Natural language processing of clinical notes for identification of critical limb ischemia

Naveed Afzal, Vishnu Priya Mallipeddi, Sunghwan Sohn, Hongfang D Liu, Rajeev Chaudhry, Christopher G. Scott, Iftikhar Jan Kullo, Adelaide M Arruda-Olson

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Background Critical limb ischemia (CLI) is a complication of advanced peripheral artery disease (PAD) with diagnosis based on the presence of clinical signs and symptoms. However, automated identification of cases from electronic health records (EHRs) is challenging due to absence of a single definitive International Classification of Diseases (ICD-9 or ICD-10) code for CLI. Methods and results In this study, we extend a previously validated natural language processing (NLP) algorithm for PAD identification to develop and validate a subphenotyping NLP algorithm (CLI-NLP) for identification of CLI cases from clinical notes. We compared performance of the CLI-NLP algorithm with CLI-related ICD-9 billing codes. The gold standard for validation was human abstraction of clinical notes from EHRs. Compared to billing codes the CLI-NLP algorithm had higher positive predictive value (PPV) (CLI-NLP 96%, billing codes 67%, p < 0.001), specificity (CLI-NLP 98%, billing codes 74%, p < 0.001) and F1-score (CLI-NLP 90%, billing codes 76%, p < 0.001). The sensitivity of these two methods was similar (CLI-NLP 84%; billing codes 88%; p < 0.12). Conclusions The CLI-NLP algorithm for identification of CLI from narrative clinical notes in an EHR had excellent PPV and has potential for translation to patient care as it will enable automated identification of CLI cases for quality projects, clinical decision support tools and support a learning healthcare system.

Original languageEnglish (US)
Pages (from-to)83-89
Number of pages7
JournalInternational Journal of Medical Informatics
Volume111
DOIs
StatePublished - Mar 1 2018

Fingerprint

Natural Language Processing
Ischemia
Extremities
International Classification of Diseases
Electronic Health Records
Peripheral Arterial Disease
Clinical Decision Support Systems

Keywords

  • Critical limb ischemia
  • Electronic health records
  • Natural language processing
  • Peripheral artery disease
  • Subphenotyping

ASJC Scopus subject areas

  • Health Informatics

Cite this

Natural language processing of clinical notes for identification of critical limb ischemia. / Afzal, Naveed; Mallipeddi, Vishnu Priya; Sohn, Sunghwan; Liu, Hongfang D; Chaudhry, Rajeev; Scott, Christopher G.; Kullo, Iftikhar Jan; Arruda-Olson, Adelaide M.

In: International Journal of Medical Informatics, Vol. 111, 01.03.2018, p. 83-89.

Research output: Contribution to journalArticle

@article{3f6bf9c40823454680ed11d7939c5d02,
title = "Natural language processing of clinical notes for identification of critical limb ischemia",
abstract = "Background Critical limb ischemia (CLI) is a complication of advanced peripheral artery disease (PAD) with diagnosis based on the presence of clinical signs and symptoms. However, automated identification of cases from electronic health records (EHRs) is challenging due to absence of a single definitive International Classification of Diseases (ICD-9 or ICD-10) code for CLI. Methods and results In this study, we extend a previously validated natural language processing (NLP) algorithm for PAD identification to develop and validate a subphenotyping NLP algorithm (CLI-NLP) for identification of CLI cases from clinical notes. We compared performance of the CLI-NLP algorithm with CLI-related ICD-9 billing codes. The gold standard for validation was human abstraction of clinical notes from EHRs. Compared to billing codes the CLI-NLP algorithm had higher positive predictive value (PPV) (CLI-NLP 96{\%}, billing codes 67{\%}, p < 0.001), specificity (CLI-NLP 98{\%}, billing codes 74{\%}, p < 0.001) and F1-score (CLI-NLP 90{\%}, billing codes 76{\%}, p < 0.001). The sensitivity of these two methods was similar (CLI-NLP 84{\%}; billing codes 88{\%}; p < 0.12). Conclusions The CLI-NLP algorithm for identification of CLI from narrative clinical notes in an EHR had excellent PPV and has potential for translation to patient care as it will enable automated identification of CLI cases for quality projects, clinical decision support tools and support a learning healthcare system.",
keywords = "Critical limb ischemia, Electronic health records, Natural language processing, Peripheral artery disease, Subphenotyping",
author = "Naveed Afzal and Mallipeddi, {Vishnu Priya} and Sunghwan Sohn and Liu, {Hongfang D} and Rajeev Chaudhry and Scott, {Christopher G.} and Kullo, {Iftikhar Jan} and Arruda-Olson, {Adelaide M}",
year = "2018",
month = "3",
day = "1",
doi = "10.1016/j.ijmedinf.2017.12.024",
language = "English (US)",
volume = "111",
pages = "83--89",
journal = "International Journal of Medical Informatics",
issn = "1386-5056",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - Natural language processing of clinical notes for identification of critical limb ischemia

