MSACL 2019 US Abstract

Open Access Data: MIMIC-III, eiCU

Christina Chen
Beth Israel Deaconess Medical Center, Harvard Medical School, MIT

Warning: Undefined variable $headshot in /var/www/html/view_abstract/view_abstract_in_program.php on line 704

Christina Chen (Presenter) Beth Israel Deaconess Medical Center, HMS, MIT

Presenter Bio: Dr. Christina Chen is a practicing physician with board certifications in Internal Medicine and Nephrology. She currently holds a faculty position at Harvard Medical School, practices nephrology at Beth Israel Deaconess Medical Center, and is a Research Scientist at the Laboratory of Computational Physiology at MIT. With her background in engineering and medicine, she is interested in bringing together expertise in medicine and machine learning to improve clinical care.

Relevant Financial Disclosures (within past 24 months) Grant/Research Support MIT-Philips Research Award Discussing Products? NO, presenter will NOT present educational content related to products/services of the ineligible company(ies) listed above. Conflict mitigation NOT REQUIRED.

We will discuss two high-resolution intensive care unit databases: MIMIC-III and eICU. We will highlight the potential that hospital data offers in understanding and improving care and provide examples of how it has been used in literature.

MIMIC-III is an openly available dataset developed by the MIT Lab for Computational Physiology, comprising deidentified health data associated with ~40,000 critical care patients. It includes demographics, vital signs, laboratory tests, medications, and more.

The eICU program is a telehealth system developed by Philips, containing highly detailed data from intensive care patients. The Philips eICU Research Institute (eRI), which maintains the data, has created the eICU Collaborative Research Database populated with data from a combination of many critical care units throughout the continental United States.