Prediction of NSCLC recurrence from microarray data with GEP

Abstract

Lung cancer is one of the deadliest diseases in the world. Non-small cell lung cancer (NSCLC) is the most common and dangerous type of lung cancer. Despite the fact that NSCLC is preventable and curable for some cases if diagnosed at early stages, the vast majority of patients are diagnosed very late. Furthermore, NSCLC usually recurs sometime after treatment. Therefore, it is of paramount importance to predict NSCLC recurrence, so that specific and suitable treatments can be sought. Nonetheless, conventional methods of predicting cancer recurrence rely solely on histopathology data and predictions are not reliable in many cases. The microarray gene expression (GE) technology provides a promising and reliable way to predict NSCLC recurrence by analysing the GE of sample cells. This study proposes a new model from GE programming to use microarray datasets for NSCLC recurrence prediction. To this end, the authors also propose a hybrid method to rank and select relevant prognostic genes that are related to NSCLC recurrence prediction. The proposed model was evaluated on real NSCLC microarray datasets and compared with other representational models. The results demonstrated the effectiveness of the proposed model.

Fig. 1

Process of building a GEP classifier

Fig. 2

Flowchart of the NSCLC recurrence prediction method based on GEP model. The gene selection model selects different number of genes from different microarray datasets

Fig. 3

Accuracy and standard deviation values on the datasets for GEP, RBFN, DT, NB and SVM models

Fig. 4

Sensitivity and standard deviation values on the datasets for GEP, RBFN, DT, NB and SVM models

Fig. 5

Specificity and standard deviation values on the datasets for GEP, RBFN, DT, NB and SVM models

Fig. 6

AU curve and standard deviation values on the datasets for GEP, RBFN, DT, NB and SVM models

Fig. 7

Graph of GEP training model on GSE8894 dataset. The X‐axis represents the observed order (the samples order from 1 to 97) and the Y‐axis represents the observation values (samples values according to GEP model). The small point represents the real value in the class of the dataset (Target) and the big point represents the misclassification result from GEP model. The cut‐off point of GEP model was at −25.231. The points above the cut‐off represent the positive values (NSCLC recurrence) and the cases under the cut‐off represent the negative values (diseases free)

Fig. 8

Graph of GEP testing model on GSE8894 dataset. The X‐axis represents the observed values order (the sample order from 1 to 41) and the Y‐axis represents the observation (samples values according to GEP model). The small point represents the real value in the class of the dataset (Target) and the big point represents the misclassification result from GEP model. The cut‐off of GEP model was at −25.231. The points above the cut‐off represent the positive values (NSCLC recurrence) and the cases under the cut‐off represent the negative values (disease free)