The eICU Collaborative Research Database, a freely available multi-center database for critical care research

By Tom J. Pollard, Alistair E. W. Johnson, J. Raffa, Leo Anthony Celi, R. Mark, O. Badawi. 2018

1,838 citations recorded by the source corpus.

Critical care patients are monitored closely through the course of their illness. As a result of this monitoring, large amounts of data are routinely collected for these patients. Philips Healthcare has developed a telehealth system, the eICU Program, which leverages these data to support management of critically ill patients. Here we describe the eICU Collaborative Research Database, a multi-center intensive care unit (ICU)database with high granularity data for over 200,000 admissions to ICUs monitored by eICU Programs across the United States. The database is deidentified, and includes vital sign measurements, care plan documentation, severity of illness measures, diagnosis information, treatment information, and more. Data are publicly available after registration, including completion of a training course in research with human subjects and signing of a data use agreement mandating responsible handling of the data and adhering to the principle of collaborative research. The freely available nature of the data will support a number of applications including the development of machine learning algorithms, decision support tools, and clinical research. Design Type(s) data integration objective • database creation objective Measurement Type(s) Administrative Activity • Clinical Evaluation • Care • Treatment Plan • Vital Signs Measurement Technology Type(s) documenting • performing a clinical assessment • multiparameter monitor Factor Type(s) anthropometric measurement • diagnosis • treatment Sample Characteristic(s) Homo sapiens • United States of America • hospital Design Type(s) data integration objective • database creation objective Measurement Type(s) Administrative Activity • Clinical Evaluation • Care • Treatment Plan • Vital Signs Measurement Technology Type(s) documenting • performing a clinical assessment • multiparameter monitor Factor Type(s) anthropometric measurement • diagnosis • treatment Sample Characteristic(s) Homo sapiens • United States of America • hospital Machine-accessible metadata file describing the reported data (ISA-Tab format)

Subfields: Artificial Intelligence, Epidemiology, Surgery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Epidemiology

In Surgery

Citations in the corpus

Analyzing the role of model uncertainty for electronic health records (2019, methodology): “(1) Medical Information Mart for Intensive Care (MIMIC-III) [15], and (2) eICU Collaborative Research Database (eICU) [25],”
Patient Clustering Improves Efficiency of Federated Machine Learning to predict mortality and hospital stay time using distributed Electronic Medical Records (2019, methodology): “lized clustering together with federated machine learning to make predictions on ICU EMRs. 2. Materials and Methods 2.1. eICU data CBFL was developed based on the eICU collaborative research database [34], which contains highly granular critical care data of 200,859 patients admitted to 208 hospital”
FADL: Federated-Autonomous Deep Learning for Distributed Electronic Health Record (2018, methodology): “The eICU Collaborative Research Database was developed by the by Philips eICU program[18] and populated with data from 208 critical care units throughout the continental United States for patients admitted in 2014 and 2015.”
The shaky foundations of large language models and foundation models for electronic health records (2023, background): “Other public datasets vary greatly in size, from eICU ’ s 139,000 patients 61 to the CPRD ’ s longitudinal records on 7% of all patients in the UK 62 .”
MIMIC-IV, a freely accessible electronic health record dataset (2023, background): “0 comprises of 200,859 stays at ICUs and step-down units across 208 hospitals in the continental United States 4 .”
Federating Recommendations Using Differentially Private Prototypes (2020, methodology): “The second dataset is from the eICU Collaborative Research Database (Pollard et al., 2018), which contains data collected from critical care units throughout the continental United States in 2014 and 2015.”
Feature Robustness in Non-stationary Health Records: Caveats to Deployable Model Performance in Common Clinical Machine Learning Tasks (2019, positive): “Using the recently released multi-source eICU dataset (Pollard et al., 2018), other work has additionally investigated the use of multi-source training data to create models with robust transferability to novel institutions (Johnson et al., 2018).”
Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer (2019, methodology): “To test GCT on real-world EHR records, we use Philips eICU Collaborative Research Dataset5 (Pollard et al. 2018).”
MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports (2019, methodology): “…signing of a data use agreement that stipulates, among other items, that the user will not share the data, will not attempt to re-identify any patients or institutions, and will release code associated with any publication using the data, as is the process for MIMIC-III 21 and eICU-CRD 22 .”
Federated Learning for Healthcare Informatics (2019, methodology): “Mortality Prediction [37] Autoencoder 5-50 eICU Collaborative Research Database [73] Hospitalizations Prediction [9] SVM 5, 10 Boston Medical Center Preterm-birth Prediction [8] RNN 50 Cerner Health Facts”
MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs (2019, methodology): “Due to the sensitivity of this dataset, access will require completion of a training course in human subjects research, as is the process for MIMIC-III [18] and eICU-CRD [19].”