Neuroblastoma is a common childhood tumor comprising cases with rapid disease progression as well as spontaneous regression. Although numerous prognostic factors have been identified, risk evaluation in individual patients remains difficult. To define a reliable prognostic predictor and gene signatures characteristic of biological subgroups, we performed mRNA expression profiling of 68 neuroblastomas of all stages. Expression data were analysed using support vector machines (SVM-rbf), prediction analysis of microarrays (PAM), k-nearest neighbors (k-NN) algorithms and multiple decision trees. SVM-rbf performed best of all methods, and predicted recurrence of neuroblastoma with an accuracy of 85\% (sensitivity 77\%, specificity 94\%). PAM identified a classifier of 39 genes reliably predicting outcome with an accuracy of 80\%. In comparison, conventional risk stratification based on stage, age and MYCN-status only reached a predictive accuracy of 64\%. Kaplan-Meier analysis using the PAM classifier indicated a 5-year survival of 20 versus 78\% for patients with unfavorably versus favorably predicted neuroblastomas, respectively (P = 0.0001). Significance analysis of microarrays (SAM) identified additional genes differentially expressed among subgroups. MYCN-amplification and high expression of NTRK1/TrkA demonstrated a strong association with specific gene expression patterns. Our data suggest that microarray-derived data in addition to traditional clinical factors will be useful for risk assessment and defining biological properties of neuroblastoma.
%0 Journal Article
%1 Schramm2005
%A Schramm, Alexander
%A Schulte, Johannes H.
%A Klein-Hitpass, Ludger
%A Havers, Werner
%A Sieverts, Hauke
%A Berwanger, Bernd
%A Christiansen, Holger
%A Warnat, Patrick
%A Brors, Benedikt
%A Eils, Jürgen
%A Eils, Roland
%A Eggert, Angelika
%D 2005
%J Oncogene
%K Algorithms; Amplification; Analysis Analysis; Array Assessment; Cohort Decision Expression Gene Humans; Infant, Infant; Messenger, Neoplasm Neuroblastoma, Newborn; Nuclear Oligonucleotide Oncogene Profiling; Prognosis; Proteins, RNA, Receptor, Risk Sequence Staging; Studies; Survival Trees; analysis; genetics/pathology; genetics; trkA,
%N 53
%P 7902--7912
%R 10.1038/sj.onc.1208936
%T Prediction of clinical outcome and biological characterization of neuroblastoma by expression profiling.
%U http://dx.doi.org/10.1038/sj.onc.1208936
%V 24
%X Neuroblastoma is a common childhood tumor comprising cases with rapid disease progression as well as spontaneous regression. Although numerous prognostic factors have been identified, risk evaluation in individual patients remains difficult. To define a reliable prognostic predictor and gene signatures characteristic of biological subgroups, we performed mRNA expression profiling of 68 neuroblastomas of all stages. Expression data were analysed using support vector machines (SVM-rbf), prediction analysis of microarrays (PAM), k-nearest neighbors (k-NN) algorithms and multiple decision trees. SVM-rbf performed best of all methods, and predicted recurrence of neuroblastoma with an accuracy of 85\% (sensitivity 77\%, specificity 94\%). PAM identified a classifier of 39 genes reliably predicting outcome with an accuracy of 80\%. In comparison, conventional risk stratification based on stage, age and MYCN-status only reached a predictive accuracy of 64\%. Kaplan-Meier analysis using the PAM classifier indicated a 5-year survival of 20 versus 78\% for patients with unfavorably versus favorably predicted neuroblastomas, respectively (P = 0.0001). Significance analysis of microarrays (SAM) identified additional genes differentially expressed among subgroups. MYCN-amplification and high expression of NTRK1/TrkA demonstrated a strong association with specific gene expression patterns. Our data suggest that microarray-derived data in addition to traditional clinical factors will be useful for risk assessment and defining biological properties of neuroblastoma.
@article{Schramm2005,
__markedentry = {[bbrors:6]},
abstract = {Neuroblastoma is a common childhood tumor comprising cases with rapid disease progression as well as spontaneous regression. Although numerous prognostic factors have been identified, risk evaluation in individual patients remains difficult. To define a reliable prognostic predictor and gene signatures characteristic of biological subgroups, we performed mRNA expression profiling of 68 neuroblastomas of all stages. Expression data were analysed using support vector machines (SVM-rbf), prediction analysis of microarrays (PAM), k-nearest neighbors (k-NN) algorithms and multiple decision trees. SVM-rbf performed best of all methods, and predicted recurrence of neuroblastoma with an accuracy of 85\% (sensitivity 77\%, specificity 94\%). PAM identified a classifier of 39 genes reliably predicting outcome with an accuracy of 80\%. In comparison, conventional risk stratification based on stage, age and MYCN-status only reached a predictive accuracy of 64\%. Kaplan-Meier analysis using the PAM classifier indicated a 5-year survival of 20 versus 78\% for patients with unfavorably versus favorably predicted neuroblastomas, respectively (P = 0.0001). Significance analysis of microarrays (SAM) identified additional genes differentially expressed among subgroups. MYCN-amplification and high expression of NTRK1/TrkA demonstrated a strong association with specific gene expression patterns. Our data suggest that microarray-derived data in addition to traditional clinical factors will be useful for risk assessment and defining biological properties of neuroblastoma.},
added-at = {2015-04-09T12:36:21.000+0200},
author = {Schramm, Alexander and Schulte, Johannes H. and Klein-Hitpass, Ludger and Havers, Werner and Sieverts, Hauke and Berwanger, Bernd and Christiansen, Holger and Warnat, Patrick and Brors, Benedikt and Eils, J{\"{u}}rgen and Eils, Roland and Eggert, Angelika},
biburl = {https://www.bibsonomy.org/bibtex/205495869b5a0a14e6e212a27939d066c/bbrors},
doi = {10.1038/sj.onc.1208936},
institution = {Department of Pediatric Oncology and Hematology, University Hospital of Essen, Hufelandstr 55, Essen 45122, Germany.},
interhash = {acbee7ae9e612e064ffe883896b1f645},
intrahash = {05495869b5a0a14e6e212a27939d066c},
journal = {Oncogene},
keywords = {Algorithms; Amplification; Analysis Analysis; Array Assessment; Cohort Decision Expression Gene Humans; Infant, Infant; Messenger, Neoplasm Neuroblastoma, Newborn; Nuclear Oligonucleotide Oncogene Profiling; Prognosis; Proteins, RNA, Receptor, Risk Sequence Staging; Studies; Survival Trees; analysis; genetics/pathology; genetics; trkA,},
language = {eng},
medline-pst = {ppublish},
month = Nov,
number = 53,
owner = {bbrors},
pages = {7902--7912},
pii = {1208936},
pmid = {16103881},
timestamp = {2015-04-09T12:36:21.000+0200},
title = {Prediction of clinical outcome and biological characterization of neuroblastoma by expression profiling.},
url = {http://dx.doi.org/10.1038/sj.onc.1208936},
volume = 24,
year = 2005
}