Artificial intelligence may be able to determine how quickly a person is aging by analyzing chest X-rays, according to a new study published in The Journals of Gerontology. The research found that a deep learning model could detect subtle age-related changes in the heart, lungs, and overall health more effectively than commonly used DNA-based "epigenetic clocks."
The study, titled "Deep learning chest X-ray age, epigenetic aging clocks, and associations with age-related subclinical disease in the Project Baseline Health Study," compared an AI model called CXR-Age with two biological age measures derived from DNA methylation: Horvath Age and DNAm PhenoAge. Data was analyzed from 2,097 adults enrolled in the Project Baseline Health Study, which is a multi-site U.S. initiative aimed at understanding health and disease over time.
CXR-Age demonstrated strong links with early indicators of heart and lung aging such as coronary calcium buildup, declining lung function, increased frailty, and higher levels of proteins associated with neuroinflammation and aging. In comparison, the DNA-based clocks showed weaker or no connections to these conditions—particularly among middle-aged participants.
"These findings suggest that deep learning applied to common medical images can reveal how our organs are aging - information that might one day help clinicians identify people at risk of age-related disease before symptoms develop," said Douglas P. Kiel, MD, MPH, director of the Musculoskeletal Research Center at the Hinda and Arthur Marcus Institute for Aging Research and co-author of the study. "AI tools like this could become an important complement to traditional risk assessments."
The researchers concluded that CXR-Age derived from AI may provide a better measure of cardiopulmonary aging than current epigenetic clocks based on DNA analysis. They highlighted the potential for medical imaging combined with machine learning to improve personalized preventive medicine.
