Please join the ISE Department in welcoming Gian-Gabriel Garcia from the University of Michigan. He will discuss using data-driven decision-making models when it comes to assessing acute concussions.
Concussion, the most common type of traumatic brain injury, is an emerging public health issue. It is characterized by an alteration of neurologic function and wide-ranging symptoms including memory loss and confusion. Furthermore, recent research has begun to shed light on the relationship between concussion and long-term health consequences including cognitive impairment, neurodegenerative disease, increased risk for depression, and early onset dementia. Concussion management plays a critical role in long and short-term health outcomes for those with concussion. A major challenges in concussion management is using large observational data sets to design guidelines for concussion diagnosis decisions. We address this challenge by formulating a data-driven framework which combines predictive modeling and stochastic programming to determine thresholds which can guide diagnosis decisions. In our analytical study, we characterize the optimal solution and show that it can be determined using quantile estimation methods. We then apply our framework to acute concussion assessment and show that it can accurately identify those with and without concussion while limiting misdiagnoses compared to existing clinical approaches. Furthermore, our framework facilitates the identification of key characteristics shared by patients who are the most difficult to diagnose accurately. Finally, we discuss ongoing extensions to this work. The models developed in this research provide valuable insights to clinicians and can be extended to application in other disease areas.
Gian-Gabriel Garcia is a PhD Candidate in the Industrial and Operations Engineering Department at the University of Michigan. He holds a Bachelor’s degree in Industrial Engineering from the University of Pittsburgh and a Master’s degree in Industrial and Operations Engineering from the University of Michigan. His primary research interest is in improving medical decision making through the development and analysis of models which incorporate optimization under uncertainty, stochastic modeling, game theory, and predictive modeling. His most recent work includes applications to concussion, glaucoma, and cardiovascular disease. Gian has been awarded the National Science Foundation Graduate Research Fellowship, the INFORMS Bonder Scholarship for Applied Operations Research in Health Services, the Rackham Merit Fellowship, the SMDM Lee B. Lusted Prize in Quantitative Methods and Theoretical Developments, and first prize at the INFORMS Minority Issues Forum Poster Competition.