An intelligent monitoring system and method for swallowing rehabilitation

Abstract

The application provides an intelligent monitoring system and method for swallowing rehabilitation, which determines the aspiration risk feature of the pressure peak in swallowing rehabilitation through the high-frequency energy mutation of cough sound and the delay feature of the bolus passing through the pharynx, determines the coordination score of each rehabilitation stage in the swallowing rehabilitation process through the biomechanical information in the swallowing rehabilitation when the aspiration risk feature is greater than the risk threshold in the swallowing rehabilitation, and then determines the functional recovery index of the pharyngeal swallowing function in the swallowing rehabilitation through all the coordination scores and the aspiration risk feature; the swallowing efficiency index in the swallowing rehabilitation is extracted, and then the rehabilitation deviation feature of the pharynx is determined through the swallowing efficiency index and the functional recovery index, and the swallowing rehabilitation scheme after the sound and light alarm is individually adjusted based on the rehabilitation deviation feature. Based on the above scheme, the individual coordination of the rehabilitation scheme in the swallowing rehabilitation can be realized, so that the recovery efficiency of the pharyngeal swallowing function can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of swallowing rehabilitation, more particularly, the present application relates to an intelligent monitoring system and method for swallowing rehabilitation. BACKGROUND

[0002] The field of swallowing rehabilitation has developed rapidly in recent years, showing the characteristics of multidisciplinary intersection, technology diversification and individualization. At present, various assessment methods such as swallowing radiography and fiber endoscopic swallowing function examination are constantly improving, while traditional oral motor training, swallowing posture adjustment and other methods are constantly optimized, and emerging virtual reality training, robot-assisted training and other technologies are also gradually applied in clinical practice.

[0003] The traditional scheme relies on pre-set swallowing times, bolus volume or training duration, and does not dynamically adjust according to the dynamic adaptability of the real-time pharyngeal pressure waveform or the risk prompt in the acoustic signal, resulting in a mismatch between the training intensity and the actual compensatory ability of the patient. Due to differences in nerve damage, muscle atrophy stage or airway sensitivity, different patients respond differently to the same training parameters, and there is a lack of individualized feedback mechanism based on the timing difference of biomechanics, which easily leads to ineffective training or secondary injury. Therefore, how to realize the individualized coordination of the rehabilitation scheme in swallowing rehabilitation so as to improve the recovery efficiency of pharyngeal swallowing function has become a difficult problem faced by the industry. SUMMARY

[0004] The present application provides an intelligent monitoring system and method for swallowing rehabilitation, which can realize the individualized coordination of the rehabilitation scheme in swallowing rehabilitation, thereby improving the recovery efficiency of pharyngeal swallowing function.

[0005] In a first aspect, the present application provides an intelligent monitoring method for swallowing rehabilitation, comprising:

[0006] Collecting the swallowing acoustic signal and the pharyngeal pressure waveform of the bolus passing through the pharynx in swallowing rehabilitation, and then extracting the high-frequency energy mutation of the cough sound in the swallowing acoustic signal and the delay feature of the bolus passing through the pharynx in the pharyngeal pressure waveform;

[0007] Determining the aspiration risk feature of the pressure peak in swallowing rehabilitation by the high-frequency energy mutation and the delay feature, starting the audible and visual alarm in swallowing rehabilitation when the aspiration risk feature is greater than the risk threshold in swallowing rehabilitation, and obtaining the biomechanical information in swallowing rehabilitation after the audible and visual alarm;

[0008] Determining the coordination score of each rehabilitation stage in the swallowing rehabilitation process by the laryngeal-muscle electromyographic movement timing difference in the biomechanical information, and then determining the functional recovery index of the pharyngeal swallowing function in swallowing rehabilitation by all coordination scores and the aspiration risk feature;

[0009] The swallowing efficiency index in the swallowing rehabilitation is extracted from the pre-acquired swallowing record, and then the swallowing efficiency index and the functional recovery index are used to determine the recovery deviation feature of the pharynx, and the swallowing rehabilitation scheme after the sound and light alarm is individually adjusted based on the recovery deviation feature.

[0010] In some embodiments, the high-frequency energy mutation of the cough sound in the swallowing acoustic signal and the delay feature of the bolus passing through the pharynx in the pharyngeal pressure waveform specifically include:

[0011] The coefficient mutation of the mel-frequency cepstrum coefficient in the swallowing acoustic signal is extracted as the high-frequency energy mutation of the cough sound.

[0012] The delay time of the pressure peak of the bolus passing through the cricopharyngeal muscle in the pharyngeal pressure waveform is extracted as the delay feature of the bolus passing through the pharynx.

[0013] In some embodiments, the swallowing acoustic signal of the bolus passing through the pharynx in the swallowing rehabilitation is collected by using a neck-attached microphone.

[0014] In some embodiments, the coordination score of each rehabilitation stage in the swallowing rehabilitation process is determined by the laryngeal-muscle movement timing difference in the biomechanical information specifically includes:

[0015] For each rehabilitation stage in the swallowing rehabilitation process, the laryngeal elevation time and the submental muscle group peak time of the rehabilitation stage are obtained from the biomechanical information.

