Australia's Leading Ophthalmic Magazine Since 1975

     Free Sign Up     

Australia's Leading Ophthalmic Magazine Since 1975

     Free Sign Up     

AI and physicians work best in unison

A study by the Google AI research group has found that a combined diagnosis made between a physician and artificial intelligence (AI) technology is more effective than either one or the other on its own when examining ocular diseases.

In one of the first studies to investigate how AI can improve physicians’ diagnostic accuracy, the research highlighted the benefit of incorporating AI into practice, while also allaying fears of a complete technological takeover.

Published in the April edition of Ophthalmology, the study expanded on previous work from Google AI that demonstrated its algorithm performed as well as practitioners in screening patients for diabetic retinopathy.

The researchers also examined whether the algorithm could do more than simply diagnose disease, and developed a new computer-assisted system that could ‘explain’ the algorithm’s diagnosis.

According to the study’s authors, previous attempts to utilise computer-assisted diagnosis demonstrated that some people were overly reliant on the equipment, leading to them repeating the machine’s errors. Others were under-reliant or ignored the equipment’s recommendations and missed accurate predictions.

The Google AI research team believed that some of these pitfalls might be avoided if the computer provided an explanation for its predictions.

The team found that this new explanation system not only improved the ophthalmologists’ diagnostic accuracy, but it also improved algorithm’s accuracy.

In testing the theory, the researchers developed two types of assistance to help physicians read the algorithm’s predictions; Grades: a set of five scores that represent the strength of evidence for the algorithm’s prediction; and Grades + heatmap: an improved grading system which includes a heatmap that measures the contribution of each pixel in the image to the algorithm’s prediction.

Ten ophthalmologists were asked to read each image once under one of three conditions: unassisted, grades only, and grades + heatmap. Both types of assistance improved physicians’ diagnostic accuracy. It also improved their confidence in the diagnosis, however, the degree of improvement depended on the physician’s level of expertise.

“What we found is that AI can do more than simply automate eye screening, it can assist physicians in more accurately diagnosing diabetic retinopathy,” lead researcher Dr Rory Sayres said.

Akin to medical technologies that preceded it, Sayres said that AI was another tool that would make the knowledge, skill, and judgment of physicians even more central.

large leaderboard

Carl Zeiss
Editor's Suggestion
Hot Stories



Subscribe for Insight in your Inbox

Get Insight with the latest in industry news, trends, new products, services and equipment!