Skip to main content

Improving Methods of Identifying Anaphylaxis for Medical Product Safety Surveillance Using Natural Language Processing and Machine Learning

    Basic Details

    We sought to determine whether machine learning and natural language processing (NLP) applied to electronic medical records could improve performance of automated healthcare claims-based algorithms to identify anaphylaxis events using data on 516 patients with outpatient, emergency department, or inpatient anaphylaxis diagnosis codes during 2015-2019 in two integrated healthcare institutions in the Northwest United States. We used one site’s manually reviewed gold standard outcomes data for model development and the other’s for external validation based on cross-validated (cv) area under the receiver operating characteristic curve (cv AUC), positive predictive value (PPV), and sensitivity.


    David S Carrell, Susan Gruber, James S Floyd, Maralyssa A Bann, Kara L Cushing-Haugen, Ron L Johnson, Vina Graham, David J Cronkite, Brian L Hazlehurst, Andrew H Felcher, Cosmin A Bejan, Adee Kennedy, Mayura Shinde, Sara Karami, Yong Ma, Danijela Stojanovic, Yueqin Zhao, Robert Ball, Jennifer Nelson

    Corresponding Author

    David S Carrell; Kaiser Permanente Washington Health Research Institute, Seattle, WA