Development and validation of a risk stratification model for pancreatic cancer: cohort study

Earlier detection might improve survival of patients with pancreatic ductal adenocarcinoma (PDAC). A cohort study using the Optum Labs Data Warehouse (a longitudinal US HER and claims database) to develop and validate a risk stratification model for PDAC in adults aged 40 year or older (‘PRIME’: PDAC Risk Model for Earlier Detection). Participants for 23 health systems (n=4,859,833) comprised the training cohort; 31 additional systems (n=5,619,091) served as validation; international validation was conducted in the UK Biobank (n=498,754). The incidence of PDAC was 55 per 100,000 person years over a mean follow-up of 5.4 ± 2.5 years in the training cohort and 54 per 100,000 person-years over a mean follow-up of 3.9 + 2.5 years in the validation cohort. PRIME retained 19 predictors of PDAC, including history of pancreatitis, gastrointestinal disorders, and prior cancers. Discrimination was strong at the 36-month time horizon (AUC 0.75 in both the training and validation cohorts) with good calibration. In the validation cohort, patients in the top 1% of predicted risk had substantially higher PDAC risk (HR 7.63; 95% CI 6.85-8,49) compared with average-risk individuals. In the UK Biobank, PRIME achieved a 36-month AUC of 0.71 with good calibration. The authors conclude that PRIME effectively stratified PDAC risk across diverse US health systems, with international validation.