[0016] The laryngeal-muscle movement timing difference is determined by the laryngeal elevation time and the submental muscle group peak time.

[0017] The coordination score of the rehabilitation stage is determined according to the laryngeal-muscle movement timing difference and the total duration of the complete swallowing action, and then the coordination score of each rehabilitation stage in the swallowing rehabilitation process is obtained.

[0018] In some embodiments, the functional recovery index of the pharyngeal swallowing function in the swallowing rehabilitation is determined by all the coordination scores and the aspiration risk feature specifically includes:

[0019] For each rehabilitation stage, the exponential decay term of the aspiration risk feature in the rehabilitation stage is obtained.

[0020] The coordination score of the rehabilitation stage and the aspiration risk feature are fused into the functional recovery value of the rehabilitation stage by the exponential decay term, and in this way, the functional recovery value of each rehabilitation stage can be obtained.

[0021] The functional recovery index of the pharyngeal swallowing function in the swallowing rehabilitation is determined according to all the functional recovery values.

[0022] In some embodiments, extracting the swallowing efficiency index in swallowing rehabilitation from pre-collected swallowing records specifically includes:

[0023] Bolus transit time, laryngeal elevation, and mean pressure were obtained from pre-collected swallowing records;

[0024] A swallowing efficiency index in swallowing rehabilitation is determined based on the bolus transit time, the laryngeal elevation amplitude, and the average pressure.

[0025] In some embodiments, determining the rehabilitation deviation characteristics of the pharynx using the swallowing efficiency index and the functional recovery index specifically includes:

[0026] determining a degree of match between the swallowing efficiency index and the functional recovery index;

[0027] The deviation degree of swallowing rehabilitation is evaluated by the matching degree to obtain the rehabilitation deviation characteristics of the pharynx.

[0028] In a second aspect, the present application provides an intelligent monitoring system for swallowing rehabilitation, comprising a monitoring unit, wherein the monitoring unit comprises:

[0029] An acquisition module is used to acquire swallowing acoustic signals and pharyngeal pressure waveforms of food boluses passing through the pharynx during swallowing rehabilitation, and then extract the high-frequency energy mutation of cough sounds in the swallowing acoustic signals and the delay characteristics of food bolus passing through the pharynx in the pharyngeal pressure waveform;

[0030] a processing module, configured to determine an aspiration risk characteristic of a pressure peak during swallowing rehabilitation based on the high-frequency energy mutation amount and the delay characteristic, and to activate an audible and visual alarm during swallowing rehabilitation when the aspiration risk characteristic is greater than a risk threshold during swallowing rehabilitation, and to obtain biomechanical information during swallowing rehabilitation after the audible and visual alarm;

[0031] The processing module is further configured to determine the coordination scores of each rehabilitation stage during the swallowing rehabilitation process based on the laryngeal-myoelectric motion timing difference in the biomechanical information, and further determine the functional recovery index of the swallowing function during the pharyngeal phase of the swallowing rehabilitation process based on all the coordination scores and the aspiration risk characteristics;

[0032] The execution module is used to extract the swallowing efficiency index in swallowing rehabilitation from the pre-collected swallowing records, and then determine the rehabilitation deviation characteristics of the pharynx through the swallowing efficiency index and the functional recovery index, and personalize the swallowing rehabilitation plan after the sound and light alarm based on the rehabilitation deviation characteristics.

[0033] In a third aspect, the present application provides a computer device, comprising a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned intelligent monitoring method for swallowing rehabilitation.

[0034] In a fourth aspect, the present application provides a computer readable storage medium, which stores instructions or codes, when the instructions or codes are run on a computer, so that the computer executes the above-mentioned intelligent monitoring method for swallowing rehabilitation.

[0035] The technical scheme provided by the embodiments of the present application has the following beneficial effects:

[0036] In the intelligent monitoring system and method for swallowing rehabilitation provided by the present application, the swallowing acoustic signal and the pharyngeal pressure waveform of the bolus passing through the pharynx in the swallowing rehabilitation are collected, and then the high-frequency energy mutation of the cough sound in the swallowing acoustic signal and the delay characteristic of the bolus passing through the pharynx in the pharyngeal pressure waveform are extracted; the aspiration risk characteristic of the pressure peak in the swallowing rehabilitation is determined through the high-frequency energy mutation and the delay characteristic, when the aspiration risk characteristic is greater than the risk threshold in the swallowing rehabilitation, the sound and light alarm in the swallowing rehabilitation is started, and the biomechanical information in the swallowing rehabilitation is obtained after the sound and light alarm; the coordination score of each rehabilitation stage in the swallowing rehabilitation process is determined through the laryngeal-muscle electrical motion time sequence difference in the biomechanical information, and then the functional recovery index of the pharyngeal swallowing function in the swallowing rehabilitation is determined through all the coordination scores and the aspiration risk characteristic; the swallowing efficiency index in the swallowing rehabilitation is extracted from the pre-collected swallowing record, and then the rehabilitation deviation characteristic of the pharynx is determined through the swallowing efficiency index and the functional recovery index, and the swallowing rehabilitation scheme after the sound and light alarm is personalized adjusted based on the rehabilitation deviation characteristic.

