Classification Criteria for Intermediate Uveitis, Non-Pars Planitis Type

Douglas A Jabs; Alastair K Denniston; Andrew D Dick; James P Dunn; Michal Kramer; Neal Oden; Annabelle A Okada; Alan G Palestine; Russell W Read; Jennifer E Thorne; Brett E Trusko; Steven Yeh

doi:10.1016/j.ajo.2021.03.054

Classification Criteria for Intermediate Uveitis, Non-Pars Planitis Type

Douglas A Jabs, Alastair K Denniston, Andrew D Dick, James P Dunn, Michal Kramer, Neal Oden, Annabelle A Okada, Alan G Palestine, Russell W Read, Jennifer E Thorne, Brett E Trusko, Steven Yeh

Research output: Contribution to journal › Article (Academic Journal) › peer-review

18 Citations (Scopus)

Abstract

PURPOSE: To determine classification criteria for intermediate uveitis, non-pars planitis type (IU- NPP, also known as undifferentiated intermediate uveitis) DESIGN: : Machine learning of cases with IU-NPP and 4 other intermediate uveitides.

METHODS: Cases of intermediate uveitides 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 intermediate uveitides. The resulting criteria were evaluated on the validation set.

RESULTS: Five hundred eighty-nine of cases of intermediate uveitides, including 114 cases of IU-NPP, were evaluated by machine learning. The overall accuracy for intermediate uveitides was 99.8% in the training set and 99.3% in the validation set (95% confidence interval 96.1, 99.9). Key criteria for IU-NPP included unilateral or bilateral intermediate uveitis with neither 1) snowballs in the vitreous nor 2) snowbanks on the pars plana. Other key exclusions included: 1) multiple sclerosis, 2) sarcoidosis, and 3) syphilis. The misclassification rates for pars planitis were 0 % in the training set and 0% in the validation set, respectively.

CONCLUSIONS: The criteria for IU-NPP had a low misclassification rate and appeared to perform well enough for use in clinical and translational research.

Original language	English
Pages (from-to)	159-164
Number of pages	6
Journal	American Journal of Ophthalmology
Volume	228
Early online date	8 Apr 2021
DOIs	https://doi.org/10.1016/j.ajo.2021.03.054
Publication status	Published - Aug 2021

Bibliographical note

Funding Information:
Funding/Support: Supported by grant R01 EY026593 from the National Eye Institute, 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.

Publisher Copyright:
© 2021 Elsevier Inc.

Access to Document

10.1016/j.ajo.2021.03.054

Handle.net

Persistent link

Cite this

@article{a2dd3c19617f43118907c0d865472ebe,

title = "Classification Criteria for Intermediate Uveitis, Non-Pars Planitis Type",

abstract = "PURPOSE: To determine classification criteria for intermediate uveitis, non-pars planitis type (IU- NPP, also known as undifferentiated intermediate uveitis) DESIGN: : Machine learning of cases with IU-NPP and 4 other intermediate uveitides.METHODS: Cases of intermediate uveitides 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 intermediate uveitides. The resulting criteria were evaluated on the validation set.RESULTS: Five hundred eighty-nine of cases of intermediate uveitides, including 114 cases of IU-NPP, were evaluated by machine learning. The overall accuracy for intermediate uveitides was 99.8% in the training set and 99.3% in the validation set (95% confidence interval 96.1, 99.9). Key criteria for IU-NPP included unilateral or bilateral intermediate uveitis with neither 1) snowballs in the vitreous nor 2) snowbanks on the pars plana. Other key exclusions included: 1) multiple sclerosis, 2) sarcoidosis, and 3) syphilis. The misclassification rates for pars planitis were 0 % in the training set and 0% in the validation set, respectively.CONCLUSIONS: The criteria for IU-NPP had a low misclassification rate and appeared to perform well enough for use in clinical and translational research.",

author = "Jabs, {Douglas A} and Denniston, {Alastair K} and Dick, {Andrew D} and Dunn, {James P} and Michal Kramer and Neal Oden and Okada, {Annabelle A} and Palestine, {Alan G} and Read, {Russell W} and Thorne, {Jennifer E} and Trusko, {Brett E} and Steven Yeh",

