A.I. predicts lifespan with 69% accuracy

By Lana Guineay

Can artificial intelligence predict your lifespan? According to University of Adelaide researchers, it’s one step closer to becoming a reality.

In news filed under both “eerie” and “amazing”, researchers from the University’s School of Public Health and School of Computer Science have just announced they have tested A.I. software to predict longevity – the first study of its kind – with positive initial results.

Using A.I. to look at the medical imaging of 48 patients’ chests, the computer-based analysis predicted which patients would die within five years, with 69% accuracy.

“Predicting the future of a patient is useful because it may enable doctors to tailor treatments to the individual,” says lead author of the study, Dr Luke Oakden-Rayner, a radiologist and PhD student with the University of Adelaide’s School of Public Health.

Dr Luke Oakden-Rayner, supplied

Dr Luke Oakden-Rayner

Dr Oakden-Rayner says doctors’ inability to look directly inside a patient’s body and assess the health of each organ has been the biggest barrier to accurately predicting longevity – but the A.I. system has been developed to do exactly that.

“Our research has investigated the use of ‘deep learning’, a technique where computer systems can learn how to understand and analyse images.

“The automated systems can predict medical outcomes in a way that doctors are not trained to do, by incorporating large volumes of data and detecting subtle patterns,” Dr Oakden-Rayner says.

Example of medical images analysed

Example of medical images analysed

Where to from here?

The South Australian research team are most confident in the system’s current ability to predict severe chronic diseases such as emphysema and congestive heart failure, but say the study opens up new avenues for the use of A.I. in healthcare.

Dr Oakden-Rayner and the research team are set to analyse tens of thousands more images as they work to apply the same techniques to predict other serious medical conditions, such as heart attacks, in the future.

“Although for this study only a small sample of patients was used, our research suggests that the computer has learnt to recognise the complex imaging appearances of diseases, something that requires extensive training for human experts,” Dr Oakden-Rayner says.

“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.”