Key points are not available for this paper at this time.
Classification and grouping of clinical data into defined categories or hierarchies is difficult in intensive care practice. Diagnosis-related groups are used to categorise patients on the basis of diagnosis. However, this approach may not be applicable to intensive care where there is wide heterogeneity within diagnostic groups. Classification tree analysis uses selected independent variables to group patients according to a dependent variable in a way that reduces variation. In this study, the influence of three easily identified patient attributes on their length of intensive care unit stay was explored using classification analysis. Two thousand five hundred and forty-five critically ill patients from three hospitals were classified into groups so that the variation in length of stay within each group was minimised. In 23 out of 39 terminal groups, the interquartile range of the length of stay was < or = 3 days.
Ridley et al. (Tue,) studied this question.