Listening to MS: AI-assisted speech analysis for diagnosis and fatigue prediction (COMMITMENT)

1

The COMMITMENT trial aimed to identify vocal biomarkers to differentiate between people with Multiple Sclerosis (pwMS) with and without fatigue.
2

Five acoustic features were linked to general fatigue in pwMS, while additional features were associated specifically with motor and cognitive fatigue.
3

The best classification models achieved specificities of 0.68–0.94 and sensitivities of 0.38–0.90 in predicting fatigue in pwMS.
4

Speech biomarkers distinguished pwMS from healthy controls with a specificity of 0.90 but had a lower sensitivity of 0.3.
5

AI-assisted speech analysis could potentially complement existing fatigue assessments in pwMS, addressing the need for objective diagnostic tools.

Frontiers In Digital Health

by Helly Hammer, Monica Gonzalez-Machorro, Pascal Hecker, Uwe Reichel, Alisha Zmutt, Lisa Pedrotti, Andrew Chan, Florian Eyben, Hesam Sagha, Matthias Kahlau, Bert Arnrich, Björn W. Schuller, Robert Hoepner
May 29, 2026

1