Demographic data were presented as percentage, mean, and
standard deviation. All continuous data were tested for normal
distribution with the Shapiro–Wilk test. Parametric tests
were used based on normal distributions, and nonparametric
tests were performed when assumptions were not met.
Contingency tables were constructed to analyze the relationships
between PUP patients and peptic ulcer with no perforation
patients. Comparison of data between the two patient groups
were undertaken with Pearson’s chi-square test or Fisher’s
exact test for categorical data and Student’s t-test or Wilcoxon
rank-sum test for continuous data. All variables, explored by
univariable analyses, were entered into a multivariable exponential
risk regression analysis to evaluate the relative risk (RR)
of PUP for the diagnostic variables. Differences
were considered
statistically significant when P , 0.05. All analyses were
performed using Stata® statistical software package, version 11
(StataCorp LP, College Station, TX).