The DeepECG.ai platform was successfully deployed, analyzing 29,211 ECGs with sub-second inference times and enrolling 285 patients via 53 users within its first three months.
DeepECG.ai provides a functional, integrated platform for AI-enhanced ECG analysis with rapid inference times, facilitating ongoing clinical validation studies.
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.
Nolin-Lapalme et al. (Fri,) conducted a other in ECG analysis and structural heart disease screening (n=285). DeepECG.ai platform was evaluated on Platform implementation and usage metrics. The DeepECG.ai platform was successfully deployed, analyzing 29,211 ECGs with sub-second inference times and enrolling 285 patients via 53 users within its first three months.