A swallowing rehabilitation training dynamic adjustment method based on a swallowing training impact index

Abstract

This invention relates to the field of swallowing rehabilitation technology, and more particularly to a dynamic adjustment method for swallowing rehabilitation training based on a swallowing training impact index. The method includes the following steps: during swallowing rehabilitation training, acquiring swallowing-related physiological signals triggered by training actions; extracting training response feature parameters reflecting the immediate physiological response caused by the training actions based on the swallowing-related physiological signals; generating a swallowing training impact index based on the training response feature parameters, the swallowing training impact index being used to characterize the immediate physiological impact intensity of the current training action on the target patient's swallowing system; comparing the swallowing training impact index with the target patient's individualized swallowing training impact adaptation threshold: when the swallowing training impact index exceeds the swallowing training impact adaptation threshold, reducing the training load parameters of the swallowing rehabilitation training; when the swallowing training impact index is lower than the swallowing training impact adaptation threshold, maintaining or increasing the training load parameters.

Description

Technical Field

[0001] This invention relates to the field of swallowing rehabilitation technology, and in particular to a dynamic adjustment method for swallowing rehabilitation training based on the swallowing training impact index. Background Technology

[0002] Dysphagia is a common functional disorder in rehabilitation medicine, widely prevalent in patients with stroke, neurodegenerative diseases, post-head and neck tumor surgery, and the elderly. Clinically, dysphagia is typically treated with swallowing rehabilitation training to gradually restore the coordination of the swallowing-related muscle groups. Current swallowing rehabilitation training methods mainly include repetitive swallowing exercises, rhythmic guided training, and oropharyngeal muscle coordination training. The training load parameters, such as training frequency, number of movements, and intervals between adjacent training movements, are usually set by the rehabilitation therapist based on clinical experience or executed according to a pre-set standardized training procedure.

[0003] In actual rehabilitation training, swallowing rehabilitation training does not always present a safe and linear stimulus-recovery process: for some patients, even if no obvious abnormalities are shown in imaging examinations or interim assessments during training, their swallowing-related muscle groups, airway structures, and nerve reflex regulation systems may still bear a large instantaneous stimulus load in a short period of time, thus producing a hidden overload effect, which manifests as delayed edema, muscle fatigue accumulation, or swallowing reflex disorder, leading to a decrease in rehabilitation effect and even increasing the risk of aspiration; however, at present, whether the training intensity is overloaded mainly depends on the therapist's subjective experience judgment, lacking objective quantitative indicators and real-time feedback mechanisms, making it difficult to adjust the training load in a timely manner, resulting in problems such as imperceptible training risks and delayed adjustment of training parameters. Summary of the Invention

[0004] In a first aspect, one embodiment of the present invention provides a method for dynamic adjustment of swallowing rehabilitation training based on a swallowing training impact index, comprising the following steps: During swallowing rehabilitation training, swallowing-related physiological signals triggered by training movements are acquired. These swallowing-related physiological signals include at least swallowing micro-vibration signals generated by swallowing-related muscle groups and airway pressure change signals during swallowing. Based on the swallowing-related physiological signals, training response feature parameters that reflect the immediate physiological response caused by the training action are extracted. The training response feature parameters include at least the energy surge magnitude of the swallowing micro-vibration signal, the instantaneous gradient of the airway pressure change, and the recovery time required for the swallowing-related physiological signals to return to the baseline state after the swallowing action is completed. Based on the training response characteristic parameters, a swallowing training impact index is generated, which is used to characterize the intensity of the immediate physiological impact of the current training action on the swallowing system of the target patient. The swallowing training impact index is compared with the individualized swallowing training impact adaptation threshold of the target patient: when the swallowing training impact index exceeds the swallowing training impact adaptation threshold, the training load parameters of the swallowing rehabilitation training are reduced; when the swallowing training impact index is lower than the swallowing training impact adaptation threshold, the training load parameters are maintained or increased.

[0005] In some embodiments, extracting training response feature parameters reflecting the immediate physiological response caused by the training action based on the swallowing-related physiological signals includes the following steps: Energy analysis is performed on the swallowing microvibration signal to obtain the energy surge magnitude of the swallowing microvibration signal relative to its corresponding baseline state. The energy surge magnitude is used to characterize the instantaneous response intensity of swallowing-related muscle groups to training stimuli. The airway pressure change signal is processed by time differentiation to obtain the instantaneous gradient of airway pressure change at the moment the training action is triggered. The instantaneous gradient of airway pressure change is used to characterize the impact of the training stimulus on the airway dynamic state. After the training action is completed, the recovery time is obtained based on the process of the swallowing micro-vibration signal and the airway pressure change signal returning from the peak state to their respective baseline state. The recovery time is used to characterize the recovery lag characteristics of the swallowing system to the training stimulus.

[0006] In some embodiments, the recovery time is characterized by the maximum value of the recovery times corresponding to the swallowing microvibration signal and the airway pressure change signal.

