A rhabdomyolysis early warning system based on a flexible wearable device

Abstract

The present application relates to the technical field of medical analysis early warning, and particularly relates to a rhabdomyolysis early warning system based on a flexible wearable device, which comprises a data acquisition module, which is used for acquiring electromyographic signals, flexible wearable device deformation and position data; a data analysis module, which is used for calculating a data acquisition risk tendency value according to bending parameters and fluid parameters, and comparing the data acquisition risk tendency value with a preset value to divide device types; an automatic correction module, which comprises an analysis unit, which is used for judging whether to perform correction analysis according to a flexible wearable device risk type and an abnormal fluctuation condition of electromyographic signals; a correction unit, which is used for determining whether to perform correction by comparing the difference degree of electromyographic signals of a flexible wearable device to be corrected and normal devices; and a monitoring module, which is used for comparing the difference of correction amounts between initial and secondary intermittent periods, and deciding to adjust correction parameters or replace the flexible wearable device. The present application improves the timeliness of rhabdomyolysis state monitoring and the timeliness of dynamic self-adaptive correction after signal acquisition is disturbed by movement.

Description

A rhabdomyolysis early warning system based on flexible wearable devices Technical Field

[0001] This invention relates to the field of medical analysis and early warning technology, and in particular to a rhabdomyolysis early warning system based on a flexible wearable device. Background Technology

[0002] Early warning of rhabdomyolysis has always faced significant challenges in the fields of sports medicine and intensive care. Traditional detection methods mainly rely on blood biochemical index analysis, which suffers from strong lag and the inability to monitor in real time. Although existing flexible wearable devices can collect electromyographic signals, signal distortion often occurs in practical applications due to factors such as device deformation and sweat interference, and they lack multi-parameter collaborative analysis mechanisms for muscle injury risk. Furthermore, existing systems generally lack adaptive correction functions, failing to effectively address dynamic interference issues such as device displacement and poor contact during exercise, severely impacting the accuracy of monitoring data and the timeliness of warnings. These technical deficiencies limit the clinical application value of flexible wearable devices in the early warning of rhabdomyolysis.

[0003] For example, Chinese patent application publication number CN118866388B discloses a method for assessing acute kidney injury induced by rhabdomyolysis. This method acquires time-series data of N-dimensional detection indicators for each rhabdomyolysis patient; constructs an N-dimensional data space; for any two data points in the N-dimensional data space, obtains an initial distance metric between the two data points; obtains a distance optimization factor between the two data points; optimizes the initial distance metric using the distance optimization factor to obtain the clustering distance between the two data points; obtains a preset number of clusters based on the clustering distance between each pair of data points; trains a Hidden Markov Model (HMM) based on each cluster to obtain a trained HMM; and uses the trained HMM to assess the risk of acute kidney injury in real time, thereby improving the predictive ability of the trained HMM and ensuring the accuracy of risk assessment for acute kidney injury induced by rhabdomyolysis.

[0004] However, existing technologies suffer from problems such as strong lag in skeletal muscle state monitoring and the inability to dynamically and adaptively correct signals due to motion interference. Summary of the Invention

[0005] To address this, the present invention provides a rhabdomyolysis early warning system based on a flexible wearable device, which overcomes the problems of strong lag in rhabdomyolysis state monitoring and the inability to timely dynamically and adaptively correct signal acquisition due to motion interference in the prior art.

[0006] To achieve the above objectives, the present invention provides a rhabdomyolysis early warning system based on a flexible wearable device, comprising:

[0007] The data acquisition module is used to collect electromyographic signals, deformation data, and position data of the flexible wearable device.

[0008] The data analysis module, which is connected to the data acquisition module, is used to calculate the data acquisition risk tendency value of the flexible wearable device based on the bending parameters and fluid parameters of the location of the smart flexible patch, and classify the flexible wearable device into types based on the comparison result of the data acquisition risk tendency value and the preset data acquisition risk tendency value.

[0009] An automatic correction module, connected to the data analysis module, includes,

[0010] The analysis unit is used to determine whether to perform corrective analysis on the flexible wearable device based on the risk tendency type of data acquisition and / or whether abnormal fluctuations occur during the electromyography signal acquisition process.

[0011] A correction unit, connected to the analysis unit, is used to determine and correct based on the difference between the electromyographic signals of the flexible wearable device that need to be corrected and the electromyographic signals of the flexible wearable device that do not need to be corrected during the intermittent period.

[0012] A monitoring module, which is connected to the automatic correction module, is used to monitor the correction amount of the corrected flexible wearable device during the second intermittent period, and determine whether to adjust the correction process parameters or replace the flexible wearable device based on the difference between the correction amount during the second intermittent period and the correction amount during the first intermittent period.

[0013] An adjustment module, which is connected to both the monitoring module and the automatic correction module, is used to determine the analysis duration of the adjustment and correction parameters based on the difference between the correction amount during the secondary intermittent period and the correction amount during the initial intermittent period.

