- Doctors can use telemedicine images to identify a rare cause of blindness in premature babies with as much accuracy as if they were examining the infant in person, according to international research done by eight health systems.
Led by the Oregon Health Sciences University (OHSU), the research team conducted more than 1,550 exams, comparing images of the eye captured by telemedicine technology with ophthalmoscopy for more than 280 premature infants in the US and Mexico, and found that each method was about the same in accuracy for diagnosing retinopathy of prematurity (ROP), a leading cause of blindness worldwide.
The condition, caused by an abnormal buildup of blood vessels near the retina, affects up to 16,000 infants a year in the US and leads to blindness in 400 to 600 cases. Among those who have been blinded by ROP is Stevie Wonder.
"A lack of access to trained ophthalmologists with experience diagnosing ROP sadly prevents many premature infants from receiving much-needed screening, both in developed and developing countries," Michael F. Chiang, MD, a professor of ophthalmology and medical informatics & clinical epidemiology at OHSU’s School of Medicine and a pediatric ophthalmologist at OHSU's Elks Children's Eye Clinic, said in a press release.
Chiang is lead author of the study, conducted by researchers from OHSU, Weill Cornell Medical College, the University of Illinois at Chicago, the University of Miami, Columbia University Medical Center, Children's Hospital Los Angeles, Cedars-Sinai Medical Center and Asociación para Evitar la Ceguera en México. The study was organized by the Imaging and Informatics in Retinopathy of Prematurity Research Consortium and appears in JAMA Ophthalmology.
In a recent news story issued by OHSU, Chiang said the study is one of more than 30 that have proven the value of telemedicine in helping to diagnose ROP. That type of evidence is needed to convince a still-skeptical pediatric healthcare – only 7 percent of NICUs in the country use retinal imaging devices to screen for ROP, according to the journal Pediatrics – that the technology is clinically accurate.
“Now we have the ability to diagnose patients via wide-angle retinal imaging, computing and information technology that requires minimal technology and expertise for providers in remote areas,” Chiang said.
“This collaboration highlights the importance of a multidisciplinary approach to clinical care,” he added. “It also demonstrates the pathway by which gaps in the delivery of clinical care motivate research and knowledge discovery, which eventually leads to technology adoption and gradual changes in health care policy.”
In a commentary published alongside the study in JAMA Ophthalmology, Ebenezer Daniel, PhD, of the University of Pennsylvania in Philadelphia’s Department of Ophthalmology, said telemedicine combined with artificial intelligence tools will give doctors and specialists many more opportunities to identify and treat ROP before it causes blindness.
"We are in an exciting age where it is possible for computerized algorithms to take the various morphologic and pathologic features of ROP in a digital retinal image and combine it with demographic and other characteristics of the premature infant, offering a more comprehensive result to the ROP specialist for making early treatment decisions," he said.