A Clinical Prediction Model to Assess Risk for Pancreatic Cancer Among Patients With Acute Pancreatitis.

OBJECTIVES: We aimed to develop and validate a prediction model as the first step in a sequential screening strategy to identify acute pancreatitis (AP) individuals at risk for pancreatic cancer (PC). MATERIALS AND METHODS: We performed a population-based retrospective cohort study among individuals 40 years or older with a hospitalization for AP in the US Veterans Health Administration. For variable selection, we used least absolute shrinkage and selection operator regression with 10-fold cross-validation to identify a parsimonious logistic regression model for predicting the outcome, PC diagnosed within 2 years after AP. We evaluated model discrimination and calibration. RESULTS: Among 51,613 eligible study patients with AP, 801 individuals were diagnosed with PC within 2 years. The final model (area under the receiver operating curve, 0.70; 95% confidence interval, 0.67-0.73) included histories of gallstones, pancreatic cyst, alcohol use, smoking, and levels of bilirubin, triglycerides, alkaline phosphatase, aspartate aminotransferase, alanine aminotransferase, and albumin. If the predicted risk threshold was set at 2% over 2 years, 20.3% of the AP population would undergo definitive screening, identifying nearly 50% of PC associated with AP. CONCLUSIONS: We developed a prediction model using widely available clinical factors to identify high-risk patients with PC-associated AP, the first step in a sequential screening strategy.

Do Polygenic Risk Scores Add to Clinical Data in Predicting Pancreatic Cancer? A Scoping Review.

BACKGROUND: Polygenic risk scores (PRS) summarize an individual's germline genetic risk, but it is unclear whether PRS offer independent information for pancreatic cancer risk prediction beyond routine clinical data. METHODS: We searched 8 databases from database inception to March 10, 2023 to identify studies evaluating the independent performance of pancreatic cancer-specific PRS for pancreatic cancer beyond clinical risk factors. RESULTS: Twenty-one studies examined associations between a pancreatic cancer-specific PRS and pancreatic cancer. Seven studies evaluated risk factors beyond age and sex. Three studies evaluated the change in discrimination associated with the addition of PRS to routine risk factors and reported improvements (AUCs: 0.715 to 0.745; AUC 0.791 to 0.830; AUC from 0.694 to 0.711). Limitations to clinical applicability included using source populations younger/healthier than those at risk for pancreatic cancer (n = 10), exclusively of European ancestry (n = 13), or controls without relevant exposures (n = 1). CONCLUSIONS: While most studies of pancreatic cancer-specific PRS did not evaluate the independent discrimination of PRS for pancreatic cancer beyond routine risk factors, three that did showed improvements in discrimination. IMPACT: For pancreatic cancer PRS to be clinically useful, they must demonstrate substantial improvements in discrimination beyond established risk factors, apply to diverse ancestral populations representative of those at risk for pancreatic cancer, and use appropriate controls.