EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A multi-stage stacking framework for accurate and interpretable life expectancy modeling

Ravikumar Chinthaginjala iD, Sivarama Prasad Tera iD, Priya Natha, Asadi Srinivasulu, Fadi Al-Turjman iD, Faruq Mohammad

PLOS One · 06.08.2026 · 21 (8) · e0353849

DOI: 10.1371/journal.pone.0353849 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 06.08.2026. Verfasst von Ravikumar Chinthaginjala und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronics Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India. Hauptthemen laut MEDLINE: Life Expectancy. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Near East University, Lefkosa, KKTC via Mersin 10, King Saud University (KSU) through Ongoing Research Funding Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate life-expectancy estimation is critical for evidence-based health policy, monitoring Sustainable Development Goal 3 (SDG 3), and guiding global resource allocation. Existing machine-learning approaches typically provide point predictions with limited interpretability and uncertainty quantification. To address these limitations, we propose NEXUS-LE ( N euro-Symbolic Ex plainable U nified S tacking for L ife E xpectancy), a unified ensemble framework that integrates predictive accuracy, calibrated uncertainty, and policy-level explainability. The model is trained on a global dataset comprising 22,050 country-year observations across 193 countries (2000–2021) and 150 World Health Organization indicators. The framework combines leave-one-out encoding, principal component analysis, and K-Means–based manifold features with SHAP-guided polynomial expansion and a three-level stacking architecture, followed by a LightGBM residual correction and split-conformal calibration. On a held-out test set ( n = 3,308), the model achieves R 2 = 0.9878, RMSE = 1.0665 years, MAE = 0.6185 years, and MAPE = 0.9239%. Conformal prediction attains 95.04% empirical coverage at the 95% nominal level with a 90% interval width of 3.32 years. Interpretability analysis shows that demographic and structural factors contribute 96.3% of total attribution, with consistent non-linear effects across policy domains. The proposed framework provides a reliable and interpretable solution for life-expectancy prediction in global health applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Life ExpectancyHumansBoosting Machine Learning AlgorithmsMachine LearningPredictive Learning Models

Autor:innen und Institutionen

  • School of Electronics Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India.
  • Cooperative Research Centre for Contamination Assessment and Remediation of the Environment (CRC CARE), Global Centre for Environmental Remediation/College of Engineering Science & Environment, The University of Newcast…
  • Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Green Fields, Vaddeswaram, Guntur, Andhra Pradesh, India.
  • Artificial Intelligence, Software, and Information Systems Engineering Departments, Research Center for AI and IoT, AI and Informatics Faculty, Near East University, Mersin, Turkey.
  • Department of Chemistry, College of Science, King Saud University, Riyadh, Kingdom of Saudi Arabia.

ORCID-Profile: Ravikumar Chinthaginjala, Sivarama Prasad Tera, Fadi Al-Turjman

Förderung

  • Near East University, Lefkosa, KKTC via Mersin 10
  • King Saud University (KSU) through Ongoing Research Funding Program

Zitieren

APA

Chinthaginjala, R., Tera, S. P., Natha, P., Srinivasulu, A., Al-Turjman, F., & Mohammad, F. (2026). A multi-stage stacking framework for accurate and interpretable life expectancy modeling. PLOS One, 21(8), e0353849. https://doi.org/10.1371/journal.pone.0353849

Vancouver

Chinthaginjala R, Tera SP, Natha P, Srinivasulu A, Al-Turjman F, Mohammad F. A multi-stage stacking framework for accurate and interpretable life expectancy modeling. PLOS One. 2026;21(8):e0353849. doi:10.1371/journal.pone.0353849

BibTeX
@article{Chinthaginjala2026,
  author = {Chinthaginjala, Ravikumar and Tera, Sivarama Prasad and Natha, Priya and Srinivasulu, Asadi and Al-Turjman, Fadi and Mohammad, Faruq},
  title = {A multi-stage stacking framework for accurate and interpretable life expectancy modeling},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {8},
  pages = {e0353849},
  doi = {10.1371/journal.pone.0353849}
}
Kostenlos starten →