# ECG Reconstruction via PPG: A Pilot Study

## TL;DR

This study explores reconstructing ECG signals from PPG signals using a DCT-based transform, demonstrating high accuracy in a diverse subject dataset.

## Contribution

It introduces a novel DCT coefficient mapping method to infer ECG waveforms from PPG signals, addressing the inverse problem.

## Key findings

- Achieves an average correlation of 0.98 in ECG reconstruction
- Effective across subjects with varying age and weight
- Demonstrates high potential for non-invasive cardiac monitoring

## Abstract

In this paper, the relation between electrocardiogram (ECG) and photoplethysmogram (PPG) signals is studied, and the waveform of ECG is inferred via the PPG signals. In order to address this inverse problem, a transform is proposed to map the discrete cosine transform (DCT) coefficients of each PPG cycle to those of the corresponding ECG cycle. The resulting DCT coefficients of the ECG cycle are inversely transformed to obtain the reconstructed ECG waveform. The proposed method is evaluated on a benchmark dataset of subjects with a variety of combinations of age and weight. Experimental results show that the proposed method can achieve a high accuracy at 0.98 in averaged correlation.