Moses Krikor Pakram Derhgopian
Research Mentor: Mohammed Saeed
Mentor Department: Department of Internal Medicine, Medicine
Author(s): Mohammed Saeed, Moses Derhgopian
Session: Session 7 (4:00 PM – 4:50 PM)
Presentation Type: Poster 127
Abstract
Atrial Fibrillation (AF) is the most common heart arrhythmia in humans. One of the most routine treatments of patients with AF includes the use of elective external electrical cardioversion. However, despite cardioversion, some patients have return of AF (almost immediately or within a few weeks). We developed machine learning (ML) techniques using routine electrocardiograms (ECGs) available prior to cardioversion along with other readily available clinical data. ML algorithms were trained with a training set of patients with known outcomes (with and without recurrence of AF). ML algorithm performance was then evaluated on a test set of patients not used for training. We hypothesize that such ML algorithms can be useful in identifying AF patients at high risk for recurrence so other therapies (such as administration of anti-arrhythmic drugs) can be considered prior to cardioversion.
