AI‐powered analysis of affective dimensions in speech and its relevance for FTD diagnosis
Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring · 2026-04 · 18 (2)
DOI: 10.1002/dad2.70300 ↗Kurz gefasst
Fachartikel in der Zeitschrift Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring, online erschienen am 15.04.2026. Verfasst von Agnès Denève und 4 weiteren Autor:innen. Beteiligte Einrichtung: Lille Neuroscience & Cognition, Inserm U1172, Univ Lille CHU Lille France. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Fondation Vaincre Alzheimer.
Abstract (Originalsprache)
INTRODUCTION Affective disturbances are common across behavioral variant frontotemporal degeneration (bvFTD), primary psychiatric disorders (PPD), and Alzheimer's disease (AD). Objective markers are needed for differential and transdiagnostic characterization. We tested whether artificial intelligence (AI)‐based analysis of natural speech could provide such markers. METHODS Speech from 112 participants (bvFTD = 31, AD = 28, PPD = 15, controls = 39) was analyzed using a fine‐tuned speech emotion recognition model estimating valence, arousal, dominance, and entropy. Group differences were assessed with analyses of covariance, diagnostic utility with logistic regression, and neuroanatomical correlates with voxel‐based morphometry. RESULTS Group‐specific affective profiles emerged. Overall, PPD exhibited a lower valence. bvFTD and AD showed a reduced arousal and a higher dominance. Affective dimensions predicted bvFTD with 80.4% accuracy (area under the curve = 0.732) and mapped onto fronto‐insular and temporal networks. Entropy was identified as a transdiagnostic marker. DISCUSSION AI‐based speech analysis provides objective, scalable biomarkers for differential diagnosis, transdiagnostic characterization, and disease monitoring.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Lille Neuroscience & Cognition, Inserm U1172, Univ Lille CHU Lille France.
- Centre national de ressources et de résilience (Cn2r) Lille Paris France.
ORCID-Profile: Agnès Denève, Thibaud Lebouvier, Fabien D'Hondt, Maxime Bertoux
Förderung
- Fondation Vaincre Alzheimer
Zitieren
APA
Denève, A., Dauchez, R., Lebouvier, T., D'Hondt, F., & Bertoux, M. (2026). AI‐powered analysis of affective dimensions in speech and its relevance for FTD diagnosis. Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring, 18(2). https://doi.org/10.1002/dad2.70300
Vancouver
Denève A, Dauchez R, Lebouvier T, D'Hondt F, Bertoux M. AI‐powered analysis of affective dimensions in speech and its relevance for FTD diagnosis. Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring. 2026;18(2). doi:10.1002/dad2.70300
BibTeX
@article{Denve2026,
author = {Denève, Agnès and Dauchez, Rosalie and Lebouvier, Thibaud and D'Hondt, Fabien and Bertoux, Maxime},
title = {AI‐powered analysis of affective dimensions in speech and its relevance for FTD diagnosis},
journal = {Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring},
year = {2026},
volume = {18},
number = {2},
doi = {10.1002/dad2.70300}
}
EUVIMED