Wearable 12-Lead ECG Acquisition Using a Novel Deep Learning Approach from Frank or EASI Leads with Clinical Validation

Fan Fu; Dacheng Zhong; Jiamin Liu; Tianxiang Xu; Qin Shen; Wei Wang; Songsheng Zhu; Jianqing Li

doi:10.3390/bioengineering11030293

Wearable 12-Lead ECG Acquisition Using a Novel Deep Learning Approach from Frank or EASI Leads with Clinical Validation

Bioengineering (Basel). 2024 Mar 21;11(3):293. doi: 10.3390/bioengineering11030293.

Authors

Fan Fu¹, Dacheng Zhong¹, Jiamin Liu¹, Tianxiang Xu¹, Qin Shen², Wei Wang³, Songsheng Zhu¹, Jianqing Li^{4

5}

Affiliations

¹ School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing 211166, China.
² The First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, China.
³ The Jiangsu Engineering Research Center of Province Intelligent Wearable Monitoring and Rehabilitation Device, Nanjing Medical University, Nanjing 211166, China.
⁴ The Engineering Research Center of Intelligent Theranostics Technology and Instruments, Ministry of Education, Nanjing Medical University, Nanjing 211166, China.
⁵ The State Key Laboratory of Bioelectronics, School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China.

Abstract

The 12-lead electrocardiogram (ECG) is crucial in assessing patient decisions. However, portable ECG devices capable of acquiring a complete 12-lead ECG are scarce. For the first time, a deep learning-based method is proposed to reconstruct the 12-lead ECG from Frank leads (V_X, V_Y, and V_Z) or EASI leads (V_ES, V_AS, and V_AI). The innovative ECG reconstruction network called M2Eformer is composed of a 2D-ECGblock and a ProbDecoder module. The 2D-ECGblock module adaptively segments EASI leads into multi-periods based on frequency energy, transforming the 1D time series into a 2D tensor representing within-cycle and between-cycle variations. The ProbDecoder module aims to extract Probsparse self-attention and achieve one-step output for the target leads. Experimental results from comparing recorded and reconstructed 12-lead ECG using Frank leads indicate that M2Eformer outperforms traditional ECG reconstruction methods on a public database. In this study, a self-constructed database (10 healthy individuals + 15 patients) was utilized for the clinical diagnostic validation of ECG reconstructed from EASI leads. Subsequently, both the ECG reconstructed using EASI and the recorded 12-lead ECG were subjected to a double-blind diagnostic experiment conducted by three cardiologists. The overall diagnostic consensus among three cardiology experts, reaching a rate of 96%, indicates the significant utility of EASI-reconstructed 12-lead ECG in facilitating the diagnosis of cardiac conditions.

Keywords: 12-lead ECG reconstruction; EASI lead system; deep neural network; electrocardiogram.

Abstract

Grants and funding