Purpose
The purpose of this study was to determine classification criteria for herpes simplex virus (HSV) anterior uveitis
Design
Machine learning of cases with HSV anterior uveitis and 8 other anterior uveitides.
Methods
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 in the training set to determine a parsimonious set of criteria that minimized the misclassification rate among the anterior uveitides. The resulting criteria were evaluated in the validation set.
Results
A total of 1,083 cases of anterior uveitides, including 101 cases of HSV 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 HSV anterior uveitis included unilateral anterior uveitis with either 1) positive aqueous humor polymerase chain reaction assay for HSV; 2) sectoral iris atrophy in a patient ≤50 years old; or 3) HSV keratitis. The misclassification rates for HSV anterior uveitis were 8.3% in the training set and 17% in the validation set.
Conclusions
The criteria for HSV anterior uveitis had a reasonably low misclassification rate and appeared to perform well enough for use in clinical and translational research.
H erpes simplex virus (HSV) anterior uveitis is an infectious anterior uveitis presumed to be due to replicating virus in the eye, as shown by the detection of HSV viral DNA in the aqueous humor of eyes using polymerase chain reaction (PCR) analysis of aqueous humor obtained by paracentesis of the anterior chamber. It nearly always is unilateral, may present with elevated intraocular pressure, may be chronic, in 30%-40% of cases may occur in the context of HSV keratitis (HSV keratouveitis) or may occur as a unilateral uveitis with sectoral iris atrophy without keratitis. In case series of patients with uveitis, it accounts for 3%-10% of all uveitis cases and 5%-10% of anterior uveitis cases. , The correct diagnosis affects management as oral antiviral medications typically are used in the treatment of HSV anterior uveitis, with some patients requiring chronic suppressive antiviral medication. ,
The Standardization of Uveitis Nomenclature (SUN) Working Group is an international collaboration, which has developed classification criteria for 25 of the most common uveitides using a formal approach to development and classification. Among the anterior uveitides studied was HSV anterior uveitis.
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. , , ,
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.
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 articles. , Because the goal was to develop classification criteria, only cases with a supermajority agreement (>75%) that the case was the disease were retained in the final database (ie, were “selected”).
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. Machine learning was used in the training set to determine criteria that minimized misclassification. The criteria then were tested in 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 compared to the consensus diagnosis. For HSV anterior uveitis, the diseases against which it was evaluated were: cytomegalovirus (CMV) anterior uveitis, varicella zoster virus (VZV) anterior uveitis, juvenile idiopathic arthritis (JIA)-associated anterior uveitis, spondylitis/HLA-B27-associated anterior uveitis, tubulointerstitial nephritis with uveitis (TINU), Fuchs uveitis syndrome, sarcoid anterior uveitis, and syphilitic anterior uveitis.
This 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 a minimal risk or exempt by individual IRBs.
Results
A total of 250 cases of HSV anterior uveitis were collected, and 101 cases (40%) achieved supermajority agreement on the diagnosis during the “selection” phase and were used in the machine learning phase. These cases of HSV anterior uveitis were compared to cases of other anterior uveitides, including 89 cases of CMV anterior uveitis; 123 cases of VZV anterior uveitis; 146 cases of Fuchs uveitis syndrome; 202 cases of JIA-associated anterior uveitis; 184 cases of spondylitis/HLA-B27-associated anterior uveitis; 94 cases of TINU; 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 the cases with HSV anterior uveitis are listed in Table 1 . The criteria developed after machine learning are listed in Table 2 . Key features included evidence of HSV infection, including: 1) positive PCR analysis for HSV in the aqueous; 2) sectoral iris atrophy ( Figure 1 ) in a patient ≤50 years old; or 3) HSV keratitis, either epithelial or stromal.
| Characteristic | Result |
|---|---|
| Number of cases | 101 |
| Demographics | |
| Median IQR (25th, 75th) age | 44 (2, 87) |
| Age category, years % | |
| ≤16 | 2 |
| 17–50 | 71 |
| 51–60 | 12 |
| >60 | 14 |
| Men, % | 42 |
| Women, % | 58 |
| Race/ethnicity, % | |
| White, non-Hispanic | 65 |
| Black, non-Hispanic | 3 |
| Hispanic | 3 |
| Asian, Pacific Islander | 6 |
| Other | 7 |
| Missing | 16 |
| Uveitis History | |
| Uveitis course, % | |
| Acute, monophasic | 13 |
| Acute, recurrent | 31 |
| Chronic | 40 |
| Indeterminate | 16 |
| Laterality, % | |
| Unilateral | 99 |
| Unilateral, alternating | 0 |
| Bilateral | 1 |
| Ophthalmic examination | |
| Cornea | |
| No keratitis | 77 |
| Keratitis | 23 |
| Keratic precipitates, % | |
| None | 26 |
| Fine | 24 |
| Round | 18 |
| Stellate | 5 |
| Mutton Fat | 26 |
| Other | 2 |
| Anterior chamber cells, % | |
| Grade ½+ | 22 |
| 1+ | 31 |
| 2+ | 25 |
| 3+ | 14 |
| 4+ | 2 |
| Hypopyon, % | 0 |
| Anterior chamber flare, % | |
| Grade 0 | 38 |
| 1+ | 47 |
| 2+ | 15 |
| 3+ | 0 |
| 4+ | 1 |
| Iris, % | |
| Normal | 36 |
| Posterior synechiae | 18 |
| Sectoral iris atrophy | 46 |
| Patch iris atrophy | 9 |
| Diffuse iris atrophy | 9 |
| Heterochromia | 1 |
| IOP involved eyes | |
| Median IQR (25th, 75th), mm Hg | 16 (12, 21) |
| Proportion patients with IOP >24 mm Hg in either eye, % | 34 |
| Vitreous cells, % | |
| Grade 0 | 78 |
| 1+ | 12 |
| 2+ | 6 |
| 3+ | 4 |
| 4+ | 0 |
| Laboratory | |
| Aqueous PCR positive for HSV (% all cases) | 41 |
| Aqueous PCR positive for HSV (% cases tested) | 100 |
Stay updated, free articles. Join our Telegram channel
Full access? Get Clinical Tree
