A clinical prediction model to assess risk for pancreatic cancer among patients with new-onset diabetes.

Abstract

e15780 Background: Approximately 50% of all patients with pancreatic ductal adenocarcinoma (PDA) develop diabetes mellitus (DM) prior to cancer diagnosis. Targeted screening for PDA among those with new-onset diabetes may allow earlier diagnosis. We sought to develop and validate a PDA risk prediction model to identify high-risk individuals among those with new-onset diabetes. Methods: We conducted a retrospective cohort study in a population representative database from the UK. Individuals with incident diabetes after the age of 35 and ≥3 years of follow-up after DM diagnosis were eligible for inclusion. Candidate predictors consisted of epidemiological and clinical characteristics available at the time of diabetes diagnosis. Variables with p-value<0.25 in the univariable analyses were further evaluated using backward stepwise approach. Model discrimination was assessed using ROC curve analysis. Calibration was evaluated using the Hosmer–Lemeshow test. Results were internally validated using a bootstrapping procedure. Results: The study included 109,385 patients with new-onset diabetes. Among them, 390 (0.4%) were diagnosed with PDA within 3 years. The final model (AUC 0.82, 95% CI: 0.75-0.89) included age, BMI, BMI change, smoking, HbA1C, cholesterol, hemoglobin, creatinine and alkaline phosphatase, and use of PPI and anti-diabetic medication. Bootstrapping validation showed negligible optimism. If the predicted risk threshold for definitive PDA screening was set at 1% over 3 years, only 6.19% of the new-onset diabetes population would undergo definitive screening, and the corresponding sensitivity, specificity and positive predictive value would be 44.7%, 94.0%, and 2.6% respectively. Conclusions: A risk model based on widely available clinical parameters can help target PDA screening in patients with new-onset diabetes.