A Comparison of a Machine Learning Model with EuroSCORE II in Predicting Mortality after Elective Cardiac Surgery: A Decision Curve Analysis.

BACKGROUND: The benefits of cardiac surgery are sometimes difficult to predict and the decision to operate on a given individual is complex. Machine Learning and Decision Curve Analysis (DCA) are recent methods developed to create and evaluate prediction models. METHODS AND FINDING: We conducted a retrospective cohort study using a prospective collected database from December 2005 to December 2012, from a cardiac surgical center at University Hospital. The different models of prediction of mortality in-hospital after elective cardiac surgery, including EuroSCORE II, a logistic regression model and a machine learning model, were compared by ROC and DCA. Of the 6,520 patients having elective cardiac surgery with cardiopulmonary bypass, 6.3% died. Mean age was 63.4 years old (standard deviation 14.4), and mean EuroSCORE II was 3.7 (4.8) %. The area under ROC curve (IC95%) for the machine learning model (0.795 (0.755-0.834)) was significantly higher than EuroSCORE II or the logistic regression model (respectively, 0.737 (0.691-0.783) and 0.742 (0.698-0.785), p < 0.0001). Decision Curve Analysis showed that the machine learning model, in this monocentric study, has a greater benefit whatever the probability threshold. CONCLUSIONS: According to ROC and DCA, machine learning model is more accurate in predicting mortality after elective cardiac surgery than EuroSCORE II. These results confirm the use of machine learning methods in the field of medical prediction.

Epidemiology of 62 patients admitted to the intensive care unit after returning from Madagascar.

BACKGROUND: To our knowledge, there is no data on the epidemiology of patients hospitalized in intensive care unit (ICU) after a stay in Madagascar or other low-income countries. It is possible that such data may improve transfer delays and care quality for these patients. METHODS: In a retrospective study, we reviewed the charts of all patients admitted to ICU of the Reunion Island Felix Guyon University Hospital from January 2011 through July 2013. We identified all patients who had stayed in Madagascar during the 6 months prior to ICU admission. RESULTS: Of 1842 ICU patients, 62 (3.4%) had stayed in Madagascar during the 6 months prior to ICU admission. Patients were 76% male and the median age was 60.5 (48.25-64.75) years; patients were more frequently residents of Madagascar than travellers (56.5%). In most cases, patients were not hospitalized or given antibiotics in Madagascar. The most frequent causes of hospitalization were infections including malaria (21%) and lower respiratory infection (11%). Carriage and infection with multidrug resistant (MDR) bacteria on ICU admission were frequent (37% and 9.7%, respectively). The mortality rate in ICU was 21%, and severity acute physiological Score II was 53.5 (37-68). CONCLUSIONS: Patients admitted to ICU after a stay to Madagascar are mainly elderly patients with chronic illnesses, and often foreign residents. The admission causes are specific of the country like malaria, or specific to the population concerned such as cardiovascular accidents that could be prevented.