Related Experiment Video
Updated: Jan 13, 2026
08:53
Author Spotlight: Automated Lifespan Monitoring – Discovering Aging Dynamics with the Lifespan Machine
Published on: January 26, 2024
1.6K
A Machine-Learning Model of Chronological Age Based on Routine Blood Biomarkers in a Central European Population: A
Pavel Borsky1, Drahomira Holmannova1, Tereza Maresova1
1Department of Preventive Medicine, Faculty of Medicine in Hradec Kralove, Charles University, Hradec Kralove, Czech Republic, cuni.cz.
Journal of Aging Research
|January 7, 2026
Summary
This study developed machine-learning models to estimate chronological age using blood biomarkers, achieving an 8.73-year error. The findings suggest these accessible markers could indicate biological age, warranting further clinical validation.
Area of Science:
- Biomarkers of aging research
- Machine learning applications in healthcare
- Gerontology and longevity studies
Background:
- Aging is a universal process with variable individual rates.
- Biomarkers of aging are crucial for predicting disease susceptibility and lifespan.
- Current research focuses on developing predictive models for aging trajectories.
Purpose of the Study:
- To develop and evaluate machine-learning models for chronological age estimation using blood biomarkers.
- To identify key blood biomarkers predictive of chronological age.
- To assess the potential of these biomarkers as a biological age marker.
Main Methods:
- Utilized a large Central European dataset of over 26 million anonymized laboratory results from 3 million individuals.
- Employed four machine-learning algorithms: multilayer neural network, Extreme Gradient Boosting (XGBoost), Random Forest, and Ridge Regression.
- Assessed model performance using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and other metrics, alongside feature importance analysis.
Main Results:
- The Extreme Gradient Boosting (XGBoost) model demonstrated the best performance with a Mean Absolute Error (MAE) of 8.73 years.
- The top 10 predictive biomarkers included alanine aminotransferase (ALT), creatinine, alkaline phosphatase (ALP), glucose, mean corpuscular volume (MCV), thrombocytes, albumin, mean corpuscular hemoglobin (MCH), urea, and aspartate aminotransferase (AST).
- These influential biomarkers represent hepatic, renal, metabolic, and hematological functions.
Conclusions:
- Chronological age can be estimated with notable accuracy (MAE 8.73 years) using readily available blood biomarkers in a Central European population.
- The developed index shows promise as a potential biological age marker.
- Further research is required to validate this index against clinical outcomes, morbidity, and mortality in independent cohorts.
