Publications by authors named "Shubha Majumder"
Episode-level and clinical characterization of asymptomatic atrial fibrillation events.
J Cardiovasc Electrophysiol
December 2024
Introduction: Not all patients experience debilitating symptoms during Atrial Fibrillation (AF), some are asymptomatic. The reasons for this inter- and intrasubject variability is unknown.
Purpose: The study objective was NOAH characterize episode-level and clinical characteristics associated with symptomatic versus asymptomatic episodes of AF in patients with an implantable cardiac monitor (ICM).
Associations Between Changes in Maximum Daily Atrial Fibrillation Duration, Ischemic Stroke, and Mortality.
JACC Clin Electrophysiol
November 2024
Background: Atrial fibrillation (AF) outcomes are strongly associated with continuous measures of AF burden.
Objectives: This study sought to assess the association between changes in maximum daily AF duration (MDAFD) and stroke or mortality in patients with cardiac implantable electronic devices (CIEDs).
Methods: The Optum deidentified electronic health record data set (2007-2021) was linked with the Medtronic CareLink heart rhythm database.
Background: Atrial fibrillation (AF) events in cardiac implantable electronic devices (CIEDs) are temporally associated with stroke risk. This study explores temporal differences in AF burden associated with HF hospitalization risk in patients with CIEDs.
Methods: Patients with HF events from the Optum de-identified Electronic Health Records from 2007 to 2021 and 120 days of preceding CIED-derived rhythm data from a linked manufacturer's data warehouse were included.
Article Synopsis
- Multiple studies have shown that convolutional neural networks (CNNs) can classify raw ECGs, and this research specifically explores a custom CNN designed to improve detection of atrial fibrillation (AF) in implantable cardiac monitors (ICMs).
- The researchers created a new set of features focusing on the unique characteristics of AF to enhance the CNN’s performance and reduce false detections, training and validating it on a large dataset.
- The custom CNN achieved a 99.2% sensitivity and 92.8% specificity during validation, successfully lowering incorrect AF detections by over 90% while maintaining high sensitivity in tests with independent patient data.