Our lab focuses on developing advanced methods for clinical information extraction, aimed at mining insights from unstructured electronic health record (EHR) data. By leveraging natural language processing (NLP) techniques, we extract critical medical information such as diagnoses, treatments, and patient outcomes from clinical narratives, allowing for more efficient data analysis and enhancing the decision-making processes in healthcare. Our work strives to improve the accuracy and timeliness of clinical insights by automating data extraction from complex medical texts.

Related Work: Kwon et al., 2024, Yao et al., 2023, Yao et al., 2024, Rawat et al., 2023, Yang et al., 2023

Recognizing that health is shaped by more than just biological factors, our lab investigates the social and behavioral determinants of health (SBDH). We explore how factors such as socioeconomic status, education, lifestyle, and community environments influence health outcomes, particularly among vulnerable populations like veterans. By integrating SBDH into our research, we aim to better understand health disparities and develop interventions that address both medical and social dimensions of care, contributing to more equitable health solutions.

[Some paper outcomes]

Our lab is at the forefront of applying large language models (LLMs) in healthcare. These models, which are trained on vast amounts of text data, are capable of understanding and generating human-like language, making them highly valuable in a medical context. We utilize LLMs to enhance clinical decision support, patient communication, and health record analysis. Our research seeks to optimize the use of these models in predicting disease risks, personalizing treatment recommendations, and improving overall patient outcomes by harnessing the power of AI-driven language processing.

[Some paper outcomes]