The accuracy of artificial neural networks in predicting long-term outcome after traumatic brain injury

Mary E. Segal, Philip H. Goodman, Richard Goldstein, Walter Hauck, John Whyte, John W. Graham, Marcia Polansky, Flora M. Hammond

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

OBJECTIVE: This study compared the accuracy of artificial neural networks to multiple regression and classification and regression trees in predicting outcomes of 1644 patients in the Traumatic Brain Injury Model Systems database 1 year after injury. METHODS: Data from rehabilitation admission were used to predict discharge scores on the Functional Independence Measure, the Disability Rating Scale, and the Community Integration Questionnaire. RESULTS: Artificial neural networks did not demonstrate greater accuracy in predicting outcomes than did the more widely used method of multiple regression. Both of these methods outperformed classification and regression trees. CONCLUSION: Because of the sophisticated form of multiple regression with splines that was used, firm conclusions are limited about the relative accuracy of artificial neural networks compared to more widely used forms of multiple regression.

Original languageEnglish (US)
Pages (from-to)298-314
Number of pages17
JournalJournal of Head Trauma Rehabilitation
Volume21
Issue number4
DOIs
StatePublished - Jul 2006

Fingerprint

Community Integration
Rehabilitation
Databases
Wounds and Injuries
Traumatic Brain Injury
Surveys and Questionnaires

All Science Journal Classification (ASJC) codes

  • Rehabilitation
  • Clinical Neurology
  • Health Professions(all)

Cite this

Segal, M. E., Goodman, P. H., Goldstein, R., Hauck, W., Whyte, J., Graham, J. W., ... Hammond, F. M. (2006). The accuracy of artificial neural networks in predicting long-term outcome after traumatic brain injury. Journal of Head Trauma Rehabilitation, 21(4), 298-314. https://doi.org/10.1097/00001199-200607000-00003
Segal, Mary E. ; Goodman, Philip H. ; Goldstein, Richard ; Hauck, Walter ; Whyte, John ; Graham, John W. ; Polansky, Marcia ; Hammond, Flora M. / The accuracy of artificial neural networks in predicting long-term outcome after traumatic brain injury. In: Journal of Head Trauma Rehabilitation. 2006 ; Vol. 21, No. 4. pp. 298-314.
@article{6d3e750bb3074198bcbc13344f266270,
title = "The accuracy of artificial neural networks in predicting long-term outcome after traumatic brain injury",
abstract = "OBJECTIVE: This study compared the accuracy of artificial neural networks to multiple regression and classification and regression trees in predicting outcomes of 1644 patients in the Traumatic Brain Injury Model Systems database 1 year after injury. METHODS: Data from rehabilitation admission were used to predict discharge scores on the Functional Independence Measure, the Disability Rating Scale, and the Community Integration Questionnaire. RESULTS: Artificial neural networks did not demonstrate greater accuracy in predicting outcomes than did the more widely used method of multiple regression. Both of these methods outperformed classification and regression trees. CONCLUSION: Because of the sophisticated form of multiple regression with splines that was used, firm conclusions are limited about the relative accuracy of artificial neural networks compared to more widely used forms of multiple regression.",
author = "Segal, {Mary E.} and Goodman, {Philip H.} and Richard Goldstein and Walter Hauck and John Whyte and Graham, {John W.} and Marcia Polansky and Hammond, {Flora M.}",
year = "2006",
month = "7",
doi = "10.1097/00001199-200607000-00003",
language = "English (US)",
volume = "21",
pages = "298--314",
journal = "Journal of Head Trauma Rehabilitation",
issn = "0885-9701",
publisher = "Lippincott Williams and Wilkins",
number = "4",

}

Segal, ME, Goodman, PH, Goldstein, R, Hauck, W, Whyte, J, Graham, JW, Polansky, M & Hammond, FM 2006, 'The accuracy of artificial neural networks in predicting long-term outcome after traumatic brain injury', Journal of Head Trauma Rehabilitation, vol. 21, no. 4, pp. 298-314. https://doi.org/10.1097/00001199-200607000-00003

The accuracy of artificial neural networks in predicting long-term outcome after traumatic brain injury. / Segal, Mary E.; Goodman, Philip H.; Goldstein, Richard; Hauck, Walter; Whyte, John; Graham, John W.; Polansky, Marcia; Hammond, Flora M.

In: Journal of Head Trauma Rehabilitation, Vol. 21, No. 4, 07.2006, p. 298-314.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The accuracy of artificial neural networks in predicting long-term outcome after traumatic brain injury

AU - Segal, Mary E.

AU - Goodman, Philip H.

AU - Goldstein, Richard

AU - Hauck, Walter

AU - Whyte, John

AU - Graham, John W.

AU - Polansky, Marcia

AU - Hammond, Flora M.

PY - 2006/7

Y1 - 2006/7

N2 - OBJECTIVE: This study compared the accuracy of artificial neural networks to multiple regression and classification and regression trees in predicting outcomes of 1644 patients in the Traumatic Brain Injury Model Systems database 1 year after injury. METHODS: Data from rehabilitation admission were used to predict discharge scores on the Functional Independence Measure, the Disability Rating Scale, and the Community Integration Questionnaire. RESULTS: Artificial neural networks did not demonstrate greater accuracy in predicting outcomes than did the more widely used method of multiple regression. Both of these methods outperformed classification and regression trees. CONCLUSION: Because of the sophisticated form of multiple regression with splines that was used, firm conclusions are limited about the relative accuracy of artificial neural networks compared to more widely used forms of multiple regression.

AB - OBJECTIVE: This study compared the accuracy of artificial neural networks to multiple regression and classification and regression trees in predicting outcomes of 1644 patients in the Traumatic Brain Injury Model Systems database 1 year after injury. METHODS: Data from rehabilitation admission were used to predict discharge scores on the Functional Independence Measure, the Disability Rating Scale, and the Community Integration Questionnaire. RESULTS: Artificial neural networks did not demonstrate greater accuracy in predicting outcomes than did the more widely used method of multiple regression. Both of these methods outperformed classification and regression trees. CONCLUSION: Because of the sophisticated form of multiple regression with splines that was used, firm conclusions are limited about the relative accuracy of artificial neural networks compared to more widely used forms of multiple regression.

UR - http://www.scopus.com/inward/record.url?scp=33747506451&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33747506451&partnerID=8YFLogxK

U2 - 10.1097/00001199-200607000-00003

DO - 10.1097/00001199-200607000-00003

M3 - Article

C2 - 16915007

AN - SCOPUS:33747506451

VL - 21

SP - 298

EP - 314

JO - Journal of Head Trauma Rehabilitation

JF - Journal of Head Trauma Rehabilitation

SN - 0885-9701

IS - 4

ER -