Clinical Report: Utilizing AI-Enhanced Speech Analysis for Diagnosing MS

Overview

This study explores the use of AI-based speech analysis to identify vocal biomarkers that differentiate between people with Multiple Sclerosis (pwMS) with and without fatigue.

Background

Multiple Sclerosis (MS) is a prevalent neurological disorder that significantly impacts the quality of life of affected individuals, with fatigue being one of the most common and debilitating symptoms. Current diagnostic methods for fatigue are largely subjective, relying on self-reported assessments.

Data Highlights

Key Findings

• Motor fatigue affected 50% and cognitive fatigue 40% of pwMS.
• Five acoustic features were associated with general fatigue, independent of depression and sleepiness.
• Specificities of classification models ranged from 0.68 to 0.94, while sensitivities ranged from 0.38 to 0.90.
• Speech biomarkers distinguished pwMS from HCs with a specificity of 0.90 but a sensitivity of only 0.3.

Clinical Implications

AI-assisted speech analysis may complement existing fatigue assessments in pwMS.

Conclusion

AI-based speech analysis presents a promising avenue for improving the assessment of fatigue in pwMS, potentially enhancing diagnostic accuracy and patient management.

Related Resources & Content

1. Brain, Artificial intelligence models using F-wave responses predict amyotrophic lateral sclerosis, 2023 -- https://academic.oup.com/brain/article/148/7/2320/7958696
2. npj Digital Medicine, Developing a Speech-Driven Digital Biomarker for Cognitive Decline: Utilizing Speech as an Indicator for Cognitive Evaluation, 2023 -- https://www.nature.com/articles/s41746-026-02360-8
3. Frontiers in Digital Health, An interpretable, clinically grounded framework for digital speech biomarker development in neurodegenerative diseases, 2023 -- https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2026.1794169/full
4. npj Digital Medicine, SpeechCARE: dynamic multimodal modeling for cognitive screening in diverse linguistic and speech task contexts, 2023 -- https://www.nature.com/articles/s41746-025-02026-x
5. Diagnosis of multiple sclerosis: 2024 revisions of the McDonald criteria - PubMed -- https://pubmed.ncbi.nlm.nih.gov/40975101/?utm_source=openai
6. Global prevalence of fatigue in patients with multiple sclerosis: a systematic review and meta-analysis - PubMed -- https://pubmed.ncbi.nlm.nih.gov/39416662/?utm_source=openai
7. Frontiers, Listening to MS: AI-Assisted Speech Analysis for Diagnosis and Fatigue Prediction, 2023 -- https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2026.1721274/full?utm_source=openai
8. Brain — Artificial intelligence models using F-wave responses predict amyotrophic lateral sclerosis
9. npj Digital Medicine — Developing a Speech-Driven Digital Biomarker for Cognitive Decline: Utilizing Speech as an Indicator for Cognitive Evaluation
10. Frontiers in Digital Health — An interpretable, clinically grounded framework for digital speech biomarker development in neurodegenerative diseases
11. npj Digital Medicine — SpeechCARE: dynamic multimodal modeling for cognitive screening in diverse linguistic and speech task contexts
12. Diagnosis of multiple sclerosis: 2024 revisions of the McDonald criteria - PubMed
13. Global prevalence of fatigue in patients with multiple sclerosis: a systematic review and meta-analysis - PubMed
14. Frontiers | Listening to MS: AI-Assisted Speech Analysis for Diagnosis and Fatigue Prediction