Frontiers journals are at the top of citation and impact metrics

Original Research ARTICLE Provisionally accepted The full-text will be published soon. Notify me

Front. Med. | doi: 10.3389/fmed.2018.00277

Retrospective Evaluation of Bayesian Risk Models of Left Ventricular Assist Device Mortality at a Single Implant Center

 Lisa C. Lohmueller1*, Manreet Kanwar2, Stephen Bailey2, Srivinas Murali2 and James F. Antaki3
  • 1Computer Science, Carnegie Mellon University, United States
  • 2Cardiovascular Institute, Allegheny General Hospital, United States
  • 3Biomedical Engineering, Cornell University, United States

Use of a left ventricular assist device (LVAD) can benefit patients with end stage heart failure, but only with careful patient selection. In this study, Bayesian network models for predicting LVAD patient mortality at 1, 3, and 12 months post-implant were evaluated on retrospective data from a single implant center. The performance of these models was better than the original model validation at all three time points, with receiver operating characteristic areas under the curves (ROC AUCs) of 78%, 76%, and 75%, respectively. The difference in performance may be due to a combination of institutional experience and patient disease severity. This evaluation of model performance verifies their utility for prospective decision making at this institution.

Keywords: left ventricular assist device, Bayesian, Mortality prediction, Patient Selection, Heart Failure, INTERMACS

Received: 16 Apr 2018; Accepted: 10 Sep 2018.

Edited by:

Christopher Basciano, Becton Dickinson (United States), United States

Reviewed by:

Harry Staines, Independent researcher
Kurt Stromberg, Medtronic (United States), United States  

Copyright: © 2018 Lohmueller, Kanwar, Bailey, Murali and Antaki. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: PhD. Lisa C. Lohmueller, Carnegie Mellon University, Computer Science, Pittsburgh, PA, United States,