The purpose of this study was to determine classification criteria for sarcoidosis-associated uveitis.

Machine learning of cases with sarcoid uveitis and 15 other uveitides.

Cases of anterior, intermediate, and panuveitides were collected in an informatics-designed preliminary database, and a final database was constructed including cases achieving supermajority agreement on the diagnosis, using formal consensus techniques. Cases were analyzed by anatomic class, and each class was split into a training set and a validation set. Machine learning using multinomial logistic regression was used in the training sets to determine a parsimonious set of criteria that minimized the misclassification rate among the uveitides. The resulting criteria were evaluated in the validation sets.

A total of 1,083 cases of anterior uveitides, 589 cases of intermediate uveitides, and 1,012 cases of panuveitides, including 278 cases of sarcoidosis-associated uveitis, were evaluated by machine learning. Key criteria for sarcoidosis-associated uveitis included a compatible uveitic syndrome of any anatomic class and evidence of sarcoidosis, either 1) tissue biopsy results demonstrating non-caseating granulomata or 2) bilateral hilar adenopathy on chest imaging. The overall accuracy of the diagnosis of sarcoidosis-associated uveitis in the validation set was 99.7% (95% confidence interval: 98.8-99.9). The misclassification rates for sarcoidosis-associated uveitis in the training sets were 3.2% in anterior uveitis, 2.6% in intermediate uveitis, and 1.2% in panuveitis; in the validation sets, the misclassification rates were 0% in anterior uveitis, 0% in intermediate uveitis, and 0% in panuveitis.

The criteria for sarcoidosis-associated uveitis had a low misclassification rate and appeared to perform sufficiently well for use in clinical and translational research.