Classification criteria for Vogt-Koyanagi-Harada Disease

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.

PRECIS

Using a formalized approach to developing classification criteria, including informatics-based case collection, consensus-technique-based case selection, and machine learning, classification criteria for Vogt-Koyanagi Harada (VKH) disease were developed. Key criteria for early-stage VKH included characteristic exudative detachments or panuveitis with ≥2 of 5 neurologic features; for late-stage VKH criteria included sunset glow fundus or uveitis with ≥1 of 3 cutaneous features. The resulting criteria had a low misclassification rate.

In 1906 Vogt and independently in 1929 Koyanagi described a disorder characterized by chronic anterior uveitis, alopecia, vitiligo, and dysacusis.^1,2 In 1929 Harada described a disorder characterized by bilateral serous retinal detachments, chronic posterior uveitis, and cerebrospinal fluid (CSF) pleocytosis.³ Subsequently it was recognized that these anterior and posterior segment inflammatory conditions were manifestations of the same disease process, and the disease was named Vogt-Koyanagi-Harada (VKH) disease.

Vogt-Koyanagi-Harada disease is a well-delineated disorder that classically follows an evolutionary disease progression. The disease starts with a prodromal phase characterized by a “flu-like” illness, headache, and meningismus, followed by bilateral choroiditis with serous retinal detachments (early-stage disease, previously termed “acute”). Typically these detachments are multiple with multiple, early pin-point leaks and late dye pooling on fluorescein angiogram; occasionally they may evolve into bullous detachments. Although the detachments can subside spontaneously, untreated disease typically evolves into a chronic anterior uveitis or panuveitis. The early stage often, though not always, is accompanied by neurological symptoms of tinnitus and dysacusis; lumbar puncture, if performed, demonstrates cerebrospinal fluid pleocytosis. Several months after disease onset, late-stage disease (previously termed “chronic”) occurs with a “sunset glow” fundus, often with peripapillary atrophy, foveal granular pigment deposition, and peripheral, depigmented, atrophic chorioretinal spots, typically in the inferior periphery. Active late-stage disease has a chronic anterior uveitis or a panuveitis with choroidal inflammatory lesions, similar to those seen in sympathetic ophthalmia and sometimes termed “Dalen-Fuchs-like nodules”. Late-stage disease also may be accompanied by cutaneous lesions, including alopecia, poliosis, and vitiligo. Ocular complications of late-stage disease include choroidal neovascularization and subretinal fibrosis.^4–7

Vogt-Koyanagi-Harada disease occurs most often in individuals of East Asian or South Asian heritage but also is common in the Middle East.^4,8 In Japan, VKH is the most common uveitic disease seen in tertiary care ophthalmology referral clinics.⁸ In the United States, it is seen most often among persons of Hispanic or Native American heritage.⁴ The HLA-DR4 genotype is a risk factor, in particular HLA-DRB1*0405.⁹

Treatment of early-stage VKH typically consists of high-dose oral or pulse intravenous corticosteroids.^7,10–13 Early corticosteroid treatment (within 2 weeks of onset of symptoms) is associated with a marked reduction in progression to late-stage disease,¹¹ but corticosteroid treatment over 6 months in duration is required.¹² Late-stage disease appears to do better with immunosuppression than with corticosteroids alone,¹⁴ and early-stage disease with a delay in treatment initiation may do better with immunosuppression as well.¹⁵

The Standardization of Uveitis Nomenclature (SUN) Working Group is an international collaboration which has developed classification criteria for 25 of the most common uveitic diseases using a formal approach to development and classification.^16–21 Among the diseases studied was VKH disease.

Methods

The SUN Developing Classification Criteria for the Uveitides project proceeded in four phases as previously described: 1) informatics, 2) case collection, 3) case selection, and 4) machine learning.^18–21

Informatics.

As previously described, the consensus-based informatics phase permitted the development of a standardized vocabulary and the development of a standardized, menu-driven hierarchical case collection instrument.¹⁸

Case collection and case selection.

De-identified information was entered into the SUN preliminary database by the 76 contributing investigators for each disease as previously described.^18–21 Cases in the preliminary database were reviewed by committees of 9 investigators for selection into the final database, using formal consensus techniques described in the accompanying article.^20,21 Because the goal was to develop classification criteria,²² only cases with a supermajority agreement (>75%) that the case was the disease in question were retained in the final database (i.e. were “selected”).²¹

Machine learning.

