Abstract. B-type erythropoietin-producing hepatocellular (EphB) receptors and their ephrin ligands are associated with aggressive behavior and poor prognosis in a number of malignancies. The aim of this study was to determine the association between the aberrant expression of these genes and prognosis in human pancreatic cancer. The expression of EphB and the ephrin ligands was determined using real-time quantitative reverse transcription PCR in 46 human primary pancreatic cancers. Overexpression of EphB2 and a more modest overexpression of ephrin-B2 mRNA were observed in more than 44% (20/46) of the pancreatic cancer specimens examined. Overexpression (>upper quartile) of EphB2 and ephrin-B2 was markedly associated with abdominal and/or back pain. Multivariate analysis identified the overexpression of EphB2 as an independent prognostic factor for disease-free and overall survival (both P<0.05). The results of the present study suggest that an increased level of ephrin-B2, in the presence of a high expression of EphB2, leads to a more aggressive tumor phenotype and that EphB2 may be used as a prognostic factor in human pancreatic cancer.

Bootstrapping technique is distribution-independent, which provides an indirect way to estimate the sample size for a clinical trial based on a relatively smaller sample. In this paper, sample size estimation to compare two parallel-design arms for continuous data by bootstrap procedure are presented for various test types (inequality, non-inferiority, superiority, and equivalence), respectively. Meanwhile, sample size calculation by mathematical formulas (normal distribution assumption) for the identical data are also carried out. Consequently, power difference between the two calculation methods is acceptably small for all the test types. It shows that the bootstrap procedure is a credible technique for sample size estimation. After that, we compared the powers determined using the two methods based on data that violate the normal distribution assumption. To accommodate the feature of the data, the nonparametric statistical method of Wilcoxon test was applied to compare the two groups in the data during the process of bootstrap power estimation. As a result, the power estimated by normal distribution-based formula is far larger than that by bootstrap for each specific sample size per group. Hence, for this type of data, it is preferable that the bootstrap method be applied for sample size calculation at the beginning, and that the same statistical method as used in the subsequent statistical analysis is employed for each bootstrap sample during the course of bootstrap sample size estimation, provided there is historical true data available that can be well representative of the population to which the proposed trial is planning to extrapolate.

No abstract

No abstract

No abstract