[0014] Furthermore, the data analysis module calculates the data acquisition risk propensity value of the flexible wearable device based on the bending parameters and fluid parameters at the location of the smart flexible patch, and classifies the flexible wearable device into different types based on the comparison result between the data acquisition risk propensity value and the preset data acquisition risk propensity value; wherein,

[0015] If the data collection risk propensity value is greater than the preset data collection risk propensity value, the flexible wearable device is classified as a high-risk type.

[0016] If the data collection risk propensity value is less than or equal to the preset data collection risk propensity value, the flexible wearable device is classified as a low-risk type.

[0017] Furthermore, the preset data collection risk propensity value is determined based on the historical average of the data collection risk propensity values ​​of several flexible wearable devices.

[0018] Furthermore, the analysis unit determines whether to perform corrective analysis on the flexible wearable device based on the risk tendency type of data acquisition from the flexible wearable device and / or whether abnormal fluctuations occur during the electromyography signal acquisition process; wherein,

[0019] If the data acquisition risk tendency type of the flexible wearable device is high-risk or abnormal fluctuations occur during the electromyography signal acquisition process, it is determined that the flexible wearable device should be corrected and analyzed.

[0020] If the data acquisition risk tendency type of the flexible wearable device is low risk and no abnormal fluctuations occur during the electromyography signal acquisition process, it is determined that the flexible wearable device will not perform correction analysis.

[0021] Furthermore, the correction unit determines the correction based on the difference between the electromyographic signals of the flexible wearable device that require correction analysis during intermittent periods and the electromyographic signals of the flexible wearable device that do not require correction analysis; wherein,

[0022] If the difference between the electromyographic signal of the flexible wearable device that needs to be corrected based on the intermittent time period and the electromyographic signal of the flexible wearable device that does not need to be corrected is greater than the preset electromyographic signal difference, then it is determined to perform correction;

[0023] If the difference between the electromyographic (EMG) signal of the flexible wearable device that needs to be corrected based on the intermittent time period and the EMG signal of the flexible wearable device that does not need to be corrected is less than or equal to the preset EMG signal difference, then no correction is performed.

[0024] Furthermore, the preset electromyographic signal difference degree is determined by taking the mean plus twice the standard deviation based on the difference degree distribution of electromyographic signals of several flexible wearable devices under normal conditions.

[0025] Furthermore, the monitoring module is used to monitor the correction amount of the corrected flexible wearable device during the secondary intermittent period, and based on the difference between the correction amount during the secondary intermittent period and the correction amount during the initial intermittent period, determine whether to adjust the correction process parameters or replace the flexible wearable device; wherein,

[0026] If the difference between the correction amount during the second intermittent period and the correction amount during the first intermittent period is greater than the difference between the first preset correction amount, it is determined that the flexible wearable device should be replaced.

[0027] If the difference between the correction amount during the second intermittent period and the correction amount during the first intermittent period is greater than the difference between the second preset correction amount and less than or equal to the difference between the first preset correction amount, the adjustment correction process parameters are determined.

[0028] If the difference between the correction amount during the second interval and the correction amount during the first interval is less than or equal to the difference between the second preset correction amount, the current correction strategy is maintained.

[0029] Furthermore, the first preset correction difference is determined based on the hardware performance limits of the flexible wearable device, and the second preset correction difference is half of the first preset correction difference.

[0030] Furthermore, the adjustment module determines the analysis duration of the adjustment and correction parameters based on the difference between the correction amount during the secondary interval and the correction amount during the initial interval; wherein...

[0031] If the difference between the correction amount in the second interval period and the correction amount in the first interval period is less than or equal to the first preset correction amount difference and greater than the second preset correction amount difference, it is determined to extend the analysis time of the correction parameter.

[0032] If the difference between the correction amount in the second interval period and the correction amount in the first interval period is greater than the difference in the first preset correction amount, it is determined to shorten the analysis time of the correction parameter.

[0033] If the difference between the correction amount in the second intermittent period and the correction amount in the first intermittent period is less than or equal to the difference in the second preset correction amount, the analysis duration for which the correction parameter is not modified is determined.

[0034] Furthermore, the difference between the correction amount of the second intermittent period and the correction amount of the first intermittent period and the difference between the second preset correction amount are positively correlated with the adjustment amount of the analysis duration of the correction parameter.

[0035] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention calculates the data acquisition risk tendency value of the flexible wearable device by using the bending parameters and fluid parameters of the location of the intelligent flexible patch, and classifies the flexible wearable device based on the comparison result of the data acquisition risk tendency value and the preset data acquisition risk tendency value. If the data acquisition risk tendency value is greater than the preset data acquisition risk tendency value, it indicates that the device is significantly affected by motion deformation or physiological environmental interference, and the reliability of electromyography signal acquisition decreases. The flexible wearable device is accurately classified as a high-risk type. If the data acquisition risk tendency value is less than or equal to the preset data acquisition risk tendency value, it indicates that the device is in a stable environment and the reliability of electromyography signal acquisition is high. The flexible wearable device is accurately classified as a low-risk type. Through the above, the timeliness of striated muscle state monitoring and the timeliness of dynamic adaptive correction after signal acquisition is affected by motion interference are improved.

