Related Experiment Video
Updated: Jun 14, 2026
Simultaneous Imaging and Flow-Cytometry-based Detection of Multiple Fluorescent Senescence Markers in Therapy-Induced Senescent Cancer Cells
Published on: July 12, 2022
A deep learning sex-specific body composition ageing biomarker using dual-energy X-ray absorptiometry scan
Jie Lian1, Pei Cai1, Fan Huang1,2
1Department of Diagnostic Radiology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong, Hong Kong SAR, China.
Background:
Chronic diseases are closely linked to alterations in body composition, yet there is a need for reliable biomarkers to assess disease risk and progression. This study aimed to develop and validate a biological age indicator based on body composition derived from dual-energy X-ray absorptiometry (DXA) scans, offering a novel approach to evaluating health status and predicting disease outcomes.
Methods:
A deep learning model was trained on a reference population from the UK Biobank to estimate body composition biological age (BCBA). The model's performance was assessed across various groups, including individuals with typical and atypical body composition, those with pre-existing diseases, and those who developed diseases after DXA imaging. Key metrics such as c-index were employed to examine BCBA's diagnostic and prognostic potential for type 2 diabetes, major adverse cardiovascular events (MACE), atherosclerotic cardiovascular disease (ASCVD), and hypertension.
Results:
Here we show that BCBA strongly correlates with chronic disease diagnoses and risk prediction. BCBA demonstrated significant associations with type 2 diabetes (odds ratio 1.08 for females and 1.04 for males, p < 0.0005), MACE (odds ratio 1.10 for females and 1.11 for males, p < 0.0005), ASCVD (odds ratio 1.07 for females and 1.10 for males, p < 0.0005), and hypertension (odds ratio 1.06 for females and 1.04 for males, p < 0.0005). It outperformed standard cardiovascular risk profiles in predicting MACE and ASCVD.
Conclusions:
BCBA is a promising biomarker for assessing chronic disease risk and progression, with potential to improve clinical decision-making. Its integration into routine health assessments could aid early disease detection and personalised interventions.
