Improving T2D machine learning-based prediction accuracy with SNPs and younger age
While traditional clinical factors remained the strongest predictors of T2D risk, integration of genomic data produced a modest improvement in model performance, especially among younger adults. Validation across independent datasets confirmed the generalizability of these findings, underscoring the value of multi-dimensional risk-prediction models to refine T2D risk assessment.
Authors
- Nantia Iakovidou (ORCID: https://orcid.org/0000-0002-7268-411X)
- Haralampos Hatzikirou (ORCID: https://orcid.org/0000-0002-1270-7885)
- Antoine Abchee
- Hao Zhou (ORCID: https://orcid.org/0000-0001-7131-3758)
- Stéphanie Chacar (ORCID: https://orcid.org/0000-0003-4073-4749)
- Pierre Zalloua (ORCID: https://orcid.org/0000-0002-8494-5081)
- Cynthia Al Hageh (ORCID: https://orcid.org/0000-0001-8386-4063)
- Andreas Henschel (ORCID: https://orcid.org/0000-0003-1386-5372)
- Jorge P. Zubelli (ORCID: https://orcid.org/0000-0003-1581-9505)
- Moni Nader (ORCID: https://orcid.org/0000-0003-2138-5213)
- Siobhán O’Sullivan
Institutions
- Harvard University (US)
- University of Balamand (LB)
- Khalifa University of Science and Technology (AE)
- Aristotle University of Thessaloniki (GR)
Publication Details
- Journal
- Computational and Structural Biotechnology Journal
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1016/j.csbj.2025.06.038
- Citations
- 1
- Primary Topic
- Artificial Intelligence in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 2.94
Funders
- Khalifa University of Science, Technology and Research