[0036] Furthermore, this invention determines whether to perform corrective analysis on the flexible wearable device by analyzing the risk tendency type of data acquisition and whether abnormal fluctuations occur during electromyography (EMG) signal acquisition. If the risk tendency type of the flexible wearable device is high or abnormal fluctuations occur during EMG signal acquisition, it indicates that the device's environment (movement or physiological conditions) has significantly threatened the stability of signal acquisition, thus accurately determining whether to perform corrective analysis on the flexible wearable device. If the risk tendency type of the flexible wearable device is low and no abnormal fluctuations occur during EMG signal acquisition, it indicates that the device's working state is stable and signal acquisition is not significantly interfered with, thus accurately determining whether to perform corrective analysis on the flexible wearable device. Through the above, the timeliness of striated muscle state monitoring and the timeliness of dynamic adaptive correction after signal acquisition is interfered with by movement are improved.

[0037] Furthermore, this invention determines correction based on the difference between the electromyographic (EMG) signals of the flexible wearable device requiring correction analysis during intermittent periods and those of the flexible wearable device not requiring correction analysis. If the difference between the EMG signals of the flexible wearable device requiring correction analysis during intermittent periods and those of the flexible wearable device not requiring correction analysis is greater than a preset EMG signal difference, it indicates that the EMG signal characteristics of the device to be corrected significantly deviate from the normal baseline, and correction is accurately determined. If the difference between the EMG signals of the flexible wearable device requiring correction analysis during intermittent periods and those of the flexible wearable device not requiring correction analysis is less than or equal to a preset EMG signal difference, it indicates that the EMG signals of the device to be corrected are not significantly different from those of the normal device and are within an acceptable fluctuation range, and no correction is accurately determined. Through the above, the timeliness of striated muscle state monitoring and the timeliness of dynamic adaptive correction after signal acquisition is disturbed by movement are improved.

[0038] Furthermore, this invention monitors the correction amount of the modified flexible wearable device during the secondary intermittent period and determines whether to adjust the correction process parameters or replace the flexible wearable device based on the difference between the correction amount during the secondary intermittent period and the correction amount during the initial intermittent period. If the difference between the correction amount during the secondary intermittent period and the correction amount during the initial intermittent period is greater than a first preset correction amount difference, it indicates that the device performance still deteriorates significantly after correction, and there is an unrecoverable hardware fault, thus accurately determining to replace the flexible wearable device. If the difference between the correction amount during the secondary intermittent period and the correction amount during the initial intermittent period is greater than a second preset correction amount difference but less than or equal to the first preset correction amount difference, it indicates that the correction strategy is effective but has not achieved the best results, and the algorithm parameters or adjustment logic need to be optimized, thus accurately determining to adjust the correction process parameters. If the difference between the correction amount during the secondary intermittent period and the correction amount during the initial intermittent period is less than or equal to the second preset correction amount difference, it indicates that the device performance is stable after correction, and the difference is within the normal fluctuation range, thus accurately determining to maintain the current correction strategy. Through the above, the timeliness of striated muscle state monitoring and the timeliness of dynamic adaptive correction after signal acquisition is disturbed by motion are improved.

[0039] Furthermore, this invention determines the analysis duration for adjusting the correction parameters by the difference between the correction amount during the second interval and the correction amount during the first interval. If the difference between the correction amount during the second interval and the correction amount during the first interval is less than or equal to a first preset correction amount difference but greater than a second preset correction amount difference, it indicates that the correction effect is stabilizing but still requires continuous verification, thus accurately determining to extend the analysis duration for the correction parameters. If the difference between the correction amount during the second interval and the correction amount during the first interval is greater than the first preset correction amount difference, it indicates that the correction effect is fluctuating more significantly or the system stability is decreasing, thus accurately determining to shorten the analysis duration for the correction parameters. If the difference between the correction amount during the second interval and the correction amount during the first interval is less than or equal to the second preset correction amount difference, it indicates that the correction strategy has reached a stable state, thus accurately determining the analysis duration without modifying the correction parameters. Through the above, the timeliness of striated muscle state monitoring and the timeliness of dynamic adaptive correction after signal acquisition is affected by motion interference are improved. Attached Figure Description

[0040] Figure 1 is a schematic diagram of the rhabdomyolysis early warning system based on a flexible wearable device according to an embodiment of the present invention;

[0041] Figure 2 is a schematic diagram of the automatic correction module of the rhabdomyolysis early warning system based on a flexible wearable device according to an embodiment of the present invention;

[0042] Figure 3 is a flowchart of the data analysis module of the rhabdomyolysis early warning system based on a flexible wearable device according to an embodiment of the present invention;

[0043] Figure 4 is a flowchart of the analysis unit of the rhabdomyolysis early warning system based on a flexible wearable device according to an embodiment of the present invention. Detailed Implementation

[0044] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0045] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0046] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0047] Please refer to Figures 1-4. Figure 1 is a schematic diagram of the structure of the rhabdomyolysis early warning system based on a flexible wearable device according to an embodiment of the present invention; Figure 2 is a schematic diagram of the structure of the automatic correction module of the rhabdomyolysis early warning system based on a flexible wearable device according to an embodiment of the present invention; Figure 3 is a flowchart of the data analysis module of the rhabdomyolysis early warning system based on a flexible wearable device according to an embodiment of the present invention; Figure 4 is a flowchart of the analysis unit of the rhabdomyolysis early warning system based on a flexible wearable device according to an embodiment of the present invention.

