Can you tell your real age from your breasts? How old are you?

*Aging is a complex process that affects different individuals in a highly heterogeneous way. At the same age, some people are frail and need help, while others are healthy and independent. *Look at your age if it's not your face

But what about your breasts ?

Scientists at Osaka University have developed an advanced artificial intelligence (AI) model that can accurately estimate actual age using chest X-rays . What's more, when a discrepancy exists, it may indicate a link to chronic diseases .
The findings, published Aug. 16 in the journal The Lancet Health and Longevity, mark a leap forward in medical imaging, paving the way for improved early disease detection and intervention.

The research team, led by graduate students Yasuhito Mitsuyama and Dr. Daiju Ueda from the Department of Diagnostic and Interventional Radiology at the Osaka University Graduate School of Medicine, first built a deep learning-based AI model to estimate age from chest X-rays of healthy individuals.

They then applied the model to X-rays of patients with known diseases to analyze the relationship between the AI-estimated age and each disease. Given that AI trained on a single dataset is prone to overfitting, the researchers collected data from multiple institutions.

Significance map from external test dataset During the biomarker modeling phase of the study, the researchers used 67,099 chest X-rays obtained from 36,051 healthy individuals who underwent health examinations at three institutions between 2008 and 2021 for the development, training, and internal and external testing of the AI ​​model. The model showed that the correlation coefficient between AI-estimated age and actual age was 0.95 . Typically, a correlation coefficient of 0.9 or higher is considered very strong.

To validate the effectiveness of AI-based age estimation using chest X-rays as a biomarker, the researchers collected an additional 34,197 chest X-rays from 34,197 patients with known diseases from two other institutions.

Correlation between different ages and various diseases

The results showed that the difference between the AI-estimated age and the patient's actual age was positively correlated with multiple chronic diseases, such as hypertension, hyperuricemia, and chronic obstructive pulmonary disease. In other words, the higher the AI-estimated age compared to the actual age, the more likely the individual was to have these diseases.

"Chance age is one of the most critical factors in medicine," Mitsuyama said. "Our results suggest that apparent age based on chest radiographs can accurately reflect health conditions beyond chronological age. Our goal is to further develop this research and apply it to estimating the severity of chronic diseases, predicting life expectancy, and anticipating possible surgical complications."