To determine classification criteria for varicella zoster virus (VZV) anterior uveitis.
Machine learning of cases with VZV anterior uveitis and 8 other anterior uveitides.
Cases of anterior 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 anterior uveitides. The resulting criteria were evaluated on the validation set.
One thousand eighty-three cases of anterior uveitides, including 123 cases of VZV anterior uveitis, were evaluated by machine learning. The overall accuracy for anterior uveitides was 97.5% in the training set and 96.7% in the validation set (95% confidence interval 92.4, 98.6). Key criteria for VZV anterior uveitis included unilateral anterior uveitis with either (1) positive aqueous humor polymerase chain reaction assay for VZV; (2) sectoral iris atrophy in a patient ≥60 years of age; or (3) concurrent or recent dermatomal herpes zoster. The misclassification rates for VZV anterior uveitis were 0.9% in the training set and 0% in the validation set, respectively.
The criteria for VZV anterior uveitis had a low misclassification rate and seemed to perform sufficiently well for use in clinical and translational research.
V aricella zoster virus (VZV) is a common herpes family DNA virus, causing varicella (“chicken pox”) in children, herpes zoster in adults, and, in immunocompromised adults, disseminated herpes zoster. Herpes zoster may erupt along the distribution of the first branch of the trigeminal nerve, resulting in herpes zoster ophthalmicus. Herpes zoster is estimated to affect 20% to 30% of the population at some point during their lifetime, and 10% to 20% of these individuals are estimated to have herpes zoster ophthalmicus. Ocular disease attributable to herpes zoster ophthalmicus is common, affecting an estimated 50% of patients with trigeminal nerve dermatomal herpes zoster, and one of the most common manifestations is anterior uveitis. A population-based study from Taiwan estimated the incidence of anterior uveitis at 0.3%/person-year after any herpes zoster with a 13-fold increased risk of uveitis for herpes zoster ophthalmicus. Prospective trials of acyclovir for herpes zoster ophthalmicus estimated the risk of anterior uveitis in patients not treated with antivirals at ∼60%, which was substantially reduced by the early use of antiviral agents, such as acyclovir and valacyclovir. One study in 2014 from North Africa similarly estimated that ∼60% of patients with herpes zoster ophthalmicus would develop anterior uveitis.
VZV anterior uveitis is presumed to be attributable to active viral replication in the eye, as evidenced by the detection of VZV DNA in the anterior chamber using polymerase chain reaction (PCR) analysis of aqueous humor obtained by paracentesis and the response to antiviral therapy. Anterior uveitis due to VZV in the absence of dermatomal herpes zoster occurs, albeit less commonly, and can be diagnosed by PCR analysis of an aqueous humor specimen. , In 1 case series of patients with VZV anterior uveitis, 6% of cases of VZV anterior uveitis occurred without dermatomal zoster. A syndrome of herpetic anterior uveitis with sectoral iris atrophy is attributable to either herpes simplex virus (HSV) or VZV in more than 95% of cases. In younger patients (<50 years of age) it typically is due to HSV, and in older patients (≥60 years of age) overwhelmingly to VZV.
The Standardization of Uveitis Nomenclature (SUN) Working Group is an international collaboration that has developed classification criteria for 25 of the most common uveitides using a formal approach to development and classification. Among the anterior uveitides being studied is VZV anterior uveitis.
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. ,
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.
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. , 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. , Because the goal was to develop classification criteria, only cases with a supermajority agreement (>75%) that the case was the disease in question were retained in the final database (ie, were “selected”).
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. 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 VZV anterior uveitis, the diseases against which it was evaluated were cytomegalovirus (CMV) anterior uveitis, HSV anterior uveitis, juvenile idiopathic arthritis–associated anterior uveitis, spondylitis/HLA-B27-associated anterior uveitis, tubulointerstitial nephritis with uveitis, Fuchs uveitis syndrome, sarcoidosis-associated anterior uveitis, and syphilitic anterior uveitis.
Comparison of Cases With and Without Dermatomal Herpes Zoster and With and Without Polymerase Chain Reaction Confirmation of Varicella Zoster Virus in the Anterior Chamber
Comparison of cases with and without dermatomal herpes zoster and with and without PCR confirmation of VZV in the anterior chamber for categorical variables was performed with the χ 2 test or Fisher exact test if a cell was less than 5. For continuous variables, the Wilcoxon rank sum test was used. P values are nominal and 2-sided.
