A new deep learning algorithm of 12-lead electrocardiogram for identifying atrial fibrillation during sinus rhythm

Abstract

Atrial fibrillation (AF) is the most prevalent arrhythmia and is associated with increased morbidity and mortality. Its early detection is challenging because of the low detection yield of conventional methods. We aimed to develop a deep learning-based algorithm to identify AF during normal sinus rhythm (NSR) using 12-lead electrocardiogram (ECG) findings. We developed a new deep neural network to detect subtle differences in paroxysmal AF (PAF) during NSR using digital data from standard 12-lead ECGs. Raw digital data of 2,412 12-lead ECGs were analyzed. The artificial intelligence (AI) model showed that the optimal interval to detect subtle changes in PAF was within 0.24 s before the QRS complex in the 12-lead ECG. We allocated the enrolled ECGs to the training, internal validation, and testing datasets in a 7:1:2 ratio. Regarding AF identification, the AI-based algorithm showed the following values in the internal and external validation datasets: area under the receiver operating characteristic curve, 0.79 and 0.75; recall, 82% and 77%; specificity, 78% and 72%; F1 score, 75% and 74%; and overall accuracy, 72.8% and 71.2%, respectively. The deep learning-based algorithm using 12-lead ECG demonstrated high accuracy for detecting AF during NSR.

EKG-Diagnostik mithilfe künstlicher Intelligenz: aktueller Stand und zukünftige Perspektiven – Teil 1

“…Bei der Arbeit an seinem KI-Projekt ist unser junger Kollege auf neue Studien gestoßen, die zeigen, dass es auch allein anhand eines EKG bei Sinusrhythmus möglich ist, das zukünftige Auftreten von Vorhofflimmern vorherzusagen [ 3 , 5 ]. In diesen Studien wurde KI basierend auf DL eingesetzt (eine Besprechung dieser Arbeiten erfolgt in Teil 2 dieser Übersicht).…”

Clinical significance, challenges and limitations in using artificial intelligence for electrocardiography-based diagnosis

“…The presence of artifacts in ECG images may pose a challenge in the use of convolutional neural network (CNN) in image training. However, the tecent, introduction of recurrent neural networks (RNN) can further minimize potential bias and discriminate AF from normal sinus rhythm [ 25 ]. Consequently, if AI enhanced ECG analysis is implemented and adopted, it may save unnecessary inspection time and costs on follow up diagnostic tests or monitoring devices.…”

Hybrid Detection Model for Meticulous Presaging of Heart Disease using Deep Learning: HDMPHD

“…It achieves accuracy, sensitivity, and specificity 99.02%, 98.76%, and 99.17%, for model VGG-MI1 and VGG-MI2, an accuracy of 99.22%, a sensitivity of 99.15%, and a specificity of 99.49%. Ali Haider et.al [12] proposed an approach using deep learning for single shoot detection in MobileNet v2. It is used to detect cardiovascular disease.…”

“…It has 152 layer models for ImageNet and produces 3.57% top 5 errors. It trains 20 layers for that the training error was low but the test error was high, and this generates overfitting problems [12]. This is for known problems .For the unknown problems, the training error was high and the test error was high.…”