Actively evaluating and learning the distinctions that matter: Vaccine safety signal detection from emergency triage notes
Preprint
Abstract
The rapid development of COVID-19 vaccines has showcased the global communitys ability to combat infectious diseases. However, the need for post-licensure surveillance systems has grown due to the limited window for safety data collection in clinical trials and early widespread implementation. This study aims to employ Natural Language Processing techniques and Active Learning to rapidly develop a classifier that detects potential vaccine safety issues from emergency department notes. ED triage notes, containing expert, succinct vital patient information at the point of entry to health systems, can significantly contribute to timely vaccine safety signal surveillance. While keyword-based classification can be effective, it may yield false positives and demand extensive keyword modifications. This is exacerbated by the infrequency of vaccination-related ED presentations and their similarity to other reasons for ED visits. NLP offers a more accurate and efficient alternative, albeit requiring annotated data, which is often scarce in the medical field. Active learning optimizes the annotation process and the quality of annotated data, which can result in faster model implementation and improved model performance. This work combines active learning, data augmentation, and active learning and evaluation techniques to create a classifier that is used to enhance vaccine safety surveillance from ED triage notes.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Improving drug safety with adverse event detection using natural language processingExpert Opinion on Drug Safety, 2023
- Data augmentation to improve syndromic detection from emergency department notes2023
- Information systems for vaccine safety surveillanceHuman Vaccines & Immunotherapeutics, 2022
- Emergency nurses’ triage narrative data, their uses and structure: a scoping review protocolBMJ Open, 2022
- Detection of self-harm and suicidal ideation in emergency department triage notesJournal of the American Medical Informatics Association, 2021
- Patients With Acute Myocarditis Following mRNA COVID-19 VaccinationJAMA Cardiology, 2021
- Thrombotic Thrombocytopenia after ChAdOx1 nCov-19 VaccinationNew England Journal of Medicine, 2021
- Using chief complaints for syndromic surveillance: A review of chief complaint based classifiers in North AmericaJournal of Biomedical Informatics, 2013
- Active learning for clinical text classification: is it better than random sampling?Journal of the American Medical Informatics Association, 2012
- Serious adverse events following receipt of trivalent inactivated influenza vaccine in Korea, 2003–2010Vaccine, 2011