A team of researchers from Japan’s Osaka Metropolitan University (OMU) developed an artificial intelligence (AI) model that estimates a subject’s true age according to the appearance of that individual’s chest X-rays.

Establishing a link between age and chronic medical conditions, the AI model can reportedly calculate a person’s age accurately according to the appearance of their chest X-rays.

AI estimation of a subject’s age as significantly higher than his or her actual age is likely due to underlying conditions, such as chronic obstructive pulmonary disease (COPD), hypertension or hyperuricemia (above normal uric acid levels in the blood), for instance.

To develop this AI model, the researchers used data from thousands of chest X-rays taken from both healthy people and from people suffering from known medical conditions.

During testing of the model, the AI accurately predicted the actual age of the subjects in the healthy chest X-rays. However, when tested on the X-rays of those with underlying medical conditions, the age of the subject estimated the patients’ ages as significantly higher. This, the researchers concluded, was due to the existence of the chronological condition.

The team believes that the AI model could be used, following further research and development, for tasks such as predicting a person’s lifespan, calculating their chances of survival from a specific disease or recommending treatments for their medical conditions.

An article detailing the findings, “Chest radiography as a biomarker of ageing: artificial intelligence-based, multi-institutional model development and validation in Japan,” appears in the journal The Lancet Healthy Longevity.