EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-Based Facial Emotion Analysis for Early and Differential Diagnosis of Dementia

Letizia Bergamasco iD, Anita Coletta iD, Gabriella Olmo iD, Aurora Cermelli iD, Elisa Rubino iD, Innocenzo Rainero iD

Bioengineering · 04.10.2025 · 12 (10) · 1082

DOI: 10.3390/bioengineering12101082 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 04.10.2025. Verfasst von Letizia Bergamasco und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Control and Computer Engineering, Politecnico di Torino, 10129 Turin, Italy. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fondazione CRT.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Early and differential diagnosis of dementia is essential for timely and targeted care. This study investigated the feasibility of using an artificial intelligence (AI)-based system to discriminate between different stages and etiologies of dementia by analyzing facial emotions. We collected video recordings of 64 participants exposed to standardized audio-visual stimuli. Facial emotion features in terms of valence and arousal were extracted and used to train machine learning models on multiple classification tasks, including distinguishing individuals with mild cognitive impairment (MCI) and overt dementia from healthy controls (HCs) and differentiating Alzheimer’s disease (AD) from other types of cognitive impairment. Nested cross-validation was adopted to evaluate the performance of different tested models (K-Nearest Neighbors, Logistic Regression, and Support Vector Machine models) and optimize their hyperparameters. The system achieved a cross-validation accuracy of 76.0% for MCI vs. HCs, 73.6% for dementia vs. HCs, and 64.1% in the three-class classification (MCI vs. dementia vs. HCs). Among cognitively impaired individuals, a 75.4% accuracy was reached in distinguishing AD from other etiologies. These results demonstrated the potential of AI-driven facial emotion analysis as a non-invasive tool for early detection of cognitive impairment and for supporting differential diagnosis of AD in clinical settings.

Schlagwörter

Stichwörter der Autor:innen

Alzheimer’s diseaseaffective computingartificial intelligencedementiafacial expression recognitionmachine learningmild cognitive impairment

Autor:innen und Institutionen

  • Department of Control and Computer Engineering, Politecnico di Torino, 10129 Turin, Italy.
  • LINKS Foundation, 10138 Turin, Italy.
  • Center for Alzheimer's Disease and Related Dementias, Department of Neuroscience and Mental Health, A.O.U. Città Della Salute e Della Scienza di Torino, 10126 Turin, Italy.
  • Department of Neuroscience "Rita Levi Montalcini", University of Torino, 10126 Turin, Italy.

ORCID-Profile: Letizia Bergamasco, Anita Coletta, Gabriella Olmo, Aurora Cermelli, Elisa Rubino, Innocenzo Rainero

Förderung

  • Fondazione CRT

Zitieren

APA

Bergamasco, L., Coletta, A., Olmo, G., Cermelli, A., Rubino, E., & Rainero, I. (2025). AI-Based Facial Emotion Analysis for Early and Differential Diagnosis of Dementia. Bioengineering, 12(10), 1082. https://doi.org/10.3390/bioengineering12101082

Vancouver

Bergamasco L, Coletta A, Olmo G, Cermelli A, Rubino E, Rainero I. AI-Based Facial Emotion Analysis for Early and Differential Diagnosis of Dementia. Bioengineering. 2025;12(10):1082. doi:10.3390/bioengineering12101082

BibTeX
@article{Bergamasco2025,
  author = {Bergamasco, Letizia and Coletta, Anita and Olmo, Gabriella and Cermelli, Aurora and Rubino, Elisa and Rainero, Innocenzo},
  title = {AI-Based Facial Emotion Analysis for Early and Differential Diagnosis of Dementia},
  journal = {Bioengineering},
  year = {2025},
  volume = {12},
  number = {10},
  pages = {1082},
  doi = {10.3390/bioengineering12101082}
}
Kostenlos starten →