Initial-impression diagnosis using low-back pain patient pain drawings

N. H. Mann, Mark Brown, D. B. Hertz, I. Enger, J. Tompkins

Research output: Contribution to journalArticle

68 Citations (Scopus)

Abstract

Patient pain drawings were blindly selected from five lumbar spine disorder categories. The drawings were classified by low-back physicians, discriminant analysis, and several computerized artificial neural network configurations. The purpose was to determine the reliability of the patient pain drawing when diagnosing low-back disorders and to delineate the pain mark patterns particular to each disorder by comparing physicians with computerized methods. The physicians averaged 51% accuracy with individual preferences for certain disorder groups. The computerized methods demonstrated comparable accuracy (48%) and more agreement in classification. Associations were found between the predicted pain patterns for each diagnostic group made by an expert and the patterns generated by computerized methods. Variances in these associations are instructive to clinicians for making accurate predictions of diagnosis from pain drawings.

Original languageEnglish
Pages (from-to)41-53
Number of pages13
JournalSpine
Volume18
Issue number1
DOIs
StatePublished - Mar 1 1993

Fingerprint

Low Back Pain
Pain
Physicians
Discriminant Analysis
Spine

Keywords

  • low-back pain
  • pain drawing diagnosis

ASJC Scopus subject areas

  • Physiology
  • Clinical Neurology
  • Orthopedics and Sports Medicine

Cite this

Initial-impression diagnosis using low-back pain patient pain drawings. / Mann, N. H.; Brown, Mark; Hertz, D. B.; Enger, I.; Tompkins, J.

In: Spine, Vol. 18, No. 1, 01.03.1993, p. 41-53.

Research output: Contribution to journalArticle

Mann, N. H. ; Brown, Mark ; Hertz, D. B. ; Enger, I. ; Tompkins, J. / Initial-impression diagnosis using low-back pain patient pain drawings. In: Spine. 1993 ; Vol. 18, No. 1. pp. 41-53.
@article{58516b8e506d47cca75441e01345b113,
title = "Initial-impression diagnosis using low-back pain patient pain drawings",
abstract = "Patient pain drawings were blindly selected from five lumbar spine disorder categories. The drawings were classified by low-back physicians, discriminant analysis, and several computerized artificial neural network configurations. The purpose was to determine the reliability of the patient pain drawing when diagnosing low-back disorders and to delineate the pain mark patterns particular to each disorder by comparing physicians with computerized methods. The physicians averaged 51{\%} accuracy with individual preferences for certain disorder groups. The computerized methods demonstrated comparable accuracy (48{\%}) and more agreement in classification. Associations were found between the predicted pain patterns for each diagnostic group made by an expert and the patterns generated by computerized methods. Variances in these associations are instructive to clinicians for making accurate predictions of diagnosis from pain drawings.",
keywords = "low-back pain, pain drawing diagnosis",
author = "Mann, {N. H.} and Mark Brown and Hertz, {D. B.} and I. Enger and J. Tompkins",
year = "1993",
month = "3",
day = "1",
doi = "10.1097/00007632-199301000-00008",
language = "English",
volume = "18",
pages = "41--53",
journal = "Spine",
issn = "0362-2436",
publisher = "Lippincott Williams and Wilkins",
number = "1",

}

TY - JOUR

T1 - Initial-impression diagnosis using low-back pain patient pain drawings

AU - Mann, N. H.

AU - Brown, Mark

AU - Hertz, D. B.

AU - Enger, I.

AU - Tompkins, J.

PY - 1993/3/1

Y1 - 1993/3/1

N2 - Patient pain drawings were blindly selected from five lumbar spine disorder categories. The drawings were classified by low-back physicians, discriminant analysis, and several computerized artificial neural network configurations. The purpose was to determine the reliability of the patient pain drawing when diagnosing low-back disorders and to delineate the pain mark patterns particular to each disorder by comparing physicians with computerized methods. The physicians averaged 51% accuracy with individual preferences for certain disorder groups. The computerized methods demonstrated comparable accuracy (48%) and more agreement in classification. Associations were found between the predicted pain patterns for each diagnostic group made by an expert and the patterns generated by computerized methods. Variances in these associations are instructive to clinicians for making accurate predictions of diagnosis from pain drawings.

AB - Patient pain drawings were blindly selected from five lumbar spine disorder categories. The drawings were classified by low-back physicians, discriminant analysis, and several computerized artificial neural network configurations. The purpose was to determine the reliability of the patient pain drawing when diagnosing low-back disorders and to delineate the pain mark patterns particular to each disorder by comparing physicians with computerized methods. The physicians averaged 51% accuracy with individual preferences for certain disorder groups. The computerized methods demonstrated comparable accuracy (48%) and more agreement in classification. Associations were found between the predicted pain patterns for each diagnostic group made by an expert and the patterns generated by computerized methods. Variances in these associations are instructive to clinicians for making accurate predictions of diagnosis from pain drawings.

KW - low-back pain

KW - pain drawing diagnosis

UR - http://www.scopus.com/inward/record.url?scp=0027457170&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027457170&partnerID=8YFLogxK

U2 - 10.1097/00007632-199301000-00008

DO - 10.1097/00007632-199301000-00008

M3 - Article

C2 - 8434324

AN - SCOPUS:0027457170

VL - 18

SP - 41

EP - 53

JO - Spine

JF - Spine

SN - 0362-2436

IS - 1

ER -