Application of a Natural Language Processing Algorithm to Asthma Ascertainment. An Automated Chart Review

Chung Il Wi, Sunghwan Sohn, Mary C. Rolfes, Alicia Seabright, Euijung Ryu, Gretchen Voge, Kay A. Bachman, Miguel Park, Hirohito Kita, Ivana T Croghan, Hongfang D Liu, Young J Juhn

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

RATIONALE: Difficulty of asthma ascertainment and its associated methodologic heterogeneity have created significant barriers to asthma care and research.

OBJECTIVES: We evaluated the validity of an existing natural language processing (NLP) algorithm for asthma criteria to enable an automated chart review using electronic medical records (EMRs).

METHODS: The study was designed as a retrospective birth cohort study using a random sample of 500 subjects from the 1997-2007 Mayo Birth Cohort who were born at Mayo Clinic and enrolled in primary pediatric care at Mayo Clinic Rochester. Performance of NLP-based asthma ascertainment using predetermined asthma criteria was assessed by determining both criterion validity (chart review of EMRs by abstractor as a gold standard) and construct validity (association with known risk factors for asthma, such as allergic rhinitis).

MEASUREMENTS AND MAIN RESULTS: After excluding three subjects whose respiratory symptoms could be attributed to other conditions (e.g., tracheomalacia), among the remaining eligible 497 subjects, 51% were male, 77% white persons, and the median age at last follow-up date was 11.5 years. The asthma prevalence was 31% in the study cohort. Sensitivity, specificity, positive predictive value, and negative predictive value for NLP algorithm in predicting asthma status were 97%, 95%, 90%, and 98%, respectively. The risk factors for asthma (e.g., allergic rhinitis) that were identified either by NLP or the abstractor were the same.

CONCLUSIONS: Asthma ascertainment through NLP should be considered in the era of EMRs because it can enable large-scale clinical studies in a more time-efficient manner and improve the recognition and care of childhood asthma in practice.

Original languageEnglish (US)
Pages (from-to)430-437
Number of pages8
JournalAmerican Journal of Respiratory and Critical Care Medicine
Volume196
Issue number4
DOIs
StatePublished - Aug 15 2017

Fingerprint

Natural Language Processing
Asthma
Electronic Health Records
Cohort Studies
Tracheomalacia
Parturition
Primary Health Care

Keywords

  • electronic medical records
  • informatics
  • retrospective study

ASJC Scopus subject areas

  • Medicine(all)
  • Pulmonary and Respiratory Medicine
  • Critical Care and Intensive Care Medicine

Cite this

Application of a Natural Language Processing Algorithm to Asthma Ascertainment. An Automated Chart Review. / Wi, Chung Il; Sohn, Sunghwan; Rolfes, Mary C.; Seabright, Alicia; Ryu, Euijung; Voge, Gretchen; Bachman, Kay A.; Park, Miguel; Kita, Hirohito; Croghan, Ivana T; Liu, Hongfang D; Juhn, Young J.

In: American Journal of Respiratory and Critical Care Medicine, Vol. 196, No. 4, 15.08.2017, p. 430-437.

Research output: Contribution to journalArticle

@article{77b242a79f62491b887c487f01b658ea,
title = "Application of a Natural Language Processing Algorithm to Asthma Ascertainment. An Automated Chart Review",
abstract = "RATIONALE: Difficulty of asthma ascertainment and its associated methodologic heterogeneity have created significant barriers to asthma care and research.OBJECTIVES: We evaluated the validity of an existing natural language processing (NLP) algorithm for asthma criteria to enable an automated chart review using electronic medical records (EMRs).METHODS: The study was designed as a retrospective birth cohort study using a random sample of 500 subjects from the 1997-2007 Mayo Birth Cohort who were born at Mayo Clinic and enrolled in primary pediatric care at Mayo Clinic Rochester. Performance of NLP-based asthma ascertainment using predetermined asthma criteria was assessed by determining both criterion validity (chart review of EMRs by abstractor as a gold standard) and construct validity (association with known risk factors for asthma, such as allergic rhinitis).MEASUREMENTS AND MAIN RESULTS: After excluding three subjects whose respiratory symptoms could be attributed to other conditions (e.g., tracheomalacia), among the remaining eligible 497 subjects, 51{\%} were male, 77{\%} white persons, and the median age at last follow-up date was 11.5 years. The asthma prevalence was 31{\%} in the study cohort. Sensitivity, specificity, positive predictive value, and negative predictive value for NLP algorithm in predicting asthma status were 97{\%}, 95{\%}, 90{\%}, and 98{\%}, respectively. The risk factors for asthma (e.g., allergic rhinitis) that were identified either by NLP or the abstractor were the same.CONCLUSIONS: Asthma ascertainment through NLP should be considered in the era of EMRs because it can enable large-scale clinical studies in a more time-efficient manner and improve the recognition and care of childhood asthma in practice.",
keywords = "electronic medical records, informatics, retrospective study",
author = "Wi, {Chung Il} and Sunghwan Sohn and Rolfes, {Mary C.} and Alicia Seabright and Euijung Ryu and Gretchen Voge and Bachman, {Kay A.} and Miguel Park and Hirohito Kita and Croghan, {Ivana T} and Liu, {Hongfang D} and Juhn, {Young J}",
year = "2017",
month = "8",
day = "15",
doi = "10.1164/rccm.201610-2006OC",
language = "English (US)",
volume = "196",
pages = "430--437",
journal = "American Journal of Respiratory and Critical Care Medicine",
issn = "1073-449X",
publisher = "American Thoracic Society",
number = "4",

