AUTHOR=Northall Alicia , Mukhopadhyay Budhaditya , Weber Miriam , Petri Susanne , Prudlo Johannes , Vielhaber Stefan , Schreiber Stefanie , Kuehn Esther 

TITLE=An Automated Tongue Tracker for Quantifying Bulbar Function in ALS

JOURNAL=Frontiers in Neurology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2022.838191

DOI=10.3389/fneur.2022.838191

ISSN=1664-2295

ABSTRACT=Introduction: Bulbar symptoms, including difficulty swallowing and speaking, are common in amyotrophic lateral sclerosis (ALS) and other neurological disorders such as stroke. The presence of bulbar symptoms provides important information regarding clinical outcomes such as survival time after diagnosis. Nevertheless, there are currently no easily-accessible, quantitative methods to measure bulbar function in patients. Methods: We developed an open-source tool to quantify bulbar function based on short video clips of lateral tongue movements by training a neural network to track kinematic tongue features. We tested 16 healthy controls and 10 patients with ALS, of which 2 patients were clinically diagnosed with bulbar-onset type and 2 patients showed sub-clinical symptoms of bulbar impairment. Results: We validated the tool by comparing it with manual delineation and demonstrate a case of one early-stage bulbar-onset patient who showed fewer and slower tongue sweeps compared to healthy controls and limb-onset patients, and two sub-clinically bulbar-impaired patients who showed a different tongue kinematic profile when compared to healthy controls. Discussion: We suggest that the tongue kinematic features, which identify the patients with bulbar symptoms, reflect the signature spasticity and weakness of the tongue associated with bulbar impairment, caused by upper and lower motor neurons in clinical and preclinical stages. Our open-source tool may serve as a quantitative marker for bulbar function in other disorders involving dysphagia beyond ALS, such as stroke.