Computerized prediction of intensive care unit discharge after cardiac surgery: development and validation of a Gaussian processes model.

Background: The intensive care unit (ICU) length of stay (LOS) of patients undergoing cardiac surgery may vary considerably, and is often difficult to predict within the first hours after admission. The early clinical evolution of a cardiac surgery patient might be predictive for his LOS. The purpose of the present study was to develop a predictive model for ICU discharge after non-emergency cardiac surgery, by analyzing the first 4 hours of data in the computerized medical record of these patients with Gaussian processes (GP), a machine learning technique.

Impact of a computer-generated alert system on the quality of tight glycemic control.

Purpose: To assess the impact of a computer-generated blood glucose (BG) alert, generated by a Patient Data Management System (PDMS) and superimposed on a paper-based guideline, on tight glycemic control (TGC) in the intensive care unit (ICU).

Methods: TGC in the Leuven University Hospitals is performed by nurses using a paper-based guideline that allows anticipative, intuitive decision-making. An electronic alert was implemented on 1 August 2007 in which a pop-up appears in the PDMS at the following BG thresholds: >180, >110, 60-80, 40-60 and <40 mg/dl.