Automated Dysphagia Screening Using Noninvasive Neck Acoustic Sensing

TL;DR

This paper presents a noninvasive, portable acoustic sensing method combined with machine learning to detect swallowing abnormalities (dysphagia), achieving high accuracy and offering a scalable solution for early diagnosis.

Contribution

It introduces a novel automated framework using neck acoustic signals and machine learning for dysphagia detection, demonstrating promising results with high AUC-ROC scores.

Findings

Achieved an AUC-ROC of 0.904 in abnormality detection

Validated the approach across five independent train-test splits

Showed feasibility of noninvasive acoustic sensing for pharyngeal health monitoring

Abstract

Pharyngeal health plays a vital role in essential human functions such as breathing, swallowing, and vocalization. Early detection of swallowing abnormalities, also known as dysphagia, is crucial for timely intervention. However, current diagnostic methods often rely on radiographic imaging or invasive procedures. In this study, we propose an automated framework for detecting dysphagia using portable and noninvasive acoustic sensing coupled with applied machine learning. By capturing subtle acoustic signals from the neck during swallowing tasks, we aim to identify patterns associated with abnormal physiological conditions. Our approach achieves promising test-time abnormality detection performance, with an AUC-ROC of 0.904 under 5 independent train-test splits. This work demonstrates the feasibility of using noninvasive acoustic sensing as a practical and scalable tool for pharyngeal health monitoring.