Bio

Ashley Stanfield Gamble is a PhD candidate in the Edward P. Fitts Department of Industrial and Systems Engineering at NC State University. Her research focuses on developing simulation models and machine learning tools to support decision-making in health systems and humanitarian logistics.

Her doctoral research explores methods such as machine learning metamodels and generative AI combined with conformal prediction to quantify uncertainty and inform decisions about health policy interventions and the allocation of limited resources. More broadly, her research aims to bridge methodological advances with practical applications in healthcare and humanitarian settings, using systems thinking to address complex challenges and improve people’s lives.

Advisor

Maria Mayorga

Concentration

Health Systems Engineering

Area(s) of Expertise

Stanfield Gamble's research focuses on developing simulation and machine learning methods that make complex health models more accessible and useful for real-world decision-making. Detailed simulation models, such as the NC-CRC model for colorectal cancer screening, can project the health outcomes and costs of different interventions. However, these models are often computationally expensive, limiting the number of scenarios that can be evaluated and the populations to which results can be applied. To address these challenges, Stanfield Gamble developed individual-level metamodels that approximate simulation outcomes in seconds and can be reweighted to represent different target populations. These tools enable clinics and public health agencies to efficiently compare screening strategies and tailor interventions to the populations they serve.

Building on this work, her future research will focus on integrating simulation modeling, machine learning, and uncertainty quantification to address complex challenges in health systems and humanitarian logistics. Her goal is to bridge the gap between advanced quantitative methods and practical decision-making by developing accessible, reliable decision-support tools that help stakeholders evaluate interventions, allocate limited resources, and make informed policy decisions.