Accuracy of retinopathy of prematurity image-based diagnosis by pediatric ophthalmology fellows

Implications for training

Jane S. Myung, Robison Vernon Paul Chan, Michael J. Espiritu, Steven L. Williams, David B. Granet, Thomas C. Lee, David J. Weissgold, Michael Chiang

Research output: Contribution to journalArticle

35 Citations (Scopus)

Abstract

Purpose: To measure the accuracy of image-based retinopathy of prematurity (ROP) diagnosis by pediatric ophthalmology fellows. Methods: This was a comparative case series of expert versus nonexpert clinicians in image-based ROP diagnosis. An atlas of 804 retinal images was captured from 248 eyes of 67 premature infants with a wide-angle camera (RetCam-II, Clarity Medical Systems, Pleasanton, CA). Images were uploaded to a study website from which an expert pediatric retinal specialist and five pediatric ophthalmology fellows independently provided a diagnosis (no ROP, mild ROP, type 2 ROP, or treatment-requiring ROP) for each eye. Two different retinal specialists experienced in ROP examination served as additional controls. Primary outcome measures were sensitivity and specificity of image-based ROP diagnosis by fellows compared to a reference standard of image-based interpretation by the expert pediatric retinal specialist. Secondary outcome measure was intraphysician reliability. Results: For detection of mild or worse ROP, the mean (range) sensitivity among the five fellows was 0.850 (0.670-0.962) and specificity was 0.919 (0.832-0.964). For detection of type 2 or worse ROP by fellows, mean (range) sensitivity was 0.527 (0.356-0.709) and specificity was 0.938 (0.777-1.000). For detection of treatment-requiring ROP, mean (range) sensitivity was 0.515 (0.267-0.765) and specificity was 0.949 (0.805-1.00). Conclusions: Pediatric ophthalmology fellows in this study demonstrated high diagnostic specificity in image-based ROP diagnosis; however, sensitivity was lower, particularly for clinically significant disease.

Original languageEnglish (US)
Pages (from-to)573-578
Number of pages6
JournalJournal of AAPOS
Volume15
Issue number6
DOIs
StatePublished - Dec 2011

Fingerprint

Retinopathy of Prematurity
Ophthalmology
Pediatrics
Outcome Assessment (Health Care)
Atlases
Premature Infants

ASJC Scopus subject areas

  • Ophthalmology
  • Pediatrics, Perinatology, and Child Health

Cite this

Accuracy of retinopathy of prematurity image-based diagnosis by pediatric ophthalmology fellows : Implications for training. / Myung, Jane S.; Paul Chan, Robison Vernon; Espiritu, Michael J.; Williams, Steven L.; Granet, David B.; Lee, Thomas C.; Weissgold, David J.; Chiang, Michael.

In: Journal of AAPOS, Vol. 15, No. 6, 12.2011, p. 573-578.

Research output: Contribution to journalArticle

Myung, JS, Paul Chan, RV, Espiritu, MJ, Williams, SL, Granet, DB, Lee, TC, Weissgold, DJ & Chiang, M 2011, 'Accuracy of retinopathy of prematurity image-based diagnosis by pediatric ophthalmology fellows: Implications for training', Journal of AAPOS, vol. 15, no. 6, pp. 573-578. https://doi.org/10.1016/j.jaapos.2011.06.011
Myung, Jane S. ; Paul Chan, Robison Vernon ; Espiritu, Michael J. ; Williams, Steven L. ; Granet, David B. ; Lee, Thomas C. ; Weissgold, David J. ; Chiang, Michael. / Accuracy of retinopathy of prematurity image-based diagnosis by pediatric ophthalmology fellows : Implications for training. In: Journal of AAPOS. 2011 ; Vol. 15, No. 6. pp. 573-578.
@article{0e9ec755ee164a05b24bff3f307544db,
title = "Accuracy of retinopathy of prematurity image-based diagnosis by pediatric ophthalmology fellows: Implications for training",
abstract = "Purpose: To measure the accuracy of image-based retinopathy of prematurity (ROP) diagnosis by pediatric ophthalmology fellows. Methods: This was a comparative case series of expert versus nonexpert clinicians in image-based ROP diagnosis. An atlas of 804 retinal images was captured from 248 eyes of 67 premature infants with a wide-angle camera (RetCam-II, Clarity Medical Systems, Pleasanton, CA). Images were uploaded to a study website from which an expert pediatric retinal specialist and five pediatric ophthalmology fellows independently provided a diagnosis (no ROP, mild ROP, type 2 ROP, or treatment-requiring ROP) for each eye. Two different retinal specialists experienced in ROP examination served as additional controls. Primary outcome measures were sensitivity and specificity of image-based ROP diagnosis by fellows compared to a reference standard of image-based interpretation by the expert pediatric retinal specialist. Secondary outcome measure was intraphysician reliability. Results: For detection of mild or worse ROP, the mean (range) sensitivity among the five fellows was 0.850 (0.670-0.962) and specificity was 0.919 (0.832-0.964). For detection of type 2 or worse ROP by fellows, mean (range) sensitivity was 0.527 (0.356-0.709) and specificity was 0.938 (0.777-1.000). For detection of treatment-requiring ROP, mean (range) sensitivity was 0.515 (0.267-0.765) and specificity was 0.949 (0.805-1.00). Conclusions: Pediatric ophthalmology fellows in this study demonstrated high diagnostic specificity in image-based ROP diagnosis; however, sensitivity was lower, particularly for clinically significant disease.",
author = "Myung, {Jane S.} and {Paul Chan}, {Robison Vernon} and Espiritu, {Michael J.} and Williams, {Steven L.} and Granet, {David B.} and Lee, {Thomas C.} and Weissgold, {David J.} and Michael Chiang",
year = "2011",
month = "12",
doi = "10.1016/j.jaapos.2011.06.011",
language = "English (US)",
volume = "15",
pages = "573--578",
journal = "Journal of AAPOS",
issn = "1091-8531",
publisher = "Mosby Inc.",
number = "6",

}

TY - JOUR

T1 - Accuracy of retinopathy of prematurity image-based diagnosis by pediatric ophthalmology fellows

T2 - Implications for training

AU - Myung, Jane S.

AU - Paul Chan, Robison Vernon

AU - Espiritu, Michael J.

AU - Williams, Steven L.

AU - Granet, David B.

AU - Lee, Thomas C.

AU - Weissgold, David J.

AU - Chiang, Michael

PY - 2011/12

Y1 - 2011/12

N2 - Purpose: To measure the accuracy of image-based retinopathy of prematurity (ROP) diagnosis by pediatric ophthalmology fellows. Methods: This was a comparative case series of expert versus nonexpert clinicians in image-based ROP diagnosis. An atlas of 804 retinal images was captured from 248 eyes of 67 premature infants with a wide-angle camera (RetCam-II, Clarity Medical Systems, Pleasanton, CA). Images were uploaded to a study website from which an expert pediatric retinal specialist and five pediatric ophthalmology fellows independently provided a diagnosis (no ROP, mild ROP, type 2 ROP, or treatment-requiring ROP) for each eye. Two different retinal specialists experienced in ROP examination served as additional controls. Primary outcome measures were sensitivity and specificity of image-based ROP diagnosis by fellows compared to a reference standard of image-based interpretation by the expert pediatric retinal specialist. Secondary outcome measure was intraphysician reliability. Results: For detection of mild or worse ROP, the mean (range) sensitivity among the five fellows was 0.850 (0.670-0.962) and specificity was 0.919 (0.832-0.964). For detection of type 2 or worse ROP by fellows, mean (range) sensitivity was 0.527 (0.356-0.709) and specificity was 0.938 (0.777-1.000). For detection of treatment-requiring ROP, mean (range) sensitivity was 0.515 (0.267-0.765) and specificity was 0.949 (0.805-1.00). Conclusions: Pediatric ophthalmology fellows in this study demonstrated high diagnostic specificity in image-based ROP diagnosis; however, sensitivity was lower, particularly for clinically significant disease.

AB - Purpose: To measure the accuracy of image-based retinopathy of prematurity (ROP) diagnosis by pediatric ophthalmology fellows. Methods: This was a comparative case series of expert versus nonexpert clinicians in image-based ROP diagnosis. An atlas of 804 retinal images was captured from 248 eyes of 67 premature infants with a wide-angle camera (RetCam-II, Clarity Medical Systems, Pleasanton, CA). Images were uploaded to a study website from which an expert pediatric retinal specialist and five pediatric ophthalmology fellows independently provided a diagnosis (no ROP, mild ROP, type 2 ROP, or treatment-requiring ROP) for each eye. Two different retinal specialists experienced in ROP examination served as additional controls. Primary outcome measures were sensitivity and specificity of image-based ROP diagnosis by fellows compared to a reference standard of image-based interpretation by the expert pediatric retinal specialist. Secondary outcome measure was intraphysician reliability. Results: For detection of mild or worse ROP, the mean (range) sensitivity among the five fellows was 0.850 (0.670-0.962) and specificity was 0.919 (0.832-0.964). For detection of type 2 or worse ROP by fellows, mean (range) sensitivity was 0.527 (0.356-0.709) and specificity was 0.938 (0.777-1.000). For detection of treatment-requiring ROP, mean (range) sensitivity was 0.515 (0.267-0.765) and specificity was 0.949 (0.805-1.00). Conclusions: Pediatric ophthalmology fellows in this study demonstrated high diagnostic specificity in image-based ROP diagnosis; however, sensitivity was lower, particularly for clinically significant disease.

UR - http://www.scopus.com/inward/record.url?scp=83455220586&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=83455220586&partnerID=8YFLogxK

U2 - 10.1016/j.jaapos.2011.06.011

DO - 10.1016/j.jaapos.2011.06.011

M3 - Article

VL - 15

SP - 573

EP - 578

JO - Journal of AAPOS

JF - Journal of AAPOS

SN - 1091-8531

IS - 6

ER -