@Article{info:doi/10.2196/36119,
author="Caskey, John
and McConnell, Iain L
and Oguss, Madeline
and Dligach, Dmitriy
and Kulikoff, Rachel
and Grogan, Brittany
and Gibson, Crystal
and Wimmer, Elizabeth
and DeSalvo, Traci E
and Nyakoe-Nyasani, Edwin E
and Churpek, Matthew M
and Afshar, Majid",
title="Identifying COVID-19 Outbreaks From Contact-Tracing Interview Forms for Public Health Departments: Development of a Natural Language Processing Pipeline",
journal="JMIR Public Health Surveill",
year="2022",
month="Mar",
day="8",
volume="8",
number="3",
pages="e36119",
keywords="natural language processing; public health informatics; named entity recognition; contact tracing; COVID-19; outbreaks; neural language model; disease surveillance; digital health; electronic surveillance; public health; digital surveillance tool",
abstract="Background: In Wisconsin, COVID-19 case interview forms contain free-text fields that need to be mined to identify potential outbreaks for targeted policy making. We developed an automated pipeline to ingest the free text into a pretrained neural language model to identify businesses and facilities as outbreaks. Objective: We aimed to examine the precision and recall of our natural language processing pipeline against existing outbreaks and potentially new clusters. Methods: Data on cases of COVID-19 were extracted from the Wisconsin Electronic Disease Surveillance System (WEDSS) for Dane County between July 1, 2020, and June 30, 2021. Features from the case interview forms were fed into a Bidirectional Encoder Representations from Transformers (BERT) model that was fine-tuned for named entity recognition (NER). We also developed a novel location-mapping tool to provide addresses for relevant NER. Precision and recall were measured against manually verified outbreaks and valid addresses in WEDSS. Results: There were 46,798 cases of COVID-19, with 4,183,273 total BERT tokens and 15,051 unique tokens. The recall and precision of the NER tool were 0.67 (95{\%} CI 0.66-0.68) and 0.55 (95{\%} CI 0.54-0.57), respectively. For the location-mapping tool, the recall and precision were 0.93 (95{\%} CI 0.92-0.95) and 0.93 (95{\%} CI 0.92-0.95), respectively. Across monthly intervals, the NER tool identified more potential clusters than were verified in WEDSS. Conclusions: We developed a novel pipeline of tools that identified existing outbreaks and novel clusters with associated addresses. Our pipeline ingests data from a statewide database and may be deployed to assist local health departments for targeted interventions. ",
issn="2369-2960",
doi="10.2196/36119",
url="https://publichealth.jmir.org/2022/3/e36119",
url="https://doi.org/10.2196/36119",
url="http://www.ncbi.nlm.nih.gov/pubmed/35144241"
}