Artificial Intelligence with ‘imagination’ identifies rare diseases better than doctors

ARTIFICIAL Intelligence programmed with “imagination” can better diagnose patients, particularly those with rare diseases, researchers have found.

A study at healthcare technology firm Babylon used an approach known as causal machine learning, where AI is given “imagination” to consider symptoms it may see if patients had different illnesses from those it was considering.

Dr Jonathan Richens, lead report author and a Babylon scientist, said: “We took an AI with a powerful algorithm, and gave it the ability to imagine alternate realities, and consider ‘Would this symptom be present if it was a different disease?’

“This allows the AI to tease apart the potential causes of a patient’s illness, and score more highly than over 70 per cent of the doctors on these written test cases.”

The research, published in Nature Communications, saw more than 1,600 realistic written medical cases created by Babylon GPS, which included typical and atypical symptoms. Another group of GPS, as well as an older AI algorithm and the new causal machine learning AI, were then asked to name the most likely illnesses for each case.

The new AI named the correct illness on average 77 per cent of the time, ahead of the older AI’S 72.5 per cent and the human doctors’ 71.4 per cent.

Dr Saurabh Johri, chief scientist at Babylon, said: “We found that the AI and doctors complemented each other.

“The AI scored more highly than the doctors on the harder cases, and vice versa. The algorithm performed particularly well for rare diseases which are more commonly misdiagnosed and more often serious.”

Babylon said it hoped that the technology could be used in the future to help speed up diagnosis, improve accuracy and free up time for clinicians.

The health tech firm said that the algorithm would face further development and testing before it would be considered for release in the company’s public app.

‘The algorithm performed particularly well for rare and serious diseases more commonly misdiagnosed’