Abstract
PURPOSE: To determine classification criteria for Vogt-Koyanagi-Harada (VKH) disease DESIGN: Machine learning of cases with VKH disease and 5 other panuveitides.
METHODS: Cases of panuveitides were collected in an informatics-designed preliminary database, and a final database was constructed of cases achieving supermajority agreement on the diagnosis, using formal consensus techniques. Cases were split into a training set and a validation set. Machine learning using multinomial logistic regression was used on the training set to determine a parsimonious set of criteria that minimized the misclassification rate among the panuveitides. The resulting criteria were evaluated on the validation set.
RESULTS: One thousand twelve cases of panuveitides, including 156 cases of early-stage VKH and 103 cases of late-stage VKH, were evaluated. Overall accuracy for panuveitides was 96.3% in the training set and 94.0% in the validation set (95% confidence interval 89.0, 96.8). Key criteria for early-stage VKH included: 1) exudative retinal detachment with characteristic appearance on fluorescein angiogram or optical coherence tomography or 2) panuveitis with ≥2 of 5 neurologic symptoms/signs. Key criteria for late-stage VKH included history of early-stage VKH and either: 1) sunset glow fundus or 2) uveitis and ≥1 of 3 cutaneous signs. The misclassification rates in the learning and validation sets for early-stage VKH were 8.0% and 7.7%, respectively, and for late-stage VKH 1.0% and 12%, respectively.
CONCLUSIONS: The criteria for VKH had a reasonably low misclassification rate and appeared to perform sufficiently well for use in clinical and translational research.
| Original language | English |
|---|---|
| Pages (from-to) | 205-211 |
| Number of pages | 7 |
| Journal | American Journal of Ophthalmology |
| Volume | 228 |
| Early online date | 9 Apr 2021 |
| DOIs | |
| Publication status | Published - Aug 2021 |
Bibliographical note
Funding Information:Funding/Support: Supported by grant R01 EY026593 from the National Eye Institute, the National Institutes of Health, Bethesda, Maryland, USA; the David Brown Fund, New York, New York, USA; the Jillian M. and Lawrence A. Neubauer Foundation, New York, New York, USA; and the New York Eye and Ear Foundation, New York, New York, USA. Financial Disclosures: Douglas A. Jabs: none; Alastair K. Denniston: none; Andrew D. Dick: consultant: AbbVie, Alimera, Apitope, Astellas, Gyroscope, Janssen, Roche; James P. Dunn: none; Michal Kramer: none; Neal Oden: none; Peter McCluskey: none; Annabelle Okada: consultant: AbbVie Japan, Astellas Pharma Japan, Bayer AG, Daiichi Sankyo; lecture fees: Alcon Pharma Japan, Mitsubishi Tanabe Pharma, Novartis Pharma Japan, Santen Pharmaceutical Corporation, Senju Pharmaceutical Corporation; grant support from Alcon Pharma Japan, Bayer Yakuhin, Mitsubishi Tanabe Pharma; Alan G. Palestine: none; Russell Read: none; Jennifer E. Thorne: Dr Thorne engaged in part of this research as a consultant and was compensated for the consulting service; Brett E. Trusko: none. All authors attest that they meet the current ICMJE criteria for authorship.
Publisher Copyright:
© 2021 Elsevier Inc.