Zeitschrift für perioperative und kritische Intensivpflege
Offener Zugang

Abstrakt

Investigate the Optimum Model for Length of Stay and Mortality Prediction in the Intensive Care Unit

Al Houssainy A. Rady and Sabah Lotfy Mohamed El Sayed

Modeling can be a useful tool to find out how the distributions of hospital length of stayand mortality. The aim of the paper is to investigate the optimum predictive statistical model for the length of stay and mortality in the intensive care unit at Zagazig University hospital, Egypt. The paper presents cross-sectional study of 340 patients who were admitted to the intensive care unit of Zagazig University hospital in Zagazig city, Egypt. The data was collected through the medical records of all patients who admitted to intensive care unit of Hospital in 2016. Several statistical analysis and uni-variate regression models were applied using of SPSS and R Package software.

The maximum and minimum lengths of stay belonged to patients were 60 days and 1 day, respectively. The analysis of results showed that both the Log-normal model and binary logistic model are the optimum techniques for length of stay and mortality prediction because they gave the best results for fitting and predicting the length of stay and mortality in the hospital intensive care unit