This one-hour seminar explores the application of natural language processing (NLP) and large language models (LLMs) in identifying people who inject drugs (PWID) within electronic health records. It covers the challenges of accurately extracting relevant information from unstructured text data, such as clinical notes, and discuss advanced NLP techniques for detecting key indicators of PWID. The session also highlights how LLMs can improve the identification process, facilitate data-driven healthcare interventions, and enable more effective targeting of resources for this underserved population.

About the speaker: David Goodman-Meza, MD, PhD, is a Senior Research Associate at the Kirby Institute, UNSW Sydney. He is a physician-scientist specialised in internal medicine, infectious diseases, and addiction medicine. He received his MD with honours from Universidad Autónoma de Baja California in Tijuana, Mexico, and a master's degree in clinical research from the University of California, San Diego, as well as a PhD from UNSW. His research work is focused on the relationship between substance use disorders and infectious diseases using data science, and developing interventions to improve health outcomes in this vulnerable population. He was a recipient of a US National Institutes of Health/National Institute of Drug Abuse Career Development Award, where he trained in the use of natural language processing and machine learning to evaluate outcomes of PWID.