New Delhi: A newly developed artificial intelligence (AI) model could estimate one’s age from their chest X-ray, new research published in The Lancet Healthy Longevity journal said. The model can also signal chronic diseases such as hypertension and chronic obstructive pulmonary disease from the difference between estimated and chronological age, the research from Osaka Metropolitan University, Japan, said.
The findings marked a leap in medical imaging and paved the way for improved early disease detection and intervention, the researchers said in their study.
As the global population ages, aging and longevity research is gaining importance.
Aging, a complex change associated with several diseases, has varied effects across individuals, they said.
“Chronological age is one of the most critical factors in medicine. Our results suggest that chest radiography-based apparent age may accurately reflect health conditions beyond chronological age,” said lead researcher Yasuhito Mitsuyama.
For age estimation, the AI model was trained using around 67,100 chest radiographs of 36,051 healthy individuals who underwent health check-ups between 2008 and 2021.
The model showed a strong correlation between the AI-estimated age and the chronological age of the individuals, the researchers found.
It was then trained to analyse the link between the AI-estimated age and each disease on additional 34,197 chest radiographs compiled from as many patients with known diseases.
In all, the model was trained on roughly 1,01,300 chest X-rays obtained from 70,248 participants across five institutions in Japan.
The difference between the individual’s AI-estimated age and their chronological age was found to be strongly associated with chronic diseases such as hypertension, hyperuricemia (high uric acid levels in blood), and chronic obstructive pulmonary disease.
This meant, the researchers said, that higher the age the AI estimated, higher the likelihood of these individuals to have the aforementioned diseases.
Chest X-rays could thus be useful as a biomarker of aging and longevity, they said, because they can show not only the shape of features within the body, but also details of internal organs and bones.
“We aim to further develop this research and apply it to estimate the severity of chronic diseases, to predict life expectancy, and to forecast possible surgical complications,” said Mitsuyama.
