# ECG Reconstruction via PPG: A Pilot Study

arXiv: https://arxiv.org/abs/1904.10481 · HTML: https://mlsanity.com/paper/1904.10481/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2019.

## Built on by (most cited first, 6 of 6)

- [Uncertainty-Aware PPG-2-ECG for Enhanced Cardiovascular Diagnosis using Diffusion Models](https://mlsanity.com/paper/2405.11566/) (2024)
- [PPG-to-ECG Signal Translation for Continuous Atrial Fibrillation Detection via Attention-based Deep State-Space Modeling](https://mlsanity.com/paper/2309.15375/) (2023)
- [Your smartphone could act as a pulse-oximeter and as a single-lead ECG](https://mlsanity.com/paper/2305.12583/) (2023)
- [P2E-VQ: ECG-linked representation augmentation for PPG via discrete patch retrieval](https://mlsanity.com/paper/2608.14656/) (2026)
- [HDformer: A Higher Dimensional Transformer for Diabetes Detection Utilizing Long Range Vascular Signals](https://mlsanity.com/paper/2303.11340/) (2023)
- [MD-ViSCo: A Unified Model for Multi-Directional Vital Sign Waveform Conversion](https://mlsanity.com/paper/2506.08357/) (2025)

## Abstract (arXiv)

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.