Discovery Park Undergraduate Research Internship Program

"Detection of hemorrhage for mass casualty application"

About the Project

Project Time & Type:
Summer 2017 - DURI
Research area(s):
Biomedical engineering, Computer science
Project Description:
Hemorrhage is a medical emergency frequently encountered by clinicians in situations as diverse as emergency and operating rooms, intensive care units or mass casualty incidents such as a battle field. A significant amount of blood loss due to hemorrhage can cause hemodynamic instability, inadequate tissue perfusion, hemorrhagic shock, and, if left untreated, eventual death [1]. Hemorrhage is the cause of 40% of deaths after a traumatic injury in the United States [2]. One of the limitations to treating hemorrhage is that vital signs can appear normal until a significant amount of blood has been lost. This delay in vital sign changes is due to the action of the sympathetic and parasympathetic control of blood pressure, which can effectively compensate until blood loss is significant. There is therefore much interest and value in identifying early and sensitive biomarkers of hemorrhage. We developed an algorithm for detection of hemorrhage that identifies change in arterial blood pressure with an animal study. The algorithm performed well with the animal model with strong correlation coefficient with shock index (median correlation coefficient of -0.95 with minimum and maximum of -0.98 and -0.58, respectively) [3]. In this project, we propose to implement the model on humans, with the Medical Information Mart for Intensive Care Unit (MIMIC) [4], which could potentially save lives in a mass casualty situation such as a battle field. [1] G. Gutierrez, H. Reines, and M. E. Wulf-Gutierrez, "Clinical review: hemorrhagic shock," Critical care, vol. 8, p. 373, 2004. [2] D. S. Kauvar, R. Lefering, and C. E. Wade, "Impact of hemorrhage on trauma outcome: an overview of epidemiology, clinical presentations, and therapeutic considerations," Journal of Trauma and Acute Care Surgery, vol. 60, pp. S3-S11, 2006. [3] M. Adibuzzaman, G. C. Kramer, L. Galeotti, S. J. Merrill, D. G. Strauss, and C. G. Scully, "The mixing rate of the arterial blood pressure waveform Markov chain is correlated with shock index during hemorrhage in anesthetized swine," in Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE, 2014, pp. 3268-3271. [4] M. Adibuzzaman, K. Musselman, A. Johnson, P. Brown, Z. Pitluk, and A. Grama, "Closing the Data Loop: An Integrated Open Access Analysis Platform for the MIMIC Database," Computing in Cardiology, 2016.
Expected Student Contributions:
He/or she can implement the algorithm with a human model, and also help write an article regarding the application in humans.
Related Website(s):
Desired Qualifications:
Computer programming in R, Matlab Course works in Calculus, Linear Algebra
Estimated Weekly Hours:
Department awards independent research credits for this project?

Professor in Charge

Griffin, Paul
School of Industrial Engineering

Student Supervisor

Mohammad Adibuzzaman
Assistant Research Scientist

Cooperating Faculty

Mohammad Adibuzzaman
Regenstrief Center for Healthcare Engineering