Key result
Hybrid EBM-XGBoost machine learning achieves ~95% diagnostic accuracy for cardiovascular risk and Parkinson's detection.
Why the study?
The rapid escalation of chronic multi-morbidities necessitates integrated diagnostic tools capable of identifying sub-clinical tipping points before pathological manifestation.
A hybrid machine learning framework integrating EBM and XGBoost achieved high diagnostic accuracy for cardiovascular risk and Parkinson's disease detection.
The rapid escalation of chronic multi-morbidities necessitates the development of integrated diagnostic tools capable of identifying sub-clinical tipping points before pathological manifestation. This research introduces a hybrid machine learning framework for the simultaneous risk stratification of Diabetes, Heart Disease, and Parkinson’s Disease. Unlike traditional modular systems, the proposed architecture utilizes a probability-based soft-voting ensemble that prioritizes sensitivity to minimize false negatives in primary screening. Benchmarked on the UCI and PIMA Indians repositories, the framework integrates Explainable Boosting Machines (EBM) with XGBoost to achieve superior diagnostic stability. Experimental results demonstrate accuracies of 95.2% for cardiovascular risk and 94.07% for Parkinson’s detection, with model interpretability facilitated through SHAP-based feature contribution analysis. This study demonstrates that the integration of deep representation learning with tree-based ensemble methods offers a transparent pathway for early disease detection in resource-constrained clinical environments.
No takes yet. Share an insight, caveat, or question.
Trivedi et al. (2026) studied Diabetes, Heart Disease, and Parkinson's Disease. Hybrid machine learning framework (EBM with XGBoost) was evaluated on Diagnostic accuracy. A hybrid machine learning framework integrating EBM and XGBoost achieved diagnostic accuracies of 95.2% for cardiovascular risk and 94.07% for Parkinson's detection.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: