Resources


Database Credentialed Access

MIMIC-IV-ECHO: Echocardiogram Matched Subset

Brian Gow, Tom Pollard, Nathaniel Greenbaum, et al.

The MIMIC-IV-ECHO module contains structured measurements from over 200,000 echocardiograms and more than 500,000 echocardiogram DICOM files. Patients overlap with those in the MIMIC-IV Clinical Database.

Published: March 10, 2026. Version: 1.0

Database Credentialed Access

Structured Viewing Classification Annotations From the MIMIC-IV-ECHO Dataset (ECHOVIEW)

Sampath Rapuri, Sofia Sapeta Dias, Maria Salomé Carvalho, et al.

ECHOVIEW provides structured viewing class annotations for 29,196 transthoracic echocardiograms derived from MIMIC-IV-ECHO using a pretrained CNN. Manual clinician review shows substantial agreement (κ=0.69) with these annotations.

Published: March 17, 2026. Version: 0.1

Database Credentialed Access

MIMIC-IV-ECHO-Ext-MIMICEchoQA: A Benchmark Dataset for Echocardiogram-Based Visual Question Answering

Rahul Thapa, Andrew Li, Qingyang Wu, et al.

We present MIMICEchoQA, a benchmark dataset for echocardiogram-based question answering, built from the publicly available MIMIC-IV-ECHO database.

Published: Oct. 7, 2025. Version: 1.0.0

Database Restricted Access

EchoNext: A Dataset for Detecting Echocardiogram-Confirmed Structural Heart Disease from ECGs

Pierre Elias, Joshua Finer

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.

heart failure clinical decision support artificial intelligence health equity ecg machine learning deep learning electrocardiogram aortic stenosis cardiovascular screening valvular heart disease digital health ai model deployment left ventricular dysfunction ai in healthcare population health transthoracic echocardiogram structural heart disease

Published: Sept. 16, 2025. Version: 1.1.0