Prediction tree for severely head-injured patients

S. C. Choi, Jan Paul Muizelaar, T. Y. Barnes, A. Marmarou, D. M. Brooks, H. F. Young

Research output: Contribution to journalArticle

135 Citations (Scopus)

Abstract

Prediction tree techniques are employed in the analysis of data from 555 patients admitted to the Medical College of Virginia hospitals with severe head injuries. Twenty-three prognostic indicators are examined to predict the distribution of 12-month outcomes among the five Glasgow Outcome Scale categories. A tree diagram, illustrating the prognostic pattern, provides critical threshold levels that split the patients into subgroups with varying degrees of risk. It is a visually useful way to look at the prognosis of head-injured patients. In previous analyses addressing this prediction problem, the same set of prognostic factors (age, motor score, and pupillary response) was used for all patients. These approaches might be considered inflexible because more informative prediction may be achieved by somewhat different combinations of factors for different patients. Tree analysis reveals that the pattern of important prognostic factors differs among various patient subgroups, although the three previously mentioned factors are still of primary importance. For example, it is noted that information concerning intracerebral lesions is useful in predicting outcome for certain patients. The overall predictive accuracy of the tree technique for these data is 77.7%, which is somewhat higher than that obtained via standard prediction methods. The predictive accuracy is highest among patients who have a good recovery or die; it is lower for patients having intermediate outcomes.

Original languageEnglish (US)
Pages (from-to)251-255
Number of pages5
JournalJournal of Neurosurgery
Volume75
Issue number2
StatePublished - 1991
Externally publishedYes

Fingerprint

Head
Glasgow Outcome Scale
Craniocerebral Trauma

Keywords

  • Glasgow Outcome Scale
  • head injury
  • prediction tree
  • prognosis

ASJC Scopus subject areas

  • Clinical Neurology
  • Neuroscience(all)

Cite this

Choi, S. C., Muizelaar, J. P., Barnes, T. Y., Marmarou, A., Brooks, D. M., & Young, H. F. (1991). Prediction tree for severely head-injured patients. Journal of Neurosurgery, 75(2), 251-255.

Prediction tree for severely head-injured patients. / Choi, S. C.; Muizelaar, Jan Paul; Barnes, T. Y.; Marmarou, A.; Brooks, D. M.; Young, H. F.

In: Journal of Neurosurgery, Vol. 75, No. 2, 1991, p. 251-255.

Research output: Contribution to journalArticle

Choi, SC, Muizelaar, JP, Barnes, TY, Marmarou, A, Brooks, DM & Young, HF 1991, 'Prediction tree for severely head-injured patients', Journal of Neurosurgery, vol. 75, no. 2, pp. 251-255.
Choi SC, Muizelaar JP, Barnes TY, Marmarou A, Brooks DM, Young HF. Prediction tree for severely head-injured patients. Journal of Neurosurgery. 1991;75(2):251-255.
Choi, S. C. ; Muizelaar, Jan Paul ; Barnes, T. Y. ; Marmarou, A. ; Brooks, D. M. ; Young, H. F. / Prediction tree for severely head-injured patients. In: Journal of Neurosurgery. 1991 ; Vol. 75, No. 2. pp. 251-255.
@article{7cea4c764b094ebaaec520f197af11f9,
title = "Prediction tree for severely head-injured patients",
abstract = "Prediction tree techniques are employed in the analysis of data from 555 patients admitted to the Medical College of Virginia hospitals with severe head injuries. Twenty-three prognostic indicators are examined to predict the distribution of 12-month outcomes among the five Glasgow Outcome Scale categories. A tree diagram, illustrating the prognostic pattern, provides critical threshold levels that split the patients into subgroups with varying degrees of risk. It is a visually useful way to look at the prognosis of head-injured patients. In previous analyses addressing this prediction problem, the same set of prognostic factors (age, motor score, and pupillary response) was used for all patients. These approaches might be considered inflexible because more informative prediction may be achieved by somewhat different combinations of factors for different patients. Tree analysis reveals that the pattern of important prognostic factors differs among various patient subgroups, although the three previously mentioned factors are still of primary importance. For example, it is noted that information concerning intracerebral lesions is useful in predicting outcome for certain patients. The overall predictive accuracy of the tree technique for these data is 77.7{\%}, which is somewhat higher than that obtained via standard prediction methods. The predictive accuracy is highest among patients who have a good recovery or die; it is lower for patients having intermediate outcomes.",
keywords = "Glasgow Outcome Scale, head injury, prediction tree, prognosis",
author = "Choi, {S. C.} and Muizelaar, {Jan Paul} and Barnes, {T. Y.} and A. Marmarou and Brooks, {D. M.} and Young, {H. F.}",
year = "1991",
language = "English (US)",
volume = "75",
pages = "251--255",
journal = "Journal of Neurosurgery",
issn = "0022-3085",
publisher = "American Association of Neurological Surgeons",
number = "2",