The final database then was randomly separated into a training set (~85% of cases) and a validation set (~15% of cases) for each disease as described in the accompanying article.²¹ Machine learning was used on the training set to determine criteria that minimized misclassification. The criteria then were tested on the validation set; for both the training set and the validation set, the misclassification rate was calculated for each disease. The misclassification rate was the proportion of cases classified incorrectly by the machine learning algorithm when compared to the consensus diagnosis. For VKH disease, the diseases against which it was evaluated were: Behçet disease uveitis, sympathetic ophthalmia, sarcoidosis-associated panuveitis, syphilitic panuveitis, and tubercular panuveitis. Early-stage and late-stage VKH were evaluated separately as they have different clinical features.

The study adhered to the principles of the Declaration of Helsinki. Institutional Review Boards (IRBs) at each participating center reviewed and approved the study; the study typically was considered either minimal risk or exempt by the individual IRBs.

Results

Two hundred twenty-four cases of early-stage VKH and 177 cases of late-stage VKH were collected, and 156 (70%) cases of early-stage VKH and 103 (58%) cases of late-stage VKH achieved supermajority agreement on the diagnosis during the “selection” phase and were used in the machine learning phase. These cases of VKH were compared to cases of other uveitides, including 194 cases of Behçet disease, 110 cases of sympathetic ophthalmia, 102 cases of sarcoidosis-associated panuveitis, 70 cases of syphilitic panuveitis, and 277 cases of tubercular panuveitis. The details of the machine learning results for these diseases are outlined in the accompanying article.²¹ The characteristics of cases with early-stage VKH are listed in Table 1 and with late-stage VKH in Table 2. The criteria developed after machine learning for early-stage VKH are listed in Table 3 and for late-stage VKH in Table 4. Key features of early-stage VKH disease are characteristic serous retinal detachments (Figures 1 and 2) or uveitis with ≥2 of 5 appropriate neurological findings. Key features of late-stage VKH are sunset glow fundus (Figure 3) or uveitis with ≥1 of 3 characteristic cutaneous findings. The 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).²¹ The misclassification rate for early-stage VKH in the training set was 8.0%, and for late-stage VKH 1.0%.¹¹ In the validation set, the misclassification rates for early-stage VKH and late-stage VKH were 7.7% and 12%, respectively. The diseases with which early-stage and late-stage VKH were most often confused were each other.

TABLE 1.

Characteristics of Cases of Early-Stage Vogt-Koyanagi-Harada Disease.

Characteristic	Result
Number of cases Demographics	156
Age, median, years (25th, 75th percentile)	39 (28, 51)
Sex (%)
Male	26
Female	74
Race/ethnicity (%)
White, non-Hispanic	12
Black, non-Hispanic	7
Hispanic	12
Asian, Pacific Islander	41
Other	27
Missing	1
Uveitis history
Uveitis course (%)
Acute, monophasic	54
Acute, recurrent	2
Chronic	35
Indeterminate	9
Laterality (%)
Unilateral	1
Unilateral, alternating	0
Bilateral	99
Ophthalmic examination
Keratic precipitates (%)
None	66
Fine	22
Round	1
Stellate	0
Mutton fat	10
Other	1
Anterior chamber cells, grade (%)
0	18
½+	13
1+	29
2+	24
3+	12
4+	4
Hypopyon (%)	0
Anterior chamber flare, grade (%)
0	54
1+	29
2+	16
3+	0
4+	1
Iris (%)
Normal	87
Posterior synechiae	13
Sectoral iris atrophy	0
Patchy iris atrophy	0
Diffuse iris atrophy	0
Heterochromia	0
IOP, involved eyes
Median, mm Hg (25th, 75th percentile)	13 (12, 16)
Proportion of patients with IOP > 24 mm Hg either eye (%)	0
Vitreous cells, grade (%)
0	47
½+	12
1+	25
2+	10
3+	6
4+	0
Vitreous haze, grade (%)
0	68
½+	12
1+	14
2+	4
3+	1
4+	0
Retinal and choroidal findings (%)
Exudative retinal detachment	94
Multifocal choroiditis without exudative detachment	6
Sunset glow fundus (%)	2
Systemic features (%)
Headache	63
Tinnitus	29
Dysacusis	17
Meningismus	17
Cerebrospinal fluid pleocytosisa	28
Vitiligo	4
Poliosis	2

IOP = intraocular pressure.

^aCerebrospinal fluid pleocytosis detected in 44/44 (100%) cases in which lumbar puncture data were available.

