Update:
Research:My research focuses on constructing a model for patients for whom it has already been determined that they need a VAD, and the specific decision is whether an LVAD or BiVAD is appropriate. A hierarchical decision model was constructed using an influence diagram of clinical risk factors derived through interviews with expert cardiologists and cardiac surgeons. The model was implemented with a personal computer, and validated with retrospective data. A nonlinear numerical optimizer was used to derive model parameters that most accurately correlated with eventual outcomes. The model using the optimized parameters was able to predict 74% of the patients who required an RVAD post-implant but also predicted RV failure would occur in 21% of patients who were treated successfully with just an LVAD.
Publications: