Scientists at Osaka Metropolitan University have developed an AI model that accurately predicts patient age using chest radiographs of healthy individuals collected from multiple facilities. In addition, they found a positive association between differences in AI-estimated and chronological age and a variety of chronic diseases, such as hypertension, hyperuricemia, and chronic obstructive pulmonary disease. In the future, it is expected that AI biomarkers will be developed to predict life expectancy, predict the severity of chronic diseases, and predict surgery-related risks.
What if “looking your age” meant not your face, but your chest? Scientists at Osaka Metropolitan University have developed an advanced artificial intelligence (AI) model that uses chest radiographs to accurately estimate a patient’s chronological age. More importantly, when there is a disparity, it may indicate an association with chronic disease. These findings signal a leap forward in medical imaging, paving the way for early detection of disease and improvements in intervention. Results ready to be published Lancet Healthy Longevity,
The research team, led by Dr. Yasuhito Mitsuyama and Dr. Daizu Ueda, graduate students of the Department of Diagnostic and Interventional Radiology at Osaka Metropolitan University’s Graduate School of Medicine, first implemented a deep learning-based AI model to estimate age from chest radiographs. build out. healthy person. They then applied the model to radiographs of patients with known diseases to analyze the relationship between the AI-estimated age and each disease. Noting that AI trained on a single dataset is prone to overfitting, the researchers pooled data from multiple institutions.
For the development, training, internal and external testing of the AI model for age estimation, a total of 67,099 chest radiographs were obtained from 36,051 healthy individuals who underwent health examination at three facilities between 2008 and 2021. The developed model showed a correlation coefficient of 0.95 between AI-estimated age and chronological age. Generally, a correlation coefficient of 0.9 or greater is considered very strong.
To validate the utility of AI-estimated age using chest radiographs as a biomarker, an additional 34,197 chest radiographs were compiled from 34,197 patients with known diseases from two other institutions. The results showed that the difference between the AI-estimated age and the patient’s chronological age was positively associated with a variety of chronic diseases, such as hypertension, hyperuricemia and chronic obstructive pulmonary disease. In other words, the higher the AI-estimated age compared to chronological age, the more likely individuals were to have these diseases.
“Chronological age is one of the most important factors in medicine,” Mr. Mitsuyama said. “Our results suggest that chest radiography-based apparent age may accurately reflect health conditions beyond chronological age. Our goal is to further develop this research and apply it to predicting the severity of chronic diseases, predicting life expectancy and and to anticipate possible surgical complications.”