A new combined criterion to better predict malignant lesions in patients with pancreatic cystic neoplasms

Objective:Cystic lesions of the pancreas have been increasingly recognized.Some lesions exhibit benign behavior,while others have unequivocal malignant potential.Thus,accurate identification of malignancy in patients diagnosed with pancreatic cystic neoplasms(PCNs)remains a major challenge.The aim of this study was to define a combined criterion to better predict malignant lesions in patients with PCNs.Methods:We retrospectively analyzed 165 patients who underwent resection of PCNs from October 2011 to May 2017.The relationship among malignancy and serum carbohydrate antigen 19-9(CA19-9),preoperative neutrophil-to-lymphocyte ratio(NLR),and the presence of enhanced solid component on imaging was analyzed.Results:NLR before surgery in patients with malignant PCNs(2.81±2.14)was significantly higher than that in patients diagnosed with pancreatic neuroendocrine tumor(1.90±0.69,P=0.013)or healthy volunteers(1.40±0.48;P<0.001).Serum CA19-9≥39U/m L,NLR>1.976 and presence of enhanced solid component were independent predictors of PCN malignancy.A combined criterion meeting any two or more of the three elements including CA19-9≥39 U/m L,NLR>1.976,and presence of enhanced solid component on computed tomography imaging is an indicator with a high positive predictive value of 80.5%and a high negative predictive value of 87.9%,and thus,represents a highly accurate test(86.1%).Conclusions:The new combined criterion is an effective predictor of tumor malignancy in patients with PCNs.

Fiducial generalized p-values for testing zero-variance components in linear mixed-effects models

Linear mixed-effects models are widely used in analysis of longitudinal data. However, testing for zero-variance components of random effects has not been well-resolved in statistical literature, although some likelihood-based procedures have been proposed and studied. In this article, we propose a generalized p-value based method in coupling with fiducial inference to tackle this problem. The proposed method is also applied to test linearity of the nonparametric functions in additive models. We provide theoretical justifications and develop an implementation algorithm for the proposed method. We evaluate its finite-sample performance and compare it with that of the restricted likelihood ratio test via simulation experiments. We illustrate the proposed approach using an application from a nutritional study.