Gene expression-based classification of malignant gliomas correlates better with survival than histological classification

Catherine L. Nutt, D. R. Mani, Rebecca Betensky, Pablo Tamayo, J. Gregory Cairncross, Christine Ladd, Ute Pohl, Christian Hartmann, Margaret E. McLaughlin, Tracy T. Batchelor, Peter M. Black, Andreas Von Deimling, Scott L. Pomeroy, Todd R. Golub, David N. Louis

Research output: Contribution to journalArticle

Abstract

In modern clinical neuro-oncology, histopathological diagnosis affects therapeutic decisions and prognostic estimation more than any other variable. Among high-grade gliomas, histologically classic glioblastomas and anaplastic oligodendrogliomas follow markedly different clinical courses. Unfortunately, many malignant gliomas are diagnostically challenging; these nonclassic lesions are difficult to classify by histological features, generating considerable interobserver variability and limited diagnostic reproducibility. The resulting tentative pathological diagnoses create significant clinical confusion. We investigated whether gene expression profiling, coupled with class prediction methodology, could be used to classify high-grade gliomas in a manner more objective, explicit, and consistent than standard pathology. Microarray analysis was used to determine the expression of ∼12,000 genes in a set of 50 gliomas, 28 glioblastomas and 22 anaplastic oligodendrogliomas. Supervised learning approaches were used to build a two-class prediction model based on a subset of 14 glioblastomas and 7 anaplastic oligodendrogliomas with classic histology. A 20-feature κ-nearest neighbor model correctly classified 18 of the 21 classic cases in leave-one-out cross-validation when compared with pathological diagnoses. This model was then used to predict the classification of clinically common, histologically nonclassic samples. When tumors were classified according to pathology, the survival of patients with nonclassic glioblastoma and nonclassic anaplastic oligodendroglioma was not significantly different (P = 0.19). However, class distinctions according to the model were significantly associated with survival outcome (P = 0.05). This class prediction model was capable of classifying high-grade, nonclassic glial tumors objectively and reproducibly. Moreover, the model provided a more accurate predictor of prognosis in these nonclassic lesions than did pathological classification. These data suggest that class prediction models, based on defined molecular profiles, classify diagnostically challenging malignant gliomas in a manner that better correlates with clinical outcome than does standard pathology.

Original languageEnglish (US)
Pages (from-to)1602-1607
Number of pages6
JournalCancer Research
Volume63
Issue number7
StatePublished - Apr 1 2003

Fingerprint

Oligodendroglioma
Glioma
Glioblastoma
Gene Expression
Survival
Pathology
Confusion
Observer Variation
Medical Oncology
Gene Expression Profiling
Microarray Analysis
Neuroglia
Neoplasms
Histology
Learning
Genes
Therapeutics

ASJC Scopus subject areas

  • Oncology
  • Cancer Research

Cite this

Nutt, C. L., Mani, D. R., Betensky, R., Tamayo, P., Cairncross, J. G., Ladd, C., ... Louis, D. N. (2003). Gene expression-based classification of malignant gliomas correlates better with survival than histological classification. Cancer Research, 63(7), 1602-1607.

Gene expression-based classification of malignant gliomas correlates better with survival than histological classification. / Nutt, Catherine L.; Mani, D. R.; Betensky, Rebecca; Tamayo, Pablo; Cairncross, J. Gregory; Ladd, Christine; Pohl, Ute; Hartmann, Christian; McLaughlin, Margaret E.; Batchelor, Tracy T.; Black, Peter M.; Von Deimling, Andreas; Pomeroy, Scott L.; Golub, Todd R.; Louis, David N.

In: Cancer Research, Vol. 63, No. 7, 01.04.2003, p. 1602-1607.

