Interobserver agreement for EUS findings in familial pancreatic-cancer kindreds

Background: EUS is a promising modality for pancreatic-cancer screening in high-risk persons, including familial pancreatic-cancer (FPC) kindreds. Objective: To assess interobserver agreement for interpretation of EUS in persons at high risk for pancreatic cancer. Design: Seventeen expert endosonographers blinded to patients' clinical history rated a "training set" of pancreatic EUS video clips for the presence of a normal examination, masses, cysts, and features of chronic pancreatitis. Clips included high-risk persons and controls (normal and various pancreatic diseases). The endosonographers then participated in a workshop on EUS findings in high-risk persons and drafted a consensus statement. Three months later, they blindly rated a "test set" composed of the same video clips. Main Outcome Measurements: Interobserver agreement at baseline (training set) and after a consensus process (test set). Results: For the training set, interobserver agreement was good (kappa >= 0.4) for the presence of cysts and was fair to poor for all other rated EUS features and diagnosis of normal. There was no overall improvement in the test set. in both the training and test sets, agreement was worse for clips from FPC kindreds (kappa >= 0.4 for cysts and < 0.4 for all other features) than for controls (kappa >= 0.4 for normal, cysts, masses, echogenic strands, and lobularity). Limitations: Video clips were not of identical image quality and duration as a clinical EUS examination. Conclusions: There was fair to poor interobserver agreement for the interpretation of pancreatic EUS video clips from members of FPC kindreds. Agreement was not improved by a consensus process.