A Two-Step Approach to Overcoming Data Imbalance in the Development of an Electrocardiography Data Quality Assessment Algorithm: A Real-World Data Challenge
-
Published:2023-03-13
Issue:1
Volume:8
Page:119
-
ISSN:2313-7673
-
Container-title:Biomimetics
-
language:en
-
Short-container-title:Biomimetics
Author:
Kim Hyun Joo1ORCID, Venkat S. Jayakumar2, Chang Hyoung Woo2ORCID, Cho Yang Hyun3ORCID, Lee Jee Yang2, Koo Kyunghee2
Affiliation:
1. Department of Anesthesiology and Pain Medicine, Anesthesia and Pain Research Institute, Severance Hospital, Yonsei University College of Medicine, Seoul 03722, Republic of Korea 2. Department of Thoracic and Cardiovascular Surgery, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Gyeonggi-do, Seongnam-si 13620, Republic of Korea 3. Department of Thoracic and Cardiovascular Surgery, Samsung Medical Center, Sungkyunkwan University College of Medicine, Seoul 06351, Republic of Korea
Abstract
Continuously acquired biosignals from patient monitors contain significant amounts of unusable data. During the development of a decision support system based on continuously acquired biosignals, we developed machine and deep learning algorithms to automatically classify the quality of ECG data. A total of 31,127 twenty-s ECG segments of 250 Hz were used as the training/validation dataset. Data quality was categorized into three classes: acceptable, unacceptable, and uncertain. In the training/validation dataset, 29,606 segments (95%) were in the acceptable class. Two one-step, three-class approaches and two two-step binary sequential approaches were developed using random forest (RF) and two-dimensional convolutional neural network (2D CNN) classifiers. Four approaches were tested on 9779 test samples from another hospital. On the test dataset, the two-step 2D CNN approach showed the best overall accuracy (0.85), and the one-step, three-class 2D CNN approach showed the worst overall accuracy (0.54). The most important parameter, precision in the acceptable class, was greater than 0.9 for all approaches, but recall in the acceptable class was better for the two-step approaches: one-step (0.77) vs. two-step RF (0.89) and one-step (0.51) vs. two-step 2D CNN (0.94) (p < 0.001 for both comparisons). For the ECG quality classification, where substantial data imbalance exists, the 2-step approaches showed more robust performance than the one-step approach. This algorithm can be used as a preprocessing step in artificial intelligence research using continuously acquired biosignals.
Funder
Ministry of Health and Welfare, Republic of Korea Seoul National University Bundang Hospital Research Fund
Subject
Molecular Medicine,Biomedical Engineering,Biochemistry,Biomaterials,Bioengineering,Biotechnology
Reference31 articles.
1. Noise detection on ECG based on agglomerative clustering of morphological features;Rodrigues;Comput. Biol. Med.,2017 2. Main artifacts in electrocardiography;Ann. Noninvasive Electrocardiol.,2018 3. Clifford, G.D., Azuaje, F., and McSharry, P. (2006). Advanced Methods and Tools for ECG Data Analysis, Artech House. 4. Liu, C., Li, P., Zhao, L., Liu, F., and Wang, R. (2011, January 18–21). Real-time signal quality assessment for ECGs collected using mobile phones. Proceedings of the 2011 Computing in Cardiology, Hangzhou, China. 5. Signal quality indices and data fusion for determining clinical acceptability of electrocardiograms;Clifford;Physiol. Meas.,2012
|
|