Automated processing of electronic medical records is a reliable method of determining aspirin use in populations at risk for cardiovascular events

Serguei V S Pakhomov, Nilay D Shah, Penny Hanson, Saranya C. Balasubramaniam, Steven A. Smith

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Background Low-dose aspirin reduces cardiovascular risk; however, monitoring over-the-counter medication use relies on the time-consuming and costly manual review of medical records. Our objective is to validate natural language processing (NLP) of the electronic medical record (EMR) for extracting medication exposure and contraindication information. Methods The text of EMRs for 499 patients with type 2 diabetes was searched using NLP for evidence of aspirin use and its contraindications. The results were compared to a standardised manual records review. Results Of the 499 patients, 351 (70%) were using aspirin and 148 (30%) were not, according to manual review. NLP correctly identified 346 of the 351 aspirin-positive and 134 of the 148 aspirin-negative patients, indicating a sensitivity of 99% (95% CI 97-100) and specificity of 91% (95% CI 88-97). Of the 148 aspirin-negative patients, 66 (45%) had contraindications and 82 (55%) did not, according to manual review.NLP search for contraindications correctly identified 61 of the 66 patients with contraindications and 58 of the 82 patients without, yielding a sensitivity of 92% (95% CI 84-97) and a specificity of 71% (95% CI 60-80). Conclusions NLP of the EMR is accurate in ascertaining documented aspirin use and could potentially be used for epidemiological research as a source of cardiovascular risk factor information.

Original languageEnglish (US)
Pages (from-to)125-133
Number of pages9
JournalInformatics in Primary Care
Volume18
Issue number2
StatePublished - Oct 2010

Fingerprint

Electronic medical equipment
Electronic Health Records
Natural Language Processing
Aspirin
Processing
Medical problems
Type 2 Diabetes Mellitus
Medical Records
Monitoring
Research

Keywords

  • Aspirin
  • Natural language processing (NLP)
  • Quality measurement

ASJC Scopus subject areas

  • Health Informatics
  • Family Practice
  • Leadership and Management

Cite this

Automated processing of electronic medical records is a reliable method of determining aspirin use in populations at risk for cardiovascular events. / Pakhomov, Serguei V S; Shah, Nilay D; Hanson, Penny; Balasubramaniam, Saranya C.; Smith, Steven A.

In: Informatics in Primary Care, Vol. 18, No. 2, 10.2010, p. 125-133.

Research output: Contribution to journalArticle

Pakhomov, Serguei V S ; Shah, Nilay D ; Hanson, Penny ; Balasubramaniam, Saranya C. ; Smith, Steven A. / Automated processing of electronic medical records is a reliable method of determining aspirin use in populations at risk for cardiovascular events. In: Informatics in Primary Care. 2010 ; Vol. 18, No. 2. pp. 125-133.
@article{b36959562ac8467c9ddff9b6de53e0f7,
title = "Automated processing of electronic medical records is a reliable method of determining aspirin use in populations at risk for cardiovascular events",
abstract = "Background Low-dose aspirin reduces cardiovascular risk; however, monitoring over-the-counter medication use relies on the time-consuming and costly manual review of medical records. Our objective is to validate natural language processing (NLP) of the electronic medical record (EMR) for extracting medication exposure and contraindication information. Methods The text of EMRs for 499 patients with type 2 diabetes was searched using NLP for evidence of aspirin use and its contraindications. The results were compared to a standardised manual records review. Results Of the 499 patients, 351 (70{\%}) were using aspirin and 148 (30{\%}) were not, according to manual review. NLP correctly identified 346 of the 351 aspirin-positive and 134 of the 148 aspirin-negative patients, indicating a sensitivity of 99{\%} (95{\%} CI 97-100) and specificity of 91{\%} (95{\%} CI 88-97). Of the 148 aspirin-negative patients, 66 (45{\%}) had contraindications and 82 (55{\%}) did not, according to manual review.NLP search for contraindications correctly identified 61 of the 66 patients with contraindications and 58 of the 82 patients without, yielding a sensitivity of 92{\%} (95{\%} CI 84-97) and a specificity of 71{\%} (95{\%} CI 60-80). Conclusions NLP of the EMR is accurate in ascertaining documented aspirin use and could potentially be used for epidemiological research as a source of cardiovascular risk factor information.",
keywords = "Aspirin, Natural language processing (NLP), Quality measurement",
author = "Pakhomov, {Serguei V S} and Shah, {Nilay D} and Penny Hanson and Balasubramaniam, {Saranya C.} and Smith, {Steven A.}",
year = "2010",
month = "10",
language = "English (US)",
volume = "18",
pages = "125--133",
journal = "BMJ Health and Care Informatics",
issn = "2058-4555",
publisher = "BMJ Publishing Group",
number = "2",

