Chest X-ray and AI showed hidden signs of aging of the body

The authors compared the algorithm’s operation with the so-called epigenetic clock, which estimates biological age based on changes in DNA. To do this, we used data from 2,097 adult participants in the Project Baseline Health Study, a large-scale American study on health and diseases throughout life. The comparison was carried out with two widely used indicators based on DNA methylation.

The results were significant. The age calculated from the X-ray images using AI closely coincided with the early signs of aging of the cardiovascular and respiratory systems. It was associated with the presence of calcium in the coronary arteries, decreased lung function, increasing fragility of the body, and increased levels of proteins involved in neuroinflammation and age-related processes. DNA-based methods in these same groups showed weaker or no connections at all, especially in middle-aged people.

According to one of the authors of the paper, this approach opens up new opportunities for early detection of risks. Analyzing medical images using machine learning allows you to see how organs age long before clinical symptoms appear. In the future, this may help doctors more accurately identify patients who need closer monitoring or early preventive measures.

The researchers emphasize that the CXR-Age should not be considered as a substitute for existing health assessment methods. Rather, it is a supplement that can enhance a personalized approach in medicine and shift the focus from treatment to prevention of age-related diseases.

It was concluded that age, calculated from an AI chest X-ray, may be a more accurate indicator of cardiorespiratory aging than many existing biological markers.