[0037] It can be seen that, in the present application, the rehabilitation deviation characteristics of the pharynx are determined by the swallowing efficiency index and the functional recovery index, and the swallowing rehabilitation scheme after the acoustic-optical alarm is individually adjusted based on the rehabilitation deviation characteristics. First, the delay characteristic is determined, that is, the neuromuscular conduction efficiency of the bolus through the pharynx is obtained, thereby providing a key timing basis for dynamic adjustment of the rehabilitation scheme. The delay characteristic in the pharyngeal pressure waveform directly reflects the regulation ability of the central nervous system to the swallowing muscle group. The traditional fixed rhythm training cannot adapt to abnormal timing. By quantifying the delay characteristic, it can be identified whether the patient belongs to peripheral nerve compensation delay or central instruction conduction disorder, and the training parameters are differentiated and adjusted. The timing correlation between the delay characteristic and the high-frequency cough sound can further locate the risk link of aspiration, and target rehabilitation intervention is realized. Then, the functional recovery index is determined, that is, a multi-dimensional dynamic evaluation system of pharyngeal swallowing function is obtained, thereby realizing closed-loop optimization of the rehabilitation scheme. The index integrates the coordination score and the aspiration risk characteristic, and can quantify the functional evolution trajectory of the patient from the acute stage to the recovery stage. When the coordination score improves but the aspiration risk is still high, it is suggested that compensatory strategies dominate, and the bolus viscosity needs to be reduced to strengthen physiological coordination. If both are improved simultaneously, it reflects substantial recovery of neuromuscular function, and the training complexity can be gradually increased. At the same time, by comparing the functional recovery index and the swallowing efficiency index, false recovery can be identified, and premature training can be avoided, thereby shortening the rehabilitation period and reducing the incidence of aspiration. In summary, the joint analysis of the delay characteristic and the functional recovery index can ensure that the individualized scheme is not only targeted at the etiology (such as delay improvement), but also meets the overall functional goal. Based on the above scheme, individualized coordination of the rehabilitation scheme in swallowing rehabilitation can be realized, thereby improving the recovery efficiency of pharyngeal swallowing function. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0039] Figure 1 is an exemplary flowchart of an intelligent monitoring method for swallowing rehabilitation according to some embodiments of the present application;

[0040] Figure 2 is a flowchart of determining a swallowing efficiency index according to some embodiments of the present application;

[0041] Figure 3 is a structural schematic diagram of a monitoring unit according to some embodiments of the present application;

[0042] Figure 4is a structural schematic diagram of a computer device for implementing an intelligent monitoring method in swallowing rehabilitation according to some embodiments of the present application. DETAILED DESCRIPTION

[0043] In order to better understand the technical solutions of the present application, the technical solutions of the present application will be described in detail below in combination with the drawings of the specification and specific embodiments.

[0044] Reference Figure 1 The figure is an exemplary flow chart of an intelligent monitoring method in swallowing rehabilitation according to some embodiments of the present application, which mainly includes the following steps:

[0045] In step 101, the swallowing acoustic signal and the pharyngeal pressure waveform of the bolus passing through the pharynx in swallowing rehabilitation are collected, and then the high-frequency energy mutation of the cough sound in the swallowing acoustic signal and the delay characteristic of the bolus passing through the pharynx in the pharyngeal pressure waveform are extracted.

[0046] It should be noted that in the present application, the swallowing acoustic signal refers to the sound signal generated by the friction and vibration of the bolus passing through the pharynx and larynx with the surrounding tissue during swallowing, mainly including normal swallowing sound and abnormal cough sound and other characteristics; the pharyngeal pressure waveform refers to the pressure change curve of the bolus passing through the pharynx, which can reflect the mechanical properties of the pharyngeal muscle contraction and the bolus propulsion.

[0047] In specific implementation, a neck-attached microphone is used to collect the swallowing acoustic signal of the bolus passing through the pharynx in swallowing rehabilitation, and a flexible impedance sensor array is used to collect the pharyngeal pressure waveform of the bolus passing through the pharynx in swallowing rehabilitation.

[0048] In some embodiments, the extraction of the high-frequency energy mutation of the cough sound in the swallowing acoustic signal and the delay characteristic of the bolus passing through the pharynx in the pharyngeal pressure waveform can be realized by the following steps:

[0049] Extracting the coefficient mutation of the mel-frequency cepstrum coefficient in the swallowing acoustic signal as the high-frequency energy mutation of the cough sound;

[0050] Extracting the pressure peak delay time of the bolus passing through the cricopharyngeal muscle in the pharyngeal pressure waveform as the delay characteristic of the bolus passing through the pharynx.

