DNA Methylation Profiling Enables Accurate Classification of Nonductal Primary Pancreatic Neoplasms

Abstract

Background and aimsCytological and histopathological diagnosis of non-ductal pancreatic neoplasms can be challenging in daily clinical practice while it is crucial for therapy and prognosis. The cancer methylome is successfully used as a diagnostic tool in other cancer entities. Here, we investigate if methylation profiling can improve the diagnostic work-up of pancreatic neoplasms. MethodsDNA methylation data were obtained for 301 primary tumors spanning six primary pancreatic neoplasms and 20 normal pancreas controls. Neural Network, Random Forest, and XGBoost machine learning models were trained to distinguish between tumor types. Methylation data of 29 non-pancreatic neoplasms (n = 3708) were used to develop an algorithm capable of detecting neoplasms of non-pancreatic origin. ResultsAfter benchmarking three state-of-the-art machine learning models, the Random Forest model emerged as the best classifier with 96.9% accuracy. All classifications received a probability score reflecting the confidence of the prediction. Increasing the score threshold, improved the Random Forest classifier performance up to 100% with 87% of samples with scores surpassing the cutoff. Using a logistic regression model, detection of non-pancreatic neoplasms achieved an area under the curve (AUC) of > 0.99. Analysis of biopsy specimens showed concordant classification with their paired resection sample. ConclusionPancreatic neoplasms can be classified with high accuracy based on DNA methylation signatures. Additionally, non-pancreatic neoplasms are identified with near perfect precision. In summary, methylation profiling can serve as a valuable adjunct in the diagnosis of pancreatic neoplasms with minimal risk for misdiagnosis, even in the pre-operative setting.