Welcome to my Research page!
My work sits at the intersection of artificial intelligence, and biomedical innovation. As a medical student with a background in computer science and a concentration in biomedical informatics, I am passionate about leveraging technology to enhance patient care, optimize medical workflows, and expand access to life-saving treatments.
I focus on creating cutting-edge AI tools for healthcare, and building computational models to unravel complex biological phenomena. My goal is to bridge the gap between technology and medicine, transforming how we approach diagnosis, treatment, and education.
Current Projects
AI in Medical Education
Working with the Office of Medical Education at Brown Medical School, we have integrated AI-Generated Summaries and Anki cards into the Pre-Clinical Curriculum. In doing so, we are hoping to understand more about the role AI has in Medical Education, and how medical schools can optimize for it
LLMs in Guideline Prediction
We are working on several LLMs to generate evidence-based patient-specific guidelines for pre-procedural management
NLP in Interventional Radiology Coding
In collaboration with UCSF’s Big Data in Radiology Lab, I am building natural language processing models to predict CPT codes from post-operative notes. This project streamlines the time-consuming process of medical coding.
Selected Publications
Predicting Survival and Recurrence of Lung Ablation Patients Using Deep Learning-Based Segmentation - CardioVascular and Interventional Radiology
- In collaboration with Dr. Aaron Maxwell from Brown VIR and Dr. Zhicheng Jiao from the Brown Radiology AI Lab, we developed an end-to-end Deep Learning Model for prediction of survival and recurrence after Lung Ablation, using novel 3d-UNets and Radiomics
Using ChatGPT to improve readability of interventional radiology procedure descriptions - CardioVascular and Interventional Radiology
- In collaboration with Dr. Aaron Maxwell and Dr. Sun Ho Ahn from Brown VIR, we showed that ChatGPT can effectively improve readability of IR procedure descriptions, but with a loss in reliability, underscoring the need for human feedback.
The Application of Large Language Models for Radiologic Decision Making - Journal of the American College of Radiology
- Working with Dr. Sun Ho Ahn from Brown VIR, we showed that LLMs can be used to predict appropriate imaging studies from patient presentations using over 1000 clinical scenarios from the ACR Appropriateness Criteria
Innovation Highlights
FibroSense - Finalist at 2025 SIR Medical Student BioDesign Competition
- In collaboration with medical students from Hofstra, UCLA, and Case Western, we developed a LLM to detect if a patient has fibroids that that be effectively treated with Uterine Fibroid Embolization. This would alert the patient, OBGYN, and Interventional Radiologist of the options for the patient, increasing access and bridging healthcare disparities.
Awards
- Medical Student Scholar, SIR 2024
- IO Essentials Scholar, SIO 2024
- Medical Student Grant, RSNA 2023
- Dr. and Mrs. W.C. Culp Medical Student Grant, SIR 2023
- Pipeline Initiative for Enrichment in Radiology (PIER) Scholar, ACR 2023
- Goldwater Scholarship, 2021
- Brown University Undergraduate Teaching and Research Award, 2021
- GE Lloyd Trotter Award, 2021