In search of similarity in adverse events journeys of patients with left ventricular assist devices

Abstract

ObjectiveThe Interagency Registry for Mechanically Assisted Circulatory Support (INTERMACS) Event data set contains an expansive collection of longitudinal evidence of the course of adverse events (AEs) of >15,000 patients who have received a left ventricular assist device (LVAD). Buried in the huge Event data set is knowledge that can provide a deeper understanding of the patterns of the “AE journey” of patients with LVAD. Thus, the goal of this study was to examine the Event data set from a comprehensive perspective to identify unique relationships and patterns of AEs, alert potential challenges, and suggest future research directions. MethodsA sequential pattern mining algorithm called SPADE (ie, Sequential PAttern Discovery using Equivalence classes) was applied to 86,912 recorded AEs of 15,820 patients with a continuous-flow LVAD between 2008 and 2016, extracted from the publicly accessible INTERMACS registry. The patterns of AE journey were investigated by posing 5 descriptive research questions about most common types of AE, concomitant AEs, AE sequences, AE subsequences, and interesting relations between AEs. ResultsThe analysis revealed several characteristics of patterns of the AE journey of patients who received an LVAD that accounts for the types and temporal ordering of successive AEs, combinations of AEs, and their timing after surgery. ConclusionsThe high diversity and sparsity of the types and timing of AE occurrences make the AE journeys of patients dissimilar from each other, impeding the discovery of highly-patterned AE journeys among the patients. This study suggests 2 salient directions for future studies to tackle this issue using cluster analysis to cluster patients into more similar groups and translate these results into a practical clinical tool to forecast the next AE based on the history of previous AEs.