Scientists at the University of Adelaide in Australia just developed an AI system that can predict how long a person will live simply by looking at the images of their organs.This is the first study in its kind where machine learning is used to predict how long we’ll live with 69 percent accuracy.
The finding may sound a little macabre but could have important implications for the early diagnosis of serious illness.
Lead author Dr. Luke Oakden-Rayner, from the University of Adelaide’s School of Public Health, said, “Predicting the future of a patient is useful because it may enable doctors to tailor treatments to the individual.”
Scientists used this artificial intelligence system to test the medical imaging of 48 patients’ chests. This computer-based analysis was able to predict which patients would die within five years, with 69% accuracy.
“The accurate assessment of biological age and the prediction of a patient’s longevity has so far been limited by doctors’ inability to look inside the body and measure the health of each organ.”
“Our research has investigated the use of ‘deep learning’, a technique where the computer systems can learn how to understand and analyze images.”
Still, scientists couldn’t identify what this AI system has seen in the images to make its predictions. But the system made confident predictions for patients with severe chronic diseases such as emphysema and congestive heart failure.
Oakden-Rayner said, “Our research opens new avenues for the application of artificial intelligence technology in medical image analysis and could offer new hope for the early detection of serious illness, requiring specific medical interventions.”
Now, scientists are planning to apply the same techniques to predict other important medical conditions, such as the onset of heart attacks.