A cardiologist-like computer-aided interpretation framework to improve arrhythmia diagnosis from imbalanced training datasets

Lianting Hu; Shuai Huang; Huazhang Liu; Yunmei Du; Junfei Zhao; Xiaoting Peng; Dantong Li; Xuanhui Chen; Huan Yang; Lingcong Kong; Jiajie Tang; Xin Li; Heng Liang; Huiying Liang

doi:10.1016/j.patter.2023.100795

A cardiologist-like computer-aided interpretation framework to improve arrhythmia diagnosis from imbalanced training datasets

Patterns (N Y). 2023 Jul 12;4(9):100795. doi: 10.1016/j.patter.2023.100795. eCollection 2023 Sep 8.

Authors

Lianting Hu^{1

2

3}, Shuai Huang^{2

3}, Huazhang Liu^{2

3}, Yunmei Du², Junfei Zhao¹, Xiaoting Peng^{2

3}, Dantong Li^{1

2

3}, Xuanhui Chen^{2

3}, Huan Yang^{1

2

3}, Lingcong Kong^{2

3}, Jiajie Tang⁴, Xin Li⁴, Heng Liang⁵, Huiying Liang^{2

3}

Affiliations

¹ Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Guangzhou, Guangdong 510080, China.
² Medical Big Data Center, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, Guangdong 510080, China.
³ Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Guangzhou, Guangdong 510080, China.
⁴ School of Information Management, Wuhan University, Wuhan, Hubei 430072, China.
⁵ School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, Shaanxi 710049, China.

Abstract

Arrhythmias can pose a significant threat to cardiac health, potentially leading to serious consequences such as stroke, heart failure, cardiac arrest, shock, and sudden death. In computer-aided electrocardiogram interpretation systems, the inclusion of certain classes of arrhythmias, which we term "aggressive" or "bullying," can lead to the underdiagnosis of other "vulnerable" classes. To address this issue, a method for arrhythmia diagnosis is proposed in this study. This method combines morphological-characteristic-based waveform clustering with Bayesian theory, drawing inspiration from the diagnostic reasoning of experienced cardiologists. The proposed method achieved optimal performance in macro-recall and macro-precision through hyperparameter optimization, including spliced heartbeats and clusters. In addition, with increasing bullying by aggressive arrhythmias, our model obtained the highest average recall and the lowest average drop in recall on the nine vulnerable arrhythmias. Furthermore, the maximum cluster characteristics were found to be consistent with established arrhythmia diagnostic criteria, lending interpretability to the proposed method.

Keywords: Bayesian approach; arrhythmia; heartbeat splicing; inter-class bullying; waveform clustering.