Related Experiment Video
Updated: May 25, 2026
BrainBeats as an Open-Source EEGLAB Plugin to Jointly Analyze EEG and Cardiovascular Signals
Published on: April 26, 2024
DeepECG.ai: An AI-enhanced ECG analysis platform to bridge the expertise gap from primary care to cardiology
Alexis Nolin-Lapalme1, Olivier Tastet2, Achille Sowa3
1Department of Biochemistry and Molecular Medicine, Faculty of Medicine, University of Montreal, Montreal, Quebec, Canada; Montreal Heart Institute, Department of Medicine, Montreal, Quebec, Canada; Mila - Québec AI Institute, Montreal, Quebec, Canada; Heartwise (heartwise.ai), Montreal Heart Institute, Montreal, Quebec, Canada.
Background:
Despite numerous open-source deep learning models for ECG interpretation achieving expert-level performance, the field lacks integrated platforms for systematic model evaluation beyond standard accuracy metrics. Current implementations require substantial computational expertise and fail to assess critical translational aspects including interventional contexts, clinical workflow integration, and real-world robustness. DeepECG.ai addresses this gap by providing a unified platform for comprehensive model testing and deployment.
Methods:
We developed DeepECG.ai, a web-based platform that integrates with existing clinical ECG systems to deliver AI-powered decision support within just a few clicks. The platform processes 12‑lead ECGs through AI models and delivers clinical recommendations based on the deployed model's focus. Two clinical studies leverage this system: DAISEA-ECG (ongoing), focused on comprehensive analysis in primary care, and HEART-AI (ongoing), targeting structured cardiology screening.
Results:
The platform successfully integrates electrophysiological systems across care settings. AI models for comprehensive ECG analysis and structural heart disease prediction are operational on a web-based, secure platform. Both clinical validation studies are active with completed user training and operational data collection infrastructure. Within the first three months of the HEART-AI study (since its launch in April 2025), 29,211 ECGs were analyzed, with inference times under one second per ECG. During this period, 53 users provided consent and actively participated, contributing to the enrollment of 285 patients.
Conclusions:
We have successfully developed the DeepECG.ai platform that bridges expertise gaps across the healthcare continuum, delivering actionable decision support to both non-specialist and specialist users. This implementation lays a robust foundation for evaluating AI's impact on diagnostic accuracy, workflow efficiency, and patient outcomes.
Related Concept Videos
01:29Electrocardiogram
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and the T...
01:28Electrocardiogram Fundamentals
An electrocardiogram (ECG) is a diagnostic tool for identifying cardiac conditions such as arrhythmias, conduction abnormalities, and myocardial ischemia.
Definition
An electrocardiogram (ECG) visualizes the heart's electrical activity by tracing the electrical movement associated with each heartbeat on a graph or monitor. As the heart beats, an electrical wave passes through it, correlating with the cardiac cycle events.
Parts of an ECG
An ECG utilizes electrodes on the skin to...
01:23Cardiopulmonary Resuscitation III: AED Use
01:30Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac muscle...
01:25Correlation between ECG and Cardiac Cycle
A cardiac action potential originates in the SA node and spreads throughout the atria and the AV node in approximately 0.03 seconds. This results in the P wave in an ECG and triggers atrial contraction. The action potential is then briefly slowed at the AV node, allowing the atria to contract and fill the ventricles with blood before...
01:25Instrumentation Amplifier
To overcome this challenge, an ECG machine utilizes an instrumentation amplifier. This specialized amplifier is...