electrocardiography
PulseAugur coverage of electrocardiography — every cluster mentioning electrocardiography across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
CogAdapt framework adapts clinical ECG models for wearable cognitive load assessment
Researchers have developed CogAdapt, a framework designed to adapt existing clinical ECG foundation models for use in wearable cognitive load assessment. This is necessary because models trained on clinical data don't d…
-
CardioMix framework improves ECG segmentation with cardiac pattern guidance
Researchers have developed CardioMix, a novel framework for semi-supervised electrocardiogram (ECG) segmentation that addresses the challenge of limited annotated data. This approach utilizes a bidirectional CutMix stra…
-
AI model predicts cardiovascular disease progression using ECG data
Researchers have developed a novel artificial intelligence model designed to predict the progression of cardiovascular disease following a myocardial infarction. This model leverages self-supervised learning on unlabele…
-
New model synthesizes physiological signals with parameter efficiency
Researchers have developed a new parameter-efficient foundation model called Compact Latent Manifold Translation (CLMT) for synthesizing physiological signals. This model addresses challenges like modality and frequency…
-
ECG foundation models benefit from contrastive learning and state space architectures
Researchers have conducted a systematic study on pretraining strategies and scaling for electrocardiography (ECG) foundation models. They evaluated five different self-supervised learning objectives, finding that contra…
-
New CoTAR module centralizes Transformer attention for medical time series analysis
Researchers have developed a new module called CoTAR (Core Token Aggregation-Redistribution) to improve Transformer models for analyzing medical time series data. Unlike standard decentralized attention mechanisms, CoTA…
-
MedMamba and MambaSL advance time series classification with state space models
Researchers have developed MedMamba, a novel architecture based on the Mamba state space model, specifically designed for classifying medical time series data like ECGs and EEGs. This approach addresses limitations of t…
-
New AI model xMAE learns biosignal timing for better health predictions
Researchers have developed a new pretraining framework called xMAE designed to learn meaningful representations from biosignals. This method specifically addresses the temporal dynamics between different biosignals, suc…
-
WARM-VR dataset enables affect recognition in virtual reality
Researchers have introduced WARM-VR, a new dataset for recognizing emotional states within virtual reality environments using wearable sensors. The dataset comprises physiological data from 31 participants, including EC…
-
Sleep data pretraining boosts performance on non-sleep biosignal tasks
Researchers have demonstrated that pretraining models on sleep biosignal data can significantly improve performance on non-sleep related tasks, such as those involving EEG and ECG signals. This approach, which leverages…
-
Deep learning models detect prenatal stress from ECG signals
Researchers have developed a novel method for detecting prenatal stress using self-supervised deep learning on electrocardiography (ECG) data. The system, trained on the FELICITy 1 cohort, demonstrated high accuracy in …
-
ECG foundation models show promise for heart disease screening
Researchers have developed a method for adapting pre-trained electrocardiogram (ECG) foundation models to screen for structural heart disease (SHD). By applying in-domain self-supervised adaptation and selective supervi…