Scientists at Osaka Metropolitan University in Japan have developed an advanced artificial intelligence (AI) model that can predict a person’s chronological age and detect chronic diseases using chest radiographs. This groundbreaking research could lead to early intervention and improved disease detection in medical imaging.
The study, led by Yasuhito Mitsuyama and Dr. Daiju Ueda from the Department of Diagnostic and Interventional Radiology at Osaka Metropolitan University’s Graduate School of Medicine, involved the construction of a deep learning-based AI model. The model was initially trained using chest radiographs from healthy individuals to estimate their age accurately. Subsequently, the researchers applied the model to radiographs of patients with known diseases to investigate the correlation between AI-estimated age and chronic diseases. To avoid overfitting, they collected data from multiple institutions.
For the development and testing of the AI model, the researchers obtained a total of 67,099 chest radiographs from 36,051 healthy individuals who underwent health check-ups at three facilities between 2008 and 2021. The AI model showed a strong correlation coefficient of 0.95 between the estimated age and the chronological age. In general, a correlation coefficient of 0.9 or higher is considered very strong.
To validate the usefulness of AI-estimated age as a biomarker, an additional 34,197 chest radiographs were compiled from 34,197 patients with known diseases from two other institutions. The results revealed a positive correlation between the difference in AI-estimated age and the patient’s chronological age with various chronic diseases such as hypertension, hyperuricemia, and chronic obstructive pulmonary disease. In other words, the higher the AI-estimated age compared to the chronological age, the higher the likelihood of these diseases.
Chronological age is one of the most critical factors in medicine, said Mr. Mitsuyama. Our results suggest that chest radiography-based apparent age may accurately reflect health conditions beyond chronological age. We aim to further develop this research and apply it to estimate the severity of chronic diseases, predict life expectancy, and forecast possible surgical complications.
Osaka Metropolitan University, the third largest public university in Japan, was formed by a merger between Osaka City University and Osaka Prefecture University in 2022. The university focuses on the Convergence of Knowledge through its 11 undergraduate schools, college, and 15 graduate schools.
This groundbreaking research has the potential to revolutionize medical imaging and drive early intervention in chronic diseases. By accurately estimating a patient’s chronological age and identifying potential correlations with chronic diseases, this AI model paves the way for improved disease detection and intervention. Further development of this research could potentially allow for the estimation of disease severity, prediction of life expectancy, and identification of possible surgical complications. The findings of this study will be published in The Lancet Healthy Longevity.
