Opioid Use as a Predictor of Pancreas Transplant Outcomes

BACKGROUND: Posttransplant opioid dependence has been linked to adverse outcomes in solid organ transplantation, but its impact on pancreas transplantation is underexplored. METHODS: This retrospective study analyzed 193 PTA/PAK recipients from Asan Medical Center (AMC) (2010-2022) and externally validated results in 77 recipients from Pusan National University Yangsan Hospital (PNUYH) (2015-2022). Posttransplant opioid dependence was defined as ≥ 10 opioid prescriptions between 3 and 12 months posttransplant. Logistic regression and three ML algorithms (CatBoost, XGBoost, and LightGBM) were used to identify risk factors and predict 5-year graft survival. RESULTS: Posttransplant opioid dependence (OR 2.87, p = 0.005) independently predicted 5-year graft failure, along with pre-transplant retinopathy, bladder drainage, and lower BMI. ML models showed favorable internal AUROC (0.695-0.719) and moderate external AUROC (0.649-0.671). Opioid dependence consistently ranked among top predictive features across models. CONCLUSIONS: Posttransplant opioid dependence is a significant predictor of graft failure after pancreas transplantation. Incorporating this variable into ML models may enhance risk stratification and candidate selection.