Classification Criteria for Spondyloarthritis/HLA-B27-Associated Anterior Uveitis

PURPOSE

The purpose of this study was to determine classification criteria for spondyloarthritis/HLA-B27-associated anterior uveitis DESIGN: Machine learning of cases with spondyloarthritis/HLA-B27-associated 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 184 cases of spondyloarthritis/HLA-B27-associated 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% CI: 92.4-98.6). Key criteria for spondyloarthritis/HLA-B27-associated anterior uveitis included 1) acute or recurrent acute unilateral or unilateral alternating anterior uveitis with either spondyloarthritis or a positive test result for HLA-B27; or 2) chronic anterior uveitis with a history of the classic course and either spondyloarthritis or HLA-B27; or 3) anterior uveitis with both spondyloarthritis and HLA-B27. The misclassification rates for spondyloarthritis/HLA-B27-associated anterior uveitis were 0% in the training set and 3.6% in the validation set.

CONCLUSIONS

The criteria for spondyloarthritis/HLA-B27-associated anterior uveitis had a low misclassification rate and appeared to perform well enough for use in clinical and translational research.

Classification Criteria for Juvenile Idiopathic Arthritis-Associated Chronic Anterior Uveitis

PURPOSE

To determine classification criteria for juvenile idiopathic arthritis (JIA)-associated chronic anterior uveitis (CAU).

DESIGN

Machine learning of cases with JIA CAU 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 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.

RESULTS

One thousand eighty-three cases of anterior uveitides, including 202 cases of JIA CAU, 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 JIA CAU included (1) chronic anterior uveitis (or, if newly diagnosed, insidious onset) and (2) JIA, except for the systemic, rheumatoid factor-positive polyarthritis, and enthesitis-related arthritis variants. The misclassification rates for JIA CAU were 2.4% in the training set and 0% in the validation set.

CONCLUSIONS

The criteria for JIA CAU had a low misclassification rate and seemed to perform well enough for use in clinical and translational research.

Classification Criteria for Herpes Simplex Virus Anterior Uveitis

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.

Classification Criteria for Varicella Zoster Virus Anterior Uveitis

PURPOSE

To determine classification criteria for varicella zoster virus (VZV) anterior uveitis.

DESIGN

Machine learning of cases with VZV 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 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.

RESULTS

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.

CONCLUSIONS

The criteria for VZV anterior uveitis had a low misclassification rate and seemed to perform sufficiently well for use in clinical and translational research.

Classification Criteria for Cytomegalovirus Anterior Uveitis

PURPOSE

To determine classification criteria for cytomegalovirus (CMV) anterior uveitis.

DESIGN

Machine learning of cases with CMV 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 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.

RESULTS

One thousand eighty-three cases of anterior uveitides, including 89 cases of CMV 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 CMV anterior uveitis included unilateral anterior uveitis with a positive aqueous humor polymerase chain reaction assay for CMV. No clinical features reliably diagnosed CMV anterior uveitis. The misclassification rates for CMV anterior uveitis were 1.3% in the training set and 0% in the validation set.

CONCLUSIONS

The criteria for CMV anterior uveitis had a low misclassification rate and seemed to perform sufficiently well for use in clinical and translational research.

[Anterior uveitis]

Anterior uveitis is the most common form of uveitis. There are several known and many possible etiologies for anterior uveitis. After examining the posterior segment and ruling out masquerade syndromes, the main step of etiologic diagnosis is clinical characterization. It is essential to establish unilateral versus bilateral involvement and presence or absence of granulomatous features. Subsequently, a work-up may be obtained which then helps to confirm diagnostic hypotheses based on the detailed history and clinical examination. The priority is to rule out an infection, although less frequent, before starting steroid therapy, adapted to the severity of the clinical picture. Finally, biologics have greatly changed the management and prevention of some forms of anterior uveitis, in particular uveitis associated with HLA-B27 and juvenile idiopathic arthritis-associated anterior uveitis.

Multiplex bead immunoassay analysis of aqueous humor reveals distinct cytokine profiles in uveitis

PURPOSE

To extensively characterize the complex network of cytokines present in uveitis aqueous humor (AqH), and the relationships between cytokines and the cellular infiltrate.

METHODS

AqH from noninflammatory control subjects and patients with idiopathic, Fuchs' heterochromic cyclitis (FHC), and herpes-viral or Behçet's uveitis were analyzed for IL-1beta, -2, -4, -5, -7, -8, -10, -12, -13, -15, TNFalpha, IFNgamma, CCL2 (MCP-1), CCL5 (RANTES), CCL11 (Eotaxin), TGFbeta2, and CXCL12 (SDF-1), using multiplex bead immunoassays. The cellular infiltrate was also determined for each sample.

RESULTS

Idiopathic uveitis AqH, compared with noninflammatory controls, was characterized by high levels of IL-6, IL-8, CCL2 and IFNgamma, the levels of which correlated with each other. For IL-6 and IL-8 these levels were proportional to the number of neutrophils present. By contrast, the levels of both TGFbeta2 and CXCL12 decreased in idiopathic uveitis AqH with increasing inflammation. Cluster analysis showed a degree of segregation between noninflammatory and idiopathic uveitis AqH. Further examination using random forest analysis yielded a complete distinction between these two groups. The minimum cytokines required for this classification were IL-6, IL-8, CCL2, IL-13, TNFalpha, and IL-2.

CONCLUSIONS

Application of multiplex bead immunoassays has allowed us to identify distinct patterns of cytokines that relate to both clinical disease and the cellular infiltrates present. Bioinformatics analysis allowed identification of cytokines that differentiate idiopathic uveitis from noninflammatory control AqH and are likely to be important for the pathogenesis of uveitis.

Classification of herpes simplex virus keratitis and anterior uveitis

PURPOSE

To review the classification of herpes simplex virus (HSV) keratitis and anterior uveitis using the available clinical, pathologic, and laboratory models of disease.

METHODS

The literature was reviewed to establish prior classifications of herpes simplex keratitis and uveitis. The author introduces a classification attempting to encompass all patients with this disease process, taking into account the newer proposed mechanisms of disease.

RESULTS

A classification of HSV keratitis and uveitis is introduced based on the literature and the experience of the author in treating patients with this condition.

CONCLUSIONS

There are multiple mechanisms of disease after ocular HSV infection, including damage from live virus, from immune and inflammatory mechanisms, and from structural damage in the aftermath of HSV infection (metaherpetic disease). Clinical, pathologic, and etiologic descriptions of these disease manifestations are offered. This may allow better communication between clinicians and authors of research protocols by defining the different aspects of this complex disease process.