Comparing four methods for predicting septic shock in children hospitalized with sepsis, Johns Hopkins researchers have found a newer machine-learning approach superior to an older one as well as to two conventional methods.

The top performer, the open-source XGBoost (for eXtreme Gradient Boosting), supplied accurate early predictions that, in clinical practice, would have given critical-care teams nearly nine hours to intervene preventively.

The researchers used data from more than 6,100 past patients of Johns Hopkins’s pediatric ICU to train and test the model retrospectively… Continue reading.