Automatic prediction of amyotrophic lateral sclerosis (ALS) disease progression provides a more efficient and objective alternative than manual approaches. We propose ALS longitudinal speech transformer (ALST), a neural network-based automatic predictor of ALS disease progression from longitudinal speech recordings of ALS patients. By taking advantage of high-quality pretrained speech features and longitudinal information in the recordings, our best model achieves 91.0\% AUC, improving upon the previous best model by 5.6\% relative on the ALS TDI dataset. Careful analysis reveals that ALST is capable of fine-grained and interpretable predictions of ALS progression, especially for distinguishing between rarer and more severe cases. Code is publicly available.
@article{arxiv.2406.18625,
title = {Automatic Prediction of Amyotrophic Lateral Sclerosis Progression using Longitudinal Speech Transformer},
author = {Liming Wang and Yuan Gong and Nauman Dawalatabad and Marco Vilela and Katerina Placek and Brian Tracey and Yishu Gong and Alan Premasiri and Fernando Vieira and James Glass},
journal= {arXiv preprint arXiv:2406.18625},
year = {2024}
}