Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Sep 20;11(18):e026196.
doi: 10.1161/JAHA.122.026196. Epub 2022 Sep 8.

Evaluation of an Ambulatory ECG Analysis Platform Using Deep Neural Networks in Routine Clinical Practice

Laurent Fiorina  1 , Carole Maupain  2 , Christophe Gardella  3 , Vladimir Manenti  1 , Fiorella Salerno  1 , Pierre Socie  2 , Jia Li  3 , Christine Henry  3 , Audrey Plesse  3 , Kumar Narayanan  4   5 , Aurélie Bourmaud  6 , Eloi Marijon  4   7
Affiliations

Evaluation of an Ambulatory ECG Analysis Platform Using Deep Neural Networks in Routine Clinical Practice

Laurent Fiorina et al. J Am Heart Assoc. .

Abstract

Background Holter analysis requires significant clinical resources to achieve a high-quality diagnosis. This study sought to assess whether an artificial intelligence (AI)-based Holter analysis platform using deep neural networks is noninferior to a conventional one used in clinical routine in detecting a major rhythm abnormality. Methods and Results A total of 1000 Holter (24-hour) recordings were collected from 3 tertiary hospitals. Recordings were independently analyzed by cardiologists for the AI-based platform and by electrophysiologists as part of clinical practice for the conventional platform. For each Holter, diagnostic performance was evaluated and compared through the analysis of the presence or absence of 5 predefined cardiac abnormalities: pauses, ventricular tachycardia, atrial fibrillation/flutter/tachycardia, high-grade atrioventricular block, and high burden of premature ventricular complex (>10%). Analysis duration was monitored. The deep neural network-based platform was noninferior to the conventional one in its ability to detect a major rhythm abnormality. There were no statistically significant differences between AI-based and classical platforms regarding the sensitivity and specificity to detect the predefined abnormalities except for atrial fibrillation and ventricular tachycardia (atrial fibrillation, 0.98 versus 0.91 and 0.98 versus 1.00; pause, 0.95 versus 1.00 and 1.00 versus 1. 00; premature ventricular contractions, 0.96 versus 0.87 and 1.00 versus 1.00; ventricular tachycardia, 0.97 versus 0.68 and 0.99 versus 1.00; atrioventricular block, 0.93 versus 0.57 and 0.99 versus 1.00). The AI-based analysis was >25% faster than the conventional one (4.4 versus 6.0 minutes; P<0.001). Conclusions These preliminary findings suggest that an AI-based strategy for the analysis of Holter recordings is faster and at least as accurate as a conventional analysis by electrophysiologists.

Keywords: cardiac arrhythmias; diagnosis; electrophysiology.

PubMed Disclaimer

Figures

Figure 1
Figure 1. Study workflow and DNN platform overview. (A) Overview of the study workflow. (B) Screenshot of the DNN‐based platform where arrhythmia categories, heart rhythm plot, and full ECG are used by the physician to validate the analysis.
AI indicates artificial intelligence; and EP indicates electrophysiologist.
Figure 2
Figure 2. Arrhythmia distribution in the dataset and detection performance of the AI‐based and the conventional analysis platforms (A) Arrhythmia prevalence and (B) platform sensitivity and (C) specificity.
Error bars correspond to 95% CI. AF indicates atrial fibrillation; AVB, atrioventricular block; PVC, >10% of premature ventricular contraction; and VT, ventricular tachycardia.
Figure 3
Figure 3. Analysis time.
AI indicates artificial intelligence.
See this image and copyright information in PMC

References

    1. Steinberg JS, Varma N, Cygankiewicz I, Aziz P, Balsam P, Baranchuk A, Cantillon DJ, Dilaveris P, Dubner SJ, El‐Sherif N, et al. 2017 ISHNE‐HRS expert consensus statement on ambulatory ECG and external cardiac monitoring/telemetry. Ann Noninvasive Electrocardiol. 2017;22:e12447. doi: 10.1111/anec.12447 - DOI - PMC - PubMed
    1. Mond HG. The spectrum of ambulatory electrocardiographic monitoring. Heart Lung Circ. 2017;26:1160–1174. doi: 10.1016/j.hlc.2017.02.034 - DOI - PubMed
    1. Johnson KW, Torres Soto J, Glicksberg BS, Shameer K, Miotto R, Ali M, Ashley E, Dudley JT. Artificial intelligence in cardiology. J Am Coll Cardiol. 2018;71:2668–2679. doi: 10.1016/j.jacc.2018.03.521 - DOI - PubMed
    1. Smith SW, Rapin J, Li J, Fleureau Y, Fennell W, Walsh BM, Rosier A, Fiorina L, Gardella C. A deep neural network for 12‐lead electrocardiogram interpretation outperforms a conventional algorithm, and its physician overread, in the diagnosis of atrial fibrillation. Int J Cardiol Heart Vasc. 2019;25:100423. doi: 10.1016/j.ijcha.2019.100423 - DOI - PMC - PubMed
    1. Hannun AY, Rajpurkar P, Haghpanahi M, Tison GH, Bourn C, Turakhia MP, Ng AY. Cardiologist‐level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med. 2019;25:65–69. doi: 10.1038/s41591-018-0268-3 - DOI - PMC - PubMed

Publication types

MeSH terms