Using the "Who, What, and When" of free text documentation to improve hospital infectious disease surveillance

Philip Zachariah; Alexandra Hill-Ricciuti; Lisa Saiman; Karthik Natarajan

doi:10.1016/j.ajic.2020.01.001

Using the "Who, What, and When" of free text documentation to improve hospital infectious disease surveillance

Am J Infect Control. 2020 Oct;48(10):1261-1263. doi: 10.1016/j.ajic.2020.01.001. Epub 2020 Feb 15.

Authors

Philip Zachariah¹, Alexandra Hill-Ricciuti², Lisa Saiman³, Karthik Natarajan⁴

Affiliations

¹ Department of Pediatrics, Columbia University Irving Medical Center, New York, NY; Department of Infection Prevention & Control, NewYork-Presbyterian Hospital, New York, NY. Electronic address: [email protected].
² Department of Pediatrics, Columbia University Irving Medical Center, New York, NY.
³ Department of Pediatrics, Columbia University Irving Medical Center, New York, NY; Department of Infection Prevention & Control, NewYork-Presbyterian Hospital, New York, NY.
⁴ Department of Biomedical Informatics, Columbia University Irving Medical Center, New York, NY.

PMID: 32070629
DOI: 10.1016/j.ajic.2020.01.001

Abstract

We demonstrate a novel method of using unstructured health data for infectious disease surveillance. A model incorporating the dynamics of documentation of a test diagnosis (UTI) in free text, without using grammatical or syntactic analysis, achieved performance comparable to ICD-10 codes (sensitivity 57.3, positive predictive value 69.5%, negative predictive value 95.9%) and detected missed cases (15% of total).

Keywords: Detection; Electronic.

Publication types

Research Support, N.I.H., Extramural

MeSH terms

Communicable Diseases* / diagnosis
Communicable Diseases* / epidemiology
Cross Infection* / diagnosis
Cross Infection* / epidemiology
Cross Infection* / prevention & control
Hospitals
Humans
International Classification of Diseases
Predictive Value of Tests

Grants and funding

UL1 TR000040/TR/NCATS NIH HHS/United States