[0007] In some embodiments, generating the swallowing training impact index based on the training response feature parameters includes the following steps: Normalize the energy surge magnitude, the instantaneous gradient of the airway pressure change, and the recovery time to generate energy characteristic values, pressure gradient characteristic values, and recovery hysteresis characteristic values. Based on the training load parameters of swallowing rehabilitation training, a training density factor is determined. The training density factor is determined by the execution frequency of training actions and / or the time interval between adjacent training actions, and is used to characterize the cumulative intensity of training stimuli on a time scale. The energy feature value, the pressure gradient feature value, the recovery hysteresis feature value, and the training density factor are weighted and fused to generate an instantaneous impact value. The instantaneous impact value is nonlinearly mapped to generate a swallowing training impact index, which monotonically increases with the increase of the instantaneous impact value within a preset range.

[0008] In some embodiments, the individualized swallowing training impact adaptation threshold for any target patient is determined by the following steps: In the initial training phase of swallowing rehabilitation training, the initial swallowing training impact adaptation threshold is determined based on the swallowing training impact index corresponding to the target patient performing multiple swallowing training actions under preset low training load parameters.

[0009] In some embodiments, the individualized swallowing training impact adaptation threshold for any target patient is also updated through the following steps: During a continuous training cycle, the swallowing training impact index of the target patient under different training load parameters was obtained. Based on the trend relationship between the swallowing training impact index and the training load parameters, the target patient's tolerance to training stimuli is determined: When the swallowing training impact index shows a downward trend while the training load parameters remain unchanged or decrease, the swallowing training impact adaptation threshold is increased. When the swallowing training impact index shows an upward trend while the training load parameters remain unchanged or increase, the swallowing training impact adaptation threshold is reduced.

[0010] In some embodiments, the process of comparing the swallowing training impact index with the target patient's individualized swallowing training impact adaptation threshold includes: Within a preset time window, a statistical analysis was conducted on the swallowing training impact index corresponding to multiple consecutive swallowing training actions: When the swallowing training impact index exceeds the individualized swallowing training impact adaptation threshold at least N times consecutively within the preset time window, the training load parameter of the swallowing rehabilitation training is reduced, where N is a positive integer greater than or equal to 2.

[0011] In some embodiments, when the swallowing training impact index exceeds the individualized swallowing training impact adaptation threshold, the training intensity is reduced by adjusting the training load parameters of the swallowing rehabilitation training. The adjustment operation includes one or a combination of the following: Reduce the frequency of swallowing training movements; Extend the time interval between adjacent swallowing training actions; Reduce the number of swallowing exercises within a single training phase.

[0012] Secondly, the present invention also provides a dynamic adjustment device for swallowing rehabilitation training based on a swallowing training impact index, comprising: The physiological signal acquisition module is used to acquire swallowing-related physiological signals triggered by training movements during swallowing rehabilitation training. The impact index generation module is used to extract training response feature parameters that reflect the immediate physiological response caused by the training action based on the swallowing-related physiological signals, and generate a swallowing training impact index according to the training response feature parameters. The training adjustment module is used to compare the swallowing training impact index with the individualized swallowing training impact adaptation threshold of the target patient, and adjust the training load parameters of swallowing rehabilitation training according to the comparison results.

[0013] Thirdly, based on the dynamic adjustment method for swallowing rehabilitation training based on the swallowing training impact index provided in the first aspect, this invention also provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program. When the computer program is executed by the processor, it implements the dynamic adjustment method for swallowing rehabilitation training based on the swallowing training impact index proposed in any of the above embodiments.

[0014] The present invention provides a method, device, and storage medium for dynamic adjustment of swallowing rehabilitation training based on the swallowing training impact index, the gains of which include at least: This invention introduces a swallowing training impact index into the swallowing rehabilitation training process. It jointly characterizes the intensity of the swallowing-related muscle group response caused by training movements, the airway dynamic impact represented by changes in airway pressure, and the lag characteristics of post-training physiological signal recovery to baseline. This transforms the instantaneous stimulus load during training into a calculable and comparable objective indicator, thereby enabling real-time identification and quantitative assessment of latent overload states during swallowing rehabilitation training. Compared to existing training methods that primarily rely on therapist experience or intermittent assessments, this invention can detect trends of training stimulus overload before patients exhibit obvious imaging abnormalities or clinical symptoms, providing an objective basis for adjusting training load parameters.

[0015] Furthermore, this invention compares the swallowing training impact index with the individualized swallowing training impact adaptation threshold of the target patient, and dynamically adjusts training load parameters such as training frequency, number of movements and / or interval between adjacent training movements during the training process. This allows the training intensity to adaptively adjust according to changes in the patient's tolerance, thereby reducing the probability that swallowing-related muscle groups and the airway system will be subjected to excessive stimulation load in a short period of time, reducing the risk of adverse events such as delayed edema, muscle fatigue accumulation and swallowing reflex disorder, and improving training safety.

[0016] Furthermore, this invention establishes an individualized adaptation threshold in the early stages of training and updates the adaptation threshold in conjunction with the trend of swallowing training impact index changes with training load during continuous training cycles. This allows training adjustment to no longer rely on a uniform fixed standard or static process, but to better fit the changes in the patient's tolerance during the rehabilitation process, thereby achieving individualized and dynamic adjustment of swallowing rehabilitation training load and improving training targeting and rehabilitation efficiency.

