ScholarDeck

AI / informaticsIEEE transactions on bio-medical engineering · 2026

A Dataset and Benchmarks for Atrial Fibrillation Detection from Electrocardiograms of Intensive Care Unit Patients.

Sarah Nassar, Nooshin Maghsoodi, Sophia Mannina … Parvin Mousavi

Read paper

CardiologyAI / informatics

Specific artificial intelligence models achieved a high F1 score for atrial fibrillation detection.

A Dataset and Benchmarks for Atrial Fibrillation Detection from Electrocardiograms of Intensive Care Unit Patients.

Sarah Nassar et al. · IEEE transactions on bio-medical engineering · 2026

Background

Atrial fibrillation (AF) is the most common cardiac arrhythmia experienced by intensive care unit (ICU) patients and can cause adverse health effects.

Purpose

Atrial fibrillation (AF) is the most common cardiac arrhythmia experienced by intensive care unit (ICU) patients and can cause adverse health effects.

Methods

We compared machine learning models across three data-driven artificial intelligence (AI) approaches: feature-based classifiers, deep learning (DL), and ECG foundation models (FMs).

F1 = 0.88

Results

this F1 score indicates high accuracy for artificial intelligence models detecting irregular heartbeat

More results

Across both datasets, ECG FMs generally performed best, followed by DL, then feature-based classifiers.

More results

However, the difference between DL and feature-based classifiers is minimal and highly dependent on the model selected, with feature-based classifiers obtaining a very slightly higher average performance on our ICU test set but DL achieving a higher overall maximum performance.

“

Conclusion · 1 of 2

This study demonstrates promising potential for using AI to build an automatic patient monitoring system.

Conclusion · 2 of 2

SIGNIFICANCE: By publishing our labelled ICU dataset 1 and performance benchmarks, this work enables the research community to continue advancing the state-of-the-art in AF detection in the ICU environment.

Post

A Dataset and Benchmarks for Atrial Fibrillation Detection from Electrocardiograms of Intensive Care Unit Patients.

Specific artificial intelligence models achieved a high F1 score for atrial fibrillation detection.

Related papers