PhysioNet: a Web-based resource for the study of physiologic signals
PulseAugur coverage of PhysioNet: a Web-based resource for the study of physiologic signals — every cluster mentioning PhysioNet: a Web-based resource for the study of physiologic signals across labs, papers, and developer communities, ranked by signal.
-
AI models show promise for detecting atrial fibrillation in ICU patients
Researchers have developed a new dataset and benchmarks for detecting atrial fibrillation (AF) in intensive care unit (ICU) patients using electrocardiograms (ECGs). The study compared three AI approaches: feature-based…
-
New Relational Hypergraph Transformer Enhances Multi-Table Learning
Researchers have introduced the Relational Hypergraph Transformer (RHT), a novel architecture designed to address the complexities of multi-table learning, particularly in healthcare data. The RHT represents relational …
-
MIT's PhysioNet becomes global standard for biomedical data sharing
PhysioNet, a resource for studying physiological signals, originated from early ECG data digitization efforts at MIT. It has since evolved into a global standard for biomedical data sharing, with over 15,000 datasets ac…
-
RG-Flow Transformer shows interpretability gains on scarce neural data
Researchers have developed an RG-Flow Transformer, a novel architecture designed to handle scarce neural data by incorporating a renormalization-group (RG) inductive bias. This model was tested on sleep stage classifica…
-
New REAN technique balances ECG privacy and utility
Researchers have developed REAN, a novel anonymization technique for electrocardiogram (ECG) data that addresses the long-standing privacy-utility trade-off. REAN utilizes a 1-D U-Net architecture trained with privacy a…
-
New benchmark tests LLMs on multi-turn clinical question answering
Researchers have introduced EHRNote-ChatQA, a novel benchmark designed to evaluate multi-turn clinical question answering over longitudinal patient discharge summaries. This benchmark, derived from de-identified MIMIC-I…
-
New framework enhances EEG channel selection for brain-computer interfaces
Researchers have developed a new multi-objective optimization framework for selecting electroencephalography (EEG) channels in brain-computer interfaces (BCIs). This framework aims to improve motor imagery classificatio…
-
LLMs simplify clinical data access with M3 system
Researchers have developed M3, a system that uses conversational LLMs to simplify access and analysis of complex clinical databases like MIMIC-IV. M3 allows users to query the data using natural language, translating qu…
-
Federated Imputation Framework Tackles Heterogeneous Feature Spaces
Researchers have developed FedHF-Impute, a new framework for federated learning that addresses the challenge of heterogeneous feature spaces. This method allows for more effective imputation of missing data across decen…