Wenqi Shi

Research Abstract:

The primary goal of precision medicine is to design and optimize the pathway for diagnosis, therapeutic intervention, and prognosis by using large-scale biomedical and clinical data. My research interest mainly focuses on developing cutting-edge precision medicine pipelines using responsible AI to facilitate translational clinical research. Responsible AI is concerned with the development, implementation, and utilization of ethical, transparent, and accountable AI technology with the goal of reducing biases, promoting fairness and equality, and facilitating the interpretability and explainability of outcomes, which is especially important in the healthcare context. I have mainly worked on promoting translational research through responsible AI by: (1) developing multi-site data harmonization and multimodal data integration methods to enable precision medicine; (2) generating explanations for black-box machine learning methods through XAI to facilitate clinical decision-making and action-taking; (3) examining dynamics of bias from observation data and build long-term fair predictive models via online meta-learning to promote healthcare equity; and (4) augmenting foundation models with complementary resources from tools to aid in clinical tasks with complex reasoning and planning. The potential broader impact is to facilitate cutting-edge precision and personalized patient care via responsible AI in translational research, especially for pediatric patients and their families.

Bio:

Wenqi Shi is a Ph.D. candidate at the School of Electrical and Computer Engineering (ECE) in Georgia Institute of Technology, advised by Professor May Dongmei Wang in the Bio-MIBLab Group. Her research interests lie at the intersection of Precision Medicine, Responsible AI, Clinical Informatics, Shared Decision-Making, and Large Language Models. She focuses on developing cutting-edge precision medicine pipelines using responsible AI to facilitate translational clinical research, especially for shared decision-making with pediatric patients and their families. With the ultimate goal of translation research, the impact of her work extends beyond academia; for example, she has collaborated with clinicians from Shriners Children's, CHOA, VA, and Emory Hospital to develop and deploy clinical decision support systems to facilitate real-world clinical research and practice.