Investigating the Utility of Multimodal Conversational Technology and Audiovisual Analytic Measures for the Assessment and Monitoring of Amyotrophic Lateral Sclerosis at Scale

TL;DR

This study introduces a cloud-based multimodal platform that automatically analyzes speech to remotely assess and monitor ALS, showing significant differences in speech metrics between healthy controls and patients, and predicting disease severity.

Contribution

The paper presents a novel scalable system using audiovisual speech metrics for remote ALS assessment, demonstrating its effectiveness in differentiating patient groups and predicting disease severity.

Findings

Significant acoustic and visual speech differences between controls and ALS patients.

High sensitivity and specificity of speech metrics in classification tasks.

Effective prediction of ALS severity using audiovisual features.

Abstract

We propose a cloud-based multimodal dialog platform for the remote assessment and monitoring of Amyotrophic Lateral Sclerosis (ALS) at scale. This paper presents our vision, technology setup, and an initial investigation of the efficacy of the various acoustic and visual speech metrics automatically extracted by the platform. 82 healthy controls and 54 people with ALS (pALS) were instructed to interact with the platform and completed a battery of speaking tasks designed to probe the acoustic, articulatory, phonatory, and respiratory aspects of their speech. We find that multiple acoustic (rate, duration, voicing) and visual (higher order statistics of the jaw and lip) speech metrics show statistically significant differences between controls, bulbar symptomatic and bulbar pre-symptomatic patients. We report on the sensitivity and specificity of these metrics using five-fold cross-validation. We further conducted a LASSO-LARS regression analysis to uncover the relative contributions of various acoustic and visual features in predicting the severity of patients' ALS (as measured by their self-reported ALSFRS-R scores). Our results provide encouraging evidence of the utility of automatically extracted audiovisual analytics for scalable remote patient assessment and monitoring in ALS.