[0017] Meanwhile, this invention expands the swallowing rehabilitation system from the previous model that focused on post-evaluation or result indication to a process control model that can adjust the training process in real time. This enables the system to actively adjust training parameters based on the patient's immediate physiological response, providing a more controllable and feasible technical path for swallowing rehabilitation training. Attached Figure Description

[0018] From the following description of embodiments in conjunction with the accompanying drawings, aspects, features, and advantages of the present invention will become clearer and more readily understood, in which: Figure 1 This is a schematic diagram of the dynamic adjustment method for swallowing rehabilitation training based on the swallowing training impact index provided by the present invention. Figure 2 This is a schematic diagram of the method for extracting training response feature parameters provided by the present invention; Figure 3 This is a schematic diagram of the method for generating the swallowing training impact index provided by the present invention. Figure 4 This is a schematic diagram of the module composition of the swallowing rehabilitation training dynamic adjustment device based on the swallowing training impact index provided by the present invention. Detailed Implementation

[0019] To facilitate understanding of the present invention by those skilled in the art, several embodiments are now described in detail with reference to the accompanying drawings. It should be understood that the embodiments are for illustrative purposes only and not for limiting the scope of protection of the present invention; the scope of protection of the present invention is defined by the claims, and includes equivalent schemes and equivalent transformations of the claims.

[0020] As mentioned above, the training load parameters of existing swallowing rehabilitation training mainly rely on the therapist's experience or fixed procedures. There is a lack of a mechanism that can objectively quantify the risk of latent overload based on the patient's immediate physiological response during training and provide real-time feedback and adjustment. This makes it difficult to adjust the training intensity in a timely and individualized manner, thereby causing latent overload and its delayed adverse consequences.

[0021] In one embodiment, the present invention provides a method for dynamic adjustment of swallowing rehabilitation training based on a swallowing training impact index. This method collects swallowing micro-vibration signals and airway pressure change signals that characterize the hidden load of the swallowing system, and generates a swallowing training impact index based on the physiological signals as an objective representation of overload risk. This provides a basis for real-time feedback adjustment of training load parameters, thereby solving the problem that the training intensity is difficult to adjust in a timely and individualized manner.

[0022] Please see Figure 1 , Figure 1 This is a schematic diagram of the dynamic adjustment method for swallowing rehabilitation training based on the swallowing training impact index provided by the present invention. Figure 1 As shown, the dynamic adjustment method for swallowing rehabilitation training based on the swallowing training impact index provided by this invention includes the following steps:

[0023] S01. During swallowing rehabilitation training, swallowing-related physiological signals triggered by training movements are acquired. The swallowing-related physiological signals include at least swallowing micro-vibration signals generated by swallowing-related muscle groups and airway pressure change signals in the airway during swallowing.

[0024] Furthermore, acquiring swallowing-related physiological signals triggered by training movements during swallowing rehabilitation training refers to the synchronous acquisition of physiological signals that reflect the immediate load status of the swallowing system when the target patient performs a single or continuous swallowing training movement.

[0025] In this embodiment, the swallowing-related physiological signals include at least the swallowing microvibration signals generated by the swallowing-related muscle groups and the airway pressure change signals in the airway during swallowing.

[0026] In other embodiments, the swallowing-related physiological signals may also include other quantifiable physiological signals related to the swallowing action, such as respiratory airflow signals, neck surface displacement signals, or swallowing-related acoustic signals that change synchronously with the swallowing process. These physiological signals can be used to further characterize the load changes of the swallowing system during training.

[0027] Furthermore, the swallowing micro-vibration signals collected in this embodiment are used to characterize the mechanical vibration response of swallowing-related muscle groups under training stimulation; the airway pressure change signals collected in this embodiment are used to characterize the changes in the internal dynamic state of the airway during swallowing.

[0028] In one specific embodiment, the swallowing microvibration signal is acquired by a microvibration sensor located in the anterior neck region of the target patient or at a position corresponding to the swallowing-related muscle group; the airway pressure change signal is acquired by a pressure sensor located on the airway communication path.

[0029] It should be noted that, in the above specific embodiments, the swallowing micro-vibration signal and the airway pressure change signal correspond to the swallowing training action in the time dimension, thereby ensuring that the collected physiological signals can truly reflect the immediate physiological response after the training action is triggered.

[0030] S02. Based on the swallowing-related physiological signals, extract training response feature parameters that reflect the immediate physiological response caused by the training action. The training response feature parameters include at least the energy surge magnitude of the swallowing micro-vibration signal, the instantaneous gradient of the airway pressure change, and the recovery time required for the swallowing-related physiological signals to return to the baseline state after the swallowing action is completed.

[0031] Further, step S02 analyzes the collected swallowing micro-vibration signals and airway pressure change signals to extract various characteristic quantities that can respectively characterize the instantaneous stimulation intensity of the swallowing system, the degree of airway dynamic impact, and the recovery ability after training, so as to depict the changes in the hidden load during swallowing rehabilitation training.

[0032] In this embodiment, the extraction of training response feature parameters reflecting the immediate physiological response caused by the training action based on the swallowing-related physiological signals includes, for example: Figure 2 The steps shown are as follows: S021. Perform energy analysis on the swallowing microvibration signal to obtain the energy surge magnitude of the swallowing microvibration signal relative to its corresponding baseline state. The energy surge magnitude is used to characterize the instantaneous response intensity of the swallowing-related muscle groups to the training stimulus.