Research output: Contribution to journalArticle

Nutt, CL, Mani, DR, Betensky, R, Tamayo, P, Cairncross, JG, Ladd, C, Pohl, U, Hartmann, C, McLaughlin, ME, Batchelor, TT, Black, PM, Von Deimling, A, Pomeroy, SL, Golub, TR & Louis, DN 2003, 'Gene expression-based classification of malignant gliomas correlates better with survival than histological classification', Cancer Research, vol. 63, no. 7, pp. 1602-1607.
Nutt, Catherine L. ; Mani, D. R. ; Betensky, Rebecca ; Tamayo, Pablo ; Cairncross, J. Gregory ; Ladd, Christine ; Pohl, Ute ; Hartmann, Christian ; McLaughlin, Margaret E. ; Batchelor, Tracy T. ; Black, Peter M. ; Von Deimling, Andreas ; Pomeroy, Scott L. ; Golub, Todd R. ; Louis, David N. / Gene expression-based classification of malignant gliomas correlates better with survival than histological classification. In: Cancer Research. 2003 ; Vol. 63, No. 7. pp. 1602-1607.
@article{aa91ed61b7fe4a4b9f02fb0270b27dc2,
title = "Gene expression-based classification of malignant gliomas correlates better with survival than histological classification",
abstract = "In modern clinical neuro-oncology, histopathological diagnosis affects therapeutic decisions and prognostic estimation more than any other variable. Among high-grade gliomas, histologically classic glioblastomas and anaplastic oligodendrogliomas follow markedly different clinical courses. Unfortunately, many malignant gliomas are diagnostically challenging; these nonclassic lesions are difficult to classify by histological features, generating considerable interobserver variability and limited diagnostic reproducibility. The resulting tentative pathological diagnoses create significant clinical confusion. We investigated whether gene expression profiling, coupled with class prediction methodology, could be used to classify high-grade gliomas in a manner more objective, explicit, and consistent than standard pathology. Microarray analysis was used to determine the expression of ∼12,000 genes in a set of 50 gliomas, 28 glioblastomas and 22 anaplastic oligodendrogliomas. Supervised learning approaches were used to build a two-class prediction model based on a subset of 14 glioblastomas and 7 anaplastic oligodendrogliomas with classic histology. A 20-feature κ-nearest neighbor model correctly classified 18 of the 21 classic cases in leave-one-out cross-validation when compared with pathological diagnoses. This model was then used to predict the classification of clinically common, histologically nonclassic samples. When tumors were classified according to pathology, the survival of patients with nonclassic glioblastoma and nonclassic anaplastic oligodendroglioma was not significantly different (P = 0.19). However, class distinctions according to the model were significantly associated with survival outcome (P = 0.05). This class prediction model was capable of classifying high-grade, nonclassic glial tumors objectively and reproducibly. Moreover, the model provided a more accurate predictor of prognosis in these nonclassic lesions than did pathological classification. These data suggest that class prediction models, based on defined molecular profiles, classify diagnostically challenging malignant gliomas in a manner that better correlates with clinical outcome than does standard pathology.",
author = "Nutt, {Catherine L.} and Mani, {D. R.} and Rebecca Betensky and Pablo Tamayo and Cairncross, {J. Gregory} and Christine Ladd and Ute Pohl and Christian Hartmann and McLaughlin, {Margaret E.} and Batchelor, {Tracy T.} and Black, {Peter M.} and {Von Deimling}, Andreas and Pomeroy, {Scott L.} and Golub, {Todd R.} and Louis, {David N.}",
year = "2003",
month = "4",
day = "1",
language = "English (US)",
volume = "63",
pages = "1602--1607",
journal = "Journal of Cancer Research",
issn = "0008-5472",
publisher = "American Association for Cancer Research Inc.",
number = "7",

}

TY - JOUR

T1 - Gene expression-based classification of malignant gliomas correlates better with survival than histological classification

AU - Nutt, Catherine L.

AU - Mani, D. R.

AU - Betensky, Rebecca

AU - Tamayo, Pablo

AU - Cairncross, J. Gregory

AU - Ladd, Christine

AU - Pohl, Ute

AU - Hartmann, Christian

AU - McLaughlin, Margaret E.

AU - Batchelor, Tracy T.

AU - Black, Peter M.

AU - Von Deimling, Andreas

AU - Pomeroy, Scott L.

