Design of a multi-signature ensemble classifier predicting neuroblastoma patients' outcome

Andrea Cornero,Luigi Varesio,Fabiola Blengio,Sara Barzaghi,Massimo Acquaviva,Alessandra Eva,Maria Carla Bosco,Rogier Versteeg,Paolo Fardin,Alexander Schramm

doi:10.1186/1471-2105-13-s4-s13

Abstract

BackgroundNeuroblastoma is the most common pediatric solid tumor of the sympathetic nervous system. Development of improved predictive tools for patients stratification is a crucial requirement for neuroblastoma therapy. Several studies utilized gene expression-based signatures to stratify neuroblastoma patients and demonstrated a clear advantage of adding genomic analysis to risk assessment. There is little overlapping among signatures and merging their prognostic potential would be advantageous. Here, we describe a new strategy to merge published neuroblastoma related gene signatures into a single, highly accurate, Multi-Signature Ensemble (MuSE)-classifier of neuroblastoma (NB) patients outcome.MethodsGene expression profiles of 182 neuroblastoma tumors, subdivided into three independent datasets, were used in the various phases of development and validation of neuroblastoma NB-MuSE-classifier. Thirty three signatures were evaluated for patients' outcome prediction using 22 classification algorithms each and generating 726 classifiers and prediction results. The best-performing algorithm for each signature was selected, validated on an independent dataset and the 20 signatures performing with an accuracy > = 80% were retained.ResultsWe combined the 20 predictions associated to the corresponding signatures through the selection of the best performing algorithm into a single outcome predictor. The best performance was obtained by the Decision Table algorithm that produced the NB-MuSE-classifier characterized by an external validation accuracy of 94%. Kaplan-Meier curves and log-rank test demonstrated that patients with good and poor outcome prediction by the NB-MuSE-classifier have a significantly different survival (p < 0.0001). Survival curves constructed on subgroups of patients divided on the bases of known prognostic marker suggested an excellent stratification of localized and stage 4s tumors but more data are needed to prove this point.ConclusionsThe NB-MuSE-classifier is based on an ensemble approach that merges twenty heterogeneous, neuroblastoma-related gene signatures to blend their discriminating power, rather than numeric values, into a single, highly accurate patients' outcome predictor. The novelty of our approach derives from the way to integrate the gene expression signatures, by optimally associating them with a single paradigm ultimately integrated into a single classifier. This model can be exported to other types of cancer and to diseases for which dedicated databases exist.

Highlights

Neuroblastoma is the most common pediatric solid tumor of the sympathetic nervous system
The method has been applied on a dataset containing the gene expression profiles of 182 neuroblastoma patients with a distribution of the common risk factors (Table 1) compatible with what reported in the literature [19]
The process can be subdivided into three main phases (Figure 1): i) single signature classifiers generation, ii) classifiers filtering on performance figures and, iii) NB-Multi-Signature Ensemble (MuSE)-classifier training and validation

Summary

Introduction

Neuroblastoma is the most common pediatric solid tumor of the sympathetic nervous system. Several studies utilized gene expression-based signatures to stratify neuroblastoma patients and demonstrated a clear advantage of adding genomic analysis to risk assessment. Neuroblastoma is the most common pediatric solid tumor, deriving from ganglionic lineage precursors of the sympathetic nervous system [1]. It is diagnosed during infancy and shows notable heterogeneity with regard to histology and clinical behavior, ranging from rapid progression associated with metastatic spread and poor clinical outcome to spontaneous, or therapy-induced regression into benign ganglioneuroma. Several groups have developed gene expression-based approaches to stratify neuroblastoma patients [4,5,6,7,8,9,10]. Prognostic gene signatures were described and neuroblastoma classifiers were trained to predict the risk class and/or patients ‘outcome [4,5,6,7,8,9,10]

Methods

Results

Discussion

Conclusion