Google Research Shows How AI can Make Ophthalmologists More Effective

As artificial intelligence continues to evolve, diagnosing disease faster and potentially with greater accuracy than physicians, some have suggested that technology may soon replace tasks that physicians currently perform. But a new study from the Google AI research group shows that physicians and algorithms working together are more effective than either alone. It's one of the first studies to examine how AI can improve physicians' diagnostic accuracy. The new research will be published in the April edition of Ophthalmology, the ournal of the American Academy of Ophthalmology.

This study expands on previous work from Google AI showing that its algorithm works roughly as well as human experts in screening patients for a common diabetic eye disease called diabetic retinopathy. For their latest study, the researchers wanted to see if their algorithm could do more than simply diagnose disease. They wanted to create a new computer-assisted system that could "explain" the algorithm's diagnosis. They found that this system not only improved the ophthalmologists' diagnostic accuracy, but it also improved algorithm's accuracy.

More than 29 million Americans have diabetes, and are at risk for diabetic retinopathy, a potentially blinding eye disease. People typically don't notice changes in their vision in the disease's early stages. But as it progresses, diabetic retinopathy usually causes vision loss that in many cases cannot be reversed. That's why it's so important that people with diabetes have yearly screenings.

Unfortunately, the accuracy of screenings can vary significantly. One study found a 49 percent error rate among internists, diabetologists, and medical residents.

Recent advances in AI promise to improve access to diabetic retinopathy screening and to improve its accuracy. But it's less clear how AI will work in the physician's office or other clinical settings. Previous attempts to use computer-assisted diagnosis shows that some screeners rely on the machine too much, which leads to repeating the machine's errors, or under-rely on it and ignore accurate predictions. Researchers at Google AI believe some of these pitfalls may be avoided if the computer can "explain" its predictions.

To test this 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.
  • Grades + heatmap: Enhance the grading system with a heatmap that measures the contribution of each pixel in the image to the algorithm's prediction.

Ten ophthalmologists (four general ophthalmologists, one trained outside the US, four retina specialists, and one retina specialist in training) 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. But the degree of improvement depended on the physician's level of expertise.

Without assistance, general ophthalmologists are significantly less accurate than the algorithm, while retina specialists are not significantly more accurate than the algorithm. With assistance, general ophthalmologists match but do not exceed the model's accuracy, while retina specialists start to exceed the model's performance.

"What we found is that AI can do more than simply automate eye screening, it can assist physicians in more accurately diagnosing diabetic retinopathy," said lead researcher, Rory Sayres, PhD.. "AI and physicians working together can be more accurate than either alone."

Like medical technologies that preceded it, Sayres said that AI is another tool that will make the knowledge, skill, and judgment of physicians even more central to quality care.

"There's an analogy in driving," Sayres explained. "There are self-driving vehicles, and there are tools to help drivers, like Android Auto. The first is automation, the second is augmentation. The findings of our study indicate that there may be space for augmentation in classifying medical images like retinal fundus images. When the combination of clinician and assistant outperforms either alone, this provides an argument for up-leveling clinicians with intelligent tools."

Rory Sayres, Ankur Taly, Ehsan Rahimy, Katy Blumer, David Coz, Naama Hammel, Jonathan Krause, Arunachalam Narayanaswamy, Zahra Rastegar, Derek Wu, Shawn Xu, Scott Barb, Anthony Joseph, Michael Shumski, Jesse Smith, Arjun B Sood, Greg S Corrado, Lily Peng, Dale R Webster.
Using a Deep Learning Algorithm and Integrated Gradients Explanationto Assist Grading for Diabetic Retinopathy.
Ophthalmology, Volume 126, Issue 4, 552 - 564. doi: 10.1016/j.ophtha.2018.11.016.

Most Popular Now

IBM Watson Health Recognizes Top-Perform…

IBM (NYSE: IBM) Watson Health® announced its 2020 Fortune/IBM Watson Health 100 Top Hospitals list and 15 Top Health Systems award winners, naming the top-performing hospitals and health systems in...

Chatbots can Ease Medical Providers' Bur…

COVID-19 has placed tremendous pressure on health care systems, not only for critical care but also from an anxious public looking for answers. Research from the Indiana University Kelley School...

Abbott Receives FDA Approval for New Hea…

Abbott (NYSE: ABT) announced that the U.S. Food and Drug Administration (FDA) has approved the company's next-generation Gallant™ implantable cardioverter defibrillator (ICD) and cardiac resynchronization therapy defibrillator (CRT-D) devices. The...

The New Tattoo: Drawing Electronics on S…

One day, people could monitor their own health conditions by simply picking up a pencil and drawing a bioelectronic device on their skin. In a new study, University of Missouri...

Towards an AI Diagnosis Like the Doctor…

Artificial intelligence (AI) is an important innovation in diagnostics, because it can quickly learn to recognize abnormalities that a doctor would also label as a disease. But the way that...

SARS-CoV-2 Antibody Test from Siemens He…

Public Health England, in partnership with the University of Oxford, recently conducted a head-to-head evaluation of four commercial immunoassay tests available in the UK and used for the detection of...

Researchers Develop Software to Find Dru…

Washington State University researchers have developed an easy-to-use software program to identify drug-resistant genes in bacteria. The program could make it easier to identify the deadly antimicrobial resistant bacteria that...

Philips Introduces First-of-a-Kind Mobil…

Royal Philips (NYSE: PHG, AEX: PHIA), a global leader in health technology, today announced it introduced first-of-its-kind mobile Intensive Care Units (ICUs) in India. Designed to meet the critical-care requirements...

Proposed Framework for Integrating Chatb…

While the technology for developing artificial intelligence-powered chatbots has existed for some time, a new viewpoint piece in JAMA lays out the clinical, ethical, and legal aspects that must be...

Clinical-Grade Wearables Offer Continuou…

Although it might be tempting to rely on your fitness tracker to catch early signs of COVID-19, Northwestern University researchers caution that consumer wearables are not sophisticated enough to monitor...

World's Smallest Imaging Device has Hear…

A team of researchers led by the University of Adelaide and University of Stuttgart has used 3D micro-printing to develop the world's smallest, flexible scope for looking inside blood vessels...

Optimizing Neural Networks on a Brain-In…

Many computational properties are maximized when the dynamics of a network are at a "critical point", a state where systems can quickly change their overall characteristics in fundamental ways, transitioning...