Artificial intelligence survival models for identifying relevant risk factors for incident diabetes in Azar cohort population
RF machine learning algorithms and LASSO-Cox regression analyses consistently identified WC, hypertension, and MCHC as the main risk factors for developing diabetes. The RF approach demonstrated slightly better accuracy in predicting the likelihood of diabetes at different time points.
Authors
- Reza Arabi Belaghi (ORCID: https://orcid.org/0000-0002-6989-9267)
- Farzaneh Hamidi (ORCID: https://orcid.org/0000-0002-5413-9185)
- Neda Gilani (ORCID: https://orcid.org/0000-0002-5399-0277)
- Pasqualina Santaguida (ORCID: https://orcid.org/0000-0001-7360-7362)
- Elnaz Faramarzi (ORCID: https://orcid.org/0000-0003-4128-433X)
- Mohammad‐Hossein Somi (ORCID: https://orcid.org/0000-0002-0770-9309)
Institutions
- Tabriz University of Medical Sciences (IR)
- Swedish University of Agricultural Sciences (SE)
- Impact (CA)
- McMaster University (CA)
Publication Details
- Journal
- Health Promotion Perspectives
- Published
- 2025-05-06
- DOI
- https://doi.org/10.34172/hpp.025.43105
- Primary Topic
- Artificial Intelligence in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Tabriz University of Medical Sciences
- University of Tabriz