of gravity of the electromyography power spectrum over time, and reflects the frequency spectrum migration phenomenon in the muscle fatigue process.

[0035] In a specific implementation, the amplitude envelope of each signal segment is extracted, and the approximate entropy of the corresponding amplitude envelope is calculated, and then the approximate entropy sequence of the amplitude envelope is obtained. This can be achieved in the following manner, for example: for each signal segment, first perform Hilbert transform on the signal segment, and calculate the modulus of the analytic signal, taking the modulus sequence as the amplitude envelope of the current signal segment; then, calculate the approximate entropy of the amplitude envelope sequence, which includes: presetting the pattern dimension and the tolerance parameter, wherein the tolerance parameter is usually set as a proportional coefficient of the standard deviation of the amplitude envelope sequence; then, in the amplitude envelope sequence, the conditional probability of matching between the vector with the pattern dimension and the vector with the pattern dimension plus one is counted; finally, the approximate entropy value of the current amplitude envelope is obtained by taking the logarithm of the conditional probability and performing operations; the above amplitude envelope extraction and approximate entropy calculation process is repeatedly performed for each signal segment, and all the obtained approximate entropy values are arranged in time sequence according to the center time of the corresponding signal segment, that is, the approximate entropy sequence of the amplitude envelope is obtained.

[0036] It should be noted that the approximate entropy sequence of the amplitude envelope in the present application refers to time series data formed by arranging the approximate entropy of the amplitude envelope of each signal segment in time sequence, which is used to represent the complexity of the amplitude envelope of the electromyography signal over time, and reflects the evolution of the neural control strategy in the muscle fatigue process.

[0037] In step 104, a risk index of muscle fatigue state is constructed according to the cooperative change relationship between the median frequency sequence and the approximate entropy sequence.

[0038] In some embodiments, constructing the risk index of muscle fatigue state according to the co-variation relationship between the median frequency sequence and the approximate entropy sequence can be implemented by the following steps: Setting the length of the time window for co-variation analysis, and then cutting the data segment in the latest time window from the median frequency sequence and the approximate entropy sequence; Determining the quantitative index of the co-variation relationship between the median frequency sequence and the approximate entropy sequence based on the cut data segment; Mapping the quantitative index to the risk index of muscle fatigue state.

[0039] In a specific implementation, setting the length of the time window for co-variation analysis, and then cutting the data segment in the latest time window from the median frequency sequence and the approximate entropy sequence can be implemented in the following manner, for example: first, according to the slow and fast characteristics of muscle fatigue state change and the real-time requirement of risk warning, a co-variation analysis time window length is preset; the length of the time window needs to be long enough to cover the duration required for observable co-variation of the median frequency and the approximate entropy, which is usually of the order of tens of seconds, and its specific value can be set within a reasonable range according to the empirical data of actual rehabilitation nursing scenarios; then, based on the current time, the latest data segment with a length equal to the co-variation analysis time window length is cut from the median frequency sequence and the approximate entropy sequence respectively, thereby obtaining two strictly time-aligned data segments for co-variation analysis, which are denoted as the current median frequency analysis segment and the current approximate entropy analysis segment, i.e. the data segment in the latest time window.

[0040] It should be noted that the data segment in the latest time window in the present application refers to the latest data subset in a time window cut from the median frequency sequence and the approximate entropy sequence, which serves to provide input data for analyzing the co-variation relationship between the two feature sequences in the recent time window to support real-time risk assessment.

[0041] In a specific implementation, the quantification index of the cooperative variation relationship between the median frequency sequence and the approximate entropy sequence based on the intercepted data segment can be implemented in the following manner, for example: in one implementation, the Pearson correlation coefficient between the current median frequency analysis segment and the current approximate entropy analysis segment is calculated, and the absolute value of the correlation coefficient or the value obtained after a specific symbol processing is performed is taken as the quantification index representing the degree of cooperative variation of the two; wherein, the process of calculating the Pearson correlation coefficient includes: first, calculating the mean and standard deviation of each of the two analysis segments, then calculating the covariance of the corresponding data points of the two analysis segments, and finally dividing the covariance by the product of the two standard deviations to obtain the correlation coefficient; in another implementation, linear trend fitting is performed on the current median frequency analysis segment and the current approximate entropy analysis segment respectively to obtain the variation slopes of the two, and then the ratio of the two slopes or the difference value obtained after normalization processing is taken as the quantification index; the specific mathematical model for calculating the quantification index is not limited in the present application, and the core is to numerically represent the consistency of the variation trends of the two sequences within the recent time window; as a preferred embodiment, the current median frequency analysis segment and the current approximate entropy analysis segment can also be combined to form a two-dimensional feature sequence, wherein each data point is composed of the median frequency value and the approximate entropy value at the same time; then, the actual joint probability distribution of the two-dimensional sequence in the feature space and the theoretical joint probability distribution assuming that the two are completely independent are calculated; subsequently, the statistical distance between the two probability distributions, such as the Jensen-Shannon divergence or the Wasserstein distance, is calculated, and the specific numerical value of the statistical distance is taken as the quantification index representing the strength of the statistical dependence relationship between the two; the greater the index value, the more the actual distribution of the two sequences deviates from the independent assumption, i.e. the stronger the cooperative variation relationship between them; this method measures the fatigue-related information contained in the joint of the two features beyond their independent information from the nature of statistics.

