SubmissionNumber#=%=#27
FinalPaperTitle#=%=#CUAMC @ MedExACT 2026: Robust Ensemble Voting for Fair Medical Decision Extraction
ShortPaperTitle#=%=#
NumberOfPages#=%=#
CopyrightSigned#=%=#
JobTitle#==#
Organization#==#
Abstract#==#Automated extraction of medical decisions from clinical notes is a critical step to constructing more granular patient health trajectories than what is currently obtainable from structured healthcare data. Here we present a system designed for the MedExACT shared task that employs an ensemble of BERT-based classifiers to account for demographic diversity when extracting mentions of medical decisions from MIMIC-III discharge summaries. A simple voting strategy combined with architectural diversity is demonstrated to work best when training data is limited.
Author{1}{Firstname}#=%=#William
Author{1}{Lastname}#=%=#Baumgartner
Author{1}{Username}#=%=#william.baumgartner
Author{1}{Orcid}#=%=#
Author{1}{Email}#=%=#william.baumgartner@cuanschutz.edu
Author{1}{Affiliation}#=%=#University of Colorado Anschutz Medical Campus
Author{2}{Firstname}#=%=#Lisa M.
Author{2}{Lastname}#=%=#Schilling
Author{2}{Orcid}#=%=#
Author{2}{Email}#=%=#LISA.SCHILLING@CUANSCHUTZ.EDU
Author{2}{Affiliation}#=%=#University of Colorado Anschutz Medical Campus

==========
èéáğö