Validation Study of Logistic Regression in Classifying Primary Vitreoretinal Lymphoma Vs. Uveitis By IL-6 and IL-10 Levels

Abstract

Background/Aim: The aim of this study was to assess the utility of intraocular IL-10 and IL-6 analysis by logistic regression in classifying primary vitreoretinal lymphoma (PVRL) vs. uveitis using a logistic regression model trained on a single-center retrospective cohort as well as the previously published ISOLD score compared against the IL-10/IL-6 ratio. Methods: Patient diagnoses of PVRL vs. uveitis and associated aqueous and/or vitreous IL-6 and IL-10 levels were retrospectively collected. From this data, cytokine levels were compared between diagnoses with the Mann-Whitney U test and a logistic regression model was developed to classify PVRL vs. uveitis from aqueous and vitreous IL-6 and IL-10 by nested cross-validation. ROC curves were plotted and AUCs were calculated for the IL-10/IL-6 ratio, ISOLD score, and our logistic regression model. Optimal cut-offs for each classifier were determined by the maximal Youden index; and sensitivity, specificity, PPV, and NPV were determined for each cut-off. Results: 79 lymphoma (10 aqueous, 69 vitreous) and 84 uveitis patients (19 aqueous, 65 vitreous) between 10/5/1999 and 9/16/2015 were included in the study. IL-6 was higher in uveitis vs. lymphoma patients while IL-10 was higher in lymphoma vs. uveitis patients (p <0.01 for all comparisons). For vitreous samples, our logistic regression model achieved an AUC of 98.3%, while ISOLD achieved an AUC of 97.8%, and the IL-10/IL-6 ratio achieved an AUC of 96.3%. The optimal cut-offs for our logistic regression model, ISOLD, and the IL-10/IL-6 ratio achieved sensitivity/specificity of 92.7%/100%, 94.2%/96.9%, 94.2%/95.3% respectively, corresponding to PPV/NPV of 100%/92.9%, 97%/94%, and 95.6%/93.9% respectively. For aqueous samples, all three classifiers achieved 100% AUC with 100% sensitivity/specificity. Odds ratios of PVRL vs. uveitis were 0.981 (aqueous) and 0.992 (vitreous) for IL-6 and 1.030 (aqueous) and 1.060 (vitreous) for IL-10 according to our logistic regression model. Conclusion: In this study, logistic regression, as demonstrated by our model and the ISOLD score, showed strong classification performance and generalizability with high sensitivity and specificity. These results, in addition to logistic regression's ability to further improve with more training data suggest a promising step forward in intraocular cytokine analysis for the early diagnosis of primary vitreoretinal lymphoma. Additional validation studies, especially with cohorts that have proven challenging for the IL-10/IL-6 ratio, would further elucidate the strengths and weakness of this approach. Disclosures No relevant conflicts of interest to declare.