EUVIMEDEUVIMED entdecken
Crossref

A Novel Adaptive Explainable Hybrid AI Framework for Personalized Medicine Recommendation Using Dynamic Ensemble–Deep Learning

Neha Saxena, Ayan Rajput

Dandao Xuebao/Journal of Ballistics · 19.05.2026 · 38 (1) · 340-348

DOI: 10.52783/dxjb.v38.282 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Dandao Xuebao/Journal of Ballistics, online erschienen am 19.05.2026. Verfasst von Neha Saxena und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid evolution of intelligent healthcare systems has highlighted the need for accurate, interpretable, and personalized clinical decision support mechanisms. While existing machine learning models provide high predictive performance, they often lack interpretability and personalization, limiting their real-world applicability. This paper proposes a novel Adaptive Explainable Hybrid Personalized Medicine Recommendation System (AEH-PMRS) that integrates ensemble learning with deep neural networks using a dynamic weight optimization mechanism and explainability-guided learning strategy. The proposed framework combines Extreme Gradient Boosting (XGBoost) and Multi-Layer Perceptron (MLP) through a meta-learning-based adaptive fusion layer.Unlike conventional hybrid models that rely on static weight assignment, the proposed system dynamically learns model contributions based on input features. Additionally, SHAP-based explainability is incorporated not only for interpretation but also for feature reweighting during training, enhancing both transparency and performance. Experimental evaluation on a dataset comprising over 10,500 patient records demonstrates that the proposed model achieves an accuracy of 97.8%, outperforming traditional machine learning and baseline hybrid models. The system also provides confidence-aware personalized medicine recommendations, improving clinical usability.

Zitieren

APA

Saxena, N., & Rajput, A. (2026). A Novel Adaptive Explainable Hybrid AI Framework for Personalized Medicine Recommendation Using Dynamic Ensemble–Deep Learning. Dandao Xuebao/Journal of Ballistics, 38(1), 340-348. https://doi.org/10.52783/dxjb.v38.282

Vancouver

Saxena N, Rajput A. A Novel Adaptive Explainable Hybrid AI Framework for Personalized Medicine Recommendation Using Dynamic Ensemble–Deep Learning. Dandao Xuebao/Journal of Ballistics. 2026;38(1):340-348. doi:10.52783/dxjb.v38.282

BibTeX
@article{Saxena2026,
  author = {Saxena, Neha and Rajput, Ayan},
  title = {A Novel Adaptive Explainable Hybrid AI Framework for Personalized Medicine Recommendation Using Dynamic Ensemble–Deep Learning},
  journal = {Dandao Xuebao/Journal of Ballistics},
  year = {2026},
  volume = {38},
  number = {1},
  pages = {340--348},
  doi = {10.52783/dxjb.v38.282}
}
Kostenlos starten →