Improving the infrastructure for drug overdose surveillance is critical for identifying new threats and responding to emerging trends. This project aimed to develop a prototype tool using principles of natural language processing that has potential to automate the extraction of information about drug overdose deaths from narrative data recorded in the Violent Death Reporting System. A point of intervention opportunity, such as contact with the healthcare system or criminal-legal system, was identified in 46% of case narratives. For most attributes, a rule-based search performed as well or better than deep-learning.
Elise Omaki is a senior research associate in the Department of Health Policy and Management at the Johns Hopkins Bloomberg School of Public Health. She is a core faculty member of the Johns Hopkins Center for Injury Research and Policy where she serves as the Center’s Associate Director for Outreach as well as a research manager, data analyst, and resident epidemiologist. She has over twelve years’ experience conducting injury prevention research and practice including work on road traffic safety, home safety, drug overdose, and violence prevention. Ms. Omaki is committed to seeing research translated to practice, and supporting effective implementation of evidence-based injury prevention interventions. Toward that end, she has worked with teams in the public and non-profit sectors to adapt and execute injury prevention efforts and communicate injury research to diverse audiences. She holds an MHS in Epidemiology from the Johns Hopkins School of Public Health and a BS in Biology from Azusa Pacific University.