EUVIMEDEUVIMED entdecken
Crossref

A Data-Driven Healthcare Framework for Obesity Level Classification Using Gradient Boosting and Feature Interpretability

Jetty Bino Mariyan, Chandra Prakash Vudatha

International Journal of Drug Delivery Technology · 04.04.2026 · 16 (89s)

DOI: 10.25258/ijddt.16.89s.49 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 04.04.2026. Verfasst von Jetty Bino Mariyan und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Obesity is a major public health concern associated with an increased risk of several chronic diseases. Machine learning techniques can support the classification of obesity levels by identifying patterns in demographic, physical, and lifestyle-related data. This study investigates the performance of three machine learning algorithms—Random Forest, Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM)—for obesity level classification. The study uses a dataset attributed to Palechor and de la Hoz Manotas (2019), with preprocessing and an 80:20 training–testing split, as described in the methodology. The reported classification accuracies are 95.03% for Random Forest, 95.98% for XGBoost, and 96.69% for LightGBM. Among the evaluated models, LightGBM achieves the highest reported accuracy. Feature importance analysis is used to examine the contribution of variables such as weight, height, and lifestyle-related factors to the classification results. However, the findings should be interpreted in light of limitations related to dataset size, self-reported information, and the absence of longitudinal or independent external validation. Further evaluation using cross-validation, additional performance metrics, and explainability methods is necessary to assess the robustness and practical applicability of the proposed approach. Keywords: Obesity classification, machine learning, Random Forest, XGBoost, LightGBM, feature importance, healthcare analytics.

Zitieren

APA

Mariyan, J. B., & Vudatha, C. P. (2026). A Data-Driven Healthcare Framework for Obesity Level Classification Using Gradient Boosting and Feature Interpretability. International Journal of Drug Delivery Technology, 16(89s). https://doi.org/10.25258/ijddt.16.89s.49

Vancouver

Mariyan JB, Vudatha CP. A Data-Driven Healthcare Framework for Obesity Level Classification Using Gradient Boosting and Feature Interpretability. International Journal of Drug Delivery Technology. 2026;16(89s). doi:10.25258/ijddt.16.89s.49

BibTeX
@article{Mariyan2026,
  author = {Mariyan, Jetty Bino and Vudatha, Chandra Prakash},
  title = {A Data-Driven Healthcare Framework for Obesity Level Classification Using Gradient Boosting and Feature Interpretability},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {89s},
  doi = {10.25258/ijddt.16.89s.49}
}
Kostenlos starten →