Multimodal AI Markers for aMCI Detection: Integrating Language, Speech, and Facial Analysis in an Argentine Cohort
This study demonstrates that AI-based multimodal markers, including language, speech acoustics, facial analysis, and emotion recognition, can effectively differentiate aMCI from healthy controls in an Argentine population. Validating these tools using Spanish-language data and cost-effective, non-invasive methods is crucial for their broader applicability.
Authors
- Lara Gauder (ORCID: https://orcid.org/0000-0001-6242-1546)
- Diego Fernández Slezak (ORCID: https://orcid.org/0000-0001-6348-1559)
- Greta Keller (ORCID: https://orcid.org/0000-0001-9774-373X)
- Luciana Ferrer (ORCID: https://orcid.org/0000-0002-0426-8683)
- Ricardo Allegri (ORCID: https://orcid.org/0000-0001-7166-1234)
- Laouen Belloli (ORCID: https://orcid.org/0000-0002-4093-7135)
- Luc¡a Crivelli
- Agostina Carello
Institutions
- Universidad de Buenos Aires (AR)
- Centro Científico Tecnológico - San Juan (AR)
- Fundación para la Lucha contra las Enfermedades Neurológicas de la Infancia (AR)
- Instituto de Neurología Cognitiva (AR)
- Instituto Tecnológico de Buenos Aires (ITBA) (AR)
Publication Details
- Journal
- Alzheimer s & Dementia
- Published
- 2025-12-01
- DOI
- https://doi.org/10.1002/alz70857_100061
- Primary Topic
- Dementia and Cognitive Impairment Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00