[0042] It should be noted that the quantification index of the cooperative variation relationship in the present application refers to a statistical quantity or a measurement value for numerically representing the degree of cooperative variation between the median frequency sequence and the approximate entropy sequence within the recent time window, and its role is to quantify the correlation strength or the misalignment state of the two features in the fatigue process.

[0043] In a specific implementation, the mapping of the quantification index to a risk index of the muscle fatigue state can be achieved in the following manner, for example: first, a mapping function is defined from the value range of the quantification index to a standard risk index value range (e.g. between 0 and 100); the mapping function can be a linear function, a piecewise linear function or a nonlinear function, aiming to convert the degree of coordination or the degree of maladjustment reflected by the quantification index into a single-dimensional scalar with a larger value representing a higher risk of muscle fatigue; for example, when using the correlation coefficient as the quantification index, the mapping function can be designed such that the closer the correlation coefficient is to -1 or 1 (indicating high coordination or high negative coordination), the lower the risk index is, and the closer the correlation coefficient is to 0 (indicating maladjustment), the higher the risk index is; finally, the calculated quantification index is input into the mapping function, and the output value is determined as the risk index of the muscle fatigue state at the current time; in other embodiments, another method can also be used to achieve this, which is not limited here.

[0044] It should be noted that the risk index of the muscle fatigue state in the present application refers to a standardized numerical value obtained by mapping the quantification index of the coordination change relationship, which is used to comprehensively represent the risk level of the current muscle fatigue, and a larger value represents a higher risk of fatigue.

[0045] In step 105, a fatigue risk warning report of the patient during rehabilitation care is generated by combining the risk index with a preset fatigue risk threshold.

[0046] In some embodiments, the fatigue risk warning report of the patient during rehabilitation care can be generated by combining the risk index with a preset fatigue risk threshold in the following steps: A fatigue risk threshold of the patient during rehabilitation care is preset; A fatigue risk level of the patient is determined by combining the risk index with the preset fatigue risk threshold; A structured report containing warning information is generated as the fatigue risk warning report according to the fatigue risk level.

[0047] In a specific implementation, one or more ordered values previously obtained through historical data analysis or clinical experience calibration can be specifically used as the fatigue risk threshold according to the clinical needs of muscle fatigue risk warning and the numerical range characteristics of the risk index; wherein the process of determining the threshold value through historical data analysis includes: collecting a large number of rehabilitation nursing cases of the risk index data and its corresponding clinical fatigue assessment results calculated, and determining one or more numerical points that can best distinguish different fatigue states through statistical methods, such as based on percentile or receiver operating characteristic curve analysis; through clinical experience calibration, a rehabilitation therapist can set it according to the general performance of the patient population or the particularity of the individual patient; for example, a lower threshold value with higher sensitivity can be set for early rehabilitation patients, and a higher threshold value with higher tolerance can be set for later rehabilitation patients; the specific value of the fatigue risk threshold in the present application is not limited, and the core of its setting is to provide an objective and adjustable benchmark for subsequent risk level determination.

[0048] In a specific implementation, the determination of the fatigue risk level of the patient through the risk index combined with the preset fatigue risk threshold can be realized in the following manner, for example: the risk index is compared with a plurality of preset ordered fatigue risk thresholds in turn; and the discrete risk label corresponding to the comparison result is specifically used as the fatigue risk level of the patient; the specific process is: the risk index is compared with the low risk threshold, the medium risk threshold and the high risk threshold, etc.; if the risk index is lower than the low risk threshold, it is determined as a low risk level; if the risk index is between the low risk threshold and the medium risk threshold, it is determined as a medium risk level; if the risk index exceeds the high risk threshold, it is determined as a high risk level; in order to enhance the stability of the determination, hysteresis comparison logic can be used, that is, when the risk index rises above a certain threshold, the level is immediately triggered to rise, and only when it falls below the threshold minus a preset hysteresis, the level is triggered to fall.

