Human-Centered Data Science for Safer Diabetes and Dementia Care
Project Description
Continuous glucose monitoring (CGM) has the potential to transform diabetes care for older adults living with Alzheimer’s disease or related dementias, yet important questions remain about how CGM can be effectively incorporated into patient care byfor patients, care partners, and clinicians. Building on an NIH K01, this project will develop and evaluate human-centered, CGM-enabled care models and interventions designed to improve hypoglycemia awareness, treatment decision-making, and coordination of diabetes care.
The Gilbreth Fellow will have the opportunity to develop an independent research direction examining how CGM can be integrated into real-world clinical care. Potential projects may include developing and analyzing longitudinal CGM measures; identifying patterns of CGM use and clinical risk; designing personalized CGM-based interventions or decision-support approaches; evaluating patient-, care-partner-, and clinician-facing strategies; and testing interventions through clinical trials. The fellow will use R and Python for data management, statistical modeling, visualization, and reproducible analytics, while applying human-centered design, usability evaluation, and mixed-methods approaches as appropriate.
Expected products include a rigorously evaluated intervention, reusable analytic tools, peer-reviewed manuscripts, conference presentations, stakeholder-facing materials, and preliminary evidence for future grant applications. By integrating industrial engineering, human-computer interaction, data science, health informatics, aging research, and clinical medicine, the project will prepare the fellow to lead an independent interdisciplinary research program with meaningful impact on healthcare delivery.
Start Date
Spring/Summer 2027
Postoc Qualifications
Candidates should hold a PhD or equivalent research doctorate in nursing, medicine/clinical research, industrial engineering, human factors, biomedical or health informatics, computer science, data science, biostatistics, epidemiology, public health, implementation science, or a related field. Strong quantitative analytical or programming skills, including proficiency in R and/or Python, are expected. Experience with CGM, diabetes technology, longitudinal health data, clinical trials, or digital health interventions is highly desirable. We welcome applicants from both engineering and health/clinical disciplines. Candidates should demonstrate quantitative research experience, strong scientific writing and communication skills, and an interest in interdisciplinary clinical research. Experience with human-centered design, usability evaluation, mixed methods, or research involving older adults, diabetes, cognitive impairment, or care partners is advantageous.
Co-advisors
Dr. April Savoy, asavoy@purdue.edu, Edwardson School of Industrial Engineering, https://engineering.purdue.edu/IE/people/ptProfile?resource_id=299035
Dr. Zachary Haas, zhaas@purdue.edu, School of Nursing, https://hhs.purdue.edu/directory/zachary-hass/
Bibliography
Savoy, A., Holden, R. J., de Groot, M., Clark, D. O., Sachs, G. A., Klonoff, D., & Weiner, M. (2024). Improving care for people living with dementia and diabetes: applying the human-centered design process to continuous glucose monitoring. Journal of Diabetes Science and Technology, 18(1), 201-206.
Savoy A, Barboi C, Bibat S, Meanwell E, Shah VN, Weiner M. How Continuous Glucose Monitoring Reports Inform Clinical Decision-Making for Older Adults With Type 2 Diabetes: Mapping Clinical Workflow to Situation Awareness. Journal of Diabetes Science and Technology. 2026;0(0). doi:10.1177/19322968261449829
Chao, W. Y., & Hass, Z. (2020, July). Choice-based user interface design of a smart healthy food recommender system for nudging eating behavior of older adult patients with newly diagnosed type ii diabetes. In International Conference on Human-Computer Interaction (pp. 221-234). Cham: Springer International Publishing.
Gonzalez-Canas, C., Pujol, T. A., Griffin, P., & Hass, Z. (2023). A multilevel logistic regression model for identifying the relevance of environmental risk factors on Gestational Diabetes Mellitus. Healthcare Analytics, 3, 100152.
Perone, A. K., Abadir, P. M., Berlinger, N., Carey, J. R., Guest, M. A., Hass, Z. J., ... & Xie, B. (2026). Multidisciplinary perspectives on artificial intelligence in aging research and education: evolving uses, ethics, and equity considerations in gerontology. The Gerontologist, 66(4), gnaf314.