CKGROUND: 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.METHODS: Non-interventional study. Predictive modeling, separate development (n = 461) and validation (n = 499) cohort. GP models were developed to predict the probability of ICU discharge the day after surgery (classification task), and to predict the day of ICU discharge as a discrete variable (regression task). GP predictions were compared with predictions by EuroSCORE, nurses and physicians. The classification task was evaluated using aROC for discrimination, and Brier Score, Brier Score Scaled, and Hosmer-Lemeshow test for calibration. The regression task was evaluated by comparing median actual and predicted discharge, loss penalty function (LPF) ((actual-predicted)/actual) and calculating root mean squared relative errors (RMSRE).RESULTS: Median (P25-P75) ICU length of stay was 3 (2-5) days. For classification, the GP model showed an aROC of 0.758 which was significantly higher than the predictions by nurses, but not better than EuroSCORE and physicians. The GP had the best calibration, with a Brier Score of 0.179 and Hosmer-Lemeshow p-value of 0.382. For regression, GP had the highest proportion of patients with a correctly predicted day of discharge (40%), which was significantly better than the EuroSCORE (p < 0.001) and nurses (p = 0.044) but equivalent to physicians. GP had the lowest RMSRE (0.408) of all predictive models.CONCLUSIONS: A GP model that uses PDMS data of the first 4 hours after admission in the ICU of scheduled adult cardiac surgery patients was able to predict discharge from the ICU as a classification as well as a regression task. The GP model demonstrated a significantly better discriminative power than the EuroSCORE and the ICU nurses, and at least as good as predictions done by ICU physicians. The GP model was the only well calibrated model.

ckground intens care unit icu length stay los patient undergo cardiac surgeri may vari consider often difficult predict within first hour admiss earli clinic evolut cardiac surgeri patient might predict los purpos present studi develop predict model icu discharg nonemerg cardiac surgeri analyz first hour data computer medic record patient gaussian process gp machin learn techniquemethod nonintervent studi predict model separ develop n valid n cohort gp model develop predict probabl icu discharg day surgeri classif task predict day icu discharg discret variabl regress task gp predict compar predict euroscor nurs physician classif task evalu use aroc discrimin brier score brier score scale hosmerlemeshow test calibr regress task evalu compar median actual predict discharg loss penalti function lpf actualpredictedactu calcul root mean squar relat error rmsreresult median pp icu length stay day classif gp model show aroc signific higher predict nurs better euroscor physician gp best calibr brier score hosmerlemeshow pvalu regress gp highest proport patient correct predict day discharg signific better euroscor p nurs p equival physician gp lowest rmsre predict modelsconclus gp model use pdms data first hour admiss icu schedul adult cardiac surgeri patient abl predict discharg icu classif well regress task gp model demonstr signific better discrimin power euroscor icu nurs least good predict done icu physician gp model well calibr model