In clinical settings, monitoring hemodynamics is crucial for managing patient prognosis, necessitating the integrated analysis of multiple physiological signals. While recent research has analyzed single signals such as electrocardiography (ECG) or photoplethysmography (PPG), there has yet to be a proposal for an approach that encompasses the complex signal analysis required in actual clinical scenarios. In this study, we introduce the SNUPHY-M (Seoul National University hospital PHYsiological signal Masked representation learning) model extracts physiological features reflecting the electrical, pressure, and fluid characteristics of the cardiac cycle in the process of restoring three masked physiological signals based on self-supervised learning (SSL): ECG, PPG, and arterial blood pressure (ABP) signals. By employing multiple physical characteristics, the model can extract more enriched features only using non-invasive signals. We evaluated the model's performance in clinical downstream tasks such as hypotension, stroke volume, systolic blood pressure, diastolic blood pressure, and age prediction. Our results showed that the SNUPHY-M significantly outperformed supervised or SSL models, especially in prediction tasks using non-invasive signals. To the best of our knowledge, SNUPHY-M is the first model to apply multi-modal SSL to cardiovascular analysis involving ECG, PPG, and ABP signals. This approach effectively supports clinical decision-making and enables precise diagnostics, contributing significantly to the early diagnosis and management of hemodynamics without invasiveness.
University of Oxford（牛津大学）；Oxford-Suzhou Centre for Advanced Research（牛津-苏州高级研究中心）
The healthcare industry generates troves of unlabelled physiological data. This data can be exploited via contrastive learning, a self-supervised pre-training method that encourages representations of instances to be similar to one another. We propose a family of contrastive learning methods, CLOCS, that encourages representations across space, time, \textit{and} patients to be similar to one another. We show that CLOCS consistently outperforms the state-of-the-art methods, BYOL and SimCLR, when performing a linear evaluation of, and fine-tuning on, downstream tasks. We also show that CLOCS ac…
Wearable sensors provide abundant physiological time series, yet the principles governing their predictive utility remain unclear. We hypothesize that temporal resolution is a fundamental axis of representation learning, with different clinical and behavioral outcomes relying on structure at distinct scales. To test this resolution hypothesis, we introduce HiMAE (Hierarchical Masked Autoencoder), a self supervised framework that combines masked autoencoding with a hierarchical convolutional encoder decoder. HiMAE produces multi resolution embeddings that enable systematic evaluation of which t…
Cross-View Attention Fusion Net: A Prior-Guided Dual-View Representation Learning for Cardiac Output Estimation from Short-Term PPG Signals
Department of Biomedical Signals and Systems（生物医学信号与系统系）；Department of Cardiovascular and Respiratory Physiology（心血管与呼吸生理学系）；Department of Intensive Care（重症医学系）
Unlocking the diagnostic potential of electrocardiograms through information transfer from cardiac magnetic resonance imaging
School of Computation, Information and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院）；University of Zurich（苏黎世大学）；School of Medicine, Klinikum Rechts der Isar, Technical University of Munich（慕尼黑工业大学雷赫特-伊萨尔医院医学院）；Imperial College London（伦敦帝国学院）；Munich Center for Machine Learning（慕尼黑机器学习中心）
School of Computation, Information and Technology（计算信息学院）；Technical University of Munich（慕尼黑技术大学）；School of Medicine, Klinikum Rechts der Isar（医学院）；Department of Computer Science（计算机科学系）；University of Sheffield（谢菲尔德大学）；Department of Quantitative Biomedicine（定量生物医学系）；University of Zurich（苏黎世大学）；Department of Computing（计算系）；Imperial College London（伦敦帝国理工学院）；Department of Engineering Science（工程科学系）；University of Oxford（牛津大学）
We present CardiacGen, a Deep Learning framework for generating synthetic but physiologically plausible cardiac signals like ECG. Based on the physiology of cardiovascular system function, we propose a modular hierarchical generative model and impose explicit regularizing constraints for training each module using multi-objective loss functions. The model comprises 2 modules, an HRV module focused on producing realistic Heart-Rate-Variability characteristics and a Morphology module focused on generating realistic signal morphologies for different modalities. We empirically show that in additio…
Rochester Institute of Technology（罗切斯特理工学院）；Dalhouse University（达尔豪斯大学）
Noninvasive reconstruction of cardiac transmembrane potential (TMP) from surface electrocardiograms (ECG) involves an ill-posed inverse problem. Model-constrained regularization is powerful for incorporating rich physiological knowledge about spatiotemporal TMP dynamics. These models are controlled by high-dimensional physical parameters which, if fixed, can introduce model errors and reduce the accuracy of TMP reconstruction. Simultaneous adaptation of these parameters during TMP reconstruction, however, is difficult due to their high dimensionality. We introduce a novel model-constrained inf…
Foundation Model for Cardiac Time Series via Masked Latent Attention
Department of Computer Science, ETH Zurich, Switzerland（苏黎世联邦理工学院计算机科学系，瑞士）；Department of Biomedical Engineering, University of Basel, Switzerland（巴塞尔大学生物医学工程系，瑞士）
