Resources

We created 23 questions resembling eligibility criteria from the apixaban clinical trial and evaluated them on a random sample of 100 patient notes from MIMIC-IV. We release the 2300 total question-answer pairs as a dataset here.

Dataset consisting of question and answer pairs synthetically generated from medical discharge summaries, designed to facilitate the training and development of large language models specifically tailored for healthcare applications

We propose ReXPref-Prior, an adapted version of MIMIC-CXR where GPT-4 has removed references to prior exams from both findings and impression sections of chest X-ray reports.

A curated subset of MIMIC-IV-ECHO providing apical four-chamber cine loops with manual ROI masks, volumetric labels, and ready-to-use MP4/NPZ derivatives for robust LV volume and ejection fraction research.

EchoNext is a curated dataset of electrocardiograms (ECGs) paired with echocardiogram-confirmed structural heart disease labels, designed to support the development and validation of machine learning models.

In our recent study, we used Llama-3.1-70B-Instruct to generate synthetic training examples resembling clinical trial eligibility criteria. We manually reviewed 1000 of these examples and release them here.

A curated subset of MIMIC-IV-ECHO providing apical four-chamber cine loops with manual ROI masks, volumetric labels, and ready-to-use MP4/NPZ derivatives for robust LV volume and ejection fraction research.

CheXStruct is an automated pipeline that derives structured diagnostic reasoning steps from chest X-rays. CXReasonBench builds on this to evaluate whether models perform clinically grounded, multi-step reasoning beyond final diagnoses.

EchoNext is a curated dataset of electrocardiograms (ECGs) paired with echocardiogram-confirmed structural heart disease labels, designed to support the development and validation of machine learning models.

In our recent study, we used Llama-3.1-70B-Instruct to generate synthetic training examples resembling clinical trial eligibility criteria. We manually reviewed 1000 of these examples and release them here.