Format

Send to

Choose Destination
J Allergy Clin Immunol Pract. 2018 Jan - Feb;6(1):126-131. doi: 10.1016/j.jaip.2017.04.041. Epub 2017 Jun 19.

Natural Language Processing for Asthma Ascertainment in Different Practice Settings.

Author information

1
Department of Pediatric and Adolescent Medicine, Mayo Clinic, Rochester, Minn; Asthma Epidemiology Research Unit, Mayo Clinic, Rochester, Minn.
2
Department of Health Sciences Research, Mayo Clinic, Rochester, Minn.
3
Department of Pediatrics, Sanford Children's Hospital, Sioux Falls, SD.
4
Department of Health Sciences Research, Mayo Clinic, Rochester, Minn. Electronic address: Liu.hongfang@mayo.edu.
5
Department of Pediatric and Adolescent Medicine, Mayo Clinic, Rochester, Minn; Asthma Epidemiology Research Unit, Mayo Clinic, Rochester, Minn. Electronic address: Juhn.young@mayo.edu.

Abstract

BACKGROUND:

We developed and validated NLP-PAC, a natural language processing (NLP) algorithm based on predetermined asthma criteria (PAC) for asthma ascertainment using electronic health records at Mayo Clinic.

OBJECTIVE:

To adapt NLP-PAC in a different health care setting, Sanford Children Hospital, by assessing its external validity.

METHODS:

The study was designed as a retrospective cohort study that used a random sample of 2011-2012 Sanford Birth cohort (n = 595). Manual chart review was performed on the cohort for asthma ascertainment on the basis of the PAC. We then used half of the cohort as a training cohort (n = 298) and the other half as a blind test cohort to evaluate the adapted NLP-PAC algorithm. Association of known asthma-related risk factors with the Sanford-NLP algorithm-driven asthma ascertainment was tested.

RESULTS:

Among the eligible test cohort (n = 297), 160 (53%) were males, 268 (90%) white, and the median age was 2.3 years (range, 1.5-3.1 years). NLP-PAC, after adaptation, and the human abstractor identified 74 (25%) and 72 (24%) subjects, respectively, with 66 subjects identified by both approaches. Sensitivity, specificity, positive predictive value, and negative predictive value for the NLP algorithm in predicting asthma status were 92%, 96%, 89%, and 97%, respectively. The known risk factors for asthma identified by NLP (eg, smoking history) were similar to the ones identified by manual chart review.

CONCLUSIONS:

Successful implementation of NLP-PAC for asthma ascertainment in 2 different practice settings demonstrates the feasibility of automated asthma ascertainment leveraging electronic health record data with a potential to enable large-scale, multisite asthma studies to improve asthma care and research.

KEYWORDS:

Algorithm adaptability; Asthma ascertainment; Electronic health records; Epidemiology; Informatics; Natural language processing; Retrospective study; Validation

PMID:
28634104
PMCID:
PMC5733699
DOI:
10.1016/j.jaip.2017.04.041
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Elsevier Science Icon for PubMed Central
Loading ...
Support Center