Artificial intelligence (AI) is not just something out of a science fiction movie like the character Data from Star Trek or Arnold Schwarzenegger in The Terminator.
It’s a technology of today that surrounds us wherever we go, from internet search engines to driverless vehicles. The one area in which AI already is thriving is image recognition, which is about more than just tagging your friends on social media photos.
At the Academy’s Mid-Year Forum 2018, physicians discussed the future of AI. Image recognition is changing various fields of medicine, including radiology, pathology, dermatology and ophthalmology.
Here are two recent developments:
1. Improving Screening and Access to Care
Ophthalmologists will be using AI to screen fundus images automatically for conditions like diabetic retinopathy and glaucoma.
In fact, this year, the U.S. Food and Drug Administration approved the first AI-powered fundus screening camera for diabetic retinopathy — and it doesn’t require a human grader.
This innovation addresses a huge unmet need because many people with diabetes simply do not get routine ophthalmic exams. By improving screening, we can identify more patients who need care and keep them from falling through the cracks of our current healthcare system.
Some ophthalmologists may fear automation, but in reality, it will make us more valuable, more in-demand and more efficient.
2. Augmenting Intelligence
AI also augments and complements what we as physicians already do. Automated systems can gather a massive volume of data, including patient records and histories along with imaging information, and apply neural networks for assessing the best outcomes. These networks are sets of algorithms that are modeled after the human brain to optimize pattern recognition.
And AI in medicine can help uncover hidden patterns in clinical data. For instance, Google technology is able to deduce sex, age, smoking history and blood pressure from fundus images and accurately determine a person’s risk of cardiovascular disease.
The modern-day ophthalmologist is flooded with information and images. AI will be the backbone to help us manage this information overload and deliver the optimal care for our patients.
* * *
Artificial Intelligence: AI is poised to revolutionize medicine. An overview of the field, with selected applications in ophthalmology. (November 2017, Academy's EyeNet magazine)
* * *
About the author: Rahul N. Khurana, MD, is the Academy’s editor-in-chief of the Ophthalmic News and Education (ONE) Network. Dr. Khurana is a vitreoretinal surgeon and partner at Northern California Retina Vitreous Associates. He is also a clinical associate professor of ophthalmology at the University of California, San Francisco. Dr. Khurana graduated from Stanford University with BS and MS degrees in biology and earned his medical degree at Duke University. He completed his ophthalmology residency and a fellowship in uveitis and ocular inflammation at the Doheny Eye Institute, University of Southern California, followed by a vitreoretinal fellowship at the Wilmer Eye Institute, John Hopkins Medical Center.