AI Revolutionizes Age Estimation and Disease Detection
Asia/ Digital/ Updates

Redefining Age: AI Uses Chest Radiographs to Detect Disease

AI Revolutionizes Age Estimation and Disease Detection Header Photo by Website/Unsplash

Osaka Metropolitan University researchers have developed an advanced AI model that could redefine how we understand age and disease. The model uses chest radiographs to estimate a patient’s chronological age with remarkable accuracy, and any disparity between the estimated and actual age can signal the presence of chronic diseases.

Yasuhito Mitsuyama and Dr. Daiju Ueda from the Department of Diagnostic and Interventional Radiology at the Graduate School of Medicine led the research.

The duo built a deep-learning AI model, trained it using 67,099 chest radiographs from 36,051 healthy individuals from multiple institutions, and achieved a correlation coefficient of 0.95 between AI-estimated and chronological ages – a very strong correlation.

But the researchers didn’t stop there. Applying the model to an additional 34,197 chest radiographs of patients with known diseases, they found a positive correlation between the difference in AI-estimated and chronological ages and a variety of chronic diseases, including hypertension, hyperuricaemia, and chronic obstructive pulmonary disease.

As Mitsuyama stated, “Our results suggest that chest radiography-based apparent age may accurately reflect health conditions beyond chronological age.” The team is now looking to further develop this research with an aim to estimate the severity of chronic diseases, predict life expectancy, and forecast possible surgical complications, marking a significant leap in medical imaging and early disease detection.

Get the latest curated content with The Beat Asia's newsletters. Sign up now for a weekly dose of the best stories, events, and deals delivered straight to your inbox. Don't miss out! Click here to subscribe.

This Week's Events In Asia View more

Sign up to receive updates on what's going on in the city. Don't miss out on exciting events, news, and more. Sign up today!

By submitting your email, you agree to our Terms and Privacy Notice
Thank you for subscribing! Click here if you were not redirected.