[0048] This invention provides a rhabdomyolysis early warning system based on a flexible wearable device, comprising:

[0049] The data acquisition module is used to collect electromyographic signals, deformation data, and position data of the flexible wearable device.

[0050] The data analysis module, which is connected to the data acquisition module, is used to calculate the data acquisition risk tendency value of the flexible wearable device based on the bending parameters and fluid parameters of the location of the smart flexible patch, and classify the flexible wearable device into types based on the comparison result of the data acquisition risk tendency value and the preset data acquisition risk tendency value.

[0051] An automatic correction module, connected to the data analysis module, includes,

[0052] The analysis unit is used to determine whether to perform corrective analysis on the flexible wearable device based on the risk tendency type of data acquisition and / or whether abnormal fluctuations occur during the electromyography signal acquisition process.

[0053] A correction unit, connected to the analysis unit, is used to determine and correct based on the difference between the electromyographic signals of the flexible wearable device that need to be corrected and the electromyographic signals of the flexible wearable device that do not need to be corrected during the intermittent period.

[0054] A monitoring module, which is connected to the automatic correction module, is used to monitor the correction amount of the corrected flexible wearable device during the second intermittent period, and determine whether to adjust the correction process parameters or replace the flexible wearable device based on the difference between the correction amount during the second intermittent period and the correction amount during the first intermittent period.

[0055] An adjustment module, which is connected to both the monitoring module and the automatic correction module, is used to determine the analysis duration of the adjustment and correction parameters based on the difference between the correction amount during the secondary intermittent period and the correction amount during the initial intermittent period.

[0056] The electromyographic signals collected by the flexible wearable device in this embodiment of the invention include, but are not limited to, "resting potential signals, action potential signals, and electromyographic spectrum signals". The deformation data of the flexible wearable device includes, but are not limited to, "degree of stretching deformation, change of bending angle, and amount of torsional displacement". The position data of the flexible wearable device includes, but are not limited to, "three-dimensional spatial coordinates, joint movement trajectory, and relative posture of limbs".

[0057] Specifically, the data analysis module, after determining the classification type of flexible wearable devices, calculates the data acquisition risk tendency value of the flexible wearable device based on the bending parameters and fluid parameters of the location of the smart flexible patch, and classifies the flexible wearable device based on the comparison result of the data acquisition risk tendency value and the preset data acquisition risk tendency value.

[0058] If the data collection risk propensity value is greater than the preset data collection risk propensity value, the data analysis module determines that the flexible wearable device is classified as a high-risk type.

[0059] If the data collection risk propensity value is less than or equal to the preset data collection risk propensity value, the data analysis module determines that the flexible wearable device is classified as a low-risk type.

[0060] In this embodiment of the invention, the bending parameters are determined based on the bending frequency and amplitude of the smart flexible patch. The calculation method is to multiply the bending frequency by a weighting coefficient and then add the bending amplitude by a weighting coefficient. The weighting coefficient ranges from 0.4 to 0.6, with a preferred value of 0.5. This preferred value is chosen because this design avoids complex weight allocation logic, facilitates engineering implementation and data calculation, and reduces algorithm complexity. For example, if the bending frequency of the smart flexible patch is 3Hz, the bending amplitude is 45°, and the weighting coefficient is 0.5, the bending parameter is 3Hz x 0.5 + 45° x 0.5 = 23. The fluid parameters are determined based on the sweating liquid velocity and flow rate. The calculation method is to multiply the sweating liquid velocity by a weighting coefficient and then add the sweating liquid flow rate by a weighting coefficient. For example, if the sweating liquid velocity is 0.5 μL / min and the sweating liquid flow rate is 1.2 μL / cm³, the fluid parameters are determined based on the sweating liquid velocity and flow rate. 2 With a weighting factor of 0.5, the fluid parameters are obtained as 0.5 μL / min × 0.5 + 1.2 μL / cm. 2 X0.5 = 0.85. The data acquisition risk tendency value of the flexible wearable device is calculated based on the bending parameters and fluid parameters at the location of the smart flexible patch. The calculation method is to add the normalized bending parameter to the normalized fluid parameter and divide by 2. For example, if the maximum value of the bending parameter is set to 30, the normalized bending parameter is 0.77. If the maximum value of the fluid parameter is set to 1.0, the normalized fluid parameter is 0.85. The resulting data acquisition risk tendency value is (0.85 + 0.77) / 2 = 0.81. The preset data acquisition risk tendency value is determined based on the historical average value of the data acquisition risk tendency values ​​of several flexible wearable devices. For example, if the historical values ​​of the data acquisition risk tendency values ​​of two groups of flexible wearable devices are 0.8 and 0.9, the preset data acquisition risk tendency value is 0.85. However, the above value is not limited to this. Those skilled in the art can also adjust the value according to actual needs.

