Syntactic and semantic errors in radiology reports associated with speech recognition software

Michael D. Ringler, Brian C. Goss, Brian Jack Bartholmai

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Speech recognition software can increase the frequency of errors in radiology reports, which may affect patient care. We retrieved 213,977 speech recognition software-generated reports from 147 different radiologists and proofread them for errors. Errors were classified as "material" if they were believed to alter interpretation of the report. "Immaterial" errors were subclassified as intrusion/omission or spelling errors. The proportion of errors and error type were compared among individual radiologists, imaging subspecialty, and time periods. In all, 20,759 reports (9.7%) contained errors, of which 3992 (1.9%) were material errors. Among immaterial errors, spelling errors were more common than intrusion/omission errors (p <.001). Proportion of errors and fraction of material errors varied significantly among radiologists and between imaging subspecialties (p <.001). Errors were more common in cross-sectional reports, reports reinterpreting results of outside examinations, and procedural studies (all p <.001). Error rate decreased over time (p <.001), which suggests that a quality control program with regular feedback may reduce errors.

Original languageEnglish (US)
Pages (from-to)3-13
Number of pages11
JournalHealth Informatics Journal
Volume23
Issue number1
DOIs
StatePublished - Mar 1 2017

Fingerprint

Speech Recognition Software
Semantics
Radiology
Quality Control
Patient Care
Radiologists

Keywords

  • PowerScribe
  • quality control
  • radiology report
  • report errors
  • speech recognition

ASJC Scopus subject areas

  • Health Informatics

Cite this

Syntactic and semantic errors in radiology reports associated with speech recognition software. / Ringler, Michael D.; Goss, Brian C.; Bartholmai, Brian Jack.

In: Health Informatics Journal, Vol. 23, No. 1, 01.03.2017, p. 3-13.

Research output: Contribution to journalArticle

@article{a5f77b82565d4a4694068f78ac4d6db5,
title = "Syntactic and semantic errors in radiology reports associated with speech recognition software",
abstract = "Speech recognition software can increase the frequency of errors in radiology reports, which may affect patient care. We retrieved 213,977 speech recognition software-generated reports from 147 different radiologists and proofread them for errors. Errors were classified as {"}material{"} if they were believed to alter interpretation of the report. {"}Immaterial{"} errors were subclassified as intrusion/omission or spelling errors. The proportion of errors and error type were compared among individual radiologists, imaging subspecialty, and time periods. In all, 20,759 reports (9.7{\%}) contained errors, of which 3992 (1.9{\%}) were material errors. Among immaterial errors, spelling errors were more common than intrusion/omission errors (p <.001). Proportion of errors and fraction of material errors varied significantly among radiologists and between imaging subspecialties (p <.001). Errors were more common in cross-sectional reports, reports reinterpreting results of outside examinations, and procedural studies (all p <.001). Error rate decreased over time (p <.001), which suggests that a quality control program with regular feedback may reduce errors.",
keywords = "PowerScribe, quality control, radiology report, report errors, speech recognition",
author = "Ringler, {Michael D.} and Goss, {Brian C.} and Bartholmai, {Brian Jack}",
year = "2017",
month = "3",
day = "1",
doi = "10.1177/1460458215613614",
language = "English (US)",
volume = "23",
pages = "3--13",
journal = "Health Informatics Journal",
issn = "1460-4582",
publisher = "SAGE Publications Ltd",
number = "1",

}

TY - JOUR

T1 - Syntactic and semantic errors in radiology reports associated with speech recognition software

AU - Ringler, Michael D.

AU - Goss, Brian C.

AU - Bartholmai, Brian Jack

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Speech recognition software can increase the frequency of errors in radiology reports, which may affect patient care. We retrieved 213,977 speech recognition software-generated reports from 147 different radiologists and proofread them for errors. Errors were classified as "material" if they were believed to alter interpretation of the report. "Immaterial" errors were subclassified as intrusion/omission or spelling errors. The proportion of errors and error type were compared among individual radiologists, imaging subspecialty, and time periods. In all, 20,759 reports (9.7%) contained errors, of which 3992 (1.9%) were material errors. Among immaterial errors, spelling errors were more common than intrusion/omission errors (p <.001). Proportion of errors and fraction of material errors varied significantly among radiologists and between imaging subspecialties (p <.001). Errors were more common in cross-sectional reports, reports reinterpreting results of outside examinations, and procedural studies (all p <.001). Error rate decreased over time (p <.001), which suggests that a quality control program with regular feedback may reduce errors.

AB - Speech recognition software can increase the frequency of errors in radiology reports, which may affect patient care. We retrieved 213,977 speech recognition software-generated reports from 147 different radiologists and proofread them for errors. Errors were classified as "material" if they were believed to alter interpretation of the report. "Immaterial" errors were subclassified as intrusion/omission or spelling errors. The proportion of errors and error type were compared among individual radiologists, imaging subspecialty, and time periods. In all, 20,759 reports (9.7%) contained errors, of which 3992 (1.9%) were material errors. Among immaterial errors, spelling errors were more common than intrusion/omission errors (p <.001). Proportion of errors and fraction of material errors varied significantly among radiologists and between imaging subspecialties (p <.001). Errors were more common in cross-sectional reports, reports reinterpreting results of outside examinations, and procedural studies (all p <.001). Error rate decreased over time (p <.001), which suggests that a quality control program with regular feedback may reduce errors.

KW - PowerScribe

KW - quality control

KW - radiology report

KW - report errors

KW - speech recognition

UR - http://www.scopus.com/inward/record.url?scp=85014868955&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85014868955&partnerID=8YFLogxK

U2 - 10.1177/1460458215613614

DO - 10.1177/1460458215613614

M3 - Article

C2 - 26635322

AN - SCOPUS:85014868955

VL - 23

SP - 3

EP - 13

JO - Health Informatics Journal

JF - Health Informatics Journal

SN - 1460-4582

IS - 1

ER -