Natural Language Processing to Quantify Microbial Keratitis Measurements

Nenita Maganti; Huan Tan; Leslie M Niziol; Sejal Amin; Andrew Hou; Karandeep Singh; Dena Ballouz; Maria A Woodward

doi:10.1016/j.ophtha.2019.06.003

Natural Language Processing to Quantify Microbial Keratitis Measurements

Ophthalmology. 2019 Dec;126(12):1722-1724. doi: 10.1016/j.ophtha.2019.06.003. Epub 2019 Jun 11.

Authors

Nenita Maganti¹, Huan Tan², Leslie M Niziol³, Sejal Amin⁴, Andrew Hou⁴, Karandeep Singh⁵, Dena Ballouz³, Maria A Woodward⁶

Affiliations

¹ Department of Ophthalmology and Visual Sciences, W. K. Kellogg Eye Center, University of Michigan, Ann Arbor, Michigan; Feinberg School of Medicine, Northwestern University, Chicago, Illinois.
² Department of Ophthalmology and Visual Sciences, W. K. Kellogg Eye Center, University of Michigan, Ann Arbor, Michigan; Department of Applied Statistics, Rackham Graduate School, University of Michigan, Ann Arbor, Michigan.
³ Department of Ophthalmology and Visual Sciences, W. K. Kellogg Eye Center, University of Michigan, Ann Arbor, Michigan.
⁴ Department of Ophthalmology, Henry Ford Health System, Detroit, Michigan.
⁵ Departments of Learning Health Systems and Internal Medicine, University of Michigan, Ann Arbor, Michigan.
⁶ Department of Ophthalmology and Visual Sciences, W. K. Kellogg Eye Center, University of Michigan, Ann Arbor, Michigan; Institute for Healthcare Policy and Innovation, University of Michigan, Ann Arbor, Michigan. Electronic address: mariawoo@umich.edu.

Abstract

A natural language processing (NLP) algorithm to extract microbial keratitis morphology measurements from the electronic health record (EHR) was 75-96% sensitive and 91%-96% specific. NLP accurately extracts data from the corneal exam free-text EHR field.

Publication types

Research Support, N.I.H., Extramural

MeSH terms

Corneal Ulcer / classification
Corneal Ulcer / diagnosis*
Corneal Ulcer / microbiology
Electronic Health Records
Eye Infections, Bacterial / classification
Eye Infections, Bacterial / diagnosis*
Eye Infections, Bacterial / microbiology
Humans
Natural Language Processing*
Reproducibility of Results
Sensitivity and Specificity

Grants and funding

K23 EY023596/EY/NEI NIH HHS/United States