Please welcome The ISE Department’s own Dr. Osman Ozaltin as he will be presenting his research on ways to use mathematical programming and statistical learning to improve healthcare.
Health systems engineering is concerned with increasing efficiency and improving overall quality of health
care using a variety of data-driven analysis techniques, modeling approaches and solution methodologies in
operations research and systems engineering. This talk will focus on two applications. The first one is about
improving patient safety in radiation therapy (RT) using mathematical programming. RT is used to treat more
than half of the over 1.6 million cancer patients diagnosed annually in the US. Several safety checks and
reviews are performed during treatment planning and delivery to ensure quality and safety in
RT. We propose a mathematical programming approach to optimize the timing and extent of these reviews by
exploring the trade-offs between patient safety and provider workload. The second application is concerned
with the impact of missing and imputed variables on the performance of prediction models used in the
development of sepsis-related severity of illness scoring systems. Patient acuity and disease progression are
frequently captured through the use of severity of illness scoring systems in clinical practice. The development
of these scores is accomplished by statistical analysis of Electronic Health Records (EHR). Many of the models
used to develop severity of illness scoring systems do not specifically consider which clinical variables are
missing and assume that missing data occur at random. However, missing information is ubiquitous in EHR,
and if not handled properly, this may lead to biased results.
Osman Ozaltin is an Assistant Professor in the Edward P. Fitts Department of Industrial and
Systems Engineering, and a member of the Personalized Medicine Faculty Cluster at the North Carolina State
University. He received his PhD degree in Industrial Engineering from the University of Pittsburgh in 2011.
His dissertation received the Pritsker Doctoral Dissertation Award from the Institute of Industrial and Systems
Engineering. His research interests span methodological and computational aspects of mathematical
programming, focusing on applications in public health, personalized medicine and healthcare delivery. He
also develops statistical learning models using massive and heterogeneous electronic health records for better
decision-making in clinical practice. His research is funded by the National Science Foundation, Natural
Sciences and Engineering Research Council of Canada, and Laboratory for Analytic Sciences. Dr. Ozaltin
currently serves as Associate Editor for the IISE Transactions in Operations Engineering and Analytics
focused issue.
