Predicting The Risk Of Pancreatic Cancer In Adults With New-onset Diabetes: Development And Internal-external Validation Of A Clinical Risk Prediction Model

This study uses large-scale, population-representative, linked electronic health record datasets to develop and evaluate clinical prediction models for estimating individual-level risks of developing pancreatic cancer within 2 years of T2DM diagnosis. Three modelling approaches were compared and results were compared against current referral criteria.