Mark H Ebell1, Anna M Afonso, Romergryko G Geocadin. 1. 1Department of Epidemiology and Biostatistics and the Institute for Evidence-Based Health Professions Education, University of Georgia, Athens, GA. 2Duke University School of Medicine, Durham, NC. 3Departments of Neurology, Anesthesiology-Critical Care Medicine, and Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, MD.
Abstract
OBJECTIVES: 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). DESIGN: 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. SETTING: 366 hospitals participating in the Get With the Guidelines-Resuscitation registry. SUBJECTS: Adult inpatients experiencing an index episode of cardiopulmonary arrest and undergoing cardiopulmonary resuscitation in the hospital. MEASUREMENTS AND MAIN RESULTS: 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. CONCLUSIONS: 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.
OBJECTIVES: 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). DESIGN: 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. SETTING: 366 hospitals participating in the Get With the Guidelines-Resuscitation registry. SUBJECTS: Adult inpatients experiencing an index episode of cardiopulmonary arrest and undergoing cardiopulmonary resuscitation in the hospital. MEASUREMENTS AND MAIN RESULTS: 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. CONCLUSIONS: 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.
Authors: Cindy H Hsu; Bryce E Haac; Mack Drake; Andrew C Bernard; Alberto Aiolfi; Kenji Inaba; Holly E Hinson; Chinar Agarwal; Joseph Galante; Emily M Tibbits; Nicholas J Johnson; David Carlbom; Mina F Mirhoseini; Mayur B Patel; Karen R OʼBosky; Christian Chan; Pascal O Udekwu; Megan Farrell; Jeffrey L Wild; Katelyn A Young; Daniel C Cullinane; Deborah J Gojmerac; Alexandra Weissman; Clifton Callaway; Sarah M Perman; Mariana Guerrero; Imoigele P Aisiku; Raghu R Seethala; Ivan N Co; Debbie Y Madhok; Bryan Darger; Dennis Y Kim; Lara Spence; Thomas M Scalea; Deborah M Stein Journal: J Trauma Acute Care Surg Date: 2018-07 Impact factor: 3.313
Authors: Alexandria J Robbins; Nicholas E Ingraham; Adam C Sheka; Kathryn M Pendleton; Rachel Morris; Alexander Rix; Victor Vakayil; Jeffrey G Chipman; Anthony Charles; Christopher J Tignanelli Journal: J Pain Symptom Manage Date: 2020-09-17 Impact factor: 3.612
Authors: Martin Christ; Wolfgang Dierschke; Katharina Isabel von Auenmueller; Marc van Bracht; Martin Grett; Hans-Joachim Trappe Journal: Int J Gen Med Date: 2014-06-30
Authors: Richard T Carrick; Jinny G Park; Hannah L McGinnes; Christine Lundquist; Kristen D Brown; W Adam Janes; Benjamin S Wessler; David M Kent Journal: J Am Heart Assoc Date: 2020-08-13 Impact factor: 5.501