A multi-module algorithm for heartbeat classification based on unsupervised learning and adaptive feature transfer

Yanan Wang; Shuaicong Hu; Jian Liu; Gaoyan Zhong; Cuiwei Yang

doi:10.1016/j.compbiomed.2024.108072

A multi-module algorithm for heartbeat classification based on unsupervised learning and adaptive feature transfer

Comput Biol Med. 2024 Mar:170:108072. doi: 10.1016/j.compbiomed.2024.108072. Epub 2024 Jan 28.

Authors

Yanan Wang¹, Shuaicong Hu², Jian Liu³, Gaoyan Zhong⁴, Cuiwei Yang⁵

Affiliations

¹ Center for Biomedical Engineering, School of Information Science and Technology, Fudan University, Shanghai, 200433, China. Electronic address: wangyn20@fudan.edu.cn.
² Center for Biomedical Engineering, School of Information Science and Technology, Fudan University, Shanghai, 200433, China. Electronic address: schu22@m.fudan.edu.cn.
³ Center for Biomedical Engineering, School of Information Science and Technology, Fudan University, Shanghai, 200433, China. Electronic address: liuj22@m.fudan.edu.cn.
⁴ Center for Biomedical Engineering, School of Information Science and Technology, Fudan University, Shanghai, 200433, China. Electronic address: zhonggaoyan@126.com.
⁵ Center for Biomedical Engineering, School of Information Science and Technology, Fudan University, Shanghai, 200433, China; Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai, 200093, China. Electronic address: yangcw@fudan.edu.cn.

PMID: 38301518
DOI: 10.1016/j.compbiomed.2024.108072

Abstract

The scarcity of annotated data is a common issue in the realm of heartbeat classification based on deep learning. Transfer learning (TL) has emerged as an effective strategy for addressing this issue. However, current TL techniques in this realm overlook the probability distribution differences between the source domain (SD) and target domain (TD) databases. The motivation of this paper is to address the challenge of labeled data scarcity at the model level while exploring an effective method to eliminate domain discrepancy between SD and TD databases, especially when SD and TD are derived from inconsistent tasks. This study proposes a multi-module heartbeat classification algorithm. Initially, unsupervised feature extractors are designed to extract rich features from unlabeled SD and TD data. Subsequently, a novel adaptive transfer method is proposed to effectively eliminate domain discrepancy between features of SD for pre-training (PTF-SD) and features of TD for fine-tuning (FTF-TD). Finally, the adapted PTF-SD is employed to pre-train a designed classifier, and FTF-TD is used for classifier fine-tuning, with the objective of evaluating the algorithm's performance on the TD task. In our experiments, MNIST-DB serves as the SD database for handwritten digit image classification task, MIT-DB as the TD database for heartbeat classification task. The overall accuracy of classifying heartbeats into normal heartbeats, supraventricular ectopic beats (SVEBs), and ventricular ectopic beats (VEBs) reaches 96.7 %. Specifically, the sensitivity (Sen), positive predictive value (PPV), and F1 score for SVEBs are 0.802, 0.701, and 0.748, respectively. For VEBs, Sen, PPV, and F1 score are 0.976, 0.840, and 0.903, respectively. The results indicate that the proposed multi-module algorithm effectively addresses the challenge labeled data scarcity in heartbeat classification through unsupervised learning and adaptive feature transfer methods.

Keywords: Adaptive feature transfer; Annotated data scarcity; Domain discrepancy; Heartbeat classification; Unsupervised learning.

MeSH terms

Algorithms
Electrocardiography / methods
Heart Rate
Humans
Signal Processing, Computer-Assisted
Unsupervised Machine Learning*
Ventricular Premature Complexes*