Swallowing Pattern Classification Method Using Multichannel Surface EMG Signals of Suprahyoid and Infrahyoid Muscles

Abstract

The ability to ne-tune the movement of swallowing-related organs and change the swallowing pattern to t the volume of a bolus, texture and the physical properties of the food to be swallowed is referred to as the swallowing reserve. In other words, it is the response capability of food swallowing to avoid choking and aspiration. Herein, we focus on the coordination of the suprahyoid and infrahyoid muscles activities, which are closely related to swallowing movement, as a rst step to develop a method to evaluate swallowing reserve, which declines due to neuromuscular disease, muscle weakness caused by aging, to mention a few. First, using two 22-channel electrodes, we measured the surface electromyography (sEMG) signals of suprahyoid and infrahyoid muscles during the following four swallowing conditions: combining two bolus volumes (3 and 15 mL water) and two techniques (normal and effortful swallow). Then, we veri ed whether the difference in swallowing patterns based on swallowing conditions can be classi ed from sEMG signals using three machine learning methods; namely, the real-time classi cation, comprehensive classi cation, and image recognition method. In the real-time classi cation method, the mean classi cation accuracy (MCA) for the four swallowing conditions was as low as 81.5%, indicating that the difference between swallowing conditions performed in a period of approximately 1 s cannot be classi ed suf ciently by this method. In the comprehensive classi cation method that applies a majority decision to all the classi cation results from the start to the end of swallowing, which can be obtained every 16 ms, MCA was 95.1%. Furthermore, in the image recognition method, the change of a series of sEMG signals in the swallowing movement was converted into swallowing pattern image, and the images were classi ed using a combination of deep convolutional neural networks and support vector machine (SVM). Compared with the comprehensive classi cation method, the number of training samples for the image recognition method was only 1/26, but the MCA reached 95.7%. This method, which can noninvasively evaluate swallowing patterns that change slightly based on swallowing conditions, could be applied to early detection of reduced swallowing function or a state of frailty (dysphagia potential) in aged individuals.

Directed Functional Coordination Analysis of Swallowing Muscles in Healthy and Dysphagic Subjects by Surface Electromyography

“…It was less safe for dysphagic patients to swallow thin liquids rather than thicker ones [65]. In this work, we also found that cG-causality was slightly higher for water and yoghurt than for saliva with no significant difference between them in healthy subjects, who seemed to have a good ability to fine-tune the activation pattern according to the type of bolus ingested, namely swallowing reserve [66], leading to similar interaction strengths among the boluses. The swallowing reserve decline due to neurological and neuromuscular diseases, muscle weakness caused by aging, and positional changes of swallowing-related organs [66].…”

“…This could explain the difference in the functional interactions among the boluses observed in dysphagic subjects. Generally, a decline in the swallowing reserve may cause a descent in the positions of the hyoid bone and larynx, a reduced antero-superior movement range for the hyoid bone and larynx elevation, larynx elevation delay, and a delay in the stimulation of the swallowing reflex [66]. The right hemispheric lateralization may also justify the preservation of the right-side muscle swallowing reserve while losing it in the left muscle group [55], which could explain the significant differences among the boluses in the LM→LSH and LSH→LIH interactions in dysphagic subjects.…”

Sincronización entre la videodeglución y la electromiografía de superficie en pacientes con afectación neurológica y síntomas de disfagia

“…A pesar de que varias investigaciones (19,21,23) , revelan el potencial de esta técnica para el estudio de patrones deglutorios, la electromiografía de superficie no se utiliza aún ni para evaluar la deglución ni para diagnosticar la disfagia en entornos clínicos, ya que con ella solo se pueden describir indirectamente los procesos musculares involucrados en la deglución, dado que es limitado el seguimiento de la actividad muscular regional y no es posible aislar músculos u otras regiones para evaluarlos (24). Esto hace necesario validar la técnica mediante pruebas de referencia, con el fin de estandarizar su uso en la práctica clínica (17).…”

“…174-7. ), tanto para la rehabilitación 15 , el diagnóstico 19 , 20 duration from the maximum amplitude to the end of the swallowing activity (duration B y el análisis de la coordinación de la fase oral de la deglución 21 , 22 . De esta manera, la electromiografía de superficie ofrece una alternativa no invasiva y de fácil acceso que eliminaría el impacto de los riesgos asociados con la radiación ionizante 11 .…”

“…A pesar de que varias investigaciones 19 , 21 , 23 (Chou W, Ou CZ, Lin BS, Ko MJ, Hu SP, Ting YM, et al . Wireless and wearable monitoring device for dysphagia evaluation.…”