[0051] It should be noted that in the present application, the high-frequency energy mutation variable refers to a characteristic variable reflecting a sudden increase in energy in the 2000-3000 Hz frequency band in the Mel frequency cepstrum coefficient (MFCC), and the high-frequency energy mutation variable is a landmark acoustic feature of silent aspiration; the MFCC is a speech feature parameter designed based on the hearing characteristics of the human ear, which can effectively represent the spectral characteristics of the sound signal, and the coefficient mutation variable refers to a significant change in the amplitude of the 2nd coefficient of the MFCC in a short time, which can be used to identify abnormal sound events; the delay time refers to the time difference from the start of the laryngeal elevation movement to the peak value of the cricopharyngeal muscle pressure, and the delay time can directly represent the coordination of the pharyngeal muscles; the cricopharyngeal muscle pressure peak value refers to the maximum pressure value recorded at the cricopharyngeal muscle position when the bolus passes through the pharynx, and the cricopharyngeal muscle pressure peak value can reflect the maximum contraction strength of the pharyngeal muscles.

[0052] In a specific implementation, first, the original swallowing acoustic signal collected is framed and windowed (a Hamming window with a frame length of 25 ms and a frame shift of 10 ms is used by default), spectral leakage is eliminated, the power spectrum of each frame of signal is obtained through fast Fourier transform, each power spectrum is mapped to a Mel scale filter bank (usually 23 triangular filters are set), and the logarithmic energy output by each filter is calculated; then, the filter bank energy is subjected to discrete cosine transform, and the coefficients after the discrete cosine transform are taken as the Mel frequency cepstrum coefficients, wherein the 2nd coefficient (MFCC-2) of the Mel frequency cepstrum coefficients is specially used to monitor the energy change in the 2000-3000 Hz frequency band, the mean value of all 2nd coefficients is calculated as a baseline, and the number of 2nd coefficients that continuously exceed the baseline at the current time is counted as the high-frequency energy mutation variable of cough sound; then, when the vertical acceleration of the larynx exceeds a specified value (0.5 by default), the swallowing starting point is marked, the local extreme value detection algorithm is used in the pharyngeal pressure waveform to determine the maximum pressure value of the cricopharyngeal muscle region and the corresponding time point, and the time difference between the pressure peak time and the laryngeal elevation starting point is calculated as the delay feature of the bolus passing through the pharynx.

[0053] In step 102, the high-frequency energy mutation variable and the delay feature are used to determine the aspiration risk feature of the pressure peak value in swallowing rehabilitation, and when the aspiration risk feature is greater than a risk threshold in swallowing rehabilitation, a sound and light alarm in swallowing rehabilitation is started, and biomechanical information in swallowing rehabilitation is obtained after the sound and light alarm.

[0054] In some embodiments, the determination of the aspiration risk feature of the pressure peak in the swallowing rehabilitation by the high-frequency energy mutation quantity and the delay feature can be achieved by the following steps: taking the product of the high-frequency energy mutation quantity and the delay feature as the aspiration risk feature of the pressure peak in the swallowing rehabilitation; it should be noted that the aspiration risk feature represents the risk degree of the food mass entering the airway, and the dynamic evaluation index is constructed by quantifying the product of the high-frequency energy mutation quantity of the cough sound and the delay time of the pharyngeal pressure peak in the swallowing process; when the food mass enters the airway, the cough reflex is triggered, which is manifested as a sudden increase in ΔMFCC-2, and the aspiration risk is aggravated by the coordination disorder of the cricopharyngeus muscle, and the product of the two amplifies the abnormal signal; when the aspiration risk feature exceeds the clinical threshold value, the system determines that it is a high-risk aspiration, and triggers a real-time alarm. This feature realizes objective and accurate early warning of implicit aspiration through multi-modal signal fusion.

[0055] In some embodiments, when the aspiration risk feature is greater than the risk threshold in the swallowing rehabilitation, the sound and light alarm in the swallowing rehabilitation is started, and the acquisition of the biomechanical information in the swallowing rehabilitation after the sound and light alarm can be achieved by the following method: when the aspiration risk feature is greater than the risk threshold in the swallowing rehabilitation, the sound and light alarm in the swallowing rehabilitation is started, the throat movement trajectory is captured in real time by the inertial measurement unit, the start time and the maximum displacement time of the laryngeal elevation are accurately marked as the laryngeal elevation time parameter, the surface electromyogram of the submental muscle group is synchronously collected, and the peak value time of the electromyogram activity is determined by using a sliding window peak value detection algorithm, so that the set of the laryngeal elevation time and the peak value time of the submental muscle group is taken as the biomechanical information in the swallowing rehabilitation.

[0056] In step 103, the coordination score of each rehabilitation stage in the swallowing rehabilitation process is determined by the laryngeal-muscle electromyogram time sequence difference in the biomechanical information, and then the functional recovery index of the pharyngeal swallowing function in the swallowing rehabilitation is determined by all the coordination scores and the aspiration risk feature.

