i3 Scholars: Adayshia Haddock, Sean Jenkins, Akisha Jordan, James McCray, Taylor Neal, Jonathan Velez, Rae-Djamaal Wallace
Research Advisor: Dmitriy Babichenko, School of Computing and Information, University of Pittsburgh
Velez, J., Neal, T., Babichenko, D., Wallace, R.-D., McCray, J., Jenkins, S., Haddock A. & Jordan, A. (2017). In iConference 2017 Proceedings (pp. 803-808). https://doi.org/10.9776/17345
Abstract: This work describes the research and development of semi-automated, user-supervised narrative generation for virtual patient (VP) simulators. We outline the system architecture required of such a system, and propose leveraging data from the health-related content of social networking websites (specifically, Facebook, PatientsLikeMe, and Inspire), in addition to electronic medical record (EMR) datasets. Our research focuses on four key areas as we work toward finalizing our system design: 1) Exploring the utilization of the Open Biomedical Ontologies and other natural language processing tools to facilitate concept identification, synonym generation, and knowledge base construction; 2) Designing templates that structure the presentation of narrative content according to author-selected parameters that serve as queries into the knowledge base; 3) Comparing various user interfaces to best support the author’s interaction with the plot graph and the logical design of narrative cases; 4) Piloting protocol for evaluating the quality of simulation narratives and its influence on simulation fidelity.
Babichenko, Dmitriy and Druzdzel, Marek J and Grieve, Lorin and Patel, Ravi and Velez, Jonathan and Neal, Taylor and McCray, James and Wallace, Rae-Djamaal and Jenkins, Sean. In 2016 IEEE International Conference on Serious Games and Applications for Health (SeGAH). Orlando, Florida.
Abstract: In this paper we describe ModelPatient, a software application developed to allow health sciences educators to create and deliver educational cases that are based on and simulate real patient behavior. ModelPatient uses data from Electronic Medical Record Systems (EMRS) or from publicly available medical data sets in combination with Bayesian network (BN) models to generate virtual patient (VP) cases. Because the underlying models are based on real data, each decision made by a learner affects outcome probabilities. Therefore the behavior of a VP reflects how a real patient with the same medical condition would have reacted to the learners’ actions. We believe that data- and model-driven approaches to creating VPs would allow educators to create higher-fidelity teaching cases and offer richer educational experience to learners.