Classification Criteria for Punctate Inner Choroiditis

PURPOSE: The purpose of this study was to determine classification criteria for punctate inner choroiditis (PIC). DESIGN: Machine learning of cases with PIC and 8 other posterior uveitides. METHODS: Cases of posterior uveitides were collected in an informatics-designed preliminary database, and a fi-nal database was constructed of cases achieving superma-jority agreement on diagnosis by using formal consensus techniques. Cases were split into a training set and a val-idation set. Machine learning using multinomial logistic regression was used in the training set to determine a parsimonious set of criteria that minimized the misclassifi-cation rate among the posterior uveitides. The resulting criteria were evaluated in the validation set. RESULTS: A total of 1,068 cases of posterior uveitides, including 144 cases of PIC, were evaluated by machine learning. Key criteria for PIC included: 1) punctateappearing choroidal spots <250 mu m in diameter; 2) ab-sent to minimal anterior chamber and vitreous inflam- mation; and 3) involvement of the posterior pole with or without mid-periphery. Overall accuracy for posterior uveitides was 93.9% in the training set and 98.0% (95% confidence interval: 94.3-99.3) in the validation set. The misclassification rates for PIC were 15% in the training set and 9% in the validation set. CONCLUSIONS: The criteria for PIC had a reasonably low misclassification rate and appeared to perform suffi-ciently well for use in clinical and translational research. ((C) 2021 Elsevier Inc. All rights reserved.)

Automated summary

This study aimed to establish classification criteria for punctate inner choroiditis (PIC) using machine learning. Key criteria for PIC included choroidal spots <250 μm in diameter, minimal or absent anterior chamber and vitreous inflammation, and involvement of the posterior pole and/or mid-periphery. The resulting criteria showed a low misclassification rate and could be useful in clinical and translational research.