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.
One hundred sixty-three cases of VZV anterior uveitis were collected, and 123 (76%) achieved supermajority agreement on the diagnosis during the “selection” phase and were used in the machine learning phase. These cases of VZV anterior uveitis were compared to 960 cases of other anterior uveitides, including 89 cases of CMV anterior uveitis, 101 cases of HSV anterior uveitis, 146 cases of Fuchs uveitis syndrome, 202 cases of juvenile idiopathic arthritis–associated anterior uveitis, 184 cases of spondylitis/HLA-B27-associated anterior uveitis, 94 cases of tubulointerstitial nephritis with uveitis, 112 cases of sarcoidosis-associated anterior uveitis, and 32 cases of syphilitic anterior uveitis. The characteristics at presentation to a SUN Working Group investigator of cases with VZV anterior uveitis are listed in Table 1 . A comparison of cases with and without dermatomal zoster is listed in Table 2 , and a comparison of cases with and without PCR testing for VZV is listed in Table 3 . Differences between cases with and without dermatomal zoster included the following for those without dermatomal zoster: younger age, more often men, more often nonwhite, less often normal iris, more vitritis, and more likely to have undergone paracentesis for PCR testing. Differences between cases with and without PCR testing included the following for those with PCR testing: more often nonwhite, suggestion of a normal iris less often ( P = .06), and dermatomal zoster less often. As 98% of cases without PCR testing had dermatomal zoster, it seems that PCR testing was used in those without dermatomal zoster and more atypical cases. Other than the iris appearance, there were no differences in the appearance of the uveitis between those with and without dermatomal zoster and those with and without PCR testing. The criteria developed after machine learning are listed in Table 4 . Key features for the diagnosis of VZV anterior uveitis included the following: (1) positive PCR for VZV in the aqueous fluid obtained on paracentesis, or (2) dermatomal herpes zoster, or (3) anterior uveitis with sectoral iris atrophy in a patient ≥60 years of age ( Figure 1 ) . The overall accuracy for anterior uveitides was 97.5% in the training set and 96.7% in the validation set (95% confidence interval 92.4, 98.6). The misclassification rate for VZV anterior uveitis in the training set was 0.9% and in the validation set 0%.
|Number of cases||123|
|Age, median, years (25th, 75th percentile)||63 (54, 73)|
|Age category, years (%)|
|Asian, Pacific Islander||11|
|Uveitis course (%)|
|Keratic precipitates (%)|
|Anterior chamber cells, grade (%)|
|Anterior chamber flare, grade (%)|
|Sectoral iris atrophy||11|
|Patch iris atrophy||3|
|Diffuse iris atrophy||2|
|IOP, involved eyes|
|Median, mm Hg (25th, 75th percentile)||14 (12, 20)|
|Proportion patients with IOP > 24 mm Hg either eye (%)||26|
|Vitreous cells, grade (%)|
|Dermatomal herpes zoster (%)||86|
|Immunocompromised host (%)||7|
|Aqueous PCR positive for VZV a (%)||20|
|Characteristic||With Dermatomal Herpes Zoster||Without Dermatomal Herpes Zoster||P Value|
|Number of cases||106||17|
|Age, median, years (25th 75th percentile)||62 (50, 74)||54 (43, 63)||.05|
|Age category, years (%)||.08|
|Asian, Pacific Islander||10||24|
|Uveitis course (%)||.64|
|Keratic precipitates (%)||.27|
|Anterior chamber cells, grade (%)||.11|
|Anterior chamber flare, grade (%)||.69|
|Sectoral iris atrophy||8||23||.08|
|Other iris abnormality||7||24||.03|
|IOP, involved eyes|
|Median, mm Hg (25th, 75th percentile)||15 (12, 20)||18 (14, 22)||.80|
|Percent patients with IOP > 24 mm Hg either eye||22||41||.21|
|Vitreous cells, grade (%)||.01|
|Immunocompromised host (%)||7||12||.42|
|Aqueous PCR positive for VZV (%)||9 a||88 b||<.0001|