[0057] In some embodiments, the determination of the coordination score of each rehabilitation stage in the swallowing rehabilitation process by the laryngeal-muscle electromyogram time sequence difference in the biomechanical information can be achieved by the following steps:

[0058] For each rehabilitation stage in the swallowing rehabilitation process, the laryngeal elevation time and the peak value time of the submental muscle group of the rehabilitation stage are obtained from the biomechanical information;

[0059] The laryngeal-muscle electromyogram time sequence difference is determined by the laryngeal elevation time and the peak value time of the submental muscle group;

[0060] The coordination score of the rehabilitation stage is determined according to the laryngeal-muscle electromyogram time sequence difference and the total duration of the complete swallowing action, and then the coordination score of each rehabilitation stage in the swallowing rehabilitation process is obtained.

[0061] It should be noted that in the present application, the coordination score is an index for quantifying the coordination degree of laryngeal movement and muscle activation, and the value range is 0-1, and the closer to 1, the better the coordination; in specific implementation, first, for each rehabilitation stage in the swallowing rehabilitation process, the laryngeal elevation time and the peak time of the submental muscle group in the rehabilitation stage are obtained from the biomechanical information; then, the difference between the laryngeal elevation time and the peak time of the submental muscle group is taken as the laryngeal-muscle electrical movement time difference, which is the difference between the laryngeal elevation start time and the peak time of the submental muscle group, and the laryngeal-muscle electrical movement time difference can reflect the synergistic efficiency of neural signal conduction and muscle mechanical response; finally, the total duration of complete swallowing action is calculated by taking the mean value of all swallowing durations in the rehabilitation stage, and the score is calculated by using a piecewise linear function, when the time difference accounts for 5% of the best physiological range interval (default is 10%-20%), the score is 1, and each deviation from the interval 5%, the score decreases by 0.1; if the time difference is negative, it means that the muscle activation lags behind, and the score is directly reduced by 0.3, so as to obtain the coordination score of the rehabilitation stage, and the coordination score of each rehabilitation stage in the swallowing rehabilitation process can be obtained through the above-mentioned manner.

[0062] In some embodiments, the function recovery index of the pharyngeal swallowing function in the swallowing rehabilitation can be determined by all coordination scores and the aspiration risk feature, which can be achieved by the following steps:

[0063] For each rehabilitation stage, the exponential decay term of the aspiration risk feature in the rehabilitation stage is obtained;

[0064] The coordination score of the rehabilitation stage and the aspiration risk feature are fused into the function recovery value of the rehabilitation stage through the exponential decay term, and the function recovery value of each rehabilitation stage can be obtained through the above-mentioned manner;

[0065] The function recovery index of the pharyngeal swallowing function in the swallowing rehabilitation is determined according to all function recovery values.

[0066] It should be noted that in the present application, the function recovery index is a global evaluation index for quantifying the overall rehabilitation progress of the patient; the function recovery value is a weighted evaluation value reflecting the overall recovery level of the swallowing function of the patient in the current rehabilitation stage; the exponential decay term represents the influence degree of the aspiration risk on the function recovery in each rehabilitation stage, and the exponential decay term is used to reduce the negative influence of high-risk data on the function recovery evaluation.

[0067] In a specific implementation, first, for each rehabilitation stage, an index decay term of the aspiration risk feature in the rehabilitation stage is obtained from the control console of the monitoring system; then, a ratio of the natural logarithm of the aspiration risk feature and the index decay term is taken as an influence value of the aspiration risk on the functional recovery, and a preset aspiration risk and coordination score are used to determine the influence weight of the functional recovery in the rehabilitation stage, so as to calculate a weighted sum of the influence value and the coordination score as the functional recovery value of the rehabilitation stage, and the functional recovery value of each rehabilitation stage can be obtained through the above manner; finally, a set of all the functional recovery values is taken as the functional recovery index of the pharyngeal swallowing function in the pharyngeal stage of the swallowing rehabilitation.

[0068] In step 104, a swallowing efficiency index in the swallowing rehabilitation is extracted from the pre-acquired swallowing record, and then a rehabilitation deviation feature of the pharynx is determined through the swallowing efficiency index and the functional recovery index, and the swallowing rehabilitation scheme after the audible and visual alarm is individually adjusted based on the rehabilitation deviation feature.

[0069] In some embodiments, the swallowing efficiency index in the swallowing rehabilitation is extracted from the pre-acquired swallowing record, and the swallowing efficiency index is determined by referring to the following steps. Figure 2 The figure is a flowchart for determining the swallowing efficiency index in some embodiments of the present application, and the swallowing efficiency index in the present embodiment can be determined by the following steps:

[0070] In step 1041, the bolus transit time, the laryngeal elevation amplitude and the average pressure are obtained from the pre-acquired swallowing record.

[0071] In step 1042, the swallowing efficiency index in the swallowing rehabilitation is determined through the bolus transit time, the laryngeal elevation amplitude and the average pressure.

