83 datasets found

Electronic Health Records (EHRs) dataset used for predictive modeling and feature representation learning

The dataset used in this paper is a diabetic cohort from the same hospital, containing 2,840 diabetic admissions.

The dataset used in this paper is a heart failure cohort from an Australian hospital, containing 1,885 heart failure admissions.

MIMIC-CXR-JPG dataset comprises 227,835 imaging studies conducted on 64,588 patients who sought treatment at the BIDMC Emergency Department from 2011 to 2016.

A large health care system with over 3.2 million 12-lead ECGs

The NFPC dataset is a population-based health survey dataset. This dataset contains detailed personal characteristics of both spouses, which are mainly divided into the...

The dataset used in this study is composed of 1.4 million individuals, with 1.2 billion laboratory test results, covering 47 laboratory-tested human physical components.

The TREC-COVID dataset is a collection of journal articles related to COVID-19 and other coronaviruses, with human annotators providing relevancy judgments at the end of each...

The dataset used in this paper is a healthcare dataset containing information about ICU length of stay for patients who have undergone cardiac surgery.

The dataset is used for training and evaluating the Onco-Retriever model, a generative classifier for retrieval of EHR records in oncology.

The dataset used in the paper is the Breast Cancer Wisconsin (Original) dataset, which contains 699 entries, 9 dimensions, and 2 classes.

The dataset used in the paper is the Pima Indian diabetes dataset, which contains 768 entries, 8 dimensions, and 2 classes.

The Pima Indians Diabetes Database contains samples from females in the Pima Indian population near Phoenix, Arizona.

The dataset used in this paper for healthcare data democratization and information leakage prevention.

Prediction of medical codes from clinical notes is both a practical and essential need for every healthcare delivery organization within current medical systems.

The SUPPORT dataset is a large collection of patient data used for survival analysis. It contains information on demographics, physiological measurements, and outcomes for...

Applications of machine learning in healthcare often require working with time-to-event prediction tasks including prognostication of an adverse event, re-hospitalization, and...

The UK Biobank dataset consists of SAX and LAX cine CMR images of normal subjects. Cardiac structures, LV cavity (LVC), LV myocardium (LVM), and right-ventricle cavity (RVC)...

The Dutch Academic Hospital Dataset is a publicly dataset made available by the Business Process Intelligence (BPI) challenge in 2011 by a hospital in the Netherlands.

A multi-center database for ICU data, from more than 208 hospitals throughout the United States between 2014-2015.