[0061] This invention calculates the data acquisition risk propensity value of the flexible wearable device based on the bending parameters and fluid parameters at the location of the intelligent flexible patch. Based on the comparison between the calculated risk propensity value and a preset risk propensity value, the flexible wearable device is categorized. If the risk propensity value is greater than the preset value, it indicates significant interference from motion or the physiological environment, leading to a decrease in the reliability of electromyography (EMG) signal acquisition; thus, the flexible wearable device is accurately classified as a high-risk type. If the risk propensity value is less than or equal to the preset value, it indicates a stable environment and high reliability of EMG signal acquisition; thus, the flexible wearable device is accurately classified as a low-risk type. This improves the timeliness of striated muscle state monitoring and the timeliness of dynamic adaptive correction after signal acquisition is affected by motion interference.

[0062] Specifically, the analysis unit determines whether to perform corrective analysis on the flexible wearable device based on the risk tendency type of the flexible wearable device data acquisition and / or whether abnormal fluctuations occur during the electromyography signal acquisition process.

[0063] If the data acquisition risk tendency type of the flexible wearable device is high-risk or abnormal fluctuations occur during the electromyography signal acquisition process, the analysis unit determines to perform corrective analysis on the flexible wearable device.

[0064] If the data acquisition risk tendency type of the flexible wearable device is low risk and no abnormal fluctuations occur during the electromyography signal acquisition process, the analysis unit determines that the flexible wearable device will not perform correction analysis.

[0065] The abnormal fluctuation described in this invention is determined based on whether the amplitude of the electromyographic signal fluctuation is greater than a preset fluctuation amplitude. For example, if the current electromyographic signal is 100μV and suddenly increases to 400μV at a certain moment, the fluctuation amplitude is 300%, which exceeds the preset fluctuation amplitude of 100%, thus determining that an abnormal fluctuation has occurred. The preset fluctuation amplitude range is set to 50%-150%, with a preferred value of 100%. The reason for selecting this preferred value is that if the threshold is too low, normal muscle contraction (such as rapid force exertion) or slight noise may be misjudged as abnormal, leading to frequent triggering of correction analysis and increased consumption of computing resources. If the threshold is too high, moderate abnormalities (such as gradual signal drift or intermittent interference) may be missed, causing the device to be in an inaccurate state for a long time. However, the above value is not limited to this, and those skilled in the art can also adjust the value according to actual needs.

[0066] This invention determines whether to perform corrective analysis on the flexible wearable device by analyzing the risk tendency type of data acquisition and the presence of abnormal fluctuations during electromyography (EMG) signal acquisition. If the risk tendency type is high or abnormal fluctuations occur during EMG signal acquisition, it indicates that the device's environment (movement or physiological conditions) significantly threatens the stability of signal acquisition, thus accurately determining whether to perform corrective analysis. Conversely, if the risk tendency type is low and no abnormal fluctuations occur during EMG signal acquisition, it indicates that the device is operating stably and signal acquisition is not significantly interfered with, thus accurately determining whether to perform corrective analysis. This improves the timeliness of striated muscle state monitoring and the timeliness of dynamic adaptive correction after signal acquisition is affected by movement.

[0067] Specifically, the correction unit determines to perform correction based on the difference between the electromyographic signals of the flexible wearable device that need to be corrected and those that do not need to be corrected during the intermittent period, under the condition that correction is to be performed.

[0068] If the difference between the electromyographic signal of the flexible wearable device that needs to be corrected based on the intermittent time period and the electromyographic signal of the flexible wearable device that does not need to be corrected is greater than a preset electromyographic signal difference, the correction unit determines to perform correction.

[0069] If the difference between the electromyographic signal of the flexible wearable device that needs to be corrected based on the intermittent time period and the electromyographic signal of the flexible wearable device that does not need to be corrected is less than or equal to a preset electromyographic signal difference, the correction unit determines not to perform correction.

[0070] In this embodiment of the invention, the intermittent period refers to a non-movement period in which the body remains still for a longer than a preset resting time. The preset resting time ranges from 4 to 6 minutes, with a preferred value of 5 minutes. This preferred value is chosen because shorter than 5 minutes may result in incomplete dissipation of residual muscle potentials or unstable electrode contact, leading to errors in the difference calculation. Longer than 5 minutes will significantly increase the system waiting time and reduce the correction response speed, especially affecting real-time performance in frequent activity scenarios. The correction amount for the flexible wearable device is based on the electromyographic signals of the flexible wearable device to be corrected and analyzed during the intermittent period, and the electromyographic signals of the flexible wearable device that do not require correction and analysis. The difference between the difference of the signal and the preset difference of the electromyographic signal is determined. For example, the electromyographic signal of the device to be corrected is 280μV, the electromyographic signal of the normal device is 200μV, the preset difference threshold is 20%, the difference is (280μV-200μV) / 200μV=40%, the difference is 20%, the gain of the signal amplifier of the device to be corrected is increased by 20%, the electromyographic signal of the device after correction drops to 240μV, the difference is recalculated, (240μV-200μV) / 200μV=20%, the difference is reduced from 40% to 20%, the correction is effective, but the above values ​​are not limited to these, and those skilled in the art can also adjust the values ​​according to actual needs.

