Optimized Ensemble Learning Framework for Early Cardiac Risk Prediction Using Random Forest and XGBoost
Al Hassani, Oras, Subaramaniam, Kasthuri, Palaniapan, Sellappan and Bin Shibghatullah, Abdul Samad (2026) Optimized Ensemble Learning Framework for Early Cardiac Risk Prediction Using Random Forest and XGBoost. ICAROB2026, 31. ISSN 2188-7829
Abstract
Cardiovascular disease remains a primary contributor to global mortality, illustrating the pivotal role of effective early detection systems that can alleviate pressure on health system resources. This work presents an automated machine learning based approach to early cardiac risk detection via ensemble-based predictive modelling. This study adopts a disciplined multi-step process, including thorough literature review, data engineering, feature extraction and algorithmic optimization for clinical data on clinical datasets, all captured with Kaggle. Among the models we examine Random Forest (RF) and XGBoost. The study is valuable for demonstrating that a well-tuned hybrid ensemble can achieve near real-time, high-fidelity cardiac risk prediction and serve as a robust substitute for traditional diagnostics.
Actions (login required)
 |
Edit Item |