Hybrid feature-selection and diversity-guided stacking framework for interpretable ensemble learning: Application to COVID-19 mortality prediction
PLOS One · 17.04.2026 · 21 (4) · e0341198
DOI: 10.1371/journal.pone.0341198 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 17.04.2026. Verfasst von Farideh Mohtasham und 4 weiteren Autor:innen. Beteiligte Einrichtung: Gastroenterology and Liver Diseases Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medica…. Hauptthemen laut MEDLINE: COVID-19. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 94 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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 (
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Gastroenterology and Liver Diseases Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
- Department of Epidemiology, School of Public Health & Safety, Shahid Beheshti University of Medical Sciences (SBMU), Tehran, Iran.
- National Institute for Health and Care Research (NIHR) Nottingham Biomedical Research Center, Hearing Sciences, Mental Health and Clinical Neurosciences, School of Medicine, University of Nottingham, Nottingham, United…
- Laboratory of Complex Biological Systems and Bioinformatics (CBB), Department of Bioinformatics, Institute of Biochemistry and Biophysics (IBB), University of Tehran, Tehran, Iran.
ORCID-Profile: Farideh Mohtasham, Kaveh Kavousi
Zitieren
APA
Mohtasham, F., Hashemi Nazari, S. S., Pourhoseingholi, M. A., Kavousi, K., & Zali, M. R. (2026). Hybrid feature-selection and diversity-guided stacking framework for interpretable ensemble learning: Application to COVID-19 mortality prediction. PLOS One, 21(4), e0341198. https://doi.org/10.1371/journal.pone.0341198
Vancouver
Mohtasham F, Hashemi Nazari SS, Pourhoseingholi MA, Kavousi K, Zali MR. Hybrid feature-selection and diversity-guided stacking framework for interpretable ensemble learning: Application to COVID-19 mortality prediction. PLOS One. 2026;21(4):e0341198. doi:10.1371/journal.pone.0341198
BibTeX
@article{Mohtasham2026,
author = {Mohtasham, Farideh and Hashemi Nazari, Seyed Saeed and Pourhoseingholi, Mohamad Amin and Kavousi, Kaveh and Zali, Mohammad Reza},
title = {Hybrid feature-selection and diversity-guided stacking framework for interpretable ensemble learning: Application to COVID-19 mortality prediction},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {4},
pages = {e0341198},
doi = {10.1371/journal.pone.0341198}
}
EUVIMED