Prediction of biological age using machine learning
PLOS One · 2025
DOI: 10.1371/journal.pone.0330184 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Kai Zhang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Yiwu Industrial and Commercial College, Yiwu, Zhejiang, China. Hauptthemen laut MEDLINE: Machine Learning, Aging. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jinhua City Science and Technology Program, Yiwu City Science and Technology Program, Jinhua Key Laboratory of Robot Intelligent Welding Technology.
Abstract (Originalsprache)
In response to Taiwan’s rapidly aging population and the rising demand for personalized health care, accurately assessing individual physiological aging has become an essential area of study. This research utilizes health examination data to propose a machine learning-based biological age prediction model that quantifies physiological age through residual life estimation. The model leverages LightGBM, which shows an 11.40% improvement in predictive performance (R-squared) compared to the XGBoost model. In the experiments, the use of MICE imputation for missing data significantly enhanced prediction accuracy, resulting in a 23.35% improvement in predictive performance. Kaplan-Meier (K-M) estimator survival analysis revealed that the model effectively differentiates between groups with varying health levels, underscoring the validity of biological age as a health status indicator. Additionally, the model identified the top ten biomarkers most influential in aging for both men and women, with a 69.23% overlap with Taiwan’s leading causes of death and previously identified top health-impact factors, further validating its practical relevance. Through multidimensional health recommendations based on SHAP and PCC interpretations, if the health recommendations provided by the model are implemented, 64.58% of individuals could potentially extend their life expectancy. This study provides new methodological support and data backing for precision health interventions and life extension.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Yiwu Industrial and Commercial College, Yiwu, Zhejiang, China.
- Graduate Institute of Network and Multimedia, National Taiwan University, Taipei, Taiwan.
- Division of Family Medicine, Taoyuan Armed Forces General Hospital, Taoyuan, Taiwan.
- Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan.
- Teaching and Researching Center, Kaohsiung Armed Forces General Hospital, Kaohsiung, Taiwan.
- Institute of Medical Science and Technology, National Sun Yat-sen University, Kaohsiung, Taiwan.
ORCID-Profile: Kai Zhang
Förderung
- Jinhua City Science and Technology Program
- Yiwu City Science and Technology Program
- Jinhua Key Laboratory of Robot Intelligent Welding Technology
- Jinhua Public Welfare Technology Application Research Project in 2024
Zitieren
APA
Zhang, K., Chen, P. C., Huang, Y., Tzou, S. J., Wu, S. T., Chu, T. W., Wang, C. C., & Jang, J. R. (2025). Prediction of biological age using machine learning. PLOS One. https://doi.org/10.1371/journal.pone.0330184
Vancouver
Zhang K, Chen PC, Huang Y, Tzou SJ, Wu ST, Chu TW, et al. Prediction of biological age using machine learning. PLOS One. 2025. doi:10.1371/journal.pone.0330184
BibTeX
@article{Zhang2025,
author = {Zhang, Kai and Chen, Po-Chung and Huang, YiYang and Tzou, Shiow-Jyu and Wu, Sheng-Tang and Chu, Ta-Wei and Wang, Chung-Che and Jang, Jyh-Shing Roger},
title = {Prediction of biological age using machine learning},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0330184}
}
EUVIMED