fmed-05-00277.pdf (955.49 kB)
Download file

Retrospective Evaluation of Bayesian Risk Models of LVAD Mortality at a Single Implant Center

Download (955.49 kB)
journal contribution
posted on 02.10.2018, 00:00 authored by Lisa CareyLisa Carey, Manreet K. Kanwar, Stephen Bailey, Srinivas Murali, James AntakiJames Antaki

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, previously derived 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 models performed well at all three time points, with a receiver operating characteristic area under the curve (ROC AUC) of 78, 76, and 75%, respectively. This evaluation of model performance verifies the utility of these models in “real life” scenarios at an individual institution.

Funding

This work was supported by an R01 grant (R01HL086918) from the National Institutes of Health/National Heart, Lung, and Blood Institute. Article published with support from the Carnegie Mellon University Article Processing Charge (APC) Fund.

History

Publisher Statement

This is the published PDF version of, “Lohmueller, L. C., Kanwar, M. K., Bailey, S., Murali, S., & Antaki, J. F. (2018). Retrospective Evaluation of Bayesian Risk Models of LVAD Mortality at a Single Implant Center. Frontiers in Medicine, 5, 277. https://doi.org/10.3389/fmed.2018.00277.”

Date

02/10/2018