Resources


Database Credentialed Access

Embedding-Based Representations for BRSET and mBRSET

David Restrepo, Chenwei Wu, Michael Morley, et al.

Precomputed image embeddings for the BRSET and mBRSET Brazilian retinal datasets to support efficient, secure, and equitable ophthalmic AI research, enabling tasks such as classification, clustering, multimodal modeling, and fairness analysis.

computer vision ophthalmology vector embeddings

Published: March 30, 2026. Version: 1.0.0

Database Credentialed Access

MIMIC-IV-Ext-CLIF: MIMIC-IV in the Common Longitudinal ICU data Format (CLIF)

Zewei Liao, Shan Guleria, Kevin Smith, et al.

Transforming the MIMIC-IV 3.1 database into the Common Longitudinal ICU data Format (CLIF)

critical care mimic clif the common longitudinal icu data format

Published: March 23, 2026. Version: 1.1.0

Database Open Access

Hillel Yaffe Glaucoma Dataset (HYGD): A Gold-Standard Annotated Fundus Dataset for Glaucoma Detection

Or Abramovich, Hadas Pizem, Jonathan Fhima, et al.

HYGD is a rigorously annotated fundus image dataset with gold-standard clinical labels designed to improve and benchmark deep learning models for accurate glaucoma detection.

ophthalmology retina glaucoma dfi gon fundus gold-standard

Published: March 16, 2026. Version: 1.1.0

Database Credentialed Access

MIMIC-III-Ext-CA: a MIMIC-III Derived Dataset of Cardiac Arrests in Photoplethysmographs

Gerben Hup, Xi Long, Rik Vullings

The MIMIC-III-Ext-CA dataset contains annotations of 31 PPG-captured cardiac arrest episodes from the MIMIC-III clinical and waveform databases.

ppg photoplethysmography mimic-iii cardiac arrest out-of-hospital cardiac arrest ohca

Published: March 10, 2026. Version: 1.0.0

Challenge Credentialed Access

SNOMED CT Entity Linking Challenge

Will Hardman, Mark Banks, Rory Davidson, et al.

272 discharge notes from the MIMIC-IV-Note dataset annotated with SNOMED CT concepts.

snomed entity linking clinical annotation

Published: Feb. 17, 2026. Version: 1.2.1

Database Open Access

tOLIet: Single-lead Thigh-based Electrocardiography Using Polimeric Dry Electrodes

Aline Santos Silva, Hugo Plácido da Silva, Miguel Correia, et al.

We present tOLIet, the first thigh ECG dataset with real signals captured by a toilet seat with electrodes. There are 149 recordings from 86 people, useful for research into cardiovascular assessment using "invisible" ECG.

Published: Feb. 2, 2026. Version: 1.0.1

Database Open Access

Multimodal Synchronized Motion Capture, Force Plate, and Radar Dataset of the One-Legged Stand Test for Fall-Risk Assessment

Daniel Copeland, Evan Linton, Xiang Zhang, et al.

A multimodal dataset of 32 participants performing the One-Legged Stand Test (OLST), with synchronized motion capture, force plate, and 24 GHz radar data. Each of 1,241 trials is labeled with foot-lift, stability phases, and foot-touchdown.

motion capture human pose estimation human movement fall risk assessment non-contact sensing one-legged stand test force plate analysis digital biomarkers human balance testing geriatrics radar signal processing postural control multimodal sensing aging and mobility biomechanics

Published: Jan. 25, 2026. Version: 1.0

Database Contributor Review

InReDD-Dataset-PAN924

Caio Uehara Martins, Camila Tirapelli, Hugo Gaêta-Araujo, et al.

InReDD‑Dataset-V1 is a collection of 924 anonymised panoramic dental radiographs curated by the Interdisciplinary Research Group in Digital Dentistry (InReDD) at the University of São Paulo.

Published: Nov. 22, 2025. Version: 1.0.0

Database Credentialed Access

Predictors of Hospital Onset Infection: A Matched Retrospective Cohort Dataset

Ziming Wei, Luke Sagers, Caroline McKenna, et al.

NPA-CP is a freely accessible dataset derived from electronic health record (EHR) information at MGB between 2015 and 2024. The dataset includes 11 different pathogens and can be used to predict hospital-onset infections for these pathogens.

electronic health records infection control clinical machine learning infectious diseases hospital onset infection colonization pressure

Published: Nov. 4, 2025. Version: 1.0.0

Model Credentialed Access

RadVLM model

Nicolas Deperrois, Hidetoshi Matsuo, Samuel Ruiperez-Campillo, et al.

RadVLM is a 7B-parameter vision-language model fine-tuned on public chest-X-ray data that drafts reports, lists abnormalities, grounds findings, and chats about a CXR through a single image-to-text interface.

Published: Oct. 8, 2025. Version: 1.0.0