[0033] In this embodiment, since the swallowing-related muscle groups will contract and displace at different intensities under the action of training stimulation, their mechanical vibration characteristics will be directly reflected in the energy changes of the swallowing micro-vibration signal. Therefore, by extracting the magnitude of the energy surge of the swallowing micro-vibration signal, it can be used to characterize the instantaneous response intensity of the swallowing-related muscle groups to the current training stimulation.

[0034] It is understandable that when the energy surge is large, it indicates that the swallowing-related muscle groups have been subjected to strong training stimulation in a short period of time, which may correspond to a high instantaneous load level.

[0035] It should be noted that the baseline state refers to the physiological signal reference state when the target patient is in a relatively stable state before the current swallowing training action is triggered. It is used to characterize the normal level of swallowing-related physiological signals in the absence of current training stimulation.

[0036] In some embodiments, by statistically characterizing the swallowing microvibration signal and the airway pressure change signal during a preset baseline time period before each training action is triggered, the baseline state corresponding to different physiological signals under that training action is obtained.

[0037] In these implementations, the swallowing microvibration signal and airway pressure change signal are sampled and their baseline reference values ​​are calculated within the preset baseline time period. The baseline reference values ​​can be determined by statistical quantities such as the average level, stable interval value, or median value of the signal within the baseline time period, thereby forming a baseline state for subsequent relative quantification to ensure that the signal changes before and after the training action are triggered can be compared under the same reference benchmark.

[0038] In other embodiments, the baseline state may also be updated or smoothed based on historical physiological signals prior to multiple training actions to reflect the target patient's stable physiological level at the current training phase.

[0039] In these embodiments, the baseline state corresponding to the current training action is obtained by sliding update or smoothing the baseline reference values ​​corresponding to the previous training actions. This reduces the impact of occasional noise, short-term respiratory fluctuations or instantaneous body movements on the single baseline estimation, enabling the baseline state to more stably track the physiological level changes of the target patient during the training phase and improve the stability and comparability of the subsequent training response characteristic parameter representation.

[0040] S022. Perform time differentiation processing on the airway pressure change signal to obtain the instantaneous gradient of airway pressure change corresponding to the moment the training action is triggered. The instantaneous gradient of airway pressure change is used to characterize the degree of impact of the training stimulus on the airway dynamic state.

[0041] In this embodiment, the airway pressure changes rapidly with the swallowing action during swallowing, and the rate of change can reflect the degree of impact of the swallowing action on the airway dynamics.

[0042] Furthermore, this embodiment extracts the instantaneous gradient of airway pressure changes to characterize the impact intensity of training stimuli on the airway system over time, thereby providing a basis for assessing airway-related loads during swallowing training.

[0043] S023. After the training action is completed, the recovery time is obtained based on the process of the swallowing micro-vibration signal and the airway pressure change signal returning from the peak state to their respective baseline state. The recovery time is used to characterize the recovery lag characteristics of the swallowing system to the training stimulus.

[0044] In this embodiment, the recovery time is used to characterize the recovery lag characteristics of the swallowing system after being stimulated by training, that is, the time required for the swallowing-related muscle groups and airway system to recover from the stimulated state to the stable state: when the recovery time is long, it indicates that the swallowing system has a relatively weak recovery ability under the current training load, and there may be a risk of load accumulation or overload.

[0045] In some embodiments, the recovery time is characterized by the maximum value of the recovery times corresponding to the swallowing microvibration signal and the airway pressure change signal.

[0046] In these embodiments, the recovery time is selected as the longer of the time required to recover to their respective baseline states between the swallowing micro-vibration signal and the airway pressure change signal. This allows the recovery time to reflect the physiological subsystems in the swallowing system with relatively weak recovery capabilities, thereby adopting a more conservative judgment criterion during training load adjustment to avoid the risk of hidden load accumulation caused by the delayed recovery of local physiological systems.

[0047] In some other embodiments, the recovery time is characterized by a weighted or statistical result of the recovery times corresponding to the swallowing microvibration signal and the airway pressure change signal.

[0048] In these embodiments, by weighted fusion, averaging, or interval statistics of the recovery time corresponding to the swallowing micro-vibration signal and the recovery time corresponding to the airway pressure change signal, a recovery time characterization value that comprehensively reflects the overall recovery characteristics of the swallowing-related muscle groups and the airway system is obtained. This improves the stability and continuity of the recovery time characterization while taking into account the recovery characteristics of different physiological systems, and reduces the impact of abnormal fluctuations in a single signal on the judgment of training load.

[0049] S03. Based on the training response characteristic parameters, generate a swallowing training impact index, which is used to characterize the instantaneous physiological impact intensity of the current training action on the target patient's swallowing system.

[0050] Furthermore, the swallowing training impact index is a single comprehensive index obtained by integrating multi-dimensional training response features. It is used to characterize the instantaneous physiological impact intensity of the current training action on the swallowing system of the target patient on a unified scale, thereby avoiding the problem of incomplete characterization of the overall load level due to relying on only one single feature.

