MIMIC-III Big Data Analytics Project
SOCR MIMIC-III Data Analytics (Mortality & Risk Factor Assessment in Heart Failure)
This SOCR GitHub partition includes the end-to-end computational protocol, results, validation and scripts supporting a Big Data discovery study involving the MIMIC-III dataset.
The Medical Information Mart for Intensive Care (MIMIC-III) is a data set developed by the Massachusetts Institute of Technology Lab for Computational Physiology (MIT-LCP) which contains de-identified healthcare data from more than 40,000 intensive care unit (ICU) patients over the years 2001-2012 (Johnson et al., 2016). It includes much of the information typically found in an electronic health record (EHR) including demographic information, diagnosis codes, procedures, lab values, vital signs, free-text clinical notes, and admission, discharge, and mortality information.
- All data used in this study is openly and publicly available from Physionet. Access requires registration and signing of an appropriate data use agreement.
- The utilities directory contains a set of R scripts used to access, process, and visualize data.
- The
data_extraction.Rmdand corresponding HTML files cover the data extraction from the dataset using utilties found in the utilities directory.
Members of the SOCR organization who wish to contribute are encouraged to do so via branch and pull request. Proposed changes will be reviewed during weekly group meetings. See CONTRIBUTING.md for details.
In the spirit of open science and in accordance with the SOCR Licensing, all materials here are CC-BY and LGPL licensed.