A deep-learning classifier for cardiac arrhythmias

2020/11/11 by Carla Sofia Carvalho, Carvalho, Carla Sofia
Biochemistry, Genetics and Molecular Biology · Computer Science · Physics and Astronomy · #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Medical Physics (physics.med-ph) #Quantitative Methods (q-bio.QM) #cs.LG #physics.med-ph #q-bio.QM

paper · pdf · doi:10.48550/arxiv.2011.05471

To appear in the IEEE BIBE 2020 conference proceedings (peer-reviewed)

arxiv created 2020/11/11 · arxiv updated 2020/11/12

Abstract

We report on a method that classifies heart beats according to a set of 13 classes, including cardiac arrhythmias. The method localises the QRS peak complex to define each heart beat and uses a neural network to infer the patterns characteristic of each heart beat class. The best performing neural network contains six one-dimensional convolutional layers and four dense layers, with the kernel sizes being multiples of the characteristic scale of the problem, thus resulting a computationally fast and physically motivated neural network. For the same number of heart beat classes, our method yields better results with a considerably smaller neural network than previously published methods, which renders our method competitive for deployment in an internet-of-things solution.

Related

• On Arrhythmia Detection by Deep Learning and Multidimensional Representation
• ECG Classification System for Arrhythmia Detection Using Convolutional Neural Networks
• Feature Extraction and Automated Classification of Heartbeats by Machine Learning
• ArrhythmiaVision: Resource-Conscious Deep Learning Models with Visual Explanations for ECG Arrhythmia Classification
• Compact Neural Network Algorithm for Electrocardiogram Classification