Accurate Prediction of Neuroblastoma Outcome based on miRNA Expression Profiles

by   Katharina Morik, et al.

For neuroblastoma, the most common extracranial tumour of childhood, identification of new biomarkers and potential therapeutic targets is mandatory to improve risk stratification and survival rates. MicroRNAs are deregulated in most cancers, including neuroblastoma. We here analysed 430 miRNAs in 69 neuroblastomas by stem-loop RT-qPCR. Prediction of event-free survival (EFS) with Support Vector Machines (SVM) and actual survival times with Cox regression-based models (CASPAR) were highly accurate and were independently validated. SVM-accuracy for prediction of EFS was 88,7% (95%CI:88,5-88,8%). For CASPAR-based predictions, 5y-EFS probability was 0.19% (95%CI:0-38%) in the CASPAR-predicted short survival group compared to 0.78% (95%CI:64-93%) in the CASPAR-predicted long survival group. Both classifiers were validated on an independent test set yielding accuracies of 94.74%(SVM) and 5y-EFS probabilities as 0.25(95%CI:0.0-0.55) for short vs 1?0.0 for long survival (CASPAR), respectively. Amplification of the MYCN oncogene was highly correlated with deregulation of miRNA expression. In addition, 37 miRNAs correlated with TrkA expression, a marker of excellent outcome, and 6 miRNAs further analysed in vitro were regulated upon TrkA transfection, suggesting a functional relationship. Expression of the most significant TrkA-correlated miRNA, miR-542-5p, also discriminated between local and metastatic disease and was inversely correlated with MYCN amplification and event-free survival. We conclude that neuroblastoma patient outcome prediction using miRNA expression is feasible and effective. Studies testing miRNA-based predictors in comparison to and in combination with mRNA and aCGH information should be initiated. Specific miRNAs (e.g. miR-542-5p) might be important in neuroblastoma tumour biology, and qualify as potential therapeutic targets.



page 1

page 3

page 4

page 6

page 8

page 10


Deep radiomic features from MRI scans predict survival outcome of recurrent glioblastoma

This paper proposes to use deep radiomic features (DRFs) from a convolut...

Integration of Survival Data from Multiple Studies

We introduce a statistical procedure that integrates survival data from ...

Why comparing survival curves between two prognostic subgroups may be misleading

We consider the validation of prognostic diagnostic tests that predict t...

Predicting Kidney Transplant Survival using Multiple Feature Representations for HLAs

Kidney transplantation can significantly enhance living standards for pe...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.