[0049] It should be noted that the fatigue risk level in the present application refers to the discrete risk classification label determined after comparing the risk index of the muscle fatigue state with the preset threshold.

[0050] In a specific implementation, the fatigue risk warning report containing the structured report of the early warning information generated according to the fatigue risk level can be implemented in the following manner: first, a report template containing a time stamp, target muscle information, a risk index, a fatigue risk level, and a corresponding early warning measure field is constructed; then, the current time, the target muscle information, the risk index, and the fatigue risk level are filled into the template; then, according to the fatigue risk level, the corresponding early warning prompt text and nursing suggestion text are retrieved and filled from a preset early warning information mapping table; finally, the filled template data is output as the fatigue risk warning report; wherein the early warning information mapping table is a pre-defined data structure that associates different fatigue risk levels with specific early warning prompts, such as "normal", "attention", "warning", and nursing suggestions, such as "continue training", "suggest rest", "stop immediately"; the output form of the report can be a screen visual interface, a voice broadcast signal, or a standardized format electronic document, which is not limited in the present application.

[0051] It should be noted that the fatigue risk warning report in the present application refers to a structured output document containing a time stamp, target muscle information, a risk index, a fatigue risk level, and corresponding early warning measures, which provides clear fatigue state evaluation results and operable nursing suggestions to rehabilitation nursing personnel.

[0052] In addition, another aspect of the present application provides a risk warning system for rehabilitation nursing, which includes a fatigue risk warning unit, which refers to Figure 4 The figure is a structural schematic diagram of a fatigue risk warning unit according to some embodiments of the present application, which includes a collection module 201, a processing module 202, and an execution module 203, which are described as follows: The collection module 201 is mainly used for synchronously collecting three-axis acceleration signals and surface electromyography signals of target muscles of a patient during rehabilitation nursing in the present application; The processing module 202 is mainly used for filtering the surface electromyography signals according to the spectral characteristics of the three-axis acceleration signals to suppress artifacts generated by limb macro-movement, to obtain pre-processed electromyography signals in the present application; In addition, the processing module 202 is also used for determining a median frequency sequence and an approximate entropy sequence of the amplitude envelope of the pre-processed electromyography signals within a continuously sliding time window in the present application; In addition, the processing module 202 is also used for constructing a risk index of muscle fatigue state according to the cooperative change relationship between the median frequency sequence and the approximate entropy sequence in the present application; The execution module 203 in this application is mainly used to generate a fatigue risk warning report for patients during rehabilitation care by combining the risk index with a preset fatigue risk threshold.

[0053] In addition, this application also provides a computer device, the computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the fatigue risk warning method described above.

[0054] In some embodiments, reference Figure 5 This figure is an internal structural diagram of a computer device implementing a fatigue risk warning method according to some embodiments of this application. The fatigue risk warning method in the above embodiments can be implemented through... Figure 5 The computer device shown is used to implement this, and the computer device 300 includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.

[0055] The processor 301 may be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more devices used to control the execution of the fatigue risk warning method in this application.

[0056] The communication bus 302 is used to transmit information between the aforementioned components.

[0057] Memory 303 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory 303 may exist independently and be connected to processor 301 via communication bus 302. Memory 303 may also be integrated with processor 301.

[0058] The memory 303 is configured to store program codes for implementing the solutions of the present application, and the processor 301 is configured to execute the program codes stored in the memory 303. The program codes can include one or more software modules. The fatigue risk early warning method in the above-described embodiments can be implemented by the processor 301 and one or more software modules in the program codes in the memory 303.

[0059] The communication interface 304 is configured to communicate with other devices or communication networks, such as an Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc., using any transceiver-like mechanism.

[0060] In specific implementations, as an example, the computer device can include multiple processors, each of which can be a single-CPU processor or a multi-CPU processor. The processor herein can refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0061] The computer device described above can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer device.

[0062] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the fatigue risk early warning method described above is implemented.

[0063] In summary, in the rehabilitation nursing risk early warning system, the fatigue risk early warning method, the equipment and the medium disclosed by the embodiments of the present application, first, the three-axis acceleration signals and the surface electromyography signals of the target muscle of the patient during rehabilitation nursing are synchronously collected; the surface electromyography signals are filtered according to the frequency spectrum characteristics of the three-axis acceleration signals, so as to suppress the artifacts generated by the macro motion of the limbs, and the preprocessed electromyography signals are obtained; the median frequency sequence and the approximate entropy sequence of the amplitude envelope of the preprocessed electromyography signals are determined in the continuous sliding time window; the risk index of the muscle fatigue state is constructed according to the cooperative change relationship between the median frequency sequence and the approximate entropy sequence; the fatigue risk early warning report of the patient during rehabilitation nursing is generated by combining the risk index with the preset fatigue risk threshold; and the normal physiological fatigue process and the abnormal neuromuscular decompensation state can be distinguished.

