Acute brain injury risk prediction models in venoarterial extracorporeal membrane oxygenation patients with tree-based machine learning: An Extracorporeal Life Support Organization Registry analysisCentral MessagePerspective
Andrew Kalra, BS,
Preetham Bachina, BS,
Benjamin L. Shou, BS,
Jaeho Hwang, MD, MPH,
Meylakh Barshay, BS,
Shreyas Kulkarni, BS,
Isaac Sears, BS,
Carsten Eickhoff, PhD,
Christian A. Bermudez, MD,
Daniel Brodie, MD,
Corey E. Ventetuolo, MD, MS,
Bo Soo Kim, MD,
Glenn J.R. Whitman, MD,
Adeel Abbasi, MD, ScM,
Sung-Min Cho, DO, MHS,
Bo Soo Kim,
David Hager,
Steven P. Keller,
Errol L. Bush,
R. Scott Stephens,
Shivalika Khanduja,
Jin Kook Kang,
Ifeanyi David Chinedozi,
Zachary Darby,
Hannah J. Rando,
Trish Brown,
Jiah Kim,
Christopher Wilcox,
Albert Leng,
Andrew Geeza,
Armaan F. Akbar,
Chengyuan Alex Feng,
David Zhao,
Marc Sussman,
Pedro Alejandro Mendez-Tellez,
Philip Sun,
Karlo Capili,
Ramon Riojas,
Diane Alejo,
Scott Stephen,
Harry Flaster
Affiliations
Andrew Kalra, BS
Division of Cardiac Surgery, Department of Surgery, Johns Hopkins Hospital, Baltimore, Md; Sidney Kimmel Medical College, Thomas Jefferson University, Philadelphia, Pa
Preetham Bachina, BS
Division of Cardiac Surgery, Department of Surgery, Johns Hopkins Hospital, Baltimore, Md
Benjamin L. Shou, BS
Division of Cardiac Surgery, Department of Surgery, Johns Hopkins Hospital, Baltimore, Md
Jaeho Hwang, MD, MPH
Division of Epilepsy, Department of Neurology, Johns Hopkins Hospital, Baltimore, Md
Meylakh Barshay, BS
Warren Alpert Medical School of Brown University, Providence, RI
Shreyas Kulkarni, BS
Warren Alpert Medical School of Brown University, Providence, RI
Isaac Sears, BS
Warren Alpert Medical School of Brown University, Providence, RI
Carsten Eickhoff, PhD
Department of Computer Science, Brown University, Providence, RI; Faculty of Medicine, University of Tübingen, Tübingen, Germany; Institute for Bioinformatics and Medical Informatics, University of Tübingen, Tübingen, Germany
Christian A. Bermudez, MD
Division of Cardiovascular Surgery, Department of Surgery, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, Pa
Daniel Brodie, MD
Division of Pulmonary and Critical Care Medicine, Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, Md
Corey E. Ventetuolo, MD, MS
Division of Pulmonary, Critical Care and Sleep Medicine, Warren Alpert Medical School of Brown University, Providence, RI
Bo Soo Kim, MD
Division of Pulmonary and Critical Care Medicine, Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, Md
Glenn J.R. Whitman, MD
Division of Cardiac Surgery, Department of Surgery, Johns Hopkins Hospital, Baltimore, Md
Adeel Abbasi, MD, ScM
Division of Pulmonary, Critical Care and Sleep Medicine, Warren Alpert Medical School of Brown University, Providence, RI
Sung-Min Cho, DO, MHS
Division of Cardiac Surgery, Department of Surgery, Johns Hopkins Hospital, Baltimore, Md; Division of Neurosciences Critical Care, Department of Neurology, Neurosurgery, Anesthesiology and Critical Care Medicine, Johns Hopkins Hospital, Baltimore, Md; Address for reprints: Sung-Min Cho, DO, MHS, Division of Neurosciences Critical Care, The Johns Hopkins Hospital, 600 N Wolfe St, Phipps 455, Baltimore, MD 21287.
Objective: We aimed to determine if machine learning can predict acute brain injury and to identify modifiable risk factors for acute brain injury in patients receiving venoarterial extracorporeal membrane oxygenation. Methods: We included adults (age ≥18 years) receiving venoarterial extracorporeal membrane oxygenation or extracorporeal cardiopulmonary resuscitation in the Extracorporeal Life Support Organization Registry (2009-2021). Our primary outcome was acute brain injury: central nervous system ischemia, intracranial hemorrhage, brain death, and seizures. We used Random Forest, CatBoost, LightGBM, and XGBoost machine learning algorithms (10-fold leave-1-out cross-validation) to predict and identify features most important for acute brain injury. We extracted 65 total features: demographics, pre-extracorporeal membrane oxygenation/on-extracorporeal membrane oxygenation laboratory values, and pre-extracorporeal membrane oxygenation/on-extracorporeal membrane oxygenation settings. Results: Of 35,855 patients receiving venoarterial extracorporeal membrane oxygenation (nonextracorporeal cardiopulmonary resuscitation) (median age of 57.8 years, 66% were male), 7.7% (n = 2769) experienced acute brain injury. In venoarterial extracorporeal membrane oxygenation (nonextracorporeal cardiopulmonary resuscitation), the area under the receiver operator characteristic curves to predict acute brain injury, central nervous system ischemia, and intracranial hemorrhage were 0.67, 0.67, and 0.62, respectively. The true-positive, true-negative, false-positive, false-negative, positive, and negative predictive values were 33%, 88%, 12%, 67%, 18%, and 94%, respectively, for acute brain injury. Longer extracorporeal membrane oxygenation duration, higher 24-hour extracorporeal membrane oxygenation pump flow, and higher on-extracorporeal membrane oxygenation partial pressure of oxygen were associated with acute brain injury. Of 10,775 patients receiving extracorporeal cardiopulmonary resuscitation (median age of 57.1 years, 68% were male), 16.5% (n = 1787) experienced acute brain injury. The area under the receiver operator characteristic curves for acute brain injury, central nervous system ischemia, and intracranial hemorrhage were 0.72, 0.73, and 0.69, respectively. Longer extracorporeal membrane oxygenation duration, older age, and higher 24-hour extracorporeal membrane oxygenation pump flow were associated with acute brain injury. Conclusions: In the largest study predicting neurological complications with machine learning in extracorporeal membrane oxygenation, longer extracorporeal membrane oxygenation duration and higher 24-hour pump flow were associated with acute brain injury in nonextracorporeal cardiopulmonary resuscitation and extracorporeal cardiopulmonary resuscitation venoarterial extracorporeal membrane oxygenation.