note = "Funding Information: Funding/Support: Supported by grant R01 EY026593 from the National Eye Institute, 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. Publisher Copyright: {\textcopyright} 2021 Elsevier Inc.",

year = "2021",

month = aug,

doi = "10.1016/j.ajo.2021.03.054",

language = "English",

volume = "228",

pages = "159--164",

journal = "American Journal of Ophthalmology",

issn = "0002-9394",

publisher = "Elsevier Science",

}

TY - JOUR

T1 - Classification Criteria for Intermediate Uveitis, Non-Pars Planitis Type

AU - Jabs, Douglas A

AU - Denniston, Alastair K

AU - Dick, Andrew D

AU - Dunn, James P

AU - Kramer, Michal

AU - Oden, Neal

AU - Okada, Annabelle A

AU - Palestine, Alan G

AU - Read, Russell W

AU - Thorne, Jennifer E

AU - Trusko, Brett E

AU - Yeh, Steven

N1 - Funding Information: Funding/Support: Supported by grant R01 EY026593 from the National Eye Institute, 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. Publisher Copyright: © 2021 Elsevier Inc.

PY - 2021/8

Y1 - 2021/8

N2 - PURPOSE: To determine classification criteria for intermediate uveitis, non-pars planitis type (IU- NPP, also known as undifferentiated intermediate uveitis) DESIGN: : Machine learning of cases with IU-NPP and 4 other intermediate uveitides.METHODS: Cases of intermediate uveitides 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 intermediate uveitides. The resulting criteria were evaluated on the validation set.RESULTS: Five hundred eighty-nine of cases of intermediate uveitides, including 114 cases of IU-NPP, were evaluated by machine learning. The overall accuracy for intermediate uveitides was 99.8% in the training set and 99.3% in the validation set (95% confidence interval 96.1, 99.9). Key criteria for IU-NPP included unilateral or bilateral intermediate uveitis with neither 1) snowballs in the vitreous nor 2) snowbanks on the pars plana. Other key exclusions included: 1) multiple sclerosis, 2) sarcoidosis, and 3) syphilis. The misclassification rates for pars planitis were 0 % in the training set and 0% in the validation set, respectively.CONCLUSIONS: The criteria for IU-NPP had a low misclassification rate and appeared to perform well enough for use in clinical and translational research.

AB - PURPOSE: To determine classification criteria for intermediate uveitis, non-pars planitis type (IU- NPP, also known as undifferentiated intermediate uveitis) DESIGN: : Machine learning of cases with IU-NPP and 4 other intermediate uveitides.METHODS: Cases of intermediate uveitides 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 intermediate uveitides. The resulting criteria were evaluated on the validation set.RESULTS: Five hundred eighty-nine of cases of intermediate uveitides, including 114 cases of IU-NPP, were evaluated by machine learning. The overall accuracy for intermediate uveitides was 99.8% in the training set and 99.3% in the validation set (95% confidence interval 96.1, 99.9). Key criteria for IU-NPP included unilateral or bilateral intermediate uveitis with neither 1) snowballs in the vitreous nor 2) snowbanks on the pars plana. Other key exclusions included: 1) multiple sclerosis, 2) sarcoidosis, and 3) syphilis. The misclassification rates for pars planitis were 0 % in the training set and 0% in the validation set, respectively.CONCLUSIONS: The criteria for IU-NPP had a low misclassification rate and appeared to perform well enough for use in clinical and translational research.

U2 - 10.1016/j.ajo.2021.03.054

DO - 10.1016/j.ajo.2021.03.054

M3 - Article (Academic Journal)

C2 - 33839089

SN - 0002-9394

VL - 228

SP - 159

EP - 164

JO - American Journal of Ophthalmology

JF - American Journal of Ophthalmology

ER -

Classification Criteria for Intermediate Uveitis, Non-Pars Planitis Type

Abstract

Bibliographical note

Access to Document

Handle.net

Fingerprint

Cite this