Classification of Bulbar ALS from Kinematic Features of the Jaw and Lips: Towards Computer-Mediated Assessment

Andrea Bandini, Jordan R. Green, Lorne Zinman, Yana Yunusova


Recent studies demonstrated that lip and jaw movements during speech may provide important information for the diagnosis of amyotrophic lateral sclerosis (ALS) and for understanding its progression. A thorough investigation of these movements is essential for the development of intelligent video- or optically-based facial tracking systems that could assist with early diagnosis and progress monitoring. In this paper, we investigated the potential for a novel and expanded set of kinematic features obtained from lips and jaw to classify articulatory data into three stages of bulbar disease progression (i.e., pre-symptomatic, early symptomatic, and late symptomatic). Feature selection methods (Relief-F and mRMR) and classification algorithm (SVM) were used for this purpose. Results showed that even with a limited number of kinematic features it was possible to obtain good classification accuracy (nearly 80%). Given the recent development of video-based markerless methods for tracking speech movements, these results provide strong rationale for supporting the development of portable and cheap systems for monitoring the orofacial function in ALS.


 DOI: 10.21437/Interspeech.2017-478

Cite as: Bandini, A., Green, J.R., Zinman, L., Yunusova, Y. (2017) Classification of Bulbar ALS from Kinematic Features of the Jaw and Lips: Towards Computer-Mediated Assessment. Proc. Interspeech 2017, 1819-1823, DOI: 10.21437/Interspeech.2017-478.


@inproceedings{Bandini2017,
  author={Andrea Bandini and Jordan R. Green and Lorne Zinman and Yana Yunusova},
  title={Classification of Bulbar ALS from Kinematic Features of the Jaw and Lips: Towards Computer-Mediated Assessment},
  year=2017,
  booktitle={Proc. Interspeech 2017},
  pages={1819--1823},
  doi={10.21437/Interspeech.2017-478},
  url={http://dx.doi.org/10.21437/Interspeech.2017-478}
}