Explainable bidirectional encoder representations from image transformers for Alzheimer's disease prediction
The experiments showed outstanding accuracy levels reaching 96%, while the <i>F</i>1-scores indicated 0.94, 1.00, and 0.95 for mild, moderate, and no AD group classifications. Performance evaluation metrics from the study demonstrate strong outcomes with a mean absolute error reaching 0.0727 and Cohen's kappa equaling 0.9451, while Matthews correlation coefficient reached 0.9455 and Hamming loss remained at 0.0365.
Authors
- Tehseen Mazhar (ORCID: https://orcid.org/0000-0002-4649-2376)
- Mona Alkhattabi
- M. A. Iqbal (ORCID: https://orcid.org/0000-0001-8069-1320)
- Waqas Tariq Paracha
- Abdul Khader Jilani Saudagar (ORCID: https://orcid.org/0000-0003-4205-3621)
- Muhammad Amir Khan (ORCID: https://orcid.org/0009-0001-6402-6942)
- Habib Hamam
- Sheikh Muhammad Saqib
Institutions
- Université de Moncton (CA)
- Gomal University (PK)
- University of Johannesburg (ZA)
- Government of Pakistan (PK)
- Omar Bongo University (GA)
- Islamic University (BD)
- Spectrum Research (United States) (US)
- National College of Business Administration and Economics (PK)
- Universiti Teknologi MARA (MY)
Publication Details
- Journal
- Digital Health
- Published
- 2026-02-01
- DOI
- https://doi.org/10.1177/20552076261416823
- Primary Topic
- Dementia and Cognitive Impairment Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00