Graduate mentor's supervisors: Prof. Ana Crissan & Prof. Jian Zhao
Healthcare data can reveal important insights that improve patient care, but analyzing it is challenging. Analysts must explore complex datasets, generate and test hypotheses, and interpret results carefully. While Generative AI can assist by creating code, visualizations, and insights, it does not always understand users' goals and can sometimes produce unreliable results. This project explores how teams of AI agents can collaborate with humans to support healthcare data analysis. We will design new interaction techniques that help people communicate their intent, understand how AI-generated results were produced, and assess whether those results are trustworthy. By making human-AI collaboration more transparent and reliable, this research aims to help healthcare professionals gain insights from data more effectively and make better-informed decisions.
Students will:
- Investigate user needs from literature review and a potential interview study with clinicians, data analysts, and people without technical expertise, to ground the research problem in the real world.
- Develop a web-based, AI-assisted prototype that lets users explore healthcare data through both natural language and direct manipulation (e.g., drag-and-drop). AI agents will help interpret, transform, and explain the data in context.
- (potentially) Conduct a user study to evaluate the user experience and usability of the prototype.
- Students will gain experience in human-computer interaction (HCI), AI-assisted work, and collaborative system design, plus a possible research publication.
We expect students to be self-motivated, have strong programming skills (especially web development and data analysis), and be interested in conducting research at the intersection of HCI and AI.