Author + information
- Received March 25, 2019
- Revision received May 31, 2019
- Accepted June 4, 2019
- Published online July 15, 2019.
- Dagmar F. Hernandez-Suarez, MD, MSca,∗ (, )
- Yeunjung Kim, MD, MPHb,
- Pedro Villablanca, MD, MScc,
- Tanush Gupta, MDd,
- Jose Wiley, MD, MPHd,
- Brenda G. Nieves-Rodriguez, BSce,
- Jovaniel Rodriguez-Maldonado, BSce,
- Roberto Feliu Maldonado, BSce,
- Istoni da Luz Sant'Ana, PhDe,
- Cristina Sanina, MDd,
- Pedro Cox-Alomar, MD, MPHf,
- Harish Ramakrishna, MDg,
- Angel Lopez-Candales, MDa,
- William W. O’Neill, MDc,
- Duane S. Pinto, MD, MPHh,
- Azeem Latib, MDd and
- Abiel Roche-Lima, PhDe
- aDivision of Cardiovascular Medicine, Department of Medicine, University of Puerto Rico School of Medicine, San Juan, Puerto Rico
- bDivision of Cardiovascular Medicine, Department of Medicine, Yale University School of Medicine, New Haven, Connecticut
- cDivision of Cardiovascular Medicine, Department of Medicine, Henry Ford Hospital, Detroit, Michigan
- dDivision of Cardiology, Department of Medicine, Montefiore Medical Center/Albert Einstein College of Medicine, New York, New York
- eCenter for Collaborative Research in Health Disparities, University of Puerto Rico School of Medicine, San Juan, Puerto Rico
- fDivision of Cardiology, Department of Medicine, Louisiana State University, New Orleans, Louisiana
- gDivision of Cardiovascular and Thoracic Anesthesiology, Mayo Clinic, Phoenix, Arizona
- hBeth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts
- ↵∗Address for correspondence:
Dr. Dagmar F. Hernandez-Suarez, Division of Cardiovascular Medicine, University of Puerto Rico School of Medicine, P.O. Box 365067, San Juan, Puerto Rico 00936-5067.
Objectives This study sought to develop and compare an array of machine learning methods to predict in-hospital mortality after transcatheter aortic valve replacement (TAVR) in the United States.
Background Existing risk prediction tools for in-hospital complications in patients undergoing TAVR have been designed using statistical modeling approaches and have certain limitations.
Methods Patient data were obtained from the National Inpatient Sample database from 2012 to 2015. The data were randomly divided into a development cohort (n = 7,615) and a validation cohort (n = 3,268). Logistic regression, artificial neural network, naive Bayes, and random forest machine learning algorithms were applied to obtain in-hospital mortality prediction models.
Results A total of 10,883 TAVRs were analyzed in our study. The overall in-hospital mortality was 3.6%. Overall, prediction models’ performance measured by area under the curve were good (>0.80). The best model was obtained by logistic regression (area under the curve: 0.92; 95% confidence interval: 0.89 to 0.95). Most obtained models plateaued after introducing 10 variables. Acute kidney injury was the main predictor of in-hospital mortality ranked with the highest mean importance in all the models. The National Inpatient Sample TAVR score showed the best discrimination among available TAVR prediction scores.
Conclusions Machine learning methods can generate robust models to predict in-hospital mortality for TAVR. The National Inpatient Sample TAVR score should be considered for prognosis and shared decision making in TAVR patients.
This study was funded by the National Institutes of Health (U54MD007587, U54MD007600, S21MD001830, R25MD007607, and TL1TR001434-3). Its contents are solely the responsibility of the authors and do not necessarily represent the official views of the National Institutes of Health. Dr. Pinto serves as a consultant for Medtronic, Abbott Vascular, Abiomed, NuPulse, Siemens, and Boston Scientific. Dr. Latib has served on the advisory boards of Medtronic and Abbott Vascular. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose.
- Received March 25, 2019.
- Revision received May 31, 2019.
- Accepted June 4, 2019.
- 2019 American College of Cardiology Foundation
This article requires a subscription or purchase to view the full text. If you are a subscriber or member, click Login or the Subscribe link (top menu above) to access this article.