197P Immune-mediated upper gastrointestinal system toxicities in patients receiving immune checkpoint inhibitors: An analysis of the food and drug administration adverse event reporting system (FAERS)

Background: Immuno-oncology (IO) therapy in India faces challenges of high cost and limited biomarker access.The Logistic Regression Immuno-Oncology Response Score (LORIS) integrates clinical and molecular predictors to guide IO benefit and may offer a practical solution in low-resource settings. Methods:We retrospectively analyzed 120 patients treated with anti-PD-1/PD-L1 therapy (2021-2024, two Indian centers).Baseline variables included albumin, neutrophil-to-lymphocyte ratio (NLR), combined positive score (CPS), tumor mutational burden (TMB), WHO performance status, and tumor volume.LORIS scores were computed, correlated with biomarkers, and evaluated for prediction of 1-year iRECIST response.Results: LORIS correlated positively with albumin (r=0.42,p<0.01) and CPS (r=0.36,p=0.02), inversely with NLR (r=-0.33,p=0.03).Higher tumor volume was associated with lower LORIS (p=0.04).LORIS independently predicted 1-year response (OR 1.6, 95% CI 1.1-2.5, p=0.02) with ROC AUC 0.74, outperforming individual biomarkers.