Application of genetic programming in analysis of quantitative gene expression profiles for identification of nodal status in bladder cancer

Nodal involvement in bladder cancer is an independent indicator of prognosis. This study employed an iterative machine learning process called genetic programming on quantitative expression values of 70 genes to classify primary urothelial carcinoma samples into those associated with or without nodal metastasis. The generated rules showed a strong predilection for ICAM1, MAP2K6 and KDR resulting in gene expression motifs that cumulatively suggested a pattern ICAM1>MAP2K6>KDR for node positive cases.