EUVIMEDEUVIMED entdecken
Crossref

Predictive Modeling of Diabetes Using Optimized Gradient Boosting and Feature Selection

Ch Prasanthi, Somisetty Ramesh Babu, V Sridhar, Kadaganchi Sudhakar, P.V.V.S.D. Nagendrudu, Amrutavalli Akula

International Journal of Drug Delivery Technology · 02.06.2026 · 16 (44s)

DOI: 10.25258/ijddt.16.44s.134 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 02.06.2026. Verfasst von Ch Prasanthi und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetes mellitus is a chronic metabolic disorder that poses a significant global health challenge due to its increasing prevalence and associated complications. Early and accurate prediction of diabetes can greatly assist in timely intervention and effective disease management. This study proposes a predictive modeling approach for diabetes detection using optimized Gradient Boosting techniques combined with feature selection methods. The objective is to enhance classification performance while reducing model complexity by identifying the most relevant clinical attributes. Initially, a comprehensive dataset containing medical and demographic features is preprocessed to handle missing values, outliers, and data normalization. Feature selection techniques such as correlation-based filtering and recursive feature elimination are employed to identify the most influential predictors. The optimized Gradient Boosting model is then trained using hyperparameter tuning to improve predictive accuracy and generalization capability. Performance evaluation is conducted using metrics such as accuracy, precision, recall, F1-score, and ROC-AUC. Experimental results demonstrate that the proposed approach achieves superior performance compared to baseline machine learning models by effectively reducing overfitting and improving interpretability. The integration of feature selection with optimized Gradient Boosting not only enhances prediction accuracy but also provides insights into critical risk factors associated with diabetes. This model can serve as a reliable decision-support tool for early diagnosis in clinical settings.

Zitieren

APA

Prasanthi, C., Babu, S. R., Sridhar, V., Sudhakar, K., Nagendrudu, P., & Akula, A. (2026). Predictive Modeling of Diabetes Using Optimized Gradient Boosting and Feature Selection. International Journal of Drug Delivery Technology, 16(44s). https://doi.org/10.25258/ijddt.16.44s.134

Vancouver

Prasanthi C, Babu SR, Sridhar V, Sudhakar K, Nagendrudu P, Akula A. Predictive Modeling of Diabetes Using Optimized Gradient Boosting and Feature Selection. International Journal of Drug Delivery Technology. 2026;16(44s). doi:10.25258/ijddt.16.44s.134

BibTeX
@article{Prasanthi2026,
  author = {Prasanthi, Ch and Babu, Somisetty Ramesh and Sridhar, V and Sudhakar, Kadaganchi and Nagendrudu, P.V.V.S.D. and Akula, Amrutavalli},
  title = {Predictive Modeling of Diabetes Using Optimized Gradient Boosting and Feature Selection},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {44s},
  doi = {10.25258/ijddt.16.44s.134}
}
Kostenlos starten →