Telemedical Diagnosis of Stage 4 and Stage 5 Retinopathy of Prematurity

Ophthalmol Retina. 2018 Jan;2(1):59-64. doi: 10.1016/j.oret.2017.04.001. Epub 2017 Jun 9.

Abstract

Purpose: To determine the accuracy of image-based diagnosis for stage 4 or worse retinopathy of prematurity (ROP) disease.

Design: Prospective cohort study.

Participants: We prospectively obtained data, from 8 major ROP centers, for 1220 eye examinations from 230 infants.

Methods: An ophthalmologist at each center provided a clinical diagnosis using indirect ophthalmoscopy. Wide-angle retinal images (RetCam; Clarity Medical Systems, Pleasanton, CA) were then obtained, and these were independently read by 2 ROP experts using a web-based system for an image-based diagnosis.

Main outcome measures: Sensitivity and specificity of image-based diagnosis from the ROP experts were calculated using the clinical diagnosis as the reference standard.

Results: Of 1220 examinations, 28 (2%) had a clinical diagnosis of stage 4 or worse. Sensitivity and specificity for stage 4 or worse disease were 75% and 99% for expert 1, and 86% and 99% for expert 2. Sensitivity and specificity for the detection of stage 5 disease were 69% and 99% for both experts.

Conclusions: There are inconsistencies in the accuracy of image-based diagnosis of stage 4 and stage 5 ROP when compared with the clinical diagnosis.

Publication types

  • Multicenter Study
  • Research Support, N.I.H., Extramural
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Follow-Up Studies
  • Gestational Age
  • Humans
  • Image Interpretation, Computer-Assisted / methods*
  • Infant, Newborn
  • Infant, Premature
  • Ophthalmoscopy / methods*
  • Prospective Studies
  • ROC Curve
  • Reproducibility of Results
  • Retina / pathology*
  • Retinopathy of Prematurity / diagnosis*
  • Severity of Illness Index
  • Telemedicine / methods*