Ensembled artificial neural networks for diffuse large B-cell lymphoma classification

In order to classify two types of diffuse large B-cell lymphoma (DLBCL), which are the germinal-center type (GCB) and the activated B-cell type (ABC), non-medical methods (i.e. engineering method such as ensembled artificial neural networks (EANN)) were applied to do quantitative analysis. Sensitivity analysis (SA) for EANN was carried out to evaluate the significance ranking of the miRNAs and finally selected 5 most important miRNAs. Besides, classical linear and logistic regression models were developed for comparison with EANN classification results. Their results were both evidently worse than EANN model. This study proves that each lymphoma type has a distinctive pattern of miRNAs expression. EANN model achieved successful results. Specially, the 5 selected important miRNAs will be helpful for further study.