[0071] In this embodiment of the invention, the electromyographic signal difference degree is determined based on the relative deviation of the root mean square (RMS) values ​​of the electromyographic signals of the device to be corrected and the normal device. For example, if the RMS value of the device to be corrected is 280 μV and that of the normal device is 200 μV, then the difference degree is (280 μV - 200 μV) / 200 μV × 100% = 40%. The preset electromyographic signal difference degree is determined by taking the mean plus twice the standard deviation based on the difference degree distribution of electromyographic signals of several flexible wearable devices under normal conditions. For example, if the mean difference degree is 10% and the standard deviation is 5%, then the electromyographic signal difference degree can be set to mean + 2 × 5% = 20%. However, the above values ​​are not limited to these, and those skilled in the art can adjust the values ​​according to actual needs.

[0072] This invention determines correction based on the difference between the electromyographic (EMG) signals of a flexible wearable device requiring correction analysis during intermittent periods and those of a flexible wearable device not requiring correction analysis. If the difference between the EMG signals of the flexible wearable device requiring correction analysis during intermittent periods and those of the flexible wearable device not requiring correction analysis is greater than a preset EMG signal difference, it indicates that the EMG signal characteristics of the device to be corrected significantly deviate from the normal baseline, and correction is precisely determined. If the difference between the EMG signals of the flexible wearable device requiring correction analysis during intermittent periods and those of the flexible wearable device not requiring correction analysis is less than or equal to the preset EMG signal difference, it indicates that the EMG signal of the device to be corrected is not significantly different from that of a normal device and is within an acceptable fluctuation range, and no correction is precisely determined. Through the above methods, the timeliness of striated muscle state monitoring and the timeliness of dynamic adaptive correction after signal acquisition is affected by motion interference are improved.

[0073] Specifically, the monitoring module, under the condition that the adjustment and correction process parameters are determined or the flexible wearable device is replaced, is used to monitor the correction amount of the corrected flexible wearable device in the second intermittent period, and determine the adjustment and correction process parameters or the replacement of the flexible wearable device based on the difference between the correction amount in the second intermittent period and the correction amount in the first intermittent period.

[0074] If the difference between the correction amount during the second intermittent period and the correction amount during the first intermittent period is greater than the difference of the first preset correction amount, the monitoring module determines to replace the flexible wearable device.

[0075] If the difference between the correction amount during the second intermittent period and the correction amount during the first intermittent period is greater than the difference between the second preset correction amount and less than or equal to the difference between the first preset correction amount, the monitoring module determines to adjust the correction process parameters.

[0076] If the difference between the correction amount during the second interval and the correction amount during the first interval is less than or equal to the difference between the second preset correction amount, the monitoring module determines to maintain the current correction strategy.

[0077] In this embodiment of the invention, the current correction strategy is based on the correction result of the initial interval period. The signal amplifier gain is adjusted to the set value after the initial correction (e.g., increased from the reference gain to 116), and this is used as the fixed parameter for subsequent monitoring. At the same time, other related correction parameters (e.g., filter range, electrode contact state) are kept unchanged. By comparing the difference between the correction amount of the second interval period and the initial correction amount, it is determined whether further adjustment of the gain parameter or replacement of the equipment is required, so as to achieve dynamic suppression of interference in electromyography signal acquisition.

[0078] In this embodiment of the invention, the range of the first preset correction difference is set to 15%-30%, with a preferred value of 20%. The reason for selecting this preferred value is that if the value is too low, it may trigger misjudgment due to individual differences in equipment or environmental interference. If the value is too high, it may lead to high-risk equipment not being replaced in time, and the risk of rhabdomyolysis cannot be effectively warned. The second preset correction difference is half of the first preset correction difference. For example, if the first preset correction difference is 20%, the second preset correction difference is 10%. However, the above value is not limited to this. Those skilled in the art can also adjust the value according to actual needs.

[0079] This invention monitors the correction amount of a modified flexible wearable device during a secondary intermittent period. Based on the difference between the correction amount during the secondary intermittent period and the correction amount during the initial intermittent period, it determines whether to adjust the correction process parameters or replace the flexible wearable device. If the difference between the correction amount during the secondary intermittent period and the correction amount during the initial intermittent period is greater than a first preset correction amount difference, it indicates that the device's performance has significantly deteriorated after correction, indicating an unrecoverable hardware fault, thus accurately determining whether to replace the flexible wearable device. If the difference between the correction amount during the secondary intermittent period and the correction amount during the initial intermittent period is greater than a second preset correction amount difference but less than or equal to the first preset correction amount difference, it indicates that the correction strategy is effective but has not achieved the optimal effect, and the algorithm parameters or adjustment logic need to be optimized, thus accurately determining whether to adjust the correction process parameters. If the difference between the correction amount during the secondary intermittent period and the correction amount during the initial intermittent period is less than or equal to the second preset correction amount difference, it indicates that the device's performance is stable after correction, and the difference is within the normal fluctuation range, thus accurately determining whether to maintain the current correction strategy. Through the above, the timeliness of striated muscle state monitoring and the timeliness of dynamic adaptive correction after signal acquisition is affected by motion interference are improved.

