How Consistent are Speech-Based Biomarkers in Remote Tracking of ALS Disease Progression Across Languages? A Case Study of English and Dutch
Abstract
Previous work has demonstrated the utility of speech-based digital biomarkers for remotely tracking longitudinal progression in people with Amyotrophic Lateral Sclerosis (pALS). Here, we investigate the responsiveness of these biomarkers across languages for consistency. We collected audiovisual data using a cloud-based multimodal dialogue platform, where pALS interacted with a virtual guide to perform several speaking exercises. We automatically extracted speech, linguistic and orofacial metrics from 143 English-speaking pALS (36 bulbar onset, 107 non-bulbar onset) and 26 Dutch-speaking pALS (10 bulbar, 16 non-bulbar onset). We used growth curve models to estimate the trajectory of these metrics over time. We observe that for most of these metrics, English-speaking pALS and Dutch-speaking pALS follow similar trajectories, i.e. the slopes are not statistically different from each other, demonstrating the potential of such speech-based biomarkers for remote monitoring across languages.