Hyperglycemic crises are the most serious acute hyperglycemic complications for people with diabetes.1, 2 Hyperglycemic crises include non-hyperosmolar hyperglycemic crises, such as diabetic ketoacidosis (DKA); and hyperosmolar hyperglycemic crises (HHC), such as hyperosmolar hyperglycemic state (HHS) and cases of combined DKA-HHS (DKA criteria plus elevated osmolality).1, 2, 3 Mortality in HHC can be as high as 20%,2 significantly higher compared with isolated DKA.1, 3 The severity of HHC can result in long lengths of stay for survivors, with mean lengths of stay of up to 11–18 days in some series.4, 5 Given the high cost of hospitalization due to hyperglycemic crises,6 predicting the length of stay at the time of admission would be of great interest. As far as we know, no study has ever aimed to predict the length of stay in HHC using variables available upon admission.

Several studies have explored the predictors of long lengths of stay in adults admitted for isolated DKA,7, 8, 9 a form of hyperglycemic crisis with distinct characteristics from HHC. Former studies have shown that length of stay and economic costs are greater for HHC vs isolated DKA.4 The few studies that have analyzed the determinants of length of stay in HHC have only examined specific variables such as the type of insulin therapy received during hospitalization,10 and the presence of hypertriglyceridemia during hospitalization11 or obesity.12 The only one of these variables10, 11, 12 that can always be known prior to admission is the presence of obesity, which was not associated with a longer length of stay.12

Length of stay is a major determinant of hospital occupancy and resource consumption. The aim of the present study is to investigate whether the baseline, clinical, and laboratory variables that can be measured in the emergency department (ED) can predict prolonged lengths of stay for HHC. As far as we know, this will be the first study ever conducted of this kind.