An optimized hybrid dynamic Bayesian network approach using differential evolution algorithm for the diagnosis of Hepatocellular Carcinoma

Computational Intelligence methods have been applied to the automatic discovery of predictive models for the diagnosis of Hepatocellular Carcinoma (a.k.a liver cancer). Evolutionary algorithms have lent themselves as efficient and robust methods for evolving best parameter values that optimize feature selection methods. Different computational methods for discovering more robust set of molecular features for liver cancer have been proposed. These include methods combining other nature-inspired evolutionary algorithms such as Particle Swarm Optimization, with classifiers like Support Vector Machine (SVM). In this paper, we apply different variants of Differential Evolution algorithm to optimize the parameters of feature selection algorithms using a proposed two-stage approach. Stage one fine-tunes the parameters of the feature selection methods and selects high quality features. In stage two, Dynamic Bayesian Network (DBN) is applied to infer temporal relationships of the selected features. We demonstrate our method using gene expression profiles of liver cancer patients. The results show that the SVM-based predictive model with the radial basis function kernel yielded a predictive accuracy of 100%. This model and a sub-set of the features consist of only 8 features (genes) that have been regarded as most informative set for the diagnosis of the disease. In addition, among all these eight genes, the DBN model of the selected features reveals that SPINT2 gene inhibits HGF activator which prevents the formation of active hepatocytes growth factor, which makes up over 80% of liver cells.