Resources

RadGraph is a dataset of entities and relations in full-text chest X-ray radiology reports, which are obtained using a novel information extraction (IE) schema to capture clinically relevant information in a radiology report.

EEG power spectra recorded during anesthesia

This dataset is designed to construct RadVLM, a vision–language model for chest X-ray interpretation. It includes instruction data for tasks such as report generation, abnormality detection, and region grounding, and multitask conversation.

This dataset contains 450K open-ended instruction-following examples generated using GPT-3.5 based on the MIMIC-IV EHR database.

A clinician-labeled dataset for fact-checking long-form clinical text against patient EHRs. The dataset contains LLM-written and human-written Brief Hospital Course summaries decomposed to atomic claim and sentence propositions with annotations.

This dataset includes bounding box-statement pairs for chest X-ray images, derived from radiologists’ eye-tracking data (for explainability) and annotations, for local visual-language models.

Image-based instruct data for Chest X-Ray understanding and analysis.

A suite of classifiers for detecting three types of stigmatizing language in electronic medical records. Trained on MIMIC-IV discharge notes.

A pressure and flow dataset was collected from a trial of 30 adults at the University of Canterbury undergoing CPAP therapy for a variety of instructed breath rates at PEEP levels of 4cmH2O and 7cmH2O.

A dataset for grounded question answering (QA) from electronic health records (EHRs).