By analyzing x-rays of your lungs, artificial intelligence would be able to determine your age.
- Researchers have developed artificial intelligence (AI) capable of determining the age of healthy patients from their chest x-rays.
- If the AI estimates a higher age, the person is sick or at risk of being sick.
- In the future, researchers plan to continue their work to develop a tool capable of predicting life expectancy.
Researchers have developed artificial intelligence (AI) capable of determining a patient’s age based on their chest x-rays. Their work was published in the journal The Lancet Healthy LongevityAugust 16, 2023.
Teaching artificial intelligence to determine the age of patients
To develop this AI, scientists from Osaka Metropolitan University taught him how to estimate the age of healthy people from chest x-rays, also called chest x-rays.
To do this, they had him analyze 67,099 lung x-rays, taken between 2008 and 2021 by 36,051 healthy patients in three health establishments. The AI proved to be very effective in estimating the age of volunteers based on images of their respiratory system.
“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.”specifies communicated published on August 17.
AI and lungs: the higher the estimated age, the greater the risk of disease
Next, the researchers compared the AI to 34,197 chest X-rays of patients with diseases such ashigh blood pressure or the chronic obstructive pulmonary disease.
Thus, they observed a difference between the age estimated by the new technology and the real age of the patients: the first was higher than the second. They concluded that the older the AI made a person, the more likely they were to have an illness.
“Our results suggest that age [déterminé en fonction de l’étude] chest x-ray can accurately reflect health conditions beyond age [réel], explains Yasuhito Mitsuyama, one of the authors, in the communicated. Our goal is to further develop this work and use it to estimate the severity of chronic diseases, predict life expectancy and possible surgical complications.“
