A comparison of two approaches to text processing: facilitating chart reviews of radiology reports in electronic medical records.

Julie A. Womack, Matthew Scotch, Cynthia Gibert, Wendy Chapman, Michael Yin, Amy C. Justice, Cynthia Brandt

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Chart review is central to health services research. Text processing, which analyzes free-text fields through automated methods, can facilitate this process. We compared precision and accuracy of NegEx and SQLServer 2008 Free-Text Search in identifying acute fractures in radiology reports.The term "fracture" was included in 23,595 radiology reports from the Veterans Aging Cohort Study. Four hundred reports were randomly selected and manually reviewed for acute fractures to establish a gold standard. Reports were then processed by SQLServer and NegEx. Results were compared to the gold standard to determine accuracy, precision, recall, and F-statistic.NegEx and the gold standard identified acute fractures in 13 reports. SQLServer identified 2 in a report-based analysis (precision: 1.00; accuracy: 0.97; recall: 0.15; F-statistic: 0.26), and 12 in a sentence-by-sentence analysis (precision: 1.00; recall: 0.92; accuracy: 0.92; F-statistic: 0.96).Text-processing tools utilizing basic database or programming skills are comparable, precise, and accurate in identifying reports for review.

Fingerprint

Electronic Health Records
Radiology
Health Services Research
Veterans
Cohort Studies
Databases

ASJC Scopus subject areas

  • Medicine(all)

Cite this

A comparison of two approaches to text processing : facilitating chart reviews of radiology reports in electronic medical records. / Womack, Julie A.; Scotch, Matthew; Gibert, Cynthia; Chapman, Wendy; Yin, Michael; Justice, Amy C.; Brandt, Cynthia.

In: Perspectives in health information management / AHIMA, American Health Information Management Association, Vol. 7, 2010.

Research output: Contribution to journalArticle

@article{3d8a27be7f2343398943d9175fddbe66,
title = "A comparison of two approaches to text processing: facilitating chart reviews of radiology reports in electronic medical records.",
abstract = "Chart review is central to health services research. Text processing, which analyzes free-text fields through automated methods, can facilitate this process. We compared precision and accuracy of NegEx and SQLServer 2008 Free-Text Search in identifying acute fractures in radiology reports.The term {"}fracture{"} was included in 23,595 radiology reports from the Veterans Aging Cohort Study. Four hundred reports were randomly selected and manually reviewed for acute fractures to establish a gold standard. Reports were then processed by SQLServer and NegEx. Results were compared to the gold standard to determine accuracy, precision, recall, and F-statistic.NegEx and the gold standard identified acute fractures in 13 reports. SQLServer identified 2 in a report-based analysis (precision: 1.00; accuracy: 0.97; recall: 0.15; F-statistic: 0.26), and 12 in a sentence-by-sentence analysis (precision: 1.00; recall: 0.92; accuracy: 0.92; F-statistic: 0.96).Text-processing tools utilizing basic database or programming skills are comparable, precise, and accurate in identifying reports for review.",
author = "Womack, {Julie A.} and Matthew Scotch and Cynthia Gibert and Wendy Chapman and Michael Yin and Justice, {Amy C.} and Cynthia Brandt",
year = "2010",
language = "English (US)",
volume = "7",
journal = "Perspectives in health information management / AHIMA, American Health Information Management Association",
issn = "1559-4122",
publisher = "American Health Information Management Association",

}

TY - JOUR

T1 - A comparison of two approaches to text processing

T2 - facilitating chart reviews of radiology reports in electronic medical records.

AU - Womack, Julie A.

AU - Scotch, Matthew

AU - Gibert, Cynthia

AU - Chapman, Wendy

AU - Yin, Michael

AU - Justice, Amy C.

AU - Brandt, Cynthia

PY - 2010

Y1 - 2010

N2 - Chart review is central to health services research. Text processing, which analyzes free-text fields through automated methods, can facilitate this process. We compared precision and accuracy of NegEx and SQLServer 2008 Free-Text Search in identifying acute fractures in radiology reports.The term "fracture" was included in 23,595 radiology reports from the Veterans Aging Cohort Study. Four hundred reports were randomly selected and manually reviewed for acute fractures to establish a gold standard. Reports were then processed by SQLServer and NegEx. Results were compared to the gold standard to determine accuracy, precision, recall, and F-statistic.NegEx and the gold standard identified acute fractures in 13 reports. SQLServer identified 2 in a report-based analysis (precision: 1.00; accuracy: 0.97; recall: 0.15; F-statistic: 0.26), and 12 in a sentence-by-sentence analysis (precision: 1.00; recall: 0.92; accuracy: 0.92; F-statistic: 0.96).Text-processing tools utilizing basic database or programming skills are comparable, precise, and accurate in identifying reports for review.

AB - Chart review is central to health services research. Text processing, which analyzes free-text fields through automated methods, can facilitate this process. We compared precision and accuracy of NegEx and SQLServer 2008 Free-Text Search in identifying acute fractures in radiology reports.The term "fracture" was included in 23,595 radiology reports from the Veterans Aging Cohort Study. Four hundred reports were randomly selected and manually reviewed for acute fractures to establish a gold standard. Reports were then processed by SQLServer and NegEx. Results were compared to the gold standard to determine accuracy, precision, recall, and F-statistic.NegEx and the gold standard identified acute fractures in 13 reports. SQLServer identified 2 in a report-based analysis (precision: 1.00; accuracy: 0.97; recall: 0.15; F-statistic: 0.26), and 12 in a sentence-by-sentence analysis (precision: 1.00; recall: 0.92; accuracy: 0.92; F-statistic: 0.96).Text-processing tools utilizing basic database or programming skills are comparable, precise, and accurate in identifying reports for review.

UR - http://www.scopus.com/inward/record.url?scp=79952794925&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952794925&partnerID=8YFLogxK

M3 - Article

C2 - 21063542

AN - SCOPUS:79952794925

VL - 7

JO - Perspectives in health information management / AHIMA, American Health Information Management Association

JF - Perspectives in health information management / AHIMA, American Health Information Management Association

SN - 1559-4122

ER -