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. The technology now exists to collect, archive and organize finely detailed ICU data, resulting in research resources of enormous potential. Since 2003, our group has been building the Multi-parameter Intelligent Monitoring in Intensive Care II (MIMIC II) Database, which now holds clinical data from about 40,000 entire stays in the ICUs of the Beth Israel Deaconess Medical Center (BIDMC) in Boston, including waveform data (continuous multi-channel recordings of physiologic signals and vital signs) for a subset of these stays. We have meticulously de-identified the data and freely shared them with the research community via the PhysioNet web site. The database is an unparalleled research resource and its value is widely recognized. More than 725 researchers have no-cost access to the clinical data under data use agreements (DUAs). This worldwide community includes academic, clinical, and industrial investigators from more than 32 countries and is growing by over 50% per year. In addition, thousands of investigators, educators, and students have used the waveform data, which we have made freely available to all without restriction. MIMIC II's demonstrated and substantial relevance for research can be enhanced by incorporation of new data, reflecting changes in patient populations, public health challenges, available medications, clinical interventions, and care guidelines, and by development of advanced software to facilitate user access to MIMIC II. Its value can be further enhanced by integration of data from multiple centers. This proposal seeks funding: a) to maintain, enhance, and document the open-source software that we have created to build and update MIMIC II, to incorporate established and emerging standards, and to provide the tools needed to create parallel data collections at other centers; b) to establish the first public, multi-center, international, scalable, continuously updatable, high-resolution data archive for critical care research; and c) to create new knowledge and to develop clinical tools, based on the data archive, to inform and support clinical decisions and practice in critical care.
Enormous amounts of data are routinely collected from patients in hospital intensive care units, but most of these data are not used to generate evidence or to discover new knowledge. This project will collect, organize, and publicly distribute detailed, de-identified, clinical and physiologic data from massive numbers of intensive care patients, and provide software tools to support the user community in exploring and mining the data. The database will catalyze and support a wide variety of biomedical engineering and clinical studies that will result in new understanding and patient-specific prognostic and therapeutic guidance for critical care.
|Stretch, Robert; Della Penna, Nicolás; Celi, Leo A et al. (2018) The authors reply. Crit Care Med 46:e1020-e1021|
|Tyler, Patrick Donnelly; Rush, Barret; Celi, Leo A (2018) The authors reply. Crit Care Med 46:e730-e731|
|Rush, Barret; Stone, David J; Celi, Leo Anthony (2018) From Big Data to Artificial Intelligence: Harnessing Data Routinely Collected in the Process of Care. Crit Care Med 46:345-346|
|Stretch, Robert; Della Penna, Nicolás; Celi, Leo Anthony et al. (2018) Effect of Boarding on Mortality in ICUs. Crit Care Med 46:525-531|
|Rush, Barret; Wiskar, Katie; Celi, Leo Anthony et al. (2018) Association of Household Income Level and In-Hospital Mortality in Patients With Sepsis: A Nationwide Retrospective Cohort Analysis. J Intensive Care Med 33:551-556|
|Lehman, Li-Wei H; Mark, Roger G; Nemati, Shamim (2018) A Model-Based Machine Learning Approach to Probing Autonomic Regulation From Nonstationary Vital-Sign Time Series. IEEE J Biomed Health Inform 22:56-66|
|Piza, Felipe Maia de Toledo; Celi, Leo Anthony; Deliberato, Rodrigo Octavio et al. (2018) Assessing team effectiveness and affective learning in a datathon. Int J Med Inform 112:40-44|
|Rush, Barret; Celi, Leo Anthony; Stone, David J (2018) Applying machine learning to continuously monitored physiological data. J Clin Monit Comput :|
|Deliberato, Rodrigo Octavio; Serpa Neto, Ary; Komorowski, Matthieu et al. (2018) An Evaluation of the Influence of Body Mass Index on Severity Scoring. Crit Care Med :|
|Rush, Barret; Tyler, Patrick D; Stone, David J et al. (2018) Outcomes of Ventilated Patients With Sepsis Who Undergo Interhospital Transfer: A Nationwide Linked Analysis. Crit Care Med 46:e81-e86|
Showing the most recent 10 out of 106 publications