AU - Afzal, Naveed

AU - Mallipeddi, Vishnu Priya

AU - Sohn, Sunghwan

AU - Liu, Hongfang D

AU - Chaudhry, Rajeev

AU - Scott, Christopher G.

AU - Kullo, Iftikhar Jan

AU - Arruda-Olson, Adelaide M

PY - 2018/3/1

Y1 - 2018/3/1

N2 - Background Critical limb ischemia (CLI) is a complication of advanced peripheral artery disease (PAD) with diagnosis based on the presence of clinical signs and symptoms. However, automated identification of cases from electronic health records (EHRs) is challenging due to absence of a single definitive International Classification of Diseases (ICD-9 or ICD-10) code for CLI. Methods and results In this study, we extend a previously validated natural language processing (NLP) algorithm for PAD identification to develop and validate a subphenotyping NLP algorithm (CLI-NLP) for identification of CLI cases from clinical notes. We compared performance of the CLI-NLP algorithm with CLI-related ICD-9 billing codes. The gold standard for validation was human abstraction of clinical notes from EHRs. Compared to billing codes the CLI-NLP algorithm had higher positive predictive value (PPV) (CLI-NLP 96%, billing codes 67%, p < 0.001), specificity (CLI-NLP 98%, billing codes 74%, p < 0.001) and F1-score (CLI-NLP 90%, billing codes 76%, p < 0.001). The sensitivity of these two methods was similar (CLI-NLP 84%; billing codes 88%; p < 0.12). Conclusions The CLI-NLP algorithm for identification of CLI from narrative clinical notes in an EHR had excellent PPV and has potential for translation to patient care as it will enable automated identification of CLI cases for quality projects, clinical decision support tools and support a learning healthcare system.

AB - Background Critical limb ischemia (CLI) is a complication of advanced peripheral artery disease (PAD) with diagnosis based on the presence of clinical signs and symptoms. However, automated identification of cases from electronic health records (EHRs) is challenging due to absence of a single definitive International Classification of Diseases (ICD-9 or ICD-10) code for CLI. Methods and results In this study, we extend a previously validated natural language processing (NLP) algorithm for PAD identification to develop and validate a subphenotyping NLP algorithm (CLI-NLP) for identification of CLI cases from clinical notes. We compared performance of the CLI-NLP algorithm with CLI-related ICD-9 billing codes. The gold standard for validation was human abstraction of clinical notes from EHRs. Compared to billing codes the CLI-NLP algorithm had higher positive predictive value (PPV) (CLI-NLP 96%, billing codes 67%, p < 0.001), specificity (CLI-NLP 98%, billing codes 74%, p < 0.001) and F1-score (CLI-NLP 90%, billing codes 76%, p < 0.001). The sensitivity of these two methods was similar (CLI-NLP 84%; billing codes 88%; p < 0.12). Conclusions The CLI-NLP algorithm for identification of CLI from narrative clinical notes in an EHR had excellent PPV and has potential for translation to patient care as it will enable automated identification of CLI cases for quality projects, clinical decision support tools and support a learning healthcare system.

KW - Critical limb ischemia

KW - Electronic health records

KW - Natural language processing

KW - Peripheral artery disease

KW - Subphenotyping

UR - http://www.scopus.com/inward/record.url?scp=85040017468&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040017468&partnerID=8YFLogxK

U2 - 10.1016/j.ijmedinf.2017.12.024

DO - 10.1016/j.ijmedinf.2017.12.024

M3 - Article

VL - 111

SP - 83

EP - 89

JO - International Journal of Medical Informatics

JF - International Journal of Medical Informatics

SN - 1386-5056

ER -