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.

Amyotrophic lateral sclerosis (ALS), a motor neuron disease, remains a clinical diagnosis with a diagnostic delay of over a year. Here we examine the possibility that interactions with an internet search engine could be used to help screen for ALS. We identified 285 anonymous Bing users whose queries indicated that they had been diagnosed with ALS and matched them to 1) 3276 control users and 2) 1814 users whose searches indicated they had ALS disease mimics. We tested whether the ALS group could be distinguished from controls and disease mimics based on search engine query data. Finally, we conducted a prospective validation from participants who provided access to their Bing search data. The model distinguished between the ALS group and controls with an area under the curve (AUC) of 0.81. Model scores for the ALS group differed from the disease mimics group (ranksum test, P<0.05 with Bonferrini correction). Mild cognitive impairment could not be distinguished from ALS (NS). In the prospective analysis, the model reached an AUC of 0.74. These results suggest that interactions with search engines could be used as a tool to assist in screening for ALS, to reduce diagnostic delay.

No abstract