Automatic diagnosis of the 12-lead ECG using a deep neural network

• Published in: Nature communications Vol. 11; no. 1; p. 1760
• Main Authors: Ribeiro, Antônio H., Ribeiro, Manoel Horta, Paixão, Gabriela M. M., Oliveira, Derick M., Gomes, Paulo R., Canazart, Jéssica A., Ferreira, Milton P. S., Andersson, Carl R., Macfarlane, Peter W., Meira Jr, Wagner, Schön, Thomas B., Ribeiro, Antonio Luiz P.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 09.04.2020; Nature Publishing Group; Nature Portfolio
• Subjects: 639/705/1042; 692/4019; 692/700/139/1449; Abnormalities; Adolescent; Adult; Aged; Aged, 80 and over; Artificial neural networks; Atrial Fibrillation - diagnosis; Atrial Fibrillation - physiopathology; Cardiology; Cardiology - methods; Clinical medicine; Deep Learning; Echocardiography; EKG; Electrocardiography; Emergency medical services; Humanities and Social Sciences; Humans; Middle Aged; Model accuracy; multidisciplinary; Neural networks; Neural Networks, Computer; Physicians; Reproducibility of Results; Science; Science (multidisciplinary); Sensitivity and Specificity; Technology; Training; Young Adult
• DOI: 10.1038/s41467-020-15432-4
• ISSN: 2041-1723

The role of automatic electrocardiogram (ECG) analysis in clinical practice is limited by the accuracy of existing models. Deep Neural Networks (DNNs) are models composed of stacked transformations that learn tasks by examples. This technology has recently achieved striking success in a variety of task and there are great expectations on how it might improve clinical practice. Here we present a DNN model trained in a dataset with more than 2 million labeled exams analyzed by the Telehealth Network of Minas Gerais and collected under the scope of the CODE (Clinical Outcomes in Digital Electrocardiology) study. The DNN outperform cardiology resident medical doctors in recognizing 6 types of abnormalities in 12-lead ECG recordings, with F1 scores above 80% and specificity over 99%. These results indicate ECG analysis based on DNNs, previously studied in a single-lead setup, generalizes well to 12-lead exams, taking the technology closer to the standard clinical practice. The role of automatic electrocardiogram (ECG) analysis in clinical practice is limited by the accuracy of existing models. In that context, the authors present a Deep Neural Network (DNN) that recognizes different abnormalities in ECG recordings which matches or outperform cardiology and emergency resident medical doctors.