[0072] It should be noted that in the present application, the swallowing efficiency index is a composite index quantifying the transmission efficiency of the bolus under the unit mechanical consumption; the bolus transit time refers to the complete time from the start of the bolus pushing at the tongue root to the passing through the cricopharyngeal muscle into the esophagus; the laryngeal elevation amplitude refers to the maximum displacement distance of the thyroid cartilage in the vertical direction during the swallowing process; and the average pressure is the pressure value reflecting the overall contraction strength of the pharyngeal muscle.

[0073] In a specific implementation, first, time nodes are determined by synchronously analyzing the video fluoroscopic image and the pharyngeal pressure waveform. The time of passage of the bolus is determined by taking the instant at which the tongue root pushes the bolus (visible in the video as the hyoid bone moves forward) as the starting point and the point at which the pressure waveform of the cricopharyngeal muscle drops to the baseline (indicating that the bolus has completely entered the esophagus) as the ending point. The vertical displacement curve is recorded by using a displacement sensor attached to the thyroid cartilage, and the straight-line distance between the resting position and the maximum lifting position in the displacement curve is taken as the laryngeal elevation amplitude, which is standardized by the patient's neck circumference (unit: mm / cm) to eliminate individual differences. The pressure data of the cricopharyngeal muscle corresponding to the channel are selected from the pharyngeal pressure sensor array, and all sampling points in the period when the bolus passes (from the starting point of the pressure rising edge to the ending point of the falling edge) are intercepted. After removing abnormal peaks (such as cough interference), the arithmetic mean value is taken as the average pressure. Then, the benchmark value of the time of passage of the bolus in the healthy population, the individualized theoretical optimal value of the laryngeal elevation amplitude and the average pressure are obtained from the control console of the monitoring system. The time of passage of the bolus is divided by the benchmark value of the time of passage of the bolus in the healthy population to obtain the relative time coefficient, and the laryngeal elevation amplitude and the average pressure are divided by their individualized theoretical optimal values to obtain the laryngeal elevation amplitude standardized value and the average pressure standardized value, respectively. The swallowing efficiency index in swallowing rehabilitation is calculated in the following manner: swallowing efficiency index = (relative time coefficient) / (laryngeal elevation amplitude standardized value x average pressure standardized value). Thus, the swallowing efficiency index in swallowing rehabilitation is obtained.

[0074] In some embodiments, determining the deviation feature of the pharynx in swallowing rehabilitation by the swallowing efficiency index and the functional recovery index can be achieved by the following steps:

[0075] determining the matching degree between the swallowing efficiency index and the functional recovery index;

[0076] evaluating the degree of deviation in swallowing rehabilitation by the matching degree to obtain the deviation feature of the pharynx in swallowing rehabilitation.

[0077] It should be noted that, in this application, the deviation feature is a quantitative index reflecting the difference between the current rehabilitation progress of the patient and the standard recovery curve. In a specific implementation, first, the ratio of the swallowing efficiency index to the functional recovery index is taken as the matching degree between the swallowing efficiency index and the functional recovery index. The matching degree refers to the degree of consistency between the swallowing efficiency index and the functional recovery index, which is used to quantify the fit between the actual swallowing function recovery of the patient and the theoretical expected recovery level. Then, the difference between the matching degree and 1 is taken as the deviation feature of the pharynx.

[0078] In some embodiments, the step of adjusting the swallowing rehabilitation scheme after the sound and light alarm based on the rehabilitation deviation feature can be achieved by the following steps: first, the positive and negative values and the amplitudes of the rehabilitation deviation feature are used to determine the corresponding deviation type (delay type or compensation type) and deviation level (mild, moderate, or severe) from the mapping table of the monitoring system console. If the rehabilitation deviation feature is <-0.2, the swallowing rehabilitation is a delay type deviation, and if the rehabilitation deviation feature is >0.3, the swallowing rehabilitation is a compensation type deviation. For the delay type deviation, the training frequency is adjusted, for example, the Shaker training is increased from 3 groups per day to 5 groups, the moderate is replaced by balloon dilation combined with neuromuscular electrical stimulation, and the severe is implemented by cricopharyngeal myotomy combined with biofeedback training. For the compensation type deviation, the neck relaxation training is used for mild, the surface electromyography biofeedback is used to suppress abnormal electromyography for moderate, and the laryngeal muscle injection therapy is combined for severe. All the schemes are dynamically adjusted according to the real-time monitoring data, such as reducing the intervention intensity when the laryngeal elevation amplitude of the delay type patient improves by more than 15%, and switching to maintenance training when the standard deviation of the electromyography of the compensation type patient meets the standard for three consecutive times, to ensure that the rehabilitation process is accurately matched with the individual recovery curve.