[0051] In this embodiment, step S03, which involves generating a swallowing training impact index based on the training response feature parameters, includes, for example: Figure 3 The steps shown are as follows: S031. Normalize the energy surge magnitude, the instantaneous gradient of the airway pressure change, and the recovery time to generate energy characteristic values, pressure gradient characteristic values, and recovery hysteresis characteristic values.

[0052] Furthermore, since the magnitude of the energy surge, the instantaneous pressure gradient, and the recovery time differ in their dimensions and numerical ranges, in order to eliminate the undesirable dominant influence of a feature with a large dimension on the fusion result, step S031 normalizes each feature so that they can be fused on the same scale, thereby improving the comparability between different patients and different training stages.

[0053] In some embodiments, feature values ​​are generated based on a normalization method of baseline state values ​​or historical statistics, such as... , , ,in, , , where r represents the energy eigenvalue, pressure gradient eigenvalue, and recovery hysteresis eigenvalue, respectively. The magnitude of the energy surge from swallowing microseismic signals. This represents the instantaneous gradient of airway pressure changes. For recovery time, , The values ​​represent the historical mean and standard deviation of the energy surge magnitude during the patient's current training phase. , The historical mean and standard deviation of the pressure gradient. , The historical mean and standard deviation of recovery time. To prevent extremely small positive numbers with a denominator of zero.

[0054] In other specific embodiments, interval normalization (Min-Max) can also be used to map each feature to the [0,1] interval, such as... , , ,in, , , , , , These are the maximum and minimum values ​​of the energy surge of the swallowing microvibration signal, the instantaneous gradient of airway pressure change, and the recovery time, which can be determined through patient history data or preset safety ranges.

[0055] S032. Based on the training load parameters of swallowing rehabilitation training, determine the training density factor, which is determined by the execution frequency of training actions and / or the time interval between adjacent training actions, and is used to characterize the cumulative intensity of training stimuli on the time scale.

[0056] Furthermore, since swallowing training impact has a cumulative effect, under the same single response intensity, the higher the training frequency or the shorter the action interval, the less sufficient the recovery window of the swallowing system, and the easier it is to generate load superposition and overload risk.

[0057] In some specific embodiments, in order to characterize the degree of stacking of training stimuli per unit time by means of a training density factor, the training density factor is defined as the frequency of execution of training actions, or the reciprocal of the interval between adjacent training actions.

[0058] In some other specific embodiments, the training density factor is used to balance the contributions of frequency and interval to the cumulative intensity. Defined as ,in, , Reference frequency and reference time interval (such as safety training parameters set by the doctor or patient baseline training parameters). , [0,1] represents the weighting coefficients used to balance the contributions of frequency and interval to the cumulative intensity.

[0059] S033. The energy feature value, the pressure gradient feature value, the recovery hysteresis feature value and the training density factor are weighted and fused to generate an instantaneous impact value. The instantaneous impact value is nonlinearly mapped to generate a swallowing training impact index. The swallowing training impact index increases monotonically with the increase of the instantaneous impact value within a preset range.

[0060] Furthermore, in order to obtain a unified impact representation, this step first performs weighted fusion of features of each dimension to obtain the instantaneous impact value S, and then maps S to a preset range through a monotonic nonlinear function to obtain the final swallowing training impact index (STI).

[0061] In this embodiment, to characterize the amplification effect of the density factor on the impact, the instantaneous impact value S is defined as follows: ,in, , , , [0,1] are weighting coefficients used to reflect the contribution of different dimensions to the impact intensity.

[0062] Specifically, in rehabilitation safety strategies, weighting coefficients for recovery lag characteristic values ​​can be set. A larger value is used to enhance sensitivity to recovery hysteresis, so as to more conservatively identify potential overloads.

[0063] Furthermore, a monotonic nonlinear mapping function is used to map the instantaneous impact value to a preset range ([0,1]), specifically as follows: Where, 𝑘>0 is the slope coefficient, and b is the bias threshold, used to adjust the transition range of the impact index from low to high.

[0064] S04. Compare the swallowing training impact index with the individualized swallowing training impact adaptation threshold of the target patient: when the swallowing training impact index exceeds the swallowing training impact adaptation threshold, reduce the training load parameters of the swallowing rehabilitation training; when the swallowing training impact index is lower than the swallowing training impact adaptation threshold, maintain or increase the training load parameters.

[0065] It should be noted that the swallowing training impact adaptation threshold mentioned in this invention refers to the upper limit of the immediate physiological impact intensity that the swallowing system of the target patient can tolerate in the current swallowing rehabilitation training stage. It is used to distinguish between the training impact range that can be safely tolerated and the training impact range that may cause hidden overload risks.

[0066] Furthermore, the pharyngeal training impact adaptation threshold is related to the target patient's etiological type, disease stage, muscle fatigue level, airway protection ability, and training progress, and may change with rehabilitation progress.

[0067] In some embodiments, the swallowing training impact adaptation threshold is a scalar threshold.

[0068] In other embodiments, the swallowing training impact adaptation threshold can be set separately for different training modes or different training load parameter ranges to achieve phased or mode-specific threshold control. Compared with a fixed threshold, an individualized threshold can avoid overly conservative or overly aggressive training due to individual differences, thereby improving the adaptability of training control.

