Progress in critical care research relies vitally on the ability to gather, store, search, and analyze “big data” – extremely large data sets that may be analyzed computationally to reveal patterns, trends, and associations. Two teams at the University of Michigan are harnessing these data platforms to accelerate research and solutions in critical care medicine.

The Michigan Center for Integrative Research in Critical Care (MCIRCC) and the Michigan Institute for Data Science (MIDAS) both have missions that focus on fostering multidisciplinary collaborations in order to reach a larger goal. MIDAS was established in 2015 as part of the university-wide Data Science Initiative to promote interdisciplinary collaboration in data science and education. MCIRCC, established in 2014, brings together integrative teams comprised of world-class scientists, clinicians, and engineers to develop and deploy cutting-edge solutions that the elevate the care and outcomes of critically ill and injured patients.

Coupling this collaborative culture with external funding has catalyzed several multidisciplinary research projects between the two teams. For example, in November 2018 a $1.4M grant from the National Science Foundation was awarded to a project led by Dr. Harm Derksen, Professor of Mathematics and member of MCIRCC and MIDAS,  Kayvan Najarian, Professor in Computational Medicine and Bioinformatics and an Associate Director at both MCIRCC and MIDAS,  and Dr. Kevin Ward, Professor of Emergency Medicine, MCIRCC Executive Director, and MIDAS Executive Committee Member. Along with a team of researchers, Najarian, Derksen, and Ward are seeking to design efficient, numerically stable and computationally feasible algorithms for tensor analysis using sepsis as a prime example, but that will also be widely relevant to a wide range big data applications. This project will also be used to develop new interdisciplinary courses on big data for MIDAS.

“The role of data science in healthcare is rapidly growing,” said Dr. Najarian. “No longer an exotic or novel approach, it is quickly becoming another tool in the toolbox for researchers and clinicians, a methodology deployed deliberately to serve a defined research need.”

Drs. Najarian, Derksen, and Ward were also part of the inventing team that developed the Analytic for Hemodynamic Instability (AHI) which was licensed to Fifth Eye, Inc. in 2017 and recently raised $11.5 M in Series A funding. Using analytics from a single streaming EKG lead, AHI can predict if a patient will deteriorate several hours before normal vital signs signal a problem is occurring.

“Projects like these highlight the importance of using data science to help patients by providing insights on the challenges they face and when to take action to meet them,” said Dr. Ward.

In addition to project-specific grants, MCIRCC has an in-house Data Science team that has developed an advanced analytics platform that captures high-fidelity physiological waveform and electronic health record data from over 400 critical care patient beds at the University of Michigan. The platform captures real-time data, performs a certified de-identification process, and stores the de-identified data on the cloud for MCIRCC member research use.