DeepECG.ai: An AI-enhanced ECG analysis platform to bridge the expertise gap from primary care to cardiology

IF 1.5 4区医学 Q3 CARDIAC & CARDIOVASCULAR SYSTEMS

Journal of electrocardiology Pub Date : 2026-05-01 Epub Date: 2026-05-16 DOI:10.1016/j.jelectrocard.2026.154359

Alexis Nolin-Lapalme , Olivier Tastet , Achille Sowa , Jacques Delfrate , Inès El Adib , Julianne Morisset , Ram Ahuja , Rohan Banerjee , Marie-Gabrielle Lessard , Alain Vadeboncoeur , Robert Avram

{"title":"DeepECG.ai: An AI-enhanced ECG analysis platform to bridge the expertise gap from primary care to cardiology","authors":"Alexis Nolin-Lapalme , Olivier Tastet , Achille Sowa , Jacques Delfrate , Inès El Adib , Julianne Morisset , Ram Ahuja , Rohan Banerjee , Marie-Gabrielle Lessard , Alain Vadeboncoeur , Robert Avram","doi":"10.1016/j.jelectrocard.2026.154359","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>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.</div></div><div><h3>Methods</h3><div>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)<em>,</em> targeting structured cardiology screening.</div></div><div><h3>Results</h3><div>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.</div></div><div><h3>Conclusions</h3><div>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.</div></div>","PeriodicalId":15606,"journal":{"name":"Journal of electrocardiology","volume":"96 ","pages":"Article 154359"},"PeriodicalIF":1.5000,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of electrocardiology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0022073626001767","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2026/5/16 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

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.

查看原文本刊更多论文

DeepECG。ai：一个人工智能增强的心电图分析平台，弥合从初级保健到心脏病学的专业知识差距

尽管有许多开源的心电解释深度学习模型达到了专家级的性能，但该领域缺乏除了标准精度指标之外的系统模型评估的集成平台。目前的实现需要大量的计算专业知识，并且无法评估关键的转化方面，包括介入环境、临床工作流程集成和现实世界的鲁棒性。DeepECG。Ai通过为全面的模型测试和部署提供一个统一的平台来解决这个问题。方法开发DeepECG。ai是一个基于网络的平台，与现有的临床心电图系统集成，只需点击几下即可提供人工智能驱动的决策支持。该平台通过人工智能模型处理12导联心电图，并根据部署模型的重点提供临床建议。两项临床研究利用了该系统：DAISEA-ECG（正在进行中），侧重于初级保健的综合分析，以及HEART-AI（正在进行中），针对结构化心脏病学筛查。结果该平台成功地集成了跨护理环境的电生理系统。用于综合心电图分析和结构性心脏病预测的人工智能模型在基于网络的安全平台上运行。两项临床验证研究都是活跃的，完成了用户培训和操作数据收集基础设施。在HEART-AI研究的前三个月（自2025年4月启动以来），分析了29,211张心电图，每张心电图的推理时间低于一秒。在此期间，53名用户表示同意并积极参与，共纳入285名患者。结论我们成功研制了DeepECG。Ai平台，可弥合医疗保健连续体之间的专业知识差距，为非专业用户和专业用户提供可操作的决策支持。这一实施为评估人工智能对诊断准确性、工作流程效率和患者治疗结果的影响奠定了坚实的基础。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of electrocardiology 医学-心血管系统

CiteScore

2.70

自引率

7.70%

发文量

152

审稿时长

38 days

期刊介绍： The Journal of Electrocardiology is devoted exclusively to clinical and experimental studies of the electrical activities of the heart. It seeks to contribute significantly to the accuracy of diagnosis and prognosis and the effective treatment, prevention, or delay of heart disease. Editorial contents include electrocardiography, vectorcardiography, arrhythmias, membrane action potential, cardiac pacing, monitoring defibrillation, instrumentation, drug effects, and computer applications.