TABLE 2.

Characteristics of Cases of Late-Stage Vogt-Koyanagi-Harada Disease.

Characteristic	Result
Number of cases	103
Demographics
Age, median, years (25th, 75th percentile)	40 (29, 49)
Sex (%)
Male	42
Female	58
Race/ethnicity (%)
White, non-Hispanic	7
Black, non-Hispanic	7
Hispanic	12
Asian, Pacific Islander	43
Other	27
Missing	4
Uveitis history
Uveitis course (%)
Acute, monophasic	2
Acute, recurrent	5
Chronic	83
Indeterminate	11
Laterality (%)
Unilateral	1
Unilateral, alternating	0
Bilateral	99
Ophthalmic examination
Keratic precipitates (%)
None	53
Fine	28
Round	3
Stellate	1
Mutton fat	15
Other	0
Anterior chamber cells, grade (%)
0	24
½+	16
1+	18
2+	27
3+	14
4+	1
Hypopyon (%)	0
Anterior chamber flare, grade (%)
0	43
1+	35
2+	18
3+	4
4+	0
Iris (%)
Normal	64
Posterior synechiae	36
Sectoral iris atrophy	0
Patchy iris atrophy	0
Diffuse iris atrophy	0
Heterochromia	0
IOP, involved eyes
Median, mm Hg (25th, 75th percentile)	14 (11, 17)
Proportion of patients with IOP > 24 mm Hg either eye (%)	6
Vitreous cells, grade (%)
0	56
½+	16
1+	16
2+	11
3+	2
4+	0
Vitreous haze, grade (%)
0	77
½+	7
1+	9
2+	8
3+	0
4+	0
Exudative retinal detachment (%)	8
Sunset glow fundus (%)	86
Multifocal choroiditis (%)a	57
Cutaneous features (%)
Vitiligo	20
Poliosis	22
Alopecia	14

IOP = intraocular pressure.

^aSometimes termed “Dalen Fuchs–like nodules.”

Table 3.

Classification Criteria for Early-Stage Vogt-Koyanagi-Harada Disease

Criteria (Diagnosis requires #1 or #2 AND #3)

1. Evidence of Harada disease

a. Serous (exudative) retinal detachment AND (b. and/or c.)

b. Multiloculated appearance on fluorescein angiogram OR

c. Septae on optical coherence tomogram

OR

2. Panuveitisa with ≥2 of the following neurologic symptoms or signsb

a. Headache OR

b. Tinnitus OR

c. Dysacusis OR

d. Meningismus OR

e. Cerebrospinal fluid pleocytosis

AND

3. No history of penetrating ocular trauma or vitreoretinal surgery prior to disease onset

Exclusions

1. Positive serology for syphilis using a treponemal test

2. Evidence for sarcoidosis (either bilateral hilar adenopathy on chest imaging or tissue biopsy demonstrating noncaseating granulomata)

^aUveitis should have evidence of choroidal involvement on clinical examination, fluorescein angiography, indocyanine green angiography, or optical coherence tomography, including enhanced depth imaging of the choroid.

^bOnset of neurologic symptoms and signs and onset of the uveitis should occur within 4 weeks of each other.

Table 4.

Classification Criteria for Late-Stage Vogt-Koyanagi-Harada Disease

Criteria
1. History of early-stage Vogt-Koyanagi-Harada disease
AND (#2 and/or #3)
2. Sunset glow fundus
OR
3. Uveitis* AND ≥1 of the following cutaneous findings
a. Vitiligo OR
b. Poliosis OR
c. Alopecia
Exclusions
1. Positive serology for syphilis using a treponemal test
2. Evidence for sarcoidosis (either bilateral hilar adenopathy on chest imaging or tissue biopsy demonstrating non-caseating granulomata)

^*Uveitis may be:1) chronic anterior uveitis; 2) anterior and intermediate uveitis; or 3) panuveitis with multifocal choroiditis (“Dalen Fuchs-like nodules”)

FIGURE 1.

Serous retinal detachments in a patient with early-stage Vogt-Koyanagi-Harada disease. A. Color fundus photograph. B. Fluorescein angiogram, demonstrating multiloculated appearance.

FIGURE 2.

Optical coherence tomogram of an exudative retinal detachment in a patient with early-stage Vogt-Koyanagi-Harada disease, demonstrating septate appearance.

FIGURE 3.

Sunset glow fundus in a patient with late-stage Vogt-Koyanagi-Harada disease.