AU - Golub, Todd R.

AU - Louis, David N.

PY - 2003/4/1

Y1 - 2003/4/1

N2 - In modern clinical neuro-oncology, histopathological diagnosis affects therapeutic decisions and prognostic estimation more than any other variable. Among high-grade gliomas, histologically classic glioblastomas and anaplastic oligodendrogliomas follow markedly different clinical courses. Unfortunately, many malignant gliomas are diagnostically challenging; these nonclassic lesions are difficult to classify by histological features, generating considerable interobserver variability and limited diagnostic reproducibility. The resulting tentative pathological diagnoses create significant clinical confusion. We investigated whether gene expression profiling, coupled with class prediction methodology, could be used to classify high-grade gliomas in a manner more objective, explicit, and consistent than standard pathology. Microarray analysis was used to determine the expression of ∼12,000 genes in a set of 50 gliomas, 28 glioblastomas and 22 anaplastic oligodendrogliomas. Supervised learning approaches were used to build a two-class prediction model based on a subset of 14 glioblastomas and 7 anaplastic oligodendrogliomas with classic histology. A 20-feature κ-nearest neighbor model correctly classified 18 of the 21 classic cases in leave-one-out cross-validation when compared with pathological diagnoses. This model was then used to predict the classification of clinically common, histologically nonclassic samples. When tumors were classified according to pathology, the survival of patients with nonclassic glioblastoma and nonclassic anaplastic oligodendroglioma was not significantly different (P = 0.19). However, class distinctions according to the model were significantly associated with survival outcome (P = 0.05). This class prediction model was capable of classifying high-grade, nonclassic glial tumors objectively and reproducibly. Moreover, the model provided a more accurate predictor of prognosis in these nonclassic lesions than did pathological classification. These data suggest that class prediction models, based on defined molecular profiles, classify diagnostically challenging malignant gliomas in a manner that better correlates with clinical outcome than does standard pathology.

AB - In modern clinical neuro-oncology, histopathological diagnosis affects therapeutic decisions and prognostic estimation more than any other variable. Among high-grade gliomas, histologically classic glioblastomas and anaplastic oligodendrogliomas follow markedly different clinical courses. Unfortunately, many malignant gliomas are diagnostically challenging; these nonclassic lesions are difficult to classify by histological features, generating considerable interobserver variability and limited diagnostic reproducibility. The resulting tentative pathological diagnoses create significant clinical confusion. We investigated whether gene expression profiling, coupled with class prediction methodology, could be used to classify high-grade gliomas in a manner more objective, explicit, and consistent than standard pathology. Microarray analysis was used to determine the expression of ∼12,000 genes in a set of 50 gliomas, 28 glioblastomas and 22 anaplastic oligodendrogliomas. Supervised learning approaches were used to build a two-class prediction model based on a subset of 14 glioblastomas and 7 anaplastic oligodendrogliomas with classic histology. A 20-feature κ-nearest neighbor model correctly classified 18 of the 21 classic cases in leave-one-out cross-validation when compared with pathological diagnoses. This model was then used to predict the classification of clinically common, histologically nonclassic samples. When tumors were classified according to pathology, the survival of patients with nonclassic glioblastoma and nonclassic anaplastic oligodendroglioma was not significantly different (P = 0.19). However, class distinctions according to the model were significantly associated with survival outcome (P = 0.05). This class prediction model was capable of classifying high-grade, nonclassic glial tumors objectively and reproducibly. Moreover, the model provided a more accurate predictor of prognosis in these nonclassic lesions than did pathological classification. These data suggest that class prediction models, based on defined molecular profiles, classify diagnostically challenging malignant gliomas in a manner that better correlates with clinical outcome than does standard pathology.

UR - http://www.scopus.com/inward/record.url?scp=0037381008&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037381008&partnerID=8YFLogxK

M3 - Article

VL - 63

SP - 1602

EP - 1607

JO - Journal of Cancer Research

JF - Journal of Cancer Research

SN - 0008-5472

IS - 7

ER -