Prediction of survival to discharge following cardiopulmonary resuscitation using classification and regression trees

• Published in: Critical care medicine Vol. 41; no. 12; p. 2688
• Main Authors: Ebell, Mark H, Afonso, Anna M, Geocadin, Romergryko G
• Format: Journal Article
• Language: English
• Published: United States 01.12.2013
• Subjects: Aged; Aged, 80 and over; Area Under Curve; Cardiopulmonary Resuscitation - statistics & numerical data; Decision Support Techniques; Decision Trees; Female; Forecasting - methods; Heart Arrest - complications; Heart Arrest - mortality; Heart Arrest - therapy; Hospital Mortality; Humans; Male; Medical Futility; Models, Statistical; Nervous System Diseases - etiology; Patient Discharge; Regression Analysis; Resuscitation Orders; ROC Curve
• ISSN: 1530-0293
• DOI: 10.1097/CCM.0b013e31829a708c

To predict the likelihood that an inpatient who experiences cardiopulmonary arrest and undergoes cardiopulmonary resuscitation survives to discharge with good neurologic function or with mild deficits (Cerebral Performance Category score = 1). Classification and Regression Trees were used to develop branching algorithms that optimize the ability of a series of tests to correctly classify patients into two or more groups. Data from 2007 to 2008 (n = 38,092) were used to develop candidate Classification and Regression Trees models to predict the outcome of inpatient cardiopulmonary resuscitation episodes and data from 2009 (n = 14,435) to evaluate the accuracy of the models and judge the degree of over fitting. Both supervised and unsupervised approaches to model development were used. 366 hospitals participating in the Get With the Guidelines-Resuscitation registry. Adult inpatients experiencing an index episode of cardiopulmonary arrest and undergoing cardiopulmonary resuscitation in the hospital. The five candidate models had between 8 and 21 nodes and an area under the receiver operating characteristic curve from 0.718 to 0.766 in the derivation group and from 0.683 to 0.746 in the validation group. One of the supervised models had 14 nodes and classified 27.9% of patients as very unlikely to survive neurologically intact or with mild deficits (< 3%); the best unsupervised model had 11 nodes and classified 21.7% as very unlikely to survive. We have developed and validated Classification and Regression Tree models that predict survival to discharge with good neurologic function or with mild deficits following in-hospital cardiopulmonary arrest. Models like this can assist physicians and patients who are considering do-not-resuscitate orders.