Discussion

The classification criteria developed by the SUN Working Group for early-stage and late-stage VKH have relatively low misclassification rates, indicating good discriminatory performance against other panuveitides and against each other.

Previously proposed sets of diagnostic criteria include the original American Uveitis Society (AUS) criteria, the Revised Diagnostic Criteria for VKH Disease, the Sugiura criteria, and the Chinese Criteria.^23–27 The poor performance of the original AUS criteria²³ led to the “Revised Diagnostic Criteria”, which were developed by an international committee.²⁴ The Revised Diagnostic Criteria classified cases as complete VKH disease, incomplete VKH disease, and probable VKH disease. An analysis of these criteria resulted in the following: 12% of cases were classified as complete VKH, 71% as incomplete VKH, and 9% as probable VKH.²⁵ One of the reasons for the low proportion of cases being classified as complete VKH by the Revised Diagnostic Criteria is the use of modern corticosteroid therapy, which may prevent the development of late-stage disease. In 2018, Yang et al²⁶ used latent class analysis of case data from Chinese patients to develop diagnostic criteria for VKH disease. These criteria classified cases as early VKH and late VKH and not as complete and incomplete VKH. The resulting criteria appeared to perform better than the Revised Diagnostic Criteria.^26,27 However, these criteria contained the problematic and tautological phrase “No evidence of infectious uveitis or accompanying systemic rheumatic disease or evidence suggestive of other ocular disease entities”, which appears to imply exhaustive diagnostic testing.^26,27 The SUN criteria for VKH disease also divide it into early-stage VKH disease and late-stage VKH disease, have many similar factors to the Chinese criteria, but eliminate the non-specific exclusions with regionally relevant ones.

Although all cases received supermajority agreement on the diagnosis of early-or late-stage VKH, a few cases had features of both stages and were classified as early-stage or late-stage based on the preponderance of features. These few cases with overlap demonstrate that some patients will not move distinctly from early-stage to late-stage disease. Nevertheless, they typically can be classified as one or the other based on the predominant ocular and systemic features.

Modern multi-modal imaging has enhanced our ability to evaluate patients with uveitic diseases. Fluorescein angiography and indocyanine green angiography demonstrate multiple choroidal lesions in patients with early-stage VKH. Enhanced-depth imaging (EDI) optical coherence tomography (OCT) of the choroid has demonstrated choroidal thickening in patients with early-stage VKH, which resolves with successful treatment.²⁸ The SUN data base did not have sufficient data on OCT EDI to evaluate it directly as a diagnostic criterion. Choroidal thickening on OCT EDI was included in the Chinese criteria,²⁶ and all cases of early-stage VKH in the SUN data base had evidence of choroidal disease, even if a serous detachment was not evident. Therefore, demonstration of choroidal involvement either by clinical examination or multi-modal imaging were included for identification of “panuveitis” in patients with early-stage VKH and neurologic findings, but without serous detachments.

The presence of any of the exclusions in Tables 3 and 4 suggests an alternate diagnosis, and the diagnosis of VKH should not be made in their presence. In prospective studies many of these tests will be performed routinely, and the alternative diagnoses excluded. However, in retrospective studies based on clinical care, not all of these tests may have been performed. Hence the presence of an exclusionary criterion excludes VKH, but the absence of such testing does not always exclude the diagnosis of VKH if the criteria for the diagnosis are met.

Classification criteria are employed to diagnose individual diseases for research purposes.²² Classification criteria differ from clinical diagnostic criteria, in that although both seek to minimize misclassification, when a trade-off is needed, diagnostic criteria typically emphasize sensitivity, whereas classification criteria emphasize specificity,²² in order to define a homogeneous group of patients for inclusion in research studies and limit the inclusion of patients without the disease in question that might confound the data. The machine learning process employed did not explicitly use sensitivity and specificity; instead it minimized the misclassification rate. Because we were developing classification criteria and because the typical agreement between two uveitis experts on diagnosis is moderate at best,²⁰ the selection of cases for the final database (“case selection”) included only cases which achieved supermajority agreement on the diagnosis. As such, some cases which clinicians would diagnose with early-stage VKH or late-stage VKH will not be so classified by classification criteria. The selection of cases during case selection which achieved supermajority agreement on the diagnosis for inclusion in the final data base was used because we were developing classification criteria.

In conclusion, the criteria for early-stage VKH disease and late-stage VKH disease outlined in Tables 3 and 4 appear to perform sufficiently well for use as classification criteria in clinical research.^21,22