Home Healthcare AI Algorithm Surpasses the Accuracy of Doctors in Diagnosing Blindness

AI Algorithm Surpasses the Accuracy of Doctors in Diagnosing Blindness

There’s no doubt that new technologies like artificial intelligence will disrupt different industries in the near future, all in an effort to make human life better. As a testament to this point, we are currently building computer programs that can hold natural talks seamlessly and even master advanced strategy games. Aside from all this, can artificial intelligence diagnose disease?

Well, a new study conducted on a specialized artificial intelligence (AI) algorithm recently found that it could automatically diagnose an illness known for causing childhood blindness with more accuracy than trained doctors, which is no mean feat. In fact, this discovery marks a significant step towards automating most of the tasks in medical facilities, which are more often than not hindered by the lack of adequate medical experts or doctors.

This groundbreaking artificial intelligence algorithm was built and studied by scientists at the Massachusetts General Hospital and Oregon Health and Science University. The scientists trained the algorithm to diagnose a medical condition referred to as retinopathy of prematurity (ROP), which when left untreated could cause total blindness. To understand how severe this condition is, it is said to be the same one that caused Stevie Wonder to lose his sight. What’s more, it is the most common cause of blindness among children.

The AI algorithm was shown different eye scan sample images and accurately diagnosed patients with retinopathy of prematurity (ROP) 91% of the time. On the other hand, specialists who are trained to do the same task scored an average of 82 percent when they were shown the same eye scan images.

READ MORE: Top 10 Ways Artificial Intelligence is Impacting Healthcare

READ MORE: Artificial Intelligence in Medicine – Top 10 Applications

According to Jayashree Kalpathy-Cramer, one of the lead authors of the study, the algorithm extracts the knowledge of ophthalmologists who are trained and skilled at recognizing ROP and in turn places it in a mathematical model. By doing so, it allows those clinicians who lack similar skills or even experience in such tasks to assist babies in receiving a timely and more accurate diagnosis. Moreover, Kalpathy-Cramer is a well-known professor at the prestigious Harvard Medical School and works at Massachusetts General Hospital.

In the press release, co-author Dr. Michael Chiang said that the results of the AI algorithm are important, especially because currently there’s a huge scarcity of ophthalmologists who are not only trained but also willing to diagnose the childhood blindness-causing disease, ROP. He added that this situation is behind the massive gaps in healthcare, even in the US, and unfortunately causes many kids across the globe to go undiagnosed. Dr. Michael Chiang is a certified pediatric ophthalmologist. He also studies both medical informatics and ophthalmology at Oregon Health and Science University (OHSU).

The AI algorithm represents some of the remarkable artificial intelligence (AI)-driven solutions that are increasingly emerging; particularly now when the healthcare system is striving to solve various problems including high medical care prices and a massive shortage of primary care physicians.

Other recent innovations include a virtual clinic application from Seattle-based startup 98point6. The app depends on AI chatbots to allow patients to hold primary care appointments through text right from their smartphones.

Source GeekWire

Subscribe to our newsletter

Signup today for free and be the first to get notified on the latest news and insights on artificial intelligence

KC Cheung
KC Cheung
KC Cheung has over 18 years experience in the technology industry including media, payments, and software and has a keen interest in artificial intelligence, machine learning, deep learning, neural networks and its applications in business. Over the years he has worked with some of the leading technology companies, building and growing dynamic teams in a fast moving international environment.
- Advertisment -


AI Model Development isn’t the End; it’s the Beginning

AI model development isn’t the end; it’s the beginning. Like children, successful models need continuous nurturing and monitoring throughout their lifecycle. Parenting is exhilarating and, if...