Mentor Areas
I am a fellowship-trained cardiovascular radiologist whose research sits at the intersection of radiology, medical artificial intelligence, imaging informatics, and health systems research. My work focuses on how modern AI methods, including large language models (LLMs), vision-language models (VLMs), foundation models, and agentic A!, when combined with data-driven analytics, can be applied to real world radiology workflows to improve quality, efficiency, and patient care.
While much of AI in radiology traditionally focuses on pixel-based analysis, such as detecting abnormalities or performing measurements on medical images, many high impact problems lie beyond the image itself. I am particularly interested in leveraging non-image radiology data, including radiology reports, using natural language processing (NLP) techniques to close the loop on follow-up recommendations, improve communication between members of the care team, increase workflow efficiency, and analyze utilization patterns.
Description:
We maintain several large real-world radiology databases, most derived from clinical and operational data, that support a wide range of research questions. Current and prior projects involve follow-up recommendations, actionable findings communication, workflow optimization, and clinical decision support. These data are well suited for projects in agentic AI, NLP, LLM development, health services research, and applied data science.
Students can work on tasks ranging from data cleaning and exploratory analysis to building LLM-powered pipelines, evaluating AI performance, and studying how AI tools interact with clinical workflows. Most projects can be completed without walking over to the medical campus (although you are always welcome to if you wish).
Where projects support or directly lead to peer-reviewed publications, you will be included as a co-author if you meet the ICMJE requirements (https://www.icmje.org/recommendations/browse/roles-and-responsibilities/defining-the-role-of-authors-and-contributors.html).
Preferred Qualifications
- Experience with or interest in data wrangling using Python, or similar tools
- Any prior experience or relevant course with AI
- Curiosity about AI in medicine, radiology, and healthcare
For AI-Focused Projects
- Python experience is required
- Prior exposure to machine learning, NLP, LLMs, or VLMs is helpful but not required.
- Motivated beginners are welcome.
Details:
Preferred Student Year
First-year, Second-Year, Junior, Senior
Academic Term
Fall, Spring, Summer
I prefer to have students start during the above term(s).Volunteer
Yes
Yes indicates that faculty are open to volunteers.Paid
No
Yes indicates that faculty are open to paying students they engage in their research, regardless of their work-study eligibility.Work Study
No
Yes indicates that faculty are open to hiring work-study-eligible students.