[0079] In addition, another aspect of the present application, in some embodiments, the present application provides an intelligent monitoring system for swallowing rehabilitation, which comprises a monitoring unit, which comprises Figure 3 The figure is a structural schematic diagram of the monitoring unit according to some embodiments of the present application, which comprises a collection module 201, a processing module 202, and an execution module 203, which are described as follows:

[0080] The collection module 201 is mainly used for collecting the swallowing acoustic signal and the pharyngeal pressure waveform of the bolus passing through the pharynx in the swallowing rehabilitation, and further extracting the high-frequency energy mutation of the cough sound in the swallowing acoustic signal and the delay feature of the bolus passing through the pharynx in the pharyngeal pressure waveform;

[0081] The processing module 202 is used for determining the aspiration risk feature of the pressure peak in the swallowing rehabilitation by the high-frequency energy mutation and the delay feature, starting the sound and light alarm in the swallowing rehabilitation when the aspiration risk feature is greater than the risk threshold in the swallowing rehabilitation, and acquiring the biomechanical information in the swallowing rehabilitation after the sound and light alarm;

[0082] It should be noted that the processing module 202 is also used for determining the coordination score of each rehabilitation stage in the swallowing rehabilitation process by the laryngeal-muscle electromyography timing difference in the biomechanical information, and further determining the functional recovery index of the pharyngeal swallowing function in the swallowing rehabilitation by all the coordination scores and the aspiration risk feature;

[0083] The execution module 203 is mainly used for extracting a swallowing efficiency index in swallowing rehabilitation from the pre-acquired swallowing record, and then determining a rehabilitation deviation feature of the pharynx by the swallowing efficiency index and the functional recovery index, and individually adjusting the swallowing rehabilitation scheme after the sound and light alarm based on the rehabilitation deviation feature.

[0084] The above describes the examples of the intelligent monitoring system and method for swallowing rehabilitation provided by the embodiments of the present application in detail. It can be understood that the corresponding device contains the hardware structure and / or software module for executing the corresponding functions in order to realize the above functions. Those skilled in the art should easily realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is realized in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0085] In some embodiments, the present application also provides a computer device, which comprises a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the intelligent monitoring method for swallowing rehabilitation described above.

[0086] In some embodiments, with reference to Figure 4 The dashed line in the figure indicates that the unit or the module is optional, and the figure is a structural schematic diagram of a computer device for implementing the intelligent monitoring method for swallowing rehabilitation according to the embodiments of the present application. The intelligent monitoring method for swallowing rehabilitation described in the above embodiments can be implemented by the computer device shown in the figure, which comprises at least one processor 301, a memory 302 and at least one communication unit 305, and the computer device can be a terminal device or a server or a chip. Figure 4 The processor 301 can be a general-purpose processor or a special-purpose processor. For example, the processor 301 can be a central processing unit (CPU), which can be used to control the computer device, execute the software program, and process the data of the software program. The computer device can also comprise a communication unit 305 to realize the input (reception) and output (transmission) of signals.

[0087] The processor 301 can be a general-purpose processor or a special-purpose processor. For example, the processor 301 can be a central processing unit (CPU), which can be used to control the computer device, execute the software program, and process the data of the software program. The computer device can also comprise a communication unit 305 to realize the input (reception) and output (transmission) of signals.

[0088] For example, the computer device can be a chip, the communication unit 305 can be an input and / or output circuit of the chip, or the communication unit 305 can be a communication interface of the chip, and the chip can be a component of a terminal device or a network device or other device.

[0089] For another example, the computer device can be a terminal device or a server, and the communication unit 305 can be a transceiver of the terminal device or the server, or the communication unit 305 can be a transceiver circuit of the terminal device or the server.

[0090] The computer device can include one or more memories 302, and the memories 302 have programs 304 stored thereon, and the programs 304 can be run by the processor 301 to generate instructions 303, so that the processor 301 executes the method described in the above method embodiments according to the instructions 303. Optionally, the memories 302 can also store data (such as a target audit model). Optionally, the processor 301 can also read the data stored in the memories 302, and the data can be stored in the same storage address as the programs 304, or the data can be stored in different storage addresses from the programs 304.

[0091] The processor 301 and the memories 302 can be separately arranged, or can be integrated together, for example, integrated on a system on chip (SOC) of the terminal device.

[0092] It should be understood that each step of the above method embodiments can be completed by a logic circuit in the form of hardware or an instruction in the form of software in the processor 301, and the processor 301 can be a CPU, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, for example, a discrete gate, a transistor logic device, or a discrete hardware component.

[0093] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) containing computer-usable program code.

[0094] For example, in some embodiments, the present application also provides a computer-readable storage medium, which stores instructions or codes. When the instructions or codes are run on a computer, the computer implements the above-mentioned intelligent monitoring method for swallowing rehabilitation.

