Resources

488 MIMIC-IV cases contain initial vignettes, discharge summaries, test names and diagnoses; 71 test cases are clinician-reviewed. Designed primarily for SDBench, they also support diagnostic benchmarks and clinical information extraction.

This database comprises clinical, transcranial Doppler (TCD), and vital signs monitoring data from adult patients with neurocritical conditions in a neurointensive care unit.

MNE contains clinical information from 300k MIMIC-IV-Note discharge summaries, converted into structured tabular data. All sections of the discharge summaries are covered, including patient history, allergies, medications, pertinent findings, etc.

EHRNote-ChatQA is a benchmark of 967 patient-level multi-turn QA samples over longitudinal MIMIC-IV discharge summaries, with 16,072 medical-expert-verified content questions and evidence-grounding questions.

Note-level stigmatizing language and misgendering annotations for 754 MIMIC-IV-Note discharge summaries, with linked demographic variables and no clinical note text.

De-identified hospital encounter-level data from a cluster-randomized trial testing a nursing-surveillance-based early warning system across 74 hospital units, including outcomes for mortality, length of stay, sepsis, and ICU transfer.

This dataset contains multiparametric physiological waveform recordings obtained from bedside monitors in the surgical intensive care unit (UCIQ) of Hospital Clínic de Barcelona (Spain).

A dataset of questionnaire responses, spectrograms, and other information for pediatric participants collected for the Bridge2AI voice as a biomarker of health project.

A dataset of features from voice recordings and metadata to enable the development, benchmarking, and validation of clinically applicable machine-learning models for diagnosing a wide range of health conditions.

Auricle is a dataset comprising synchronous noninvasive cardiovascular signals collected from 42 healthy subjects and 28 people with lived experience of heart failure.