A machine-learning approach to predicting hypotensive events in ICU settings

•Machine-learning algorithms effectively predict hypotension in ICU settings.•A labeling method is proposed to mimic real-time monitoring of ICU patients.•Short-term physiological history is used to predict events at each data point.•The algorithm performance is assessed as a function of time to event onset.•Optimizing the F1 score helps to attain a high PPV and sensitivity on the test set.