[0069] In one specific embodiment, the individualized swallowing training impact adaptation threshold for any target patient is determined through the following steps: In the initial training phase of swallowing rehabilitation training, the initial swallowing training impact adaptation threshold is determined based on the swallowing training impact index corresponding to the target patient performing multiple swallowing training actions under preset low training load parameters.

[0070] Furthermore, the initial training phase typically corresponds to the stage where the target patient has not yet developed a stable tolerance level. To avoid training overload in the initial phase, this embodiment collects the impact index sequence corresponding to the target patient performing multiple swallowing training actions under preset low training load parameters (e.g., lower training frequency, longer action interval, and fewer training times), and determines the initial threshold based on the statistical characteristics of the sequence.

[0071] In some embodiments, the individualized swallowing training impact adaptation threshold for any target patient is also updated through the following steps: During continuous training cycles, the swallowing training impact index of the target patient under different training load parameters is obtained; based on the trend relationship between the swallowing training impact index and the training load parameters, the tolerance change status of the target patient to the training stimulus is determined. When the swallowing training impact index shows a downward trend while the training load parameters remain unchanged or decrease, the swallowing training impact adaptation threshold is increased; when the swallowing training impact index shows an upward trend while the training load parameters remain unchanged or increase, the swallowing training impact adaptation threshold is decreased.

[0072] In this embodiment, the process of comparing the swallowing training impact index with the target patient's individualized swallowing training impact adaptation threshold includes: Within a preset time window, the swallowing training impact index corresponding to multiple consecutive swallowing training actions is statistically analyzed: when the swallowing training impact index exceeds the individualized swallowing training impact adaptation threshold at least N times within the preset time window, the training load parameter of the swallowing rehabilitation training is reduced, where N is a positive integer greater than or equal to 2.

[0073] Furthermore, to avoid overload misjudgment caused by a single anomaly (such as instantaneous body movement, sensor noise, or occasional coughing), this embodiment does not use a single overload as the overload trigger condition, but improves robustness and reliability by judging continuous overloads within a preset time window.

[0074] In some other embodiments, the excess ratio rule is also used as a supplementary determination method: Within a preset time window, the swallowing training impact index corresponding to multiple swallowing training actions is statistically analyzed, and the proportion of swallowing training impact indices exceeding the individualized swallowing training impact adaptation threshold is calculated: When the proportion of the swallowing training impact index exceeding the individualized swallowing training impact adaptation threshold within the time window is greater than or equal to a preset proportion threshold, it is determined that the target patient has an overload trend within that time window.

[0075] Specifically, the percentage threshold can be set according to the safety strategy, such as 60% or 70%, so that the judgment method can be applied to the situation where the swallowing training impact index does not continuously exceed the threshold but the overall level is high, thereby improving the comprehensiveness and reliability of overload recognition.

[0076] Furthermore, in any of the above embodiments, when overload is determined, the training intensity is reduced by performing adjustment operations on the training load parameters of the swallowing rehabilitation training. The adjustment operations include one or a combination of the following: reducing the execution frequency of swallowing training actions; extending the time interval between adjacent swallowing training actions; and reducing the number of swallowing training actions within a single training phase.

[0077] Conversely, if it is necessary to increase the training intensity, the adjustment operation includes one or a combination of the following: increasing the frequency of swallowing training actions; shortening the time interval between adjacent swallowing training actions; increasing the number of swallowing training actions within a single training phase.

[0078] It should be noted that the adjustment operations of reducing or increasing training intensity are not limited to the adjustment methods listed above. To ensure the executability and controllability of the adjustment operations, in some embodiments, the adjustment operations can be performed step by step using preset step sizes or proportional coefficients. For example, the reduction in training frequency can be set to 10% to 30%, the increase in interval length can be set to 10% to 50%, and the step size for reducing / increasing the number of training sessions in a single phase can be set to 1 to 3 times. Furthermore, after each adjustment, the adjustment effect is verified based on the trend of the swallowing training impact index change in the subsequent training actions. When the swallowing training impact index continues to exceed the individualized swallowing training impact adaptation threshold, the next level of deload adjustment is executed to form a closed-loop control strategy of step-by-step deload.

[0079] In other embodiments, based on the swallowing rehabilitation training dynamic adjustment method based on the swallowing training impact index provided in the above embodiments, the present invention also provides a swallowing rehabilitation training dynamic adjustment device based on the swallowing training impact index.

[0080] See Figure 4 The swallowing rehabilitation training dynamic adjustment device based on the swallowing training impact index includes at least: a physiological signal acquisition module, an impact index generation module, and a training adjustment module.

[0081] The physiological signal acquisition module is used to acquire swallowing-related physiological signals triggered by training actions during swallowing rehabilitation training.

[0082] The impact index generation module is used to extract training response feature parameters that reflect the immediate physiological response caused by the training action based on the swallowing-related physiological signals acquired by the physiological signal acquisition module, and generate a swallowing training impact index based on the training response feature parameters.

[0083] Specifically, the impact index generation module can perform energy analysis on the swallowing micro-vibration signal to obtain the energy surge magnitude, perform time differentiation processing on the airway pressure change signal to obtain the instantaneous pressure change gradient, and obtain the recovery time based on the process of swallowing-related physiological signals returning from the peak state to the baseline state; on this basis, the training response feature parameters are normalized, weighted fusion, and nonlinearly mapped to obtain the swallowing training impact index, which characterizes the instantaneous physiological impact intensity of the current training action on the target patient's swallowing system.

