A novel algorithm for disease diagnosis
Fei He, Huamin Yang, Liguo Fan - · 2012
In this paper, a disease diagnosis algorithm is proