An open access database for evaluating the algorithms of electrocardiogram rhythm and morphology abnormality detection

• Main Authors: Ng, Eddie Yin Kwee, Liu, Feifei, Liu, Chengyu, Zhao, Lina, Zhang, Xiangyu, Wu, Xiaoling, Xu, Xiaoyan, Liu, Yulin, Ma, Caiyun, Wei, Shoushui, He, Zhiqiang, Li, Jianqing
• Other Authors: School of Mechanical and Aerospace Engineering
• Format: Article
• Language: English
• Published: 2019
• Subjects: DRNTU::Engineering::Mechanical engineering; Database; Electrocardiogram
• Online Access: https://hdl.handle.net/10356/81375; http://hdl.handle.net/10220/49067
• Institution: Nanyang Technological University

Over the past few decades, methods for classification and detection of rhythm or morphology abnormalities in ECG signals have been widely studied. However, it lacks the comprehensive performance evaluation on an open database. This paper presents a detailed introduction for the database used for the 1st China Physiological Signal Challenge 2018 (CPSC 2018), which will be run as a special section during the ICBEB 2018. CPSC 2018 aims to encourage the development of algorithms to identify the rhythm/morphology abnormalities from 12-lead ECGs. The data used in CPSC 2018 include one normal ECG type and eight abnormal types. This paper details the data source, recording information, patients' clinical baseline parameters as age, gender and so on. Meanwhile, it also presents the commonly used detection/classification methods for the abovementioned abnormal ECG types. We hope this paper could be a guide reference for the CPSC 2018, to facilitate the researchers familiar with the data and the related research advances.