TY - GEN

T1 - Semi-Supervised Analysis of the Electrocardiogram Using Deep Generative Models

AU - Rasmussen, Soren M.

AU - Jensen, Malte E.K.

AU - Meyhoff, Christian S.

AU - Aasvang, Eske K.

AU - Slrensen, Helge B.D.

N1 - Publisher Copyright: © 2021 IEEE.

PY - 2021

Y1 - 2021

N2 - Deep learning has gained increased impact on medical classification problems in recent years, with models being trained to high performance. However neural networks require large amounts of labeled data, which on medical data can be expensive and cumbersome to obtain. We propose a semi-supervised setup using an unsupervised variational autoencoder combined with a supervised classifier to distinguish between atrial fibrillation and non-atrial fibrillation using ECG records from the MIT-BIH Atrial Fibrillation Database. The proposed model was compared to a fully-supervised convolutional neural network at different proportions of labeled and unlabeled data (1%-50% labeled and the remaining unlabeled). The results demonstrate that the semi-supervised approach was superior to the fully-supervised, from using as little as 5% (5,594 samples) labeled data with an accuracy of 98.7%. The work provides proof of concept and demonstrates that the proposed semisupervised setup can train high accuracy models at low amounts of labeled data.

AB - Deep learning has gained increased impact on medical classification problems in recent years, with models being trained to high performance. However neural networks require large amounts of labeled data, which on medical data can be expensive and cumbersome to obtain. We propose a semi-supervised setup using an unsupervised variational autoencoder combined with a supervised classifier to distinguish between atrial fibrillation and non-atrial fibrillation using ECG records from the MIT-BIH Atrial Fibrillation Database. The proposed model was compared to a fully-supervised convolutional neural network at different proportions of labeled and unlabeled data (1%-50% labeled and the remaining unlabeled). The results demonstrate that the semi-supervised approach was superior to the fully-supervised, from using as little as 5% (5,594 samples) labeled data with an accuracy of 98.7%. The work provides proof of concept and demonstrates that the proposed semisupervised setup can train high accuracy models at low amounts of labeled data.

UR - http://www.scopus.com/inward/record.url?scp=85122502593&partnerID=8YFLogxK

U2 - 10.1109/EMBC46164.2021.9629915

DO - 10.1109/EMBC46164.2021.9629915

M3 - Article in proceedings

C2 - 34891485

AN - SCOPUS:85122502593

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 1124

EP - 1127

BT - 2021 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021

PB - IEEE

T2 - 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021

Y2 - 1 November 2021 through 5 November 2021

ER -