ENCASE: an ENsemble ClASsifiEr for ECG Classification Using Expert Features and Deep Neural Networks

Abstract

We propose ENCASE to combine expert features and DNNs (Deep Neural Networks) together for ECG classification. We first explore and implement expert features from statistical area, signal processing area and medical area. Then, we build DNNs to automatically extract deep features. Besides, we propose a new algorithm to find the most representative wave (called centerwave) among long ECG record, and extract features from centerwave. Finally, we combine these features together and put them into ensemble classifiers. Experiment on 4-class ECG data classification reports 0.84 F 1 score, which is much better than any of the single model.

MINA: Multilevel Knowledge-Guided Attention for Modeling Electrocardiography Signals

“…Recently, deep neural networks (DNNs) have been used in ECG diagnosis [Kiranyaz et al, 2016;Rajpurkar et al, 2017;Hannun et al, 2019;Zihlmann et al, 2017;Hong et al, 2017;Schwab et al, 2017]. Many of them have demonstrated stateof-the-art performance due to their ability in extracting effective features [Rajpurkar et al, 2017;Hong et al, 2017].…”

“…Recently, deep neural networks (DNNs) have been used in ECG diagnosis [Kiranyaz et al, 2016;Rajpurkar et al, 2017;Hannun et al, 2019;Zihlmann et al, 2017;Hong et al, 2017;Schwab et al, 2017]. Many of them have demonstrated stateof-the-art performance due to their ability in extracting effective features [Rajpurkar et al, 2017;Hong et al, 2017]. Some of them build an end-to-end classifier [Kiranyaz et al, 2016;Rajpurkar et al, 2017;Zihlmann et al, 2017], others build a mixture model which combines traditional feature engineering methods and deep models [Hong et al, 2017;Schwab et al, 2017;Hong et al, 2019].…”

“…Many of them have demonstrated stateof-the-art performance due to their ability in extracting effective features [Rajpurkar et al, 2017;Hong et al, 2017]. Some of them build an end-to-end classifier [Kiranyaz et al, 2016;Rajpurkar et al, 2017;Zihlmann et al, 2017], others build a mixture model which combines traditional feature engineering methods and deep models [Hong et al, 2017;Schwab et al, 2017;Hong et al, 2019]. However, existing deep models are insufficient in three aspects.…”

“…Convolutional neural networks (CNN) were used to learn beat level patterns [Kiranyaz et al, 2016;Rajpurkar et al, 2017;Hannun et al, 2019]. Recurrent neural networks (RNN) are suitable for capturing rhythm fea-tures [Schwab et al, 2017;Hong et al, 2017;Zihlmann et al, 2017]. Moreover, attention mechanism is employed to extract interpretable rhythm features [Schwab et al, 2017].…”

ECG Arrhythmia Classification Using Transfer Learning from 2- Dimensional Deep CNN Features

“…In independent studies, similar to this work, when the challenge of examining a unique abnormal rhythm is faced, the existence of sufficient amount of training data (containing records of the target rhythm) is vital. The details that need to be examined in an ECG signal are often fine-grained and similar, therefore, have patterns that are hard to detect, even for trained cardiologists [1]. However, the datasets existing in this domain contain a small amount of data or none for many abnormal rhythms.…”