}

TY - JOUR

T1 - Automated processing of electronic medical records is a reliable method of determining aspirin use in populations at risk for cardiovascular events

AU - Pakhomov, Serguei V S

AU - Shah, Nilay D

AU - Hanson, Penny

AU - Balasubramaniam, Saranya C.

AU - Smith, Steven A.

PY - 2010/10

Y1 - 2010/10

N2 - Background Low-dose aspirin reduces cardiovascular risk; however, monitoring over-the-counter medication use relies on the time-consuming and costly manual review of medical records. Our objective is to validate natural language processing (NLP) of the electronic medical record (EMR) for extracting medication exposure and contraindication information. Methods The text of EMRs for 499 patients with type 2 diabetes was searched using NLP for evidence of aspirin use and its contraindications. The results were compared to a standardised manual records review. Results Of the 499 patients, 351 (70%) were using aspirin and 148 (30%) were not, according to manual review. NLP correctly identified 346 of the 351 aspirin-positive and 134 of the 148 aspirin-negative patients, indicating a sensitivity of 99% (95% CI 97-100) and specificity of 91% (95% CI 88-97). Of the 148 aspirin-negative patients, 66 (45%) had contraindications and 82 (55%) did not, according to manual review.NLP search for contraindications correctly identified 61 of the 66 patients with contraindications and 58 of the 82 patients without, yielding a sensitivity of 92% (95% CI 84-97) and a specificity of 71% (95% CI 60-80). Conclusions NLP of the EMR is accurate in ascertaining documented aspirin use and could potentially be used for epidemiological research as a source of cardiovascular risk factor information.

AB - Background Low-dose aspirin reduces cardiovascular risk; however, monitoring over-the-counter medication use relies on the time-consuming and costly manual review of medical records. Our objective is to validate natural language processing (NLP) of the electronic medical record (EMR) for extracting medication exposure and contraindication information. Methods The text of EMRs for 499 patients with type 2 diabetes was searched using NLP for evidence of aspirin use and its contraindications. The results were compared to a standardised manual records review. Results Of the 499 patients, 351 (70%) were using aspirin and 148 (30%) were not, according to manual review. NLP correctly identified 346 of the 351 aspirin-positive and 134 of the 148 aspirin-negative patients, indicating a sensitivity of 99% (95% CI 97-100) and specificity of 91% (95% CI 88-97). Of the 148 aspirin-negative patients, 66 (45%) had contraindications and 82 (55%) did not, according to manual review.NLP search for contraindications correctly identified 61 of the 66 patients with contraindications and 58 of the 82 patients without, yielding a sensitivity of 92% (95% CI 84-97) and a specificity of 71% (95% CI 60-80). Conclusions NLP of the EMR is accurate in ascertaining documented aspirin use and could potentially be used for epidemiological research as a source of cardiovascular risk factor information.

KW - Aspirin

KW - Natural language processing (NLP)

KW - Quality measurement

UR - http://www.scopus.com/inward/record.url?scp=78449302970&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78449302970&partnerID=8YFLogxK

M3 - Article

C2 - 21078235

AN - SCOPUS:78449302970

VL - 18

SP - 125

EP - 133

JO - BMJ Health and Care Informatics

JF - BMJ Health and Care Informatics

SN - 2058-4555

IS - 2

ER -