Prediction of obesity levels based on physical activity and eating habits with a machine learning model integrated with explainable artificial intelligence
This research demonstrates that ML algorithms, when integrated with XAI technologies, can accurately predict obesity levels and explain important contributing risk factors. The use of SHAP and LIME increases model transparency, facilitating the identification of specific lifestyle patterns linked to obesity risk. These findings help to formulate more precise intervention techniques guided by a reliable and understandable predictive framework.
Authors
- Abedalrhman Alkhateeb (ORCID: https://orcid.org/0000-0002-1751-7570)
- Hulusi Böke (ORCID: https://orcid.org/0000-0002-5728-680X)
- Georgian Bădicu (ORCID: https://orcid.org/0000-0003-4100-8765)
- Matheus Santos de Sousa Fernandes (ORCID: https://orcid.org/0000-0002-1066-9176)
- Fatma Hilal Yağın (ORCID: https://orcid.org/0000-0002-9848-7958)
- Yalın Aygün (ORCID: https://orcid.org/0000-0002-1018-657X)
- Yasin Görmez (ORCID: https://orcid.org/0000-0001-8276-2030)
- Burak Yagin (ORCID: https://orcid.org/0000-0001-6687-979X)
- Mohammadreza Aghaei
- Mahmood Basil A. Al-Rawi
Institutions
- Sivas Cumhuriyet Üniversitesi (TR)
- Ministry of Higher Education (MY)
- University of Freiburg (DE)
- Inonu University (TR)
- Norwegian University of Science and Technology (NO)
- Universidade Federal de Pernambuco (BR)
- King Saud University (SA)
- Transylvania University of Brașov (RO)
- Malatya Turgut Özal Üniversitesi (TR)
- Turgut Özal University (TR)
- Lakehead University (CA)
Publication Details
- Journal
- Frontiers in Physiology
- Published
- 2025-07-16
- DOI
- https://doi.org/10.3389/fphys.2025.1549306
- Citations
- 5
- Primary Topic
- Explainable Artificial Intelligence (XAI)
- Type
- article
- Field-Weighted Citation Impact
- 12.40