Hybrid feature-selection and diversity-guided stacking framework for interpretable ensemble learning: Application to COVID-19 mortality prediction

Clinical Snapshot

Key Findings

• P Value: Not explicitly reported

• Effect Size: 1.2% improvement over best individual model (AdaBoost: 90.2%)

• Primary Outcome: COVID-19 mortality prediction accuracy: 91.4%

• Nnt Or Sensitivity: AUC = 0.955, F1 = 0.801, MCC = 0.746

• Confidence Interval: 95% CI: 89.8-92.8%

Clinical Application

Computationally feasible with training time ~450s and inference <0.2s per case, suitable for clinical implementation Would require validation in Australian hospital systems and integration with existing clinical decision support tools. Potential application in ICU triage and resource allocation decisions. Hospitalized COVID-19 patients requiring mortality risk stratification

Abstract

BACKGROUND: Reliable predictive modeling in high-dimensional biomedical data requires a balance between accuracy, interpretability, and computational efficiency. However, existing ensemble methods often overlook model diversity or rely on ad hoc feature-selection approaches, which limit generalizability. This study introduces a hybrid feature-selection and diversity-guided stacking framework designed to improve robustness and scalability across clinical and other data-intensive domains. METHODS: The proposed framework integrates a hybrid feature-selection pipeline-combining Variance Inflation Factor (VIF), Analysis of Variance (ANOVA), Sequential Backward Elimination (SBE), and Lasso regression-to reduce multicollinearity and overfitting. It also employs a diversity-aware stacking strategy that constructs sub-model sets based on pairwise diversity measures (Disagreement, Yule's Q, and Cohen's Kappa) and non-pairwise metrics (Entropy and Kohavi-Wolpert). Sixteen base classifiers and five meta-learners were trained using repeated 10-fold cross-validation. The framework was evaluated using data from 4,778 hospitalized COVID-19 patients with 116 clinical and laboratory attributes, preprocessed using robust scaling and ROSE-based class balancing. RESULTS: The optimal configuration, which stacked Random Forest and XGBoost models using a Neural Network meta-learner, achieved 91.4% accuracy (95% CI: 89.8-92.8), AUC = 0.955, F1 = 0.801, and MCC = 0.746, outperforming the best individual model (AdaBoost, 90.2%). Training time (~450 s) and per-case inference time (<0.2 s) demonstrated computational feasibility. Feature-importance analysis and SHAP-based interpretation confirmed clinical relevance and interpretability. CONCLUSIONS: The hybrid feature-selection and diversity-guided stacking framework improves predictive accuracy and interpretability while maintaining computational efficiency. Although validated using COVID-19 mortality data, the approach is broadly applicable to biomedical, environmental, and engineering prediction tasks that require interpretable and scalable ensemble learning.

References

1. 1.Mohtasham, F., Hashemi Nazari, S. S., Pourhoseingholi, M. A., Kavousi, K., & Zali, M. R. (2024). Hybrid feature-selection and diversity-guided stacking framework for interpretable ensemble learning: Application to COVID-19 mortality prediction. PLoS One, 19(7), e0341198. https://doi.org/10.1371/journal.pone.0341198