Original article
Classification Criteria For Multiple Evanescent White Dot Syndrome

https://doi.org/10.1016/j.ajo.2021.03.050Get rights and content

Purpose

The purpose of this study was to determine classification criteria for multiple evanescent white dot syndrome (MEWDS).

Design

Machine learning of cases with MEWDS and 8 other posterior uveitides.

Methods

Cases of posterior uveitides were collected in an informatics-designed preliminary database, and a final database was constructed of cases achieving supermajority agreement on diagnosis using formal consensus techniques. Cases were split into a training set and a validation set. Machine learning using multinomial logistic regression was used in the training set to determine a parsimonious set of criteria that minimized the misclassification rate among the infectious posterior, or panuveitides. The resulting criteria were evaluated in the validation set.

Results

A total of 1,068 cases of posterior uveitides, including 51 cases of MEWDS, were evaluated by machine learning. Key criteria for MEWDS included: 1) multifocal gray-white chorioretinal spots with foveal granularity; 2) characteristic imaging on fluorescein angiography (“wreath-like” hyperfluorescent lesions) and/or optical coherence tomography (hyper-reflective lesions extending from retinal pigment epithelium through ellipsoid zone into the retinal outer nuclear layer); and 3) absent to mild anterior chamber and vitreous inflammation. Overall accuracy for posterior uveitides was 93.9% in the training set and 98.0% (95% confidence interval: 94.3-99.3) in the validation set. Misclassification rates for MEWDS were 7% in the training set and 0% in the validation set.

Conclusions

The criteria for MEWDS had a low misclassification rate and appeared to perform sufficiently well for use in clinical and translational research.

Section snippets

METHODS

The SUN Developing Classification Criteria for the Uveitides project proceeded in 4 phases as previously described: 1) informatics, 2) case collection, 3) case selection, and 4) machine learning.15, 16, 17, 18

RESULTS

Ninety-five cases of MEWDS were collected, and 51 (54%) achieved supermajority agreement on the diagnosis during the “selection” phase and were used in the machine learning phase These cases of MEWDS were compared to cases of posterior uveitides, including 82 cases of APMPPE; 207 cases of BSCR; 122 cases of serpiginous choroiditis; 138 cases of MFCPU; 144 cases of PIC; 12 cases of sarcoid posterior uveitis; 35 cases of syphilitic posterior uveitis; and 277 cases of tubercular

DISCUSSION

The classification criteria developed by the SUN Working Group for MEWDS have an acceptable misclassification rate, indicating good discriminatory performance relative to other non-infectious posterior and panuveitides. Because the goal of the SUN criteria was classification at presentation and because MEWDS spontaneously resolves, these criteria were most appropriate for the early, active stage of the disease.20

Unlike other diseases in this class, the primary lesion appears to be at the level

CRediT roles

Douglas A. Jabs, MD, MBA: Conceptualization, Methodology, Validation, Investigation, Data curation, Writing–Review and editing, Visualization, Supervision, Project administration, Funding acquisition. Antoine P. Brezin, MD: Investigation, Writing–Review and editing. Andrew D. Dick, MBBS, MD, FRCP, FRCS, FRCOphth: Investigation, Writing–Review and editing. Ralph D. Levinson, MD: Investigation, Writing–Review and editing. Lyndell L. Lim, MD: Investigation, Writing–Review and editing. Peter

References (26)

  • NE Abu-Yaghi et al.

    White dot syndromes: a 20-year study of incidence, clinical features, and outcomes

    Ocular Immunol Inflamm

    (2011)
  • MHT Nguyen et al.

    Microstructural abnormalities in MEWDS demonstrated by ultrahigh resolution optical coherence tomography

    Retina

    (2007)
  • C Furino et al.

    Fundus autofluorescence and multiple evanescent white dot syndrome

    Retina

    (2009)
  • Cited by (31)

    View all citing articles on Scopus

    Supplemental Material available at AJO.com.

    1

    Members of the SUN Working Group are listed online at AJO.com.

    2

    Writing Committee: Douglas A. Jabs, Antoine P. Brezin, Andrew D. Dick, Ralph D. Levinson, Lyndell L. Lim, Peter McCluskey, Neal Oden, Alan G. Palestine, Jennifer E. Thorne, Brett E. Trusko, Albert Vitale, and Susan E. Wittenberg.

    3

    Writing Committee Affiliations: Members of the SUN Working Group are listed online at AJO.com. Department of Epidemiology (D.A.J., J.E.T.), the Johns Hopkins University Bloomberg School of Public Health, and the Wilmer Eye Institute, Department of Ophthalmology (D.A.J., J.E.T.), Johns Hopkins University School of Medicine, Baltimore, Maryland, USA; Department of Ophthalmology (A.P.B.), University of Paris V-Hôpital Cochin, Paris, France; Academic Unit of Ophthalmology (A.D.D.), Bristol Medical School, University of Bristol, Bristol, UK; National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital (A.D.D.), London, UK; University College London Institute of Ophthalmology (A.D.D.), London UK; Stein Eye Institute and Department of Ophthalmology (R.D.L.), David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California, USA; Center for Eye Research Australia (L.L.L.), Royal Victorian Eye and Ear Hospital, Melbourne, Victoria, Australia; Save Sight Institute (P.M.), Department of Ophthalmology, University of Sydney School of Medicine, Sydney, New South Wales, Australia; Emmes Co, LLC, (N.O.) Rockville, Maryland, USA; Department of Ophthalmology (A.G.P.), University of Colorado School of Medicine, Aurora, Colorado, USA; Department of Medicine (B.E.T.), Texas A&M University, College Station, Texas, USA; Department of Ophthalmology (A.V.), University of Utah School of Medicine, Salt Lake City, Utah, USA; and the Houston Eye Associates (S.E.W.), Houston, Texas, USA.

    4

    Financial Disclosures: Douglas A. Jabs: none. Antoine Brezin: none. Andrew Dick: none. Ralph Levinson: none. Lyndell L. Lim: none. Peter McCluskey: none. Neal Oden: none. Alan G. Palestine: none. Jennifer E. Thorne: Dr. Thorne engaged in a portion of this research as a consultant and was compensated for the consulting service; Brett E. Trusko: none. Albert Vitale: none. Susan E. Wittenberg: none.

    Inquiries to: Douglas A. Jabs, Department of Epidemiology, the Johns Hopkins University Bloomberg School of Public Health, 615 N Wolfe St, Baltimore, MD, 20215 USA. E-mail: [email protected].

    View full text