Where the Industrial Revolution enabled the mechanization of human labor, says rheumatologist Antony Rosen, the AI revolution “essentially is enabling the rapid amplification and acceleration of human thinking.” In many ways, AI technology is massively democratizing, he notes, “because everybody now will have access to mental processing powers that used to be the domain of very few.”

Preventive care could be improved dramatically with AI by making screening easier and more widely available, says ophthalmologist T.Y. Alvin Liu. Consider diabetic retinopathy, a leading cause of blindness that hits hard in underserved communities. Traditionally, patients would need to make a separate trip to an eye doctor for screening. Starting in 2020, Johns Hopkins deployed IDx-DR, an autonomous AI system, across several Johns Hopkins Community Physicians clinical sites.

“Now the screening is not done at an ophthalmologist’s office — it’s done in the primary care setting. The doctor checks your A1C levels, and right then and there, you get your retinal photographs taken. In real time, those photos are analyzed by an AI model that can tell right away whether you have diabetic involvement in the back of the eye,” says Liu. “It’s a one-stop shop. And it has closed the equity gap.”

In 2018, pediatric diabetes specialist Risa Wolf led research efforts at Johns Hopkins to use IDx-DR in clinics serving children. “Before we implemented it, about 49% of the kids who needed screening actually had it done. We went to 95% after implementation,” she says. “This AI system has allowed us to improve screening rates for a recommended guideline for kids with diabetes and added convenience and cost savings to families.”

… and Training

Physician Swaroop Vedula and his Johns Hopkins team are developing AI algorithms for systems that analyze surgical performance using data from many sources — such as video, speech, instrument motion, eye gaze and the electronic medical record — and then give feedback to the surgeons and predict patient outcomes.

Who will benefit? Surgeons all across the career spectrum, their patients and health care administrators. “If I go to a surgeon one year out of residency, my risk of severe complications after cataract surgery is nine times higher than if I go to a surgeon 10 years into their practice,” says Vedula, citing results from a large Canadian study. “Experience plays a huge role in that variation in outcomes.”

Surgery is so highly standardized that it is ideal for AI analysis, he says. “We are going after algorithms that are built on collective intelligence of experiential knowledge and that we can make available to surgeons all over the world.”