Literature DB >> 33816974

A hybrid method for heartbeat classification via convolutional neural networks, multilayer perceptrons and focal loss.

Tao Wang1, Changhua Lu1, Mei Yang2, Feng Hong1, Chun Liu3.   

Abstract

BACKGROUND: Heart arrhythmia, as one of the most important cardiovascular diseases (CVDs), has gained wide attention in the past two decades. The article proposes a hybrid method for heartbeat classification via convolutional neural networks, multilayer perceptrons and focal loss.
METHODS: In the method, a convolution neural network is used to extract the morphological features. The reason behind this is that the morphological characteristics of patients have inter-patient variations, which makes it difficult to accurately describe using traditional hand-craft ways. Then the extracted morphological features are combined with the RR intervals features and input into the multilayer perceptron for heartbeat classification. The RR intervals features contain the dynamic information of the heartbeat. Furthermore, considering that the heartbeat classes are imbalanced and would lead to the poor performance of minority classes, a focal loss is introduced to resolve the problem in the article.
RESULTS: Tested using the MIT-BIH arrhythmia database, our method achieves an overall positive predictive value of 64.68%, sensitivity of 68.55%, f1-score of 66.09%, and accuracy of 96.27%. Compared with existing works, our method significantly improves the performance of heartbeat classification.
CONCLUSIONS: Our method is simple yet effective, which is potentially used for personal automatic heartbeat classification in remote medical monitoring. The source code is provided on https://github.com/JackAndCole/Deep-Neural-Network-For-Heartbeat-Classification.
© 2020 Wang et al.

Entities:  

Keywords:  Arrhythmia; Class imbalance; Convolutional neural network; Focal loss; Heartbeat classification

Year:  2020        PMID: 33816974      PMCID: PMC7924512          DOI: 10.7717/peerj-cs.324

Source DB:  PubMed          Journal:  PeerJ Comput Sci        ISSN: 2376-5992


  13 in total

1.  The impact of the MIT-BIH arrhythmia database.

Authors:  G B Moody; R G Mark
Journal:  IEEE Eng Med Biol Mag       Date:  2001 May-Jun

2.  Automatic classification of heartbeats using ECG morphology and heartbeat interval features.

Authors:  Philip de Chazal; Maria O'Dwyer; Richard B Reilly
Journal:  IEEE Trans Biomed Eng       Date:  2004-07       Impact factor: 4.538

3.  Optimization of ECG classification by means of feature selection.

Authors:  Tanis Mar; Sebastian Zaunseder; Juan Pablo Martínez; Mariano Llamedo; Rüdiger Poll
Journal:  IEEE Trans Biomed Eng       Date:  2011-02-10       Impact factor: 4.538

4.  Heartbeat classification using morphological and dynamic features of ECG signals.

Authors:  Can Ye; B V K Vijaya Kumar; Miguel Tavares Coimbra
Journal:  IEEE Trans Biomed Eng       Date:  2012-08-15       Impact factor: 4.538

5.  Electrocardiogram heartbeat classification based on a deep convolutional neural network and focal loss.

Authors:  Taissir Fekih Romdhane; Haikel Alhichri; Ridha Ouni; Mohamed Atri
Journal:  Comput Biol Med       Date:  2020-07-05       Impact factor: 4.589

6.  The cardiovascular toxicity induced by high doses of gatifloxacin and ciprofloxacin in zebrafish.

Authors:  Rong Shen; Yichang Yu; Rong Lan; Ran Yu; Ze Yuan; Zhining Xia
Journal:  Environ Pollut       Date:  2019-07-09       Impact factor: 8.071

7.  Focal loss of the glutamate transporter EAAT2 in a transgenic rat model of SOD1 mutant-mediated amyotrophic lateral sclerosis (ALS).

Authors:  David S Howland; Jian Liu; Yijin She; Beth Goad; Nicholas J Maragakis; Benjamin Kim; Jamie Erickson; John Kulik; Lisa DeVito; George Psaltis; Louis J DeGennaro; Don W Cleveland; Jeffrey D Rothstein
Journal:  Proc Natl Acad Sci U S A       Date:  2002-01-29       Impact factor: 11.205

8.  Arrhythmia detection using deep convolutional neural network with long duration ECG signals.

Authors:  Özal Yıldırım; Paweł Pławiak; Ru-San Tan; U Rajendra Acharya
Journal:  Comput Biol Med       Date:  2018-09-15       Impact factor: 4.589

9.  Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network.

Authors:  Awni Y Hannun; Pranav Rajpurkar; Masoumeh Haghpanahi; Geoffrey H Tison; Codie Bourn; Mintu P Turakhia; Andrew Y Ng
Journal:  Nat Med       Date:  2019-01-07       Impact factor: 53.440

10.  Inter-Patient ECG Heartbeat Classification with Temporal VCG Optimized by PSO.

Authors:  Gabriel Garcia; Gladston Moreira; David Menotti; Eduardo Luz
Journal:  Sci Rep       Date:  2017-09-05       Impact factor: 4.379

View more
  1 in total

1.  Expression profiling of the Dof gene family under abiotic stresses in spinach.

Authors:  Hongying Yu; Yaying Ma; Yijing Lu; Jingjing Yue; Ray Ming
Journal:  Sci Rep       Date:  2021-07-13       Impact factor: 4.379

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.