A Machine Learning Derived Risk Score Improves Prediction of Outcomes Post-LVAD Implantation: An Analysis of the INTERMACS database.

Abstract

Background: Significant variability in post-left ventricular assist device (LVAD) implantation outcomes emphasize the importance of accurately assessing patients' risk prior to surgery. This study assesses the MARKER-HF mortality risk model, a machine learning-based tool utilizing 8 clinical variables, to predict post-LVAD implantation mortality and its prognostic enhancement over the INTERMACS profile.

Methods: Analyzing 25,365 INTERMACS database patients (mean age 56.8 years, 78% male), 5,663 (22.3%) and 19,702 (77.7%) received HeartMate 3 and other types of LVAD. They were categorized into low, moderate, high, and very high-risk groups based on MARKER-HF score. The outcomes of interest were in-hospital and 1-year post-discharge mortality.

Results: In patients receiving HM3 devices, 6.2% died during index hospitalization. In-hospital mortality progressively increased from 4.4% in low to 15.2% in very high -risk groups with MARKER-HF score. MARKER-HF provided additional risk discrimination within each INTERMACS profile. Combining MARKER-HF score and INTERMACS profile identified patients with the lowest (3.5%) and highest in-hospital mortality (19.8%) rates. Post-discharge mortality rate at one year was 5.8% in this population. In a Cox-proportional hazard regression analysis adjusting for both MARKER-HF and INTERMACS profile, only MARKER-HF score (hazard ratio: 1.27, 95% CI: 1.11-1.46, P<0.001) was associated with post-discharge mortality. Similar findings were observed for patients receiving other types of LVAD.

Conclusions: The MARKER-HF score is a valuable tool for assessing mortality risk in HF patients undergoing HM3 and other LVAD implantation. It offers prognostic information beyond that of the INTERMACS profile alone and it's use should help in the shared decision-making process for LVAD implantation.