[0080] Specifically, the adjustment module determines the analysis time of the adjustment and correction parameters based on the difference between the correction amount in the second intermittent period and the correction amount in the first intermittent period, provided that the analysis time of the adjustment and correction parameters is determined.

[0081] If the difference between the correction amount in the second interval period and the correction amount in the first interval period is less than or equal to the first preset correction amount difference and greater than the second preset correction amount difference, the adjustment module determines to extend the analysis time of the correction parameter.

[0082] If the difference between the correction amount during the second interval and the correction amount during the first interval is greater than the difference between the first preset correction amount, the adjustment module determines to shorten the analysis time of the correction parameter.

[0083] If the difference between the correction amount of the second intermittent period and the correction amount of the first intermittent period is less than or equal to the difference of the second preset correction amount, the adjustment module determines the analysis duration for which the correction parameter is not modified.

[0084] In the embodiments of the present invention, the analysis duration is set to a range of 1 min to 5 min, with a preferred value of 3 min. The reason for selecting this preferred value is that a duration of 3 minutes can capture abnormal fluctuations in electromyography signals and changes in the device correction effect in a timely manner, without consuming too many computing resources due to excessive analysis frequency. This is suitable for the low-power operation requirements of wearable devices. However, the above value is not limited to this, and those skilled in the art can adjust the value according to actual needs.

[0085] In this embodiment of the invention, the difference between the correction amount of the second intermittent period and the correction amount of the first intermittent period and the difference of the second preset correction amount are positively correlated with the adjustment amount of the analysis duration of the correction parameter. The adjustment module adjusts the analysis duration of the correction parameter with a first adjustment coefficient. The range of the first adjustment coefficient is set to 0.1-0.3, with a preferred value of 0.2. The reason for selecting this preferred value is to avoid insufficient adjustment due to the coefficient being too small, which would prevent effective response to changes in the difference, and to prevent over-adjustment due to the coefficient being too large, which would lead to system oscillation or instability of the correction strategy. For example, if the initial analysis duration is 10 minutes, and the difference between the correction amount of the second intermittent period and the correction amount of the first intermittent period is less than or equal to the difference of the second preset correction amount, it is determined that the analysis duration of the correction parameter is extended. The calculation method is 10 minutes + 10 minutes * 0.2 = 12 minutes. However, the above value is not limited to this, and those skilled in the art can also adjust the value according to actual needs.

[0086] This invention determines the analysis duration for adjusting correction parameters by the difference between the correction amount during the second interval and the correction amount during the first interval. If the difference between the correction amount during the second interval and the correction amount during the first interval is less than or equal to a first preset correction amount difference but greater than a second preset correction amount difference, it indicates that the correction effect is stabilizing but still requires continuous verification. Therefore, the analysis duration for extending the correction parameters is precisely determined. If the difference between the correction amount during the second interval and the correction amount during the first interval is greater than the first preset correction amount difference, it indicates that the correction effect is fluctuating more significantly or the system stability is decreasing. Therefore, the analysis duration for shortening the correction parameters is precisely determined. If the difference between the correction amount during the second interval and the correction amount during the first interval is less than or equal to the second preset correction amount difference, it indicates that the correction strategy has reached a stable state. Therefore, the analysis duration for not modifying the correction parameters is precisely determined. These methods improve the timeliness of striated muscle state monitoring and the timeliness of dynamic adaptive correction after signal acquisition is affected by motion interference.

[0087] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A rhabdomyolysis early warning system based on a flexible wearable device, characterized in that, include: The data acquisition module is used to collect electromyographic signals, deformation data, and position data of the flexible wearable device. A data analysis module, connected to the data acquisition module, calculates the data acquisition risk tendency value of the flexible wearable device based on the bending parameters and fluid parameters at the location of the smart flexible patch, and classifies the flexible wearable device into types based on the comparison result of the data acquisition risk tendency value and the preset data acquisition risk tendency value. The data acquisition risk tendency value is the average of the sum of normalized bending parameters and normalized fluid parameters. The bending parameters are the weighted sum of the bending frequency and bending amplitude of the smart flexible patch, and the fluid parameters are the weighted sum of the sweat liquid flow rate and liquid flow rate. An automatic correction module, also connected to the data analysis module, includes an analysis unit... The system is used to determine whether to perform correction analysis on the flexible wearable device based on the risk tendency type of data acquisition and / or whether abnormal fluctuations occur during the acquisition of electromyography (EMG) signals. A correction unit, connected to the analysis unit, is used to determine whether to perform correction based on the difference between the EMG signals of the flexible wearable device requiring correction analysis and those of the flexible wearable device not requiring correction analysis during the intermittent interval. A monitoring module, connected to the automatic correction module, is used to monitor the correction amount of the corrected flexible wearable device during the second intermittent interval and, based on the difference between the correction amount during the second intermittent interval and the correction amount during the first intermittent interval, determine whether to adjust the correction process parameters or replace the flexible wearable device. The device includes an adjustment module connected to both the monitoring module and the automatic correction module. This module determines the analysis duration of the adjustment parameters based on the difference between the correction amount during the secondary intermittent period and the correction amount during the initial intermittent period. The data analysis module calculates the data acquisition risk tendency value of the flexible wearable device based on the bending parameters and fluid parameters at the location of the intelligent flexible patch. It then classifies the flexible wearable device based on a comparison between the data acquisition risk tendency value and a preset data acquisition risk tendency value. If the data acquisition risk tendency value is greater than the preset data acquisition risk tendency value, the flexible wearable device is classified as a high-risk type. If the data acquisition risk tendency value is less than the preset data acquisition risk tendency value, the flexible wearable device is classified as a high-risk type. If the value is less than or equal to a preset data acquisition risk tendency value, the flexible wearable device is classified as a low-risk type. The analysis unit determines whether to perform corrective analysis on the flexible wearable device based on the data acquisition risk tendency type of the flexible wearable device and / or whether abnormal fluctuations occur during the electromyography (EMG) signal acquisition process. Specifically, if the data acquisition risk tendency type of the flexible wearable device is a high-risk type or abnormal fluctuations occur during the EMG signal acquisition process, corrective analysis is performed on the flexible wearable device. If the data acquisition risk tendency type of the flexible wearable device is a low-risk type and no abnormal fluctuations occur during the EMG signal acquisition process, no corrective analysis is performed on the flexible wearable device.The monitoring module monitors the correction amount of the corrected flexible wearable device during the second intermittent period and determines whether to adjust the correction process parameters or replace the flexible wearable device based on the difference between the correction amount during the second intermittent period and the correction amount during the first intermittent period. Specifically, if the difference between the correction amount during the second intermittent period and the correction amount during the first intermittent period is greater than a first preset correction amount difference, the flexible wearable device is replaced; if the difference between the correction amount during the second intermittent period and the correction amount during the first intermittent period is greater than a second preset correction amount difference but less than or equal to the first preset correction amount difference, the correction process parameters are adjusted; if the difference between the correction amount during the second intermittent period and the correction amount during the first intermittent period is less than or equal to the second preset correction amount difference, the current correction strategy is maintained.

2. The rhabdomyolysis early warning system based on a flexible wearable device according to claim 1, characterized in that, The preset data collection risk propensity value is determined based on the historical average of the data collection risk propensity values ​​of several flexible wearable devices.

3. The rhabdomyolysis early warning system based on a flexible wearable device according to claim 2, characterized in that, The correction unit determines whether to perform correction based on the difference between the electromyographic (EMG) signals of the flexible wearable device that require correction analysis during the intermittent period and those of the flexible wearable device that do not require correction analysis. Specifically, if the difference between the EMG signals of the flexible wearable device requiring correction analysis during the intermittent period and those of the flexible wearable device that do not require correction analysis is greater than a preset EMG signal difference, correction is determined to be performed; if the difference between the EMG signals of the flexible wearable device requiring correction analysis during the intermittent period and those of the flexible wearable device that do not require correction analysis is less than or equal to the preset EMG signal difference, no correction is determined to be performed.

4. The rhabdomyolysis early warning system based on a flexible wearable device according to claim 3, characterized in that, The preset electromyographic signal difference degree is determined by taking the mean plus twice the standard deviation based on the difference degree distribution of electromyographic signals of several flexible wearable devices under normal conditions.

5. The rhabdomyolysis early warning system based on a flexible wearable device according to claim 4, characterized in that, The first preset correction difference is determined based on the hardware performance limits of the flexible wearable device, and the second preset correction difference is half of the first preset correction difference.

6. The rhabdomyolysis early warning system based on a flexible wearable device according to claim 5, characterized in that, The adjustment module determines the analysis duration of the adjustment parameter based on the difference between the adjustment amount in the second interval period and the adjustment amount in the first interval period; wherein if the difference between the adjustment amount in the second interval period and the adjustment amount in the first interval period is less than or equal to the first preset adjustment amount difference and greater than the second preset adjustment amount difference, the analysis duration of the adjustment parameter is extended. If the difference between the correction amount in the second interval period and the correction amount in the first interval period is greater than the difference in the first preset correction amount, it is determined to shorten the analysis time of the correction parameter. If the difference between the correction amount in the second intermittent period and the correction amount in the first intermittent period is less than or equal to the difference in the second preset correction amount, the analysis duration for which the correction parameter is not modified is determined.

7. The rhabdomyolysis early warning system based on a flexible wearable device according to claim 6, characterized in that, The difference between the correction amount of the second intermittent period and the correction amount of the first intermittent period, and the difference between the second preset correction amount, are positively correlated with the adjustment amount of the analysis duration of the correction parameter.

Images