8th Association for Computing Machinery Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB-2017)
Materials for the eICU Collaborative Research Database tutorial at ACM-BCB 2017
- Conference program: http://www.acm-bcb.org/2017/downloads/ACM-BCB-2017-Program.pdf
- Title: Introducing the New eICU Collaborative Research Database
- Date: Sunday, 20 August 2017 (8am - 12.30pm)
- Location: Enterprise Room, Boston Marriott, Cambridge, 50 Broadway, Cambridge, MA 02142
T1: Introducing the New eICU Collaborative Research Database
Alistair E. W. Johnson, Tom J. Pollard and Roger G. Mark, Massachusetts Institute of Technology Leo A. Celi, Beth Israel Deaconess Medical Center
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. They are connected to an array of equipment and monitors, and are carefully attended by the clinical staff. Staggering amounts of data are collected daily on each patient in an ICU: multi-channel waveform data 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. Petabytes of data are captured daily during care delivery in the country’s ICUs; however, most of these data are not used to generate evidence or to discover new knowledge.
Critically ill patients are an ideal population for clinical database investigations because the clinical value of many treatments and interventions they receive remains largely unproven, and high-quality data supporting or discouraging specific practices are relatively sparse. The technology now exists to collect, archive and organize finely detailed ICU data, making possible research resources of enormous potential. However, the highly sensitive nature of the data and the need to take necessary protective precautions has created a substantial barrier to access for the research community.
Over the past decade, the Laboratory of Computational Physiology at the Massachusetts Institute of Technology, Beth Israel Deaconess Medical Center (BIDMC) and Philips Healthcare, with support from the National Institute of Biomedical Imaging and Bioinformatics, have partnered to build and maintain the public-access Medical Information Mart for Intensive Care (MIMIC) database. It contains de-identified but comprehensive and highly detailed clinical data from more than 60,000 ICU admissions, and provides unprecedented detail about the pathophysiology and care of ICU patients.
The aim of this tutorial is to introduce a new and even larger publicly available database that we have released this year: the eICU Collaborative Research Database. It contains de-identified detailed information from over 200,000 admissions to intensive care units from many different hospitals around the United States, with representation from 10-12% of US ICU beds. The data were collected during routine clinical care, and will facilitate a number of research studies, including investigating treatment efficacy, providing interpretation of key clinical markers in certain illnesses, inventing new data visualizations to synthesize patient state, building decision support models, and more.
The eICU Collaborative Research Database provides an unparalleled insight into ICU care. Access is made available to legitimate researchers who request it, provided they complete a training course in human subjects research and sign a data use agreement. We anticipate that the worldwide research community will use this unique resource to further human knowledge in the field of critical care.