PTB-XL, a large publicly available electrocardiography dataset
PulseAugur coverage of PTB-XL, a large publicly available electrocardiography dataset — every cluster mentioning PTB-XL, a large publicly available electrocardiography dataset across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
Looped vs. Stacked Transformers: ECG Classification Comparison
Researchers have conducted a mechanistic comparison between looped and stacked transformer encoders, focusing on their application to 12-lead ECG classification. The study trained two models, bViT (a recurrent transform…
-
New VAE method aids ECG analysis for myocardial scar diagnosis
Researchers have developed a new method using variational autoencoders (VAEs) to analyze electrocardiogram (ECG) data for the differential diagnosis of myocardial scar. The study evaluated $\beta$-VAE-derived ECG repres…
-
AI models for ECG analysis adopt beat-synchronous tokenization for efficiency
Researchers have developed a beat-synchronous tokenization method for ECG Transformers, a type of AI model used for analyzing electrocardiograms. This new approach aligns tokenization with the physiological structure of…
-
Frequency Selective Neural Networks advance time series learning with physical interpretability
Researchers have introduced the Frequency Selective Neural Network (FSNN), a novel architecture designed to improve time series learning by explicitly incorporating signal processing mathematics. Unlike existing models …
-
ECG lead-channel allocation policies depend on diagnostic evaluators
A new research paper explores the dependency of electrocardiography (ECG) lead-channel allocation policies on the specific diagnostic evaluator used. The study found that policies optimized for one evaluator may not per…
-
New ECG classification framework improves test-time adaptation
Researchers have developed BeatRhythm-TTA, a novel test-time adaptation framework specifically designed for electrocardiogram (ECG) classification. This method addresses the performance degradation of deep learning mode…
-
New Winder method captures cardiac cyclicity with self-supervised learning
Researchers have developed a new self-supervised learning method called Winder, designed to capture the cyclical nature of physiological processes, specifically the cardiac cycle. This method utilizes a phase-equivarian…
-
Study tackles rare cardiac condition detection with imbalanced ECG data
Researchers have conducted a study on the detection of Wolff-Parkinson-White (WPW) syndrome, a rare cardiac condition, using a large dataset of electrocardiography (ECG) recordings. The study aimed to address the signif…
-
New PECS framework improves concept drift detection for cardiovascular AI
Researchers have developed a new framework called PECS to detect concept drift in multimodal physiological signals for cardiovascular AI models. This framework compares changes within the model to measurable changes in …
-
AI models struggle with ECG classification; new methods aim for better accuracy and interpretability · 2 sources tracked
Two new research papers explore the limitations of current AI methods in classifying electrocardiograms (ECGs) and propose novel approaches to improve accuracy and interpretability. The first paper introduces RecursiveE…
-
New LLM framework grounds ECG diagnosis in clinical knowledge
Researchers have developed a novel multimodal LLM framework designed to improve the explainability and trustworthiness of AI-driven cardiac diagnosis using electrocardiograms (ECGs). This new approach anchors report gen…
-
New PEACE framework improves AI transfer learning for pediatric ECG analysis
Researchers have developed a novel framework called PEACE (Pediatric-Adult ECG Alignment via Cross-modal Enhancement) to improve the transfer of adult-trained electrocardiogram (ECG) models to pediatric populations. Thi…
-
New AG-SCL method improves ECG arrhythmia diagnosis for rare conditions
Researchers have developed Angular Gaussian Supervised Contrastive Learning (AG-SCL), a novel framework designed to improve the accuracy of deep learning models in diagnosing long-tailed ECG arrhythmias. This method add…
-
New AI framework digitizes paper ECGs for remote heart attack screening
Researchers have developed ECGLight, a compute-light framework designed to digitize paper electrocardiogram (ECG) printouts and screen for myocardial infarction (MI). This on-device system converts smartphone photos of …
-
Deep learning model reconstructs complete ECGs from incomplete data
Researchers have developed ImputeECG, a deep learning model designed to reconstruct complete 12-lead electrocardiograms (ECGs) from incomplete recordings. This Transformer autoencoder model was trained on datasets like …
-
New AI method improves ECG deployment without raw data retention
Researchers have developed a novel method called \"ours\" for deploying AI models in multi-source Electrocardiogram (ECG) scenarios where raw data from earlier sources cannot be retained. This approach freezes a pretrai…
-
LeNEPA: New Time-Series SSL Method Reduces Reliance on Data Augmentation
Researchers have introduced LeNEPA, a novel self-supervised learning method for time-series data that does not require data augmentation. LeNEPA utilizes a causal backbone and a next-latent-token prediction objective, e…
-
New method calibrates temporal classification by separating representation and decision errors
This paper introduces a novel approach to temporal classification by decomposing errors into representation failures and decision-making issues. The proposed method involves freezing a trained classifier and adding two …
-
New framework improves ECG classification with out-of-distribution data
Researchers have developed SafeECGMatch, a novel semi-supervised learning framework designed for electrocardiogram (ECG) classification. This method addresses the challenge of limited labeled data in clinical settings b…
-
New deep learning model improves ECG analysis for heart conditions
Researchers have developed a new deep learning model called MSAIC-Net to improve the detection of myocardial substrate abnormalities using electrocardiograms (ECGs). This model utilizes multi-scale attention mechanisms …