ABSTRACT
Patients in hospital intensive care units (ICUs) are physiologically fragile and unstable, generally have life-threatening conditions, and require close monitoring and rapid therapeutic interventions. Staggering amounts of data are collected in the ICU daily: multi-channel waveforms sampled hundreds of times each second, vital sign time series updated each second or minute, alarms and alerts, lab results, imaging results, records of medication and fluid administration, staff notes and more. Reducing the barriers to data access has the potential to accelerate knowledge generation and ultimately improve patient care. In this interactive tutorial we introduce the eICU Collaborative Research Database: a large, publicly available database created by the MIT Laboratory for Computational Physiology in partnership with the Philips eICU Research Institute. The database contains routinely collected data from over 200,000 admissions to intensive care units across the United States, with representation from 10-12% of US ICU beds. The data facilitates a breadth of research studies, such as investigations into treatment efficacy, discovery of clinical markers in illnesses, and the development of decision support models. Participants in the tutorial gain an overview of the eICU Collaborative Research Database, in particular being introduced to its structure, content, and limitations. Following this overview, participants explore a demo version of the database using a laptop in a hands-on project. This exercise requires minimal technical expertise and gives an insight into the type of study that can be carried out using the database. We also highlight the growing online community centered around secondary analysis of this data. All tutorial materials are open source and publicly available. The eICU Collaborative Research Database offers an unparalleled insight into ICU care. Access to the database is granted to legitimate researchers who request it, following completion of a training course in human subjects research and acceptance of a data use agreement. We anticipate that the research community will use this unique resource to further human knowledge in the field of critical care.
Index Terms
- Analyzing the eICU Collaborative Research Database
Recommendations
Automated detection of medication administration errors in neonatal intensive care
Display Omitted We developed computerized algorithms to detect medication administration errors.We defined administration error rates for high-risk medications using the algorithms.Compared to incident reporting, the algorithms had better sensitivity ...
Quality and Cost Improvement of Healthcare via Complementary Measurement and Diagnosis of Patient General Health Outcome Using Electronic Health Record Data: Research Rationale and Design
In this evolving `third era of health', one of the US Health Care Reform Act's goals is to effectively facilitate the primary care physician's ability to better diagnose and manage the health outcome of the outpatient. That goal must include research on ...
Identification of Major Adverse Kidney Events Within the Electronic Health Record
AbstractAcute kidney injury is common among critically ill adults and is associated with increased mortality and morbidity. The Major Adverse Kidney Events by 30 days (MAKE30) composite of death, new renal replacement therapy, or persistent renal ...
Comments