Ufa State Aviation Technical University（乌法国立航空技术大学）；Bashkir State Pedagogical University（巴什基尔国立师范大学）；Ural Federal University（乌拉尔联邦大学）；Institute of Immunology and Physiology UrB RAS（俄罗斯科学院乌拉尔分院免疫学与生理学研究所）
Machine learning shows great performance in various problems of electrocardiography (ECG) signal analysis. However, collecting a dataset for biomedical engineering is a very difficult task. Any dataset for ECG processing contains from 100 to 10,000 times fewer cases than datasets for image or text analysis. This issue is especially important because of physiological phenomena that can significantly change the morphology of heartbeats in ECG signals. In this preliminary study, we analyze the effects of lead choice from the standard ECG recordings, variation of ECG during 24-hours, and the effec…
Cross-Learning Between ECG and PCG: Exploring Common and Exclusive Characteristics of Bimodal Electromechanical Cardiac Waveforms
School of Medicine, Emory University（埃默里大学医学院）；Rollins School of Public Health, Department of Epidemiology, Emory University（埃默里大学罗林斯公共卫生学院流行病学系）；Department of Biomedical Engineering, Georgia Institute of Technology and Emory University（佐治亚理工学院生物医学工程系）
Goal: To achieve-high quality comprehensive feature extraction from physiological signals that enables precise physiological parameter estimation despite evolving waveform morphologies. Methods: We propose Boosted-SpringDTW, a probabilistic framework that leverages dynamic time warping (DTW) and minimal domain-specific heuristics to simultaneously segment physiological signals and identify fiducial points that represent cardiac events. An automated dynamic template adapts to evolving waveform morphologies. We validate Boosted-SpringDTW performance with a benchmark PPG dataset whose morphologie…
Seoul National University Hospital（首尔国立大学医院）；Seoul National University College of Medicine（首尔国立大学医学院）
Attention mechanisms are widely used to dramatically improve deep learning model performance in various fields. However, their general ability to improve the performance of physiological signal deep learning model is immature. In this study, we experimentally analyze four attention mechanisms (e.g., squeeze-and-excitation, non-local, convolutional block attention module, and multi-head self-attention) and three convolutional neural network (CNN) architectures (e.g., VGG, ResNet, and Inception) for two representative physiological signal prediction tasks: the classification for predicting hypot…
Low-power sensing technologies, such as wearables, have emerged in the healthcare domain since they enable continuous and non-invasive monitoring of physiological signals. In order to endow such devices with clinical value, classical signal processing has encountered numerous challenges. However, data-driven methods, such as machine learning, offer attractive accuracies at the expense of being resource and memory demanding. In this paper, we focus on the inference of neural networks running in microcontrollers and low-power processors which wearable sensors and devices are generally equipped w…
Computational analysis on physiological signals would provide immense impact for enabling automated clinical analytics. However, the class imbalance issue where negative or minority class instances are rare in number impairs the robustness of the practical solution. The key idea of our approach is intelligent augmentation of minority class examples to construct smooth, unbiased decision boundary for robust semi-supervised learning. This solves the practical class imbalance problem in anomaly detection task for computational clinical analytics using physiological signals. We choose two critical…
Electrocardiogram (ECG) signal is an important physiological signal which contains cardiac information and is the basis to diagnosis cardiac related diseases. In this paper, several innovative and efficient methods based on adaptive filter and empirical mode decomposition (EMD) to denoise ECG signal contaminated by various kinds of noise, including baseline wander (BW), power line interference (PLI), electrode motion artifact (EM) and muscle artifact (MA), are proposed. We first present a novel method based on EMD and adaptive filter for the removal of BW and PLI in ECG signal. We then extend …
University of Graz（格拉茨大学）；Medical University of Graz（格拉茨医科大学）；Università della Svizzera italiana（瑞士意大利语区大学）
The field of cardiac electrophysiology tries to abstract, describe and finally model the electrical characteristics of a heartbeat. With recent advances in cardiac electrophysiology, models have become more powerful and descriptive as ever. However, to advance to the field of inverse electrophysiological modeling, i.e. creating models from electrical measurements such as the ECG, the less investigated field of smoothness of the simulated ECGs w.r.t. model parameters need to be further explored. The present paper discusses smoothness in terms of the whole pipeline which describes how from physi…
Probabilistic learning of the Purkinje network from the electrocardiogram
Pontificia Universidad Católica de Chile（智利天主教大学）；Delft University of Technology（代尔夫特理工大学）；Università di Trento（特伦托大学）；Università della Svizzera italiana（瑞士意大利语区大学）
Efficient physiological control of an integrated system architecture for continuous-flow ventricular assist devices: in-silico study
Universidade de São Paulo（圣保罗大学）；Instituto do Coração, Hospital das Clinicas HCFMUSP, Faculdade de Medicina, Universidade de São Paulo（圣保罗大学医学院心脏研究所临床医院）
