Academic appointment: Adjunct faculty, School of Informatics, Computing, and Engineering, Indiana University
Joined the Institute: 2019
Education and training: PhD and clinical internship, Medical University of South Carolina
Overview/research interests:
I am an interdisciplinary scientists with strong grounding in behavioral and social science, public/population health, and systems science methodologies.
I have three primary research areas of interest:
- Use of modeling and simulation to both understand health and health inequalities, and to support policy and clinical decision making in complex environments (e.g., development of policy simulators)
- Use of network science and artificial intelligence (AI, including machine learning and deep learning) to understand and improve in the biomedical research workforce and the biomedical research enterprise
- Application of systems science and AI to understand and improve healthcare delivery and population health (e.g., use of deep learning on EHR’s to delivery recommendations for personalized medicine)
Current research activities and funding:
- Co-Project Director on a two-year grant awarded by the U.S. Institute for Museum and Library Services (IMLS). The project is building a sustainable, cloud-based research asset and data sharing platform, designed for academic libraries and their researcher patrons while also incubating a vibrant user community.
- Co-Investigator on an NIH R01 grant application led by Dr. Mike Maciosek (PI) of HealthPartners Institute (submitted February 2019). The proposed project will develop a simulation model to explore how state and national tobacco control policies aimed at reducing combustible cigarette use ultimately impact population health and costs. An important aspect of the model is to explore how these policies could affect the use of electronic nicotine delivery devices (aka, electronic cigarettes), potentially conveying additional harms.
- Lead investigator (PI) on an NIH R01 grant application under development for Spring 2019. The proposed project introduces novel analytic framework bridging social network theory, network science, and deep learning to uncover attributes of trajectories that explain success among NIH grantees. The project is designed to detect patterns in the evolution of grant collaboration networks and coauthorship networks that result in “K to R transition”, identifying complex pathways by which those who were successful in competing for an NIH K (Career Award) are able to succeed in obtaining NIH R01 support. The broader impacts of this work lie in the potential to identify targets for early career intervention in service of developing and retaining a fruitful, diverse workforce.
- In the nascent stages of conceiving of a project to develop a system dynamics or hybrid system dynamics/agent-based simulation model to understand colorectal cancer screening uptake. The goal of the project would be to obtain actionable insights about which strategies would most effectively (and affordably) increase colorectal cancer screening participation among the general population and hard-to-reach subpopulations.
Academic appointment: Adjunct faculty, School of Informatics, Computing, and Engineering, Indiana University
Joined the Institute: 2019
Education and training: PhD and clinical internship, Medical University of South Carolina
Overview/research interests:
I am an interdisciplinary scientists with strong grounding in behavioral and social science, public/population health, and systems science methodologies.
I have three primary research areas of interest:
- Use of modeling and simulation to both understand health and health inequalities, and to support policy and clinical decision making in complex environments (e.g., development of policy simulators)
- Use of network science and artificial intelligence (AI, including machine learning and deep learning) to understand and improve in the biomedical research workforce and the biomedical research enterprise
- Application of systems science and AI to understand and improve healthcare delivery and population health (e.g., use of deep learning
