Matlab r2016b version 9

The primary outcome of our investigation was hospital mortality related to hypoglycaemia. Patients with hypoglycaemia were separated into survivors and non-survivors. Categorical variables were summarized with the use of proportions, and comparisons between groups were conducted using a chi-squared test.
Continuous variables were summarized using either the mean (standard deviation, SD) or median (interquartile range, IQR) as appropriate. Comparisons between groups were assessed with a t test or the Wilcoxon rank-sum test as suitable. A P value < 0.05 was considered statistically significant.
To predict the influence of hypoglycaemia on mortality, multivariate logistic regression models were developed using all available demographic variables and possible predictors of mortality (APACHE IV scores, hypoglycaemia, age, gender, ethnicity), and stepwise regression. Model calibration was determined using the Hosmer-Lemeshow goodness-of-fit test. A generalized linear model (GLM) was used to assess LOS in both unadjusted and adjusted analyses (adjusting for baseline characteristics and APACHE scores).
All analyses were performed using either MATLAB R2016b version 9.1 (MathWorks, Inc., Natick, MA, USA) or IBM SPSS version 24 (IBM Corp., Armonk, NY, USA) software. Missing data were assumed to be missing at random (MAR) and were imputed using the 'impute missing value' function of IBM SPSS.