}

TY - JOUR

T1 - Prediction tree for severely head-injured patients

AU - Choi, S. C.

AU - Muizelaar, Jan Paul

AU - Barnes, T. Y.

AU - Marmarou, A.

AU - Brooks, D. M.

AU - Young, H. F.

PY - 1991

Y1 - 1991

N2 - Prediction tree techniques are employed in the analysis of data from 555 patients admitted to the Medical College of Virginia hospitals with severe head injuries. Twenty-three prognostic indicators are examined to predict the distribution of 12-month outcomes among the five Glasgow Outcome Scale categories. A tree diagram, illustrating the prognostic pattern, provides critical threshold levels that split the patients into subgroups with varying degrees of risk. It is a visually useful way to look at the prognosis of head-injured patients. In previous analyses addressing this prediction problem, the same set of prognostic factors (age, motor score, and pupillary response) was used for all patients. These approaches might be considered inflexible because more informative prediction may be achieved by somewhat different combinations of factors for different patients. Tree analysis reveals that the pattern of important prognostic factors differs among various patient subgroups, although the three previously mentioned factors are still of primary importance. For example, it is noted that information concerning intracerebral lesions is useful in predicting outcome for certain patients. The overall predictive accuracy of the tree technique for these data is 77.7%, which is somewhat higher than that obtained via standard prediction methods. The predictive accuracy is highest among patients who have a good recovery or die; it is lower for patients having intermediate outcomes.

AB - Prediction tree techniques are employed in the analysis of data from 555 patients admitted to the Medical College of Virginia hospitals with severe head injuries. Twenty-three prognostic indicators are examined to predict the distribution of 12-month outcomes among the five Glasgow Outcome Scale categories. A tree diagram, illustrating the prognostic pattern, provides critical threshold levels that split the patients into subgroups with varying degrees of risk. It is a visually useful way to look at the prognosis of head-injured patients. In previous analyses addressing this prediction problem, the same set of prognostic factors (age, motor score, and pupillary response) was used for all patients. These approaches might be considered inflexible because more informative prediction may be achieved by somewhat different combinations of factors for different patients. Tree analysis reveals that the pattern of important prognostic factors differs among various patient subgroups, although the three previously mentioned factors are still of primary importance. For example, it is noted that information concerning intracerebral lesions is useful in predicting outcome for certain patients. The overall predictive accuracy of the tree technique for these data is 77.7%, which is somewhat higher than that obtained via standard prediction methods. The predictive accuracy is highest among patients who have a good recovery or die; it is lower for patients having intermediate outcomes.

KW - Glasgow Outcome Scale

KW - head injury

KW - prediction tree

KW - prognosis

UR - http://www.scopus.com/inward/record.url?scp=0025895471&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025895471&partnerID=8YFLogxK

M3 - Article

C2 - 2072162

AN - SCOPUS:0025895471

VL - 75

SP - 251

EP - 255

JO - Journal of Neurosurgery

JF - Journal of Neurosurgery

SN - 0022-3085

IS - 2

ER -