AI-based 3-Lead to 12-Lead ECG Reconstruction: Towards Smartphone-based Public Healthcare

TL;DR

This paper explores AI methods for reconstructing 12-lead ECGs from 3-lead signals in smartphone-based healthcare, highlighting the potential of generative models like 1D Pix2Pix GAN to handle population variability.

Contribution

It introduces a novel application of 1D Pix2Pix GAN for ECG reconstruction in shared device settings, addressing variability challenges in public healthcare.

Findings

1D Pix2Pix GAN outperforms LSTM-UNet in ECG reconstruction accuracy.

Generative models show promise for scalable, population-wide ECG analysis.

First study to compare AI models for 3-to-12 lead ECG reconstruction in shared device scenarios.

Abstract

Clinicians generally diagnose cardiovascular diseases (CVDs) using standard 12-Lead electrocardiogram (ECG). However, for smartphone-based public healthcare systems, a reduced 3-lead system may be preferred because of (i) increased portability, and (ii) reduced requirement for power, storage and bandwidth. Subsequently, clinicians require accurate 3-lead to 12-Lead ECG reconstruction, which has so far been studied only in the personalized setting. When each device is dedicated to one individual, artificial intelligence (AI) methods such as temporal long short-term memory (LSTM) and a further improved spatio-temporal LSTM-UNet combine have proven effective. In contrast, in the current smartphone-based public health setting where a common device is shared by many, developing an AI lead-reconstruction model that caters to the extensive ECG signal variability in the general population appears a far greater challenge. In this direction, we take a first step, and observe that the performance improvement achieved by a generative model, specifically, 1D Pix2Pix GAN (generative adversarial network), over LSTM-UNet is encouraging.