[Skip to Content]
Access to paid content on this site is currently suspended due to excessive activity being detected from your IP address Please contact the publisher to request reinstatement.
[Skip to Content Landing]
Views 628
Citations 0
Invited Commentary
July 3, 2019

Automated Algorithms and Retinopathy of Prematurity Treatment

Author Affiliations
  • 1Smith-Kettlewell Eye Research Institute, San Francisco, California
JAMA Ophthalmol. 2019;137(9):1036-1037. doi:10.1001/jamaophthalmol.2019.2463

Machines are inexorably taking the place of human analyses of many clinical disorders. Clinical disorders that require human judgment for diagnosis are most vulnerable to a mathematical approach because there is a temptation to blame human behavior and observation for less-than-perfect outcomes. The quintessential example and arguably the potentially most problematic of these disorders in ophthalmology is plus disease. Plus disease refers to dilation and tortuosity of retinal blood vessels in retinopathy of prematurity (ROP). Its recognition by the practitioner is essential to informing decisions to treat ROP. Plus disease is currently defined by a standard photograph published in several ophthalmology journals.1 Practitioners refer to the picture to make decisions about the presence or absence of plus disease.