[0095] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0096] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. An intelligent monitoring method for swallowing rehabilitation, characterized in that: The steps include: Acquiring swallowing acoustic signals and pharyngeal pressure waveforms of food boluses passing through the pharynx during swallowing rehabilitation, and then extracting high-frequency energy mutations of cough sounds from the swallowing acoustic signals and delay characteristics of food boluses passing through the pharynx from the pharyngeal pressure waveforms, wherein the coefficient mutations of the Mel-frequency cepstral coefficients in the swallowing acoustic signals are extracted as the high-frequency energy mutations of cough sounds, and the pressure peak delay time of the food bolus passing through the cricopharyngeal muscle from the pharyngeal pressure waveform is extracted as the delay characteristics of food bolus passing through the pharynx; The product of the high-frequency energy mutation amount and the delay feature is used as the aspiration risk feature of the pressure peak in swallowing rehabilitation. When the aspiration risk feature is greater than the risk threshold in swallowing rehabilitation, the sound and light alarm in swallowing rehabilitation is activated, and the biomechanical information in swallowing rehabilitation is obtained after the sound and light alarm, wherein the laryngeal motion trajectory is captured in real time by an inertial measurement unit, the start time of laryngeal lifting and the maximum displacement time are accurately marked as laryngeal lifting time parameters, the surface electromyography signal of the submental muscle group is synchronously collected, the sliding window peak detection algorithm is used to determine the peak time of the electromyography activity, and the collection of the laryngeal lifting time and the peak time of the submental muscle group is used as the biomechanical information in swallowing rehabilitation; The coordination scores of each rehabilitation stage in the swallowing rehabilitation process are determined by the laryngeal-myoelectric motion timing difference in the biomechanical information, wherein the difference between the laryngeal lifting time and the submental muscle group peak time is used as the laryngeal-myoelectric motion timing difference, and the coordination score of the rehabilitation stage is determined according to the laryngeal-myoelectric motion timing difference and the total duration of the complete swallowing action, and the exponential decay term of the aspiration risk feature in the rehabilitation stage is obtained, and the ratio of the aspiration risk feature to the natural logarithm of the exponential decay term is used as the impact value of the aspiration risk on functional recovery, and the weighted sum of the impact value and the coordination score is calculated as the functional recovery value of the rehabilitation stage, and the collection of all functional recovery values ​​is used as the functional recovery index of the swallowing function in the pharyngeal stage of swallowing rehabilitation; The swallowing efficiency index in swallowing rehabilitation is extracted from the pre-collected swallowing records. The swallowing efficiency index = (relative time coefficient) / (standardized value of laryngeal elevation amplitude × standardized value of average pressure). The bolus transit time is divided by the baseline value of the healthy population as the relative time coefficient. The laryngeal elevation amplitude and average pressure are divided by their individualized theoretical optimal values ​​as the standardized value of laryngeal elevation amplitude and the standardized value of average pressure, respectively. The bolus transit time refers to the complete time from the push of the bolus from the root of the tongue to the entry of the esophagus through the cricopharyngeal muscle. The laryngeal elevation amplitude refers to the maximum vertical displacement distance of the thyroid cartilage during swallowing; the average pressure is a pressure value that reflects the overall contraction strength of the pharyngeal muscles. The ratio of the swallowing efficiency index to the functional recovery index is used as the matching degree between the swallowing efficiency index and the functional recovery index. The difference between this matching degree and 1 is used as the rehabilitation deviation feature of the pharynx. Based on the rehabilitation deviation feature, the swallowing rehabilitation plan after the sound and light alarm is personalized.

2. The method according to claim 1, wherein A neck-mounted microphone was used to collect swallowing acoustic signals of food bolus passing through the pharynx during swallowing rehabilitation.

3. An intelligent monitoring system for swallowing rehabilitation, used to execute the intelligent monitoring method for swallowing rehabilitation according to any one of claims 1 to 2, the intelligent monitoring system for swallowing rehabilitation comprising a monitoring unit, characterized in that: The monitoring unit includes: An acquisition module is used to acquire swallowing acoustic signals and pharyngeal pressure waveforms of food boluses passing through the pharynx during swallowing rehabilitation, and then extract the high-frequency energy mutation of cough sounds in the swallowing acoustic signals and the delay characteristics of food bolus passing through the pharynx in the pharyngeal pressure waveform; a processing module, configured to determine an aspiration risk characteristic of a pressure peak during swallowing rehabilitation based on the high-frequency energy mutation amount and the delay characteristic, and to activate an audible and visual alarm during swallowing rehabilitation when the aspiration risk characteristic is greater than a risk threshold during swallowing rehabilitation, and to obtain biomechanical information during swallowing rehabilitation after the audible and visual alarm; The processing module is further configured to determine the coordination scores of each rehabilitation stage during the swallowing rehabilitation process based on the laryngeal-myoelectric motion timing difference in the biomechanical information, and further determine the functional recovery index of the swallowing function during the pharyngeal phase of the swallowing rehabilitation process based on all the coordination scores and the aspiration risk characteristics; The execution module is used to extract the swallowing efficiency index in swallowing rehabilitation from the pre-collected swallowing records, and then determine the rehabilitation deviation characteristics of the pharynx through the swallowing efficiency index and the functional recovery index, and personalize the swallowing rehabilitation plan after the sound and light alarm based on the rehabilitation deviation characteristics.

4. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the intelligent monitoring method for swallowing rehabilitation according to any one of claims 1 to 2.

5. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions or codes, which, when executed on a computer, enable the computer to implement the intelligent monitoring method for swallowing rehabilitation according to any one of claims 1 to 2.

Images