[0084] The training adjustment module is used to compare the swallowing training impact index output by the impact index generation module with the individualized swallowing training impact adaptation threshold of the target patient, and adjust the training load parameters of swallowing rehabilitation training according to the comparison results.

[0085] Specifically, when the swallowing training impact index exceeds the individualized swallowing training impact adaptation threshold, the training adjustment module is used to reduce the training intensity; when the swallowing training impact index is lower than the individualized swallowing training impact adaptation threshold, the training adjustment module is used to maintain or increase the training intensity.

[0086] The training load parameters include at least one of the following: the execution frequency of training actions, the time interval between adjacent training actions, and the number of training sessions within a single training phase.

[0087] It should be noted that the above-mentioned functional modules can be implemented by software or by a combination of software and hardware. In specific implementations, the modules can be integrated into the same processing unit or deployed in different processing units and interact through communication. Those skilled in the art can make corresponding modifications to the specific composition and module division of the device without departing from the technical concept of this invention, and all such modifications should fall within the protection scope of this invention.

[0088] In other embodiments, based on the swallowing rehabilitation training dynamic adjustment method based on the swallowing training impact index provided in the above embodiments, the present invention also provides a computer-readable storage medium.

[0089] The computer-readable storage medium provided by the present invention stores a computer program, which, when executed by a processor, is used to implement the dynamic adjustment method for swallowing rehabilitation training based on the swallowing training impact index provided by the present invention.

[0090] Furthermore, computer-readable storage media include, but are not limited to: disks, optical disks, flash memory, read-only memory (ROM), random access memory (RAM), solid-state drives, USB flash drives, portable hard drives, or other media capable of storing program instructions and readable by computing devices.

[0091] Furthermore, the computer program may exist in the form of source code, object code, executable file or any other form, and can be loaded and executed by computing devices including general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs) or field-programmable gate arrays (FPGAs).

[0092] In the implementation process, the computer program can call the input / output interface and communication interface provided by the operating system to complete data acquisition, data processing, and control output related to swallowing rehabilitation training. Specifically, the computer program can receive swallowing micro-vibration signals and airway pressure change signals output by micro-vibration sensors and pressure sensors through the input interface, and perform buffering, timestamp alignment, and preprocessing on the signals; then, it performs feature extraction and fusion calculation to obtain the swallowing training impact index, and compares the swallowing training impact index with the individualized swallowing training impact adaptation threshold of the target patient, and generates training load adjustment instructions based on the comparison results. The training load adjustment instructions can be applied to the training guidance terminal or training control terminal through the output interface or communication interface to adjust the execution frequency of training actions, the time interval between adjacent training actions, the number of training sessions within a single training phase, and / or perform training mode switching, training pause, and other controls, thereby completing the various functional steps proposed in this invention.

[0093] It should be noted that the computer-readable storage medium described in this embodiment is not limited to any specific physical form and packaging method. As long as it has information storage and program loading functions, it can fall within the protection scope of this invention. The method flow of this invention can be fully implemented by software or combined with some hardware modules. The specific implementation method can be flexibly selected according to the actual deployment requirements, and technicians can complete it accordingly.

[0094] In the above embodiments, the descriptions of different embodiments have different emphases; technical features not detailed or recorded in a certain embodiment can be understood and implemented by referring to the corresponding records of other embodiments. Unless otherwise expressly stated to the contrary: technical features in each embodiment can be substituted or combined with each other without technical conflict; the order of method steps can be adjusted without affecting the function; the device / module / unit can be implemented by hardware, software or a combination thereof, and can be centralized or distributed; parameters, values ​​or ranges include reasonable errors and equivalent values, and the terms "about", "greater than / less than", "between", and range endpoints are all covered without affecting the technical effect; ordinal numbers such as "first / second" are only used for distinction and do not limit the quantity, priority or structural relationship; the reference numerals and names in the specification and drawings are only illustrative and do not limit the structural form, size ratio or installation position; improvements, substitutions or equivalent solutions that are not explicitly stated but can be obtained by those skilled in the art without creative effort should all be included in the protection scope of this invention.

Claims

1. A method for dynamically adjusting swallowing rehabilitation training based on the swallowing training impact index, characterized in that, Includes the following steps: During swallowing rehabilitation training, swallowing-related physiological signals triggered by training movements are acquired. These swallowing-related physiological signals include at least swallowing micro-vibration signals generated by swallowing-related muscle groups and airway pressure change signals during swallowing. Based on the swallowing-related physiological signals, training response feature parameters that reflect the immediate physiological response caused by the training action are extracted. The training response feature parameters include at least the energy surge magnitude of the swallowing micro-vibration signal, the instantaneous gradient of the airway pressure change, and the recovery time required for the swallowing-related physiological signals to return to the baseline state after the swallowing action is completed. Based on the training response characteristic parameters, a swallowing training impact index is generated, which is used to characterize the intensity of the immediate physiological impact of the current training action on the swallowing system of the target patient. The swallowing training impact index is compared with the individualized swallowing training impact adaptation threshold of the target patient: when the swallowing training impact index exceeds the swallowing training impact adaptation threshold, the training load parameters of the swallowing rehabilitation training are reduced; when the swallowing training impact index is lower than the swallowing training impact adaptation threshold, the training load parameters are maintained or increased.