}

TY - JOUR

T1 - Application of a Natural Language Processing Algorithm to Asthma Ascertainment. An Automated Chart Review

AU - Wi, Chung Il

AU - Sohn, Sunghwan

AU - Rolfes, Mary C.

AU - Seabright, Alicia

AU - Ryu, Euijung

AU - Voge, Gretchen

AU - Bachman, Kay A.

AU - Park, Miguel

AU - Kita, Hirohito

AU - Croghan, Ivana T

AU - Liu, Hongfang D

AU - Juhn, Young J

PY - 2017/8/15

Y1 - 2017/8/15

N2 - RATIONALE: Difficulty of asthma ascertainment and its associated methodologic heterogeneity have created significant barriers to asthma care and research.OBJECTIVES: We evaluated the validity of an existing natural language processing (NLP) algorithm for asthma criteria to enable an automated chart review using electronic medical records (EMRs).METHODS: The study was designed as a retrospective birth cohort study using a random sample of 500 subjects from the 1997-2007 Mayo Birth Cohort who were born at Mayo Clinic and enrolled in primary pediatric care at Mayo Clinic Rochester. Performance of NLP-based asthma ascertainment using predetermined asthma criteria was assessed by determining both criterion validity (chart review of EMRs by abstractor as a gold standard) and construct validity (association with known risk factors for asthma, such as allergic rhinitis).MEASUREMENTS AND MAIN RESULTS: After excluding three subjects whose respiratory symptoms could be attributed to other conditions (e.g., tracheomalacia), among the remaining eligible 497 subjects, 51% were male, 77% white persons, and the median age at last follow-up date was 11.5 years. The asthma prevalence was 31% in the study cohort. Sensitivity, specificity, positive predictive value, and negative predictive value for NLP algorithm in predicting asthma status were 97%, 95%, 90%, and 98%, respectively. The risk factors for asthma (e.g., allergic rhinitis) that were identified either by NLP or the abstractor were the same.CONCLUSIONS: Asthma ascertainment through NLP should be considered in the era of EMRs because it can enable large-scale clinical studies in a more time-efficient manner and improve the recognition and care of childhood asthma in practice.

AB - RATIONALE: Difficulty of asthma ascertainment and its associated methodologic heterogeneity have created significant barriers to asthma care and research.OBJECTIVES: We evaluated the validity of an existing natural language processing (NLP) algorithm for asthma criteria to enable an automated chart review using electronic medical records (EMRs).METHODS: The study was designed as a retrospective birth cohort study using a random sample of 500 subjects from the 1997-2007 Mayo Birth Cohort who were born at Mayo Clinic and enrolled in primary pediatric care at Mayo Clinic Rochester. Performance of NLP-based asthma ascertainment using predetermined asthma criteria was assessed by determining both criterion validity (chart review of EMRs by abstractor as a gold standard) and construct validity (association with known risk factors for asthma, such as allergic rhinitis).MEASUREMENTS AND MAIN RESULTS: After excluding three subjects whose respiratory symptoms could be attributed to other conditions (e.g., tracheomalacia), among the remaining eligible 497 subjects, 51% were male, 77% white persons, and the median age at last follow-up date was 11.5 years. The asthma prevalence was 31% in the study cohort. Sensitivity, specificity, positive predictive value, and negative predictive value for NLP algorithm in predicting asthma status were 97%, 95%, 90%, and 98%, respectively. The risk factors for asthma (e.g., allergic rhinitis) that were identified either by NLP or the abstractor were the same.CONCLUSIONS: Asthma ascertainment through NLP should be considered in the era of EMRs because it can enable large-scale clinical studies in a more time-efficient manner and improve the recognition and care of childhood asthma in practice.

KW - electronic medical records

KW - informatics

KW - retrospective study

UR - http://www.scopus.com/inward/record.url?scp=85028622979&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028622979&partnerID=8YFLogxK

U2 - 10.1164/rccm.201610-2006OC

DO - 10.1164/rccm.201610-2006OC

M3 - Article

VL - 196

SP - 430

EP - 437

JO - American Journal of Respiratory and Critical Care Medicine

JF - American Journal of Respiratory and Critical Care Medicine

SN - 1073-449X

IS - 4

ER -