R Language

Emergency department (ED) syndromic surveillance relies on a chief complaint, which is often a free-text field, and may contain misspelled words, syntactic errors, and healthcare-specific and/or facility-specific abbreviations. Cleaning of the chief complaint field may improve syndrome capture sensitivity and reduce misclassification of syndromes. We are building a spell-checker, customized with language found in ED corpora, as our first step in cleaning our chief complaint field. This exercise would elucidate the value of pre-processing text and would lend itself to future work using natural language processing (NLP) techniques, such as topic modeling. Such a tool could be extensible to other datasets that contain free-text fields, including electronic reportable disease lab and case reporting.

Objective: To share progress on a custom spell-checker for emergency department chief complaint free-text data and demonstrate a spell-checker validation Shiny application.

Data-driven decision-making is a cornerstone of public health emergency response; therefore, a highly-configurable and rapidly deployable data capture system with built-in quality assurance (QA; e.g., completeness, standardization) is critical. Additionally, to keep key stakeholders informed of developments during an emergency, data need to be shared in a timely and effective manner. Dynamic data visualization is a particularly useful means of sharing data with healthcare providers and the public.2 During Spring 2018, detection of canine influenza H3N2 among dogs in NYC caused concern in the veterinary community. Canine influenza is a highly contagious respiratory infection caused by an influenza A virus.3 However, no central database existed in NYC to monitor the outbreak and no single agency was responsible for data capture. Our team at the NYC Department of Health and Mental Hygiene (DOHMH) partnered with the NYC Veterinary Medical Association (VMA) to monitor the canine influenza H3N2 outbreak by building a web-based reporting platform and interactive dashboard.

Objective: The objectives of this project were to rapidly build and deploy a web-based reporting platform in response to a canine influenza H3N2 outbreak in New York City (NYC) and provide aggregate data back to the veterinary community as an interactive dashboard.