[0064] Although the preferred embodiments of the present application have been described, those skilled in the art who, once aware of the basic inventive concept, can make additional changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0065] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and variations.

Claims

1. A fatigue risk early warning method, used to provide early warning of fatigue risk to users during rehabilitation care, characterized in that, The method includes the following steps: Simultaneously collect triaxial acceleration signals and surface electromyography signals of the target muscles during rehabilitation care; The surface electromyography signal is filtered based on the spectral characteristics of the triaxial acceleration signal to suppress artifacts generated by macroscopic limb movements, resulting in a preprocessed electromyography signal. Within a continuously sliding time window, the median frequency sequence and the approximate entropy sequence of the amplitude envelope of the preprocessed electromyographic signal are determined; A risk index for muscle fatigue state is constructed based on the synergistic relationship between the median frequency sequence and the approximate entropy sequence. The risk index is combined with a preset fatigue risk threshold to generate a fatigue risk warning report for patients during rehabilitation care.

2. The method as described in claim 1, characterized in that, The surface electromyography (EMG) signal is filtered based on the spectral characteristics of the triaxial acceleration signal to suppress artifacts generated by macroscopic limb movements, resulting in a preprocessed EMG signal. Specifically, this preprocessed EMG signal includes: Extract reference noise features characterizing the macroscopic movement patterns of the limbs from the triaxial acceleration signals; An adaptive filter for filtering motion artifacts is constructed based on the reference noise characteristics; The surface electromyography (EMG) signal is processed by the adaptive filter to suppress artifacts generated by macroscopic limb movements, resulting in a preprocessed EMG signal.

3. The method as described in claim 1, characterized in that, Determining the median frequency sequence and approximate entropy sequence of the amplitude envelope of the preprocessed electromyographic signal within a continuously sliding time window specifically includes: Preset the time window for continuous sliding; The preprocessed electromyographic signal is divided into a sliding window using the time window to obtain continuous signal segments. The median frequency of each signal segment is determined, thereby obtaining the median frequency sequence of the preprocessed electromyographic signal; The amplitude envelope of each signal segment is extracted and the approximate entropy of the corresponding amplitude envelope is calculated, thereby obtaining the approximate entropy sequence of the amplitude envelope.

4. The method as described in claim 1, characterized in that, The risk index for muscle fatigue state is constructed based on the synergistic relationship between the median frequency sequence and the approximate entropy sequence, specifically including: Set the time window length for collaborative change analysis, and then extract the data segment within the most recent time window from the median frequency sequence and the approximate entropy sequence; A quantitative index for determining the cooperative change relationship between the median frequency sequence and the approximate entropy sequence based on the extracted data segments; The quantitative indicators are mapped to a risk index for muscle fatigue.

5. The method as described in claim 1, characterized in that, The fatigue risk warning report for patients during rehabilitation care is generated by combining the risk index with a preset fatigue risk threshold, specifically including: Preset a fatigue risk threshold for patients during rehabilitation care; The patient's fatigue risk level is determined by combining the risk index with a preset fatigue risk threshold. A structured report containing early warning information is generated based on the fatigue risk level as the fatigue risk early warning report.

6. The method as described in claim 1, characterized in that, The target muscles refer to the main muscle groups selected as the subjects of fatigue monitoring based on the rehabilitation nursing movement patterns.

7. The method as described in claim 1, characterized in that, The surface electromyography signal refers to the electrophysiological signal generated by the activity of the target muscle motor unit.

8. A risk warning system for rehabilitation nursing, comprising a fatigue risk warning unit, characterized in that, The fatigue risk early warning unit includes: The acquisition module is used to simultaneously acquire triaxial acceleration signals and surface electromyography signals of the target muscles during rehabilitation care. The processing module is used to filter the surface electromyography signal according to the spectral characteristics of the triaxial acceleration signal to suppress artifacts generated by macroscopic limb movement and obtain a preprocessed electromyography signal. The processing module is also used to determine the median frequency sequence and the approximate entropy sequence of the amplitude envelope of the preprocessed electromyographic signal within a continuously sliding time window. The processing module is also used to construct a risk index of muscle fatigue state based on the synergistic change relationship between the median frequency sequence and the approximate entropy sequence; The execution module is used to generate a fatigue risk warning report for patients during rehabilitation care by combining the risk index with a preset fatigue risk threshold.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the fatigue risk warning method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the fatigue risk warning method as described in any one of claims 1 to 7.

Images