2. The method for dynamic adjustment of swallowing rehabilitation training based on the swallowing training impact index according to claim 1, characterized in that, The step of extracting training response feature parameters reflecting the immediate physiological response caused by the training action based on the swallowing-related physiological signals includes the following steps: Energy analysis is performed on the swallowing microvibration signal to obtain the energy surge magnitude of the swallowing microvibration signal relative to its corresponding baseline state. The energy surge magnitude is used to characterize the instantaneous response intensity of swallowing-related muscle groups to training stimuli. The airway pressure change signal is processed by time differentiation to obtain the instantaneous gradient of airway pressure change at the moment the training action is triggered. The instantaneous gradient of airway pressure change is used to characterize the impact of the training stimulus on the airway dynamic state. After the training action is completed, the recovery time is obtained based on the process of the swallowing micro-vibration signal and the airway pressure change signal returning from the peak state to their respective baseline state. The recovery time is used to characterize the recovery lag characteristics of the swallowing system to the training stimulus.

3. The method for dynamic adjustment of swallowing rehabilitation training based on the swallowing training impact index according to claim 2, characterized in that, The recovery time is represented by the maximum value of the recovery time corresponding to the swallowing microvibration signal and the airway pressure change signal.

4. The method for dynamic adjustment of swallowing rehabilitation training based on the swallowing training impact index according to claim 1, characterized in that, The step of generating the swallowing training impact index based on the training response feature parameters includes the following steps: Normalize the energy surge magnitude, the instantaneous gradient of the airway pressure change, and the recovery time to generate energy characteristic values, pressure gradient characteristic values, and recovery hysteresis characteristic values. Based on the training load parameters of swallowing rehabilitation training, a training density factor is determined. The training density factor is determined by the execution frequency of training actions and / or the time interval between adjacent training actions, and is used to characterize the cumulative intensity of training stimuli on a time scale. The energy feature value, the pressure gradient feature value, the recovery hysteresis feature value, and the training density factor are weighted and fused to generate an instantaneous impact value. The instantaneous impact value is nonlinearly mapped to generate a swallowing training impact index, which monotonically increases with the increase of the instantaneous impact value within a preset range.

5. The method for dynamic adjustment of swallowing rehabilitation training based on the swallowing training impact index according to claim 1, characterized in that, The individualized swallowing training impact adaptation threshold for any target patient is determined through the following steps: In the initial training phase of swallowing rehabilitation training, the initial swallowing training impact adaptation threshold is determined based on the swallowing training impact index corresponding to the target patient performing multiple swallowing training actions under preset low training load parameters.

6. The method for dynamic adjustment of swallowing rehabilitation training based on the swallowing training impact index according to claim 5, characterized in that, The individualized swallowing training threshold for any target patient is also updated through the following steps: During a continuous training cycle, the swallowing training impact index of the target patient under different training load parameters was obtained. Based on the trend relationship between the swallowing training impact index and the training load parameters, the target patient's tolerance to training stimuli is determined: When the swallowing training impact index shows a downward trend while the training load parameters remain unchanged or decrease, the swallowing training impact adaptation threshold is increased. When the swallowing training impact index shows an upward trend while the training load parameters remain unchanged or increase, the swallowing training impact adaptation threshold is reduced.

7. The method for dynamic adjustment of swallowing rehabilitation training based on the swallowing training impact index according to claim 1, characterized in that, The process of comparing the swallowing training impact index with the individualized swallowing training impact adaptation threshold for the target patient includes: Within a preset time window, a statistical analysis was conducted on the swallowing training impact index corresponding to multiple consecutive swallowing training actions: When the swallowing training impact index exceeds the individualized swallowing training impact adaptation threshold at least N times consecutively within the preset time window, the training load parameter of the swallowing rehabilitation training is reduced, where N is a positive integer greater than or equal to 2.

8. The method for dynamic adjustment of swallowing rehabilitation training based on the swallowing training impact index according to claim 1, characterized in that, When the swallowing training impact index exceeds the individualized swallowing training impact adaptation threshold, the training intensity is reduced by adjusting the training load parameters of the swallowing rehabilitation training. The adjustment operation includes one or a combination of the following: Reduce the frequency of swallowing training movements; Extend the time interval between adjacent swallowing training actions; Reduce the number of swallowing exercises within a single training phase.

9. A dynamic adjustment device for swallowing rehabilitation training based on the swallowing training impact index, characterized in that, include: The physiological signal acquisition module is used to acquire swallowing-related physiological signals triggered by training movements during swallowing rehabilitation training. The impact index generation module is used to extract training response feature parameters that reflect the immediate physiological response caused by the training action based on the swallowing-related physiological signals, and generate a swallowing training impact index according to the training response feature parameters. The training adjustment module is used to compare the swallowing training impact index with the individualized swallowing training impact adaptation threshold of the target patient, and adjust the training load parameters of swallowing rehabilitation training according to the comparison results.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program. When the computer program is executed by the processor, it implements the dynamic adjustment method for swallowing rehabilitation training based on the swallowing training impact index as described in any one of claims 1 to 8.

Images