A decision tree for tuberculosis contact investigation

Lynn B Gerald, Shenghui Tang, Frank Bruce, David Redden, Michael E. Kimerling, Nancy Brook, Nancy Dunlap, William C. Bailey

Research output: Contribution to journalArticle

51 Citations (Scopus)

Abstract

The University of Alabama at Birmingham and the Alabama Department of Public Health recently developed a logistic regression model showing those variables that are most likely to predict a positive tuberculin skin test in contacts of tuberculosis cases. However, translating such a model into field application requires a stepwise approach. This article describes a decision tree developed to assist public health workers in determining which contacts are most likely to have a positive tuberculin skin test. The Classification and Regression Tree analysis was performed on 292 consecutive cases and their 2,941 contacts seen by the Alabama Department of Public Health from January 1, 1998, to October 15, 1998. Several decision trees were developed and were then tested using prospectively collected data from 366 new tuberculosis cases and their 3,162 contacts from October 15, 1998, to April 30, 2000. Testing showed the trees to have sensitivities of 87-94%, specificities of 22-28%, and false-negative rates between 7 and 10%. The use of the decision trees would decrease the number of contacts investigated by 17-25% while maintaining a false-negative rate that was close to that of the presumed background rate of latent tuberculosis infection in the state of Alabama.

Original languageEnglish (US)
Pages (from-to)1122-1127
Number of pages6
JournalAmerican Journal of Respiratory and Critical Care Medicine
Volume166
Issue number8
DOIs
StatePublished - Oct 15 2002
Externally publishedYes

Fingerprint

Decision Trees
Tuberculosis
Tuberculin Test
Public Health
Skin Tests
Logistic Models
Latent Tuberculosis
Regression Analysis

Keywords

  • Classification and Regression Tree analysis
  • Contact investigation
  • Decision tree
  • Tuberculosis

ASJC Scopus subject areas

  • Pulmonary and Respiratory Medicine

Cite this

Gerald, L. B., Tang, S., Bruce, F., Redden, D., Kimerling, M. E., Brook, N., ... Bailey, W. C. (2002). A decision tree for tuberculosis contact investigation. American Journal of Respiratory and Critical Care Medicine, 166(8), 1122-1127. https://doi.org/10.1164/rccm.200202-124OC

A decision tree for tuberculosis contact investigation. / Gerald, Lynn B; Tang, Shenghui; Bruce, Frank; Redden, David; Kimerling, Michael E.; Brook, Nancy; Dunlap, Nancy; Bailey, William C.

In: American Journal of Respiratory and Critical Care Medicine, Vol. 166, No. 8, 15.10.2002, p. 1122-1127.

Research output: Contribution to journalArticle

Gerald, LB, Tang, S, Bruce, F, Redden, D, Kimerling, ME, Brook, N, Dunlap, N & Bailey, WC 2002, 'A decision tree for tuberculosis contact investigation', American Journal of Respiratory and Critical Care Medicine, vol. 166, no. 8, pp. 1122-1127. https://doi.org/10.1164/rccm.200202-124OC
Gerald, Lynn B ; Tang, Shenghui ; Bruce, Frank ; Redden, David ; Kimerling, Michael E. ; Brook, Nancy ; Dunlap, Nancy ; Bailey, William C. / A decision tree for tuberculosis contact investigation. In: American Journal of Respiratory and Critical Care Medicine. 2002 ; Vol. 166, No. 8. pp. 1122-1127.
@article{281249a82c9b446c84f51d8d9e86c3e8,
title = "A decision tree for tuberculosis contact investigation",
abstract = "The University of Alabama at Birmingham and the Alabama Department of Public Health recently developed a logistic regression model showing those variables that are most likely to predict a positive tuberculin skin test in contacts of tuberculosis cases. However, translating such a model into field application requires a stepwise approach. This article describes a decision tree developed to assist public health workers in determining which contacts are most likely to have a positive tuberculin skin test. The Classification and Regression Tree analysis was performed on 292 consecutive cases and their 2,941 contacts seen by the Alabama Department of Public Health from January 1, 1998, to October 15, 1998. Several decision trees were developed and were then tested using prospectively collected data from 366 new tuberculosis cases and their 3,162 contacts from October 15, 1998, to April 30, 2000. Testing showed the trees to have sensitivities of 87-94{\%}, specificities of 22-28{\%}, and false-negative rates between 7 and 10{\%}. The use of the decision trees would decrease the number of contacts investigated by 17-25{\%} while maintaining a false-negative rate that was close to that of the presumed background rate of latent tuberculosis infection in the state of Alabama.",
keywords = "Classification and Regression Tree analysis, Contact investigation, Decision tree, Tuberculosis",
author = "Gerald, {Lynn B} and Shenghui Tang and Frank Bruce and David Redden and Kimerling, {Michael E.} and Nancy Brook and Nancy Dunlap and Bailey, {William C.}",
year = "2002",
month = "10",
day = "15",
doi = "10.1164/rccm.200202-124OC",
language = "English (US)",
volume = "166",
pages = "1122--1127",
journal = "American Journal of Respiratory and Critical Care Medicine",
issn = "1073-449X",
publisher = "American Thoracic Society",
number = "8",

}

TY - JOUR

T1 - A decision tree for tuberculosis contact investigation

AU - Gerald, Lynn B

AU - Tang, Shenghui

AU - Bruce, Frank

AU - Redden, David

AU - Kimerling, Michael E.

AU - Brook, Nancy

AU - Dunlap, Nancy

AU - Bailey, William C.

PY - 2002/10/15

Y1 - 2002/10/15

N2 - The University of Alabama at Birmingham and the Alabama Department of Public Health recently developed a logistic regression model showing those variables that are most likely to predict a positive tuberculin skin test in contacts of tuberculosis cases. However, translating such a model into field application requires a stepwise approach. This article describes a decision tree developed to assist public health workers in determining which contacts are most likely to have a positive tuberculin skin test. The Classification and Regression Tree analysis was performed on 292 consecutive cases and their 2,941 contacts seen by the Alabama Department of Public Health from January 1, 1998, to October 15, 1998. Several decision trees were developed and were then tested using prospectively collected data from 366 new tuberculosis cases and their 3,162 contacts from October 15, 1998, to April 30, 2000. Testing showed the trees to have sensitivities of 87-94%, specificities of 22-28%, and false-negative rates between 7 and 10%. The use of the decision trees would decrease the number of contacts investigated by 17-25% while maintaining a false-negative rate that was close to that of the presumed background rate of latent tuberculosis infection in the state of Alabama.

AB - The University of Alabama at Birmingham and the Alabama Department of Public Health recently developed a logistic regression model showing those variables that are most likely to predict a positive tuberculin skin test in contacts of tuberculosis cases. However, translating such a model into field application requires a stepwise approach. This article describes a decision tree developed to assist public health workers in determining which contacts are most likely to have a positive tuberculin skin test. The Classification and Regression Tree analysis was performed on 292 consecutive cases and their 2,941 contacts seen by the Alabama Department of Public Health from January 1, 1998, to October 15, 1998. Several decision trees were developed and were then tested using prospectively collected data from 366 new tuberculosis cases and their 3,162 contacts from October 15, 1998, to April 30, 2000. Testing showed the trees to have sensitivities of 87-94%, specificities of 22-28%, and false-negative rates between 7 and 10%. The use of the decision trees would decrease the number of contacts investigated by 17-25% while maintaining a false-negative rate that was close to that of the presumed background rate of latent tuberculosis infection in the state of Alabama.

KW - Classification and Regression Tree analysis

KW - Contact investigation

KW - Decision tree

KW - Tuberculosis

UR - http://www.scopus.com/inward/record.url?scp=0037108545&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037108545&partnerID=8YFLogxK

U2 - 10.1164/rccm.200202-124OC

DO - 10.1164/rccm.200202-124OC

M3 - Article

C2 - 12379558

AN - SCOPUS:0037108545

VL - 166

SP - 1122

EP - 1127

JO - American Journal of Respiratory and Critical Care Medicine

JF - American Journal of Respiratory and Critical Care Medicine

SN - 1073-449X

IS - 8

ER -