Can artificial intelligence predict your “real” age — and how long you’ll live — just from a chest X-ray?Reported by Euronews

Scientists have developed an artificial intelligence (AI) model capable of determining a person’s biological age by reading chest X-rays.

In a new study published in The Lancet Health and Longevity, researchers at Osaka Metropolitan University (Japan) found that, The older the AI-estimated age compared to a person’s actual age, the more likely a person is to suffer from a chronic disease.

“Our results show that apparent age based on chest x-rays can accurately reflect health status beyond chronological age.

Yasuhito Mitsuyama, a graduate student and author of the study, said in a statement.

“Our goal is to develop this research further and apply it to estimate the severity of chronic disease, predict life expectancy, and predict potential surgical complications,” the authors explain.

To create an AI model capable of reading chest x-rays, or x-rays, the researchers** used more than 67,000 chest x-rays obtained between 2008 and 2011 from healthy individuals at multiple institutions. **For healthy individuals, there is a strong correlation between the AI-estimated age and the actual age of the person.

h2 Age compared to chronological age/h2 The researchers also analyzed more than 34,000 chest x-rays from patients with known medical conditions.

They found that for certain chronic diseases, such as high blood pressure, chronic obstructive pulmonary disease (COPD), liver disease, lung disease, and chronic kidney failure, the AI-estimated model gave a higher age than the actual age.

However, there was little correlation with cases of acute illness such as recent infections such as pneumonia.

“This result means that Our AI catches more chronic changes than acute changes in chest X-rayswhich is plausible because aging is the result of chronic changes that accumulate over time,” the study authors noted.

author claims This AI model could serve as an indicator of age-related diseases and assist in early detection and intervention.

But they called for more research to confirm cause and effect.comparing AI models to other age biomarkers and studying other ethnic groups.