Data Science in Clinical Care (2023-2024)
Clinical decision support (CDS) tools are data science innovations that promise to improve healthcare outcomes. For example, they can predict which patients are at risk of rapid deterioration and alert providers to act. However, these tools have proven difficult to implement in healthcare settings; clinicians may be reluctant to use them due to a lack of transparency about how predictions are made or find it difficult to communicate with the data scientists that develop the tools. As a result, important predictions are often ignored.
While the Food and Drug Administration provides guidance on the technical development of CDS tools, more needs to be done to ensure that they are well-suited for the clinical setting, connecting development and implementation so that the tools achieve their objectives in practice.
This project will develop a formal process to facilitate the adoption of CDS tools in different clinical contexts. Team members will work in interdisciplinary subteams to create case studies of specific clinical settings through participatory systems dynamics modeling. They will take primary responsibility for these case studies and create an online simulator to make the case studies interactive.
Through structured, facilitated sessions, the team will meet with multiple stakeholders involved in every part of the design and implementation process such as data scientists, healthcare providers, health information technology staff and clinicians. Team members will then develop their model for adopting CDS tools from the ground up based on the feedback of these stakeholders.
Case studies to help policymakers and practitioners guide the design and implementation of CDS tools; materials that guide modeling sessions as part of design and implementation efforts; online simulator that can be tuned to a range of specific clinical settings; peer-reviewed publications and conference presentations
Ideally, this project team will include 1 graduate student and 6-9 undergraduate students with technical, organizational and policy backgrounds. Technical backgrounds would include engineering, computer science, statistics, and interdisciplinary engineering and applied science. Organizational backgrounds would include business, sociology, psychology and anthropology. Policy backgrounds would include public policy studies majors and students interested in healthcare.
Students will obtain practical skills for health-policy research, implementing innovations and managing change, including conducting field research using participatory systems dynamics modeling methods; writing case studies; working in cross-disciplinary teams; and communicating lessons learned from field research through publications and presentations.
Graduate students will have the chance to refine those same skills, and additionally learn to teach research methods, guide field-research teams and present findings in professional settings.
This project includes an optional summer component in 2024.
A graduate student may be selected to serve as project manager.
Fall 2023 – Summer 2024
- Fall 2023: Attend weekly in-person meetings; train to facilitate participatory systems dynamics sessions
- Spring 2024: Conduct participatory systems dynamics sessions; write case studies for dissemination; materials for online simulator
- Summer 2024 (optional): Continue supporting simulator refinement and use
Academic credit available for fall and spring semesters; summer funding available
This Team in the News
Image: Yeu-Li Yeung, OT/L, CPE, CSPHP, Patient Care Ergonomics Coordinator, shows a nurse how to operate a total-assist patient lift in a hospital room at Duke Medicine Pavilion's Neuroscience unit, by Jared Lazarus/Duke University
- Scott Rockart, Fuqua School of Business
- Nina Sperber, School of Medicine-Population Health Sciences
/graduate Team Members
Shatanshu Choudhary, Master of Engineering Mgmt-MEG
/undergraduate Team Members
/yfaculty/staff Team Members
Armando Bedoya, Duke University Health System
Sophia Bessias, Ai Health
Lauren Caton, Population Health Sciences
Benjamin Goldstein, School of Medicine-Biostatistics and Bioinformatics
Adam Johnson, School of Medicine-Surgery
/zcommunity Team Members
Gabriel Escobar, Kaiser Permanente (Retired Research Scientist)
Andrew Goodwin, Medical University South Carolina
Lindsey Zimmerman, Office of Mental Health and Suicide Prevention, Veterans Affairs