2.7 Data Analysis
Continuous variables were expressed as means with standard deviation and 95% confidence interval. Categorical variables were expressed as frequencies (percentages) with 95% confidence interval. Where appropriate, the t-test and chi-square test (Fisher’s exact test where required) were used to compare the differences between the survival and death groups. Single-factor logistic analysis was used to explore the risk factors associated with hospital deaths. If the number of events was too small to calculate the odds ratio or there was collinearity between the variables, the variable was excluded from the univariate logistic analysis. P < 0.05 was considered statistically significant unless otherwise stated.