Aetiological clustering of newly diagnosed type 2 diabetes using machine learning: a retrospective cross-sectional study in Dubai, UAE
The study confirms that both severe and mild T2D phenotypes are present in newly diagnosed, complication-free patients, supporting the applicability of cluster-based classification early in disease. These results highlight the potential for personalised treatment strategies to optimise management and prevent complications. Future studies should investigate longitudinal outcomes and therapeutic response across clusters.
Authors
- Stafny Dsouza (ORCID: https://orcid.org/0000-0001-5618-6930)
- Riad Bayoumi (ORCID: https://orcid.org/0000-0001-8177-8129)
- Fatima Sulaiman (ORCID: https://orcid.org/0000-0003-2053-1186)
- Nandu Goswami (ORCID: https://orcid.org/0000-0002-6704-0723)
- Fayha Salah Ahmed (ORCID: https://orcid.org/0009-0005-2542-9959)
- Niaz Ali (ORCID: https://orcid.org/0000-0001-7525-3916)
- Fahad Mulla (ORCID: https://orcid.org/0009-0009-0017-8339)
- Amar Hassan Khamis (ORCID: https://orcid.org/0000-0002-8518-3066)
- Ahmad A. Abdul-Aziz
- M. Al-Sharhan
- A Rafie
- Suhaila Alnuaimi
- Ayesha AlOlama
- Fatima Abdul (ORCID: https://orcid.org/0000-0002-9873-5640)
Institutions
- Dubai Health Authority (AE)
- Dubai Hospital (AE)
- Mohammed Bin Rashid University of Medicine and Health Sciences (AE)
- Primary HealthCare (MT)
Publication Details
- Journal
- BMJ Open
- Published
- 2025-11-01
- DOI
- https://doi.org/10.1136/bmjopen-2025-101284
- Primary Topic
- Diabetes and associated disorders
- Type
- article
- Field-Weighted Citation Impact
- 0.00