Data Scientist
CurrentI am researching applications of Natural Language Processing (NLP) techniques and Large Language Models (LLMs) to clinical and education domains in the Jamieson Lab of the Lyda Hill Department of Bioinformatics.๐๐ฎ๐ญ๐จ๐ฆ๐๐ญ๐๐ ๐๐๐จ๐ซ๐ข๐ง๐ ๐จ๐ ๐๐ญ๐ฎ๐๐๐ง๐ญ ๐๐จ๐ฌ๐ญ-๐๐ง๐๐จ๐ฎ๐ง๐ญ๐๐ซ ๐๐จ๐ญ๐๐ฌ ๐๐ซ๐จ๐ฆ ๐๐ข๐ฆ๐ฎ๐ฅ๐๐ญ๐๐ ๐๐ง๐๐จ๐ฎ๐ง๐ญ๐๐ซ๐ฌWe developed and evaluated GPT and open-source LLMs as potential 0-shot classifiers within a more extensive automatic grading system. Preliminary findings presented at UTSW's 6th Annual Simulation-Based Quality Improvement and Research Forum (๐ฟ๐๐ฃ๐๐๐๐๐๐๐ ๐ด๐๐ฃ๐๐๐๐๐ ๐๐ ๐ฟ๐๐๐๐ ๐๐๐๐๐๐ ๐ก๐ ๐ด๐๐๐๐๐๐๐๐ก๐ ๐๐๐๐ข๐๐๐ก๐๐๐ ๐๐๐๐๐๐๐๐๐๐๐ ๐ด๐ ๐ ๐๐ ๐ ๐๐๐๐ก ๐ค๐๐กโ ๐น๐๐ค-๐โ๐๐ก ๐๐๐ฅ๐ก๐ข๐๐ ๐ธ๐๐ก๐๐๐๐๐๐๐ก. 2023)๐๐ฎ๐๐ซ๐ข๐๐ฌ ๐ญ๐จ ๐๐ซ๐จ๐ฆ๐ฉ๐ญ๐ฌ: ๐๐ฑ๐ฉ๐๐ซ๐ญ-๐ฅ๐๐ฏ๐๐ฅ ๐๐๐ซ๐๐จ๐ซ๐ฆ๐๐ง๐๐ ๐๐ฌ๐ฌ๐๐ฌ๐ฌ๐ฆ๐๐ง๐ญ ๐๐ง๐ ๐ ๐๐๐๐๐๐๐ค ๐ข๐ง ๐๐๐๐ข๐๐๐ฅ ๐๐๐ฎ๐๐๐ญ๐ข๐จ๐ง ๐ฐ๐ข๐ญ๐ก ๐ ๐จ๐ฎ๐ง๐๐๐ญ๐ข๐จ๐ง ๐๐จ๐๐๐ฅ๐ฌWe are developing enhanced summary feedback reports for medical students after simulated encounters using LLMs to help provide more detailed, actionable suggestions for improvement or reinforcement. Awarded Accelerating Foundation Models Research grant by Microsoft.๐๐ง๐๐๐ซ๐ฌ๐ญ๐๐ง๐๐ข๐ง๐ ๐ญ๐ก๐ ๐๐ฆ๐ฉ๐๐๐ญ ๐จ๐ ๐๐๐๐๐-๐๐ ๐จ๐ง ๐๐จ๐ซ๐ญ๐ก ๐๐๐ฑ๐๐ฌI helped develop the UTSW North Texas COVID-19 Hospital impact model and published several papers on the disease's impact on North Texas.๐ด๐๐ฃ๐๐ ๐๐๐ -๐ด๐โ๐๐๐ก, ๐๐ก ๐๐ ๐๐ก๐๐ญ ๐ญ๐ก๐ ๐๐จ๐ซ๐จ๐ง๐๐ฏ๐ข๐ซ๐ฎ๐ฌ ๐๐ข๐ฌ๐๐๐ฌ๐ ๐๐๐๐ (๐๐๐๐๐-๐๐) ๐๐๐ง๐๐๐ฆ๐ข๐ ๐๐๐ฌ ๐๐๐ข๐ง๐๐จ๐ซ๐๐๐: ๐๐ก๐ ๐๐๐๐ ๐๐จ๐ซ ๐๐๐๐ฎ๐ซ๐๐ญ๐ ๐๐๐ญ๐. Clinical Infectious Diseases. 2021๐๐๐ ๐ก, ๐๐ก ๐๐ ๐ ๐๐ข๐ฅ๐ฏ๐๐ซ ๐๐ข๐ง๐ข๐ง๐ ? ๐ ๐๐ฐ๐๐ซ ๐ง๐จ๐ง-๐๐๐๐-๐๐จ๐-๐ ๐๐๐ฌ๐ฉ๐ข๐ซ๐๐ญ๐จ๐ซ๐ฒ ๐๐ข๐ซ๐ฎ๐ฌ๐๐ฌ ๐๐ฎ๐ซ๐ข๐ง๐ ๐ญ๐ก๐ ๐๐๐๐๐-๐๐ ๐๐๐ง๐๐๐ฆ๐ข๐. J Infectious Diseases. 2021