Reconstructing ECG from PPG is a promising yet challenging task. While recent advancements in generative models have significantly improved ECG reconstruction, accurately capturing fine-grained waveform features remains a key challenge. To address this, we propose a novel PPG-to-ECG reconstruction method that leverages a Vision Transformer (ViT) as the core network. Unlike conventional approaches that rely on single-channel PPG, our method employs a four-channel signal image representation, incorporating the original PPG, its first-order di ff erence, second-order di fference, and area under the curve. This multi-channel design enriches feature extraction by preserving both temporal and physiological variations within the PPG. Experimental results demonstrate that our method consistently outperforms existing 1D convolution-based approaches, achieving up to 29% reduction in PRD and 15% reduction in RMSE. The proposed approach also produces improvements in other evaluation metrics, highlighting its robustness and e ff ectiveness in reconstructing ECG signals. Furthermore, to ensure a clinically relevant evaluation, we introduce new performance metrics, including QRS area error, PR interval error, RT interval error, and RT amplitude di fference error. Beyond demonstrating the potential of PPG as a viable alternative for heart activity monitoring, our approach opens new avenues for cyclic signal analysis and prediction. Introduction Electrocardiograms (ECGs) are essential tools for diagnosing and monitoring cardiovascular health, providing crucial insights into heart rate variability (HRV), heart rate, and key waveform features. These include the QRS complex, PR interval, ST segment, TP interval, and QT interval, which are vital for understanding the heart's electrical activity and diagnosing various cardiac conditions [1, 2]. Prolonged PR intervals may indicate first-degree atrioventricular (A V) block or delayed conduction through the A V node, suggesting potential cardiac conduction issues [3]. Conversely, shortened PR intervals might imply conditions such as Wol ff-Parkinson-White (WPW) syndrome or Lown-Ganong-Levine syndrome, where accessory pathways bypass the normal A V nodal delay [3].

This study addresses the challenge of reconstructing unseen ECG signals from PPG signals, a critical task for non-invasive cardiac monitoring. While numerous public ECG-PPG datasets are available, they lack the diversity seen in image datasets, and data collection processes often introduce noise, complicating ECG reconstruction from PPG even with advanced machine learning models. To tackle these challenges, we first introduce a novel synthetic ECG-PPG data generation technique using an ODE model to enhance training diversity. Next, we develop a novel subject-independent PPG-to-ECG reconstruction model that integrates contrastive learning, adversarial learning, and attention gating, achieving results comparable to or even surpassing existing approaches for unseen ECG reconstruction. Finally, we examine factors such as sex and age that impact reconstruction accuracy, emphasizing the importance of considering demographic diversity during model training and dataset augmentation.

This study introduces a deep learning model based on the U-net architecture to reconstruct missing leads in electrocardiograms (ECGs). Using publicly available datasets, the model was trained to regenerate 12-lead ECG data from reduced lead configurations, demonstrating high accuracy in lead reconstruction. The results highlight the ability of the model to quantify the information content of each ECG lead and their inter-lead correlations. This has significant implications for optimizing lead selection in diagnostic scenarios, particularly in settings where full 12-lead ECGs are impractical. Additionally, the study provides insights into the physiological underpinnings of ECG signals and their propagation. The findings pave the way for advancements in telemedicine, portable ECG devices, and personalized cardiac diagnostics by reducing redundancy and enhancing signal interpretation.

We present ConvexECG, an explainable and resource-efficient method for reconstructing six-lead electrocardiograms (ECG) from single-lead data, aimed at advancing personalized and continuous cardiac monitoring. ConvexECG leverages a convex reformulation of a two-layer ReLU neural network, enabling the potential for efficient training and deployment in resource constrained environments, while also having deterministic and explainable behavior. Using data from 25 patients, we demonstrate that ConvexECG achieves accuracy comparable to larger neural networks while significantly reducing computational overhead, highlighting its potential for real-time, low-resource monitoring applications.

Radar-based contactless cardiac monitoring has become a popular research direction recently, but the fine-grained electrocardiogram (ECG) signal is still hard to reconstruct from millimeter-wave radar signal. The key obstacle is to decouple the cardiac activities in the electrical domain (i.e., ECG) from that in the mechanical domain (i.e., heartbeat), and most existing research only uses pure data-driven methods to map such domain transformation as a black box. Therefore, this work first proposes a signal model for domain transformation, and then a novel deep learning framework called radarODE is designed to fuse the temporal and morphological features extracted from radar signals and generate ECG. In addition, ordinary differential equations are embedded in radarODE as a decoder to provide morphological prior, helping the convergence of the model training and improving the robustness under body movements. After being validated on the dataset, the proposed radarODE achieves better performance compared with the benchmark in terms of missed detection rate, root mean square error, Pearson correlation coefficient with the improvement of 9%, 16% and 19%, respectively. The validation results imply that radarODE is capable of recovering ECG signals from radar signals with high fidelity and can be potentially implemented in real-life scenarios.