Fig. 3From: Prediction model of in-hospital mortality in intensive care unit patients with cardiac arrest: a retrospective analysis of MIMIC -IV database based on machine learningPredictor variables selection. AÂ Predictor variables selected by LASSO. B Importance ranking of the predictor variables selected by XGBoost algorithm. BUN, blood urea nitrogen; CHF, congestive heart failure; DBP, diastolic blood pressure; GCS, Glasgow coma scale; HB, hemoglobin; HR, heart rate; LASSO, least absolute shrinkage and selection operator; MBP, mean blood pressure; PT, prothrombin time; RR, respiratory rate; SAPS III, simplified acute physiology score; SPO2, saturation pulse oxygen; WBC, white blood cells; XGBoost, extreme gradient boostingBack to article page