Self-adapting Classification System for Swallow Intention Detection in Dysphagia Therapy

Abstract

In dysphagia the ability of elevating the larynx and hyoid is usually impaired. Electromyography (EMG) and Bioimpedance (BI) measurements at the neck can be used to trigger functional electrical stimulation (FES) of swallowing related muscles. The height and speed of larynx elevation can be assessed by evaluating the BI during a swallow. For the triggering of an supporting FES and for biofeedback online detection of swallow onsets is required. Patients can practice by a gamified biofeedback to swallow harder, swallow in a timely manner or to maintain the larynx elevation for a longer time period (Mendelson maneuver). The success of the stimulation and biofeedback therapy as well as the acceptance by the patient strongly depends on the precise detection of swallow onsets. We have introduced a classification algorithm based on a random forest classifier to trigger FES in phase with voluntary swallowing based on EMG and BI. Although the classification is successful in healthy subjects, difficulties appear in the utilization on some patients. The reason for this can be found in a strongly varying residual swallow activity. Usually the activity of EMG and change in BI are smaller in patients compared to healthy subjects. Thus an adaption procedure is needed, that can be easily applied. In this paper we introduce an algorithm that is capable to find an optimal classifier for a patient in terms of sensitivity. The adaption algorithm uses a small number of recorded swallow onsets of a patient at the beginning of a therapy session to evaluate different classifiers and to pick the most suitable for the treatment. The set of random forest classifiers has been trained with data from healthy subjects by step wise shifting the class weights of swallows and non-swallows, yielding classifiers with different sensitivities. The evaluation is done using data from 41 patients. It showed that the sensitivity of the classification can be increased by 4 to 6 % in average compared to fixed classifiers, but up to 66 % for individual patients. Finally, we studied the effect this adaptive classifier in triggered stimulation therapy in a single dysphagia patient. Swallowing performance was measurements during one week of therapy consisting of eleven therapy session. An improvement of 40 and 63 % in larynx elevation and speed could be observed, respectively.

Treatment of Dysphagia with Biofeedback and Functional Electrical Stimulation in a Patient with Wallenberg Syndrome: A Prospective Case Report

“…A few times the apparatus stimulated, even though S.G. did not initiate a swallow. False-positive stimulation can lead to a behaviour in which the subject attempts to prevent inappropriate stimulation [ 13 ] and can lead to poor sensorimotor learning. The algorithms for swallowing detection are in a continuous process of improvement based on the results of this and other studies to reduce detection error.…”

Identification of Family-Specific Features in Cas9 and Cas12 Proteins: A Machine Learning Approach Using Complete Protein Feature Spectrum

“…This method assigns weights to individual classes, such that the weights are inversely proportional to their class frequency. This procedure avoids bias toward the majority class ensuring that the model learns equal representation of all classes. , To observe the variance of our models, we repeated the steps of feature selection, model training, evaluation, and test set prediction over 15 different data splits. For further evaluation, the developed models were also predicted on their respective independent data sets, and an average of the evaluation matrices over the 15 splits is reported.…”

Pilot Study: Magnetic Motion Analysis for Swallowing Detection Using MEMS Cantilever Actuators

“…Several studies have explored the use of surface electromyography for dysphagia evaluation and biofeedback, based on electrophysiological information [ 22 , 23 , 24 ]. Nevertheless, the majority of these studies are mostly descriptive and focused on differences in amplitude and duration of normal/abnormal swallows, with some exceptions related to the use of automatic algorithms for detection of onset and specific swallowing phases [ 25 , 26 , 27 , 28 , 29 , 30 ]. Other sensors have been tested to detect swallows, such as bioimpedance, electromyography [ 25 , 28 ], nasal airflow [ 31 , 32 ], mechanomyography [ 27 , 32 ], and piezoelectric sensors, which all have shown the capability of swallow detection and dysphagia evaluation [ 33 , 34 ].…”