Prediction of obesity levels based on physical activity and eating habits with a machine learning model integrated with explainable artificial intelligence

Basit Öğe Kaydı
dc.contributor.authorGormez, Yasin
dc.contributor.authorYagin, Fatma Hilal
dc.contributor.authorYagin, Burak
dc.contributor.authorAygun, Yalin
dc.contributor.authorBoke, Hulusi
dc.contributor.authorBadicu, Georgian
dc.contributor.authorDe Sousa Fernandes, Matheus Santos
dc.date.accessioned2026-04-04T13:31:18Z
dc.date.available2026-04-04T13:31:18Z
dc.date.issued2025
dc.departmentİnönü Üniversitesi
dc.description.abstractObjectives This study aims to build a machine learning (ML) prediction model integrated with explainable artificial intelligence (XAI) to categorize obesity levels from physical activity and dietary patterns. The inclusion of XAI methodologies facilitates a comprehensive understanding of the risk factors influencing the model predictions and thus increases transparency in the identification of obesity risk factors.Methods Six ML models were used: Bernoulli Naive Bayes, CatBoost, Decision Tree, Extra Trees Classifier, Histogram-based Gradient Boosting and Support Vector Machine. For each model, hyperparameters were tuned by random search methodology and model effectiveness was evaluated by repeated holdout testing. SHAP (SHapley Additive Annotations) and LIME (Local Interpretable Model Independent Annotations) interpretability methods were used to generate local and global feature importance measures.Results The CatBoost model exhibited the highest overall performance and achieved superior results in accuracy, precision, F1 score and AUC metrics. Nonetheless, other models such as Decision Tree and Histogram-based Gradient Boosting also yielded strong and competitive results. The results also highlighted age, weight, height and specific food patterns as key predictors of obesity. In terms of interpretability, LIME showed superior in fidelity, whereas SHAP showed improved sparsity and consistency across models, facilitating a comprehensive understanding of trait importance.Conclusion 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.
dc.description.sponsorshipOngoing Research Funding Program [ORF-2025-378]
dc.description.sponsorshipThe authors of this study extend their appreciation to the Ongoing Research Funding Program, King Saud University, Riyadh, Saudi Arabia, for their encouragement and assistance.
dc.identifier.doi10.3389/fphys.2025.1549306
dc.identifier.issn1664-042X
dc.identifier.orcid0000-0003-4100-8765
dc.identifier.pmid40740428
dc.identifier.scopus2-s2.0-105012176468
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.3389/fphys.2025.1549306
dc.identifier.urihttps://hdl.handle.net/11616/108694
dc.identifier.volume16
dc.identifier.wosWOS:001539005300001
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.language.isoen
dc.publisherFrontiers Media Sa
dc.relation.ispartofFrontiers in Physiology
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WOS_20250329
dc.subjectobesity prediction
dc.subjectmachine learning
dc.subjectexplainable artificial intelligence
dc.subjectphysical activity and diet
dc.subjectfeature importance
dc.titlePrediction of obesity levels based on physical activity and eating habits with a machine learning model integrated with explainable artificial intelligence
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
PubMed İndeksli Yayın Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu