CardioGAN: Attentive Generative Adversarial Network with Dual Discriminators for Synthesis of ECG from PPG

TL;DR

CardioGAN is a novel adversarial network that converts PPG signals into ECG signals, enhancing heart rate measurement accuracy from wearable device data by leveraging attention mechanisms and dual discriminators.

Contribution

This work introduces CardioGAN, the first model combining attention-based generators with dual discriminators for PPG-to-ECG synthesis, improving heart rate estimation accuracy.

Findings

Generated ECG reduces heart rate measurement error from 9.74 to 2.89 bpm.

ECG synthesis improves reliability of heart rate monitoring from PPG signals.

Model outperforms baseline methods in preserving ECG signal integrity.

Abstract

Electrocardiogram (ECG) is the electrical measurement of cardiac activity, whereas Photoplethysmogram (PPG) is the optical measurement of volumetric changes in blood circulation. While both signals are used for heart rate monitoring, from a medical perspective, ECG is more useful as it carries additional cardiac information. Despite many attempts toward incorporating ECG sensing in smartwatches or similar wearable devices for continuous and reliable cardiac monitoring, PPG sensors are the main feasible sensing solution available. In order to tackle this problem, we propose CardioGAN, an adversarial model which takes PPG as input and generates ECG as output. The proposed network utilizes an attention-based generator to learn local salient features, as well as dual discriminators to preserve the integrity of generated data in both time and frequency domains. Our experiments show that the ECG generated by CardioGAN provides more reliable heart rate measurements compared to the original input PPG, reducing the error from 9.74 beats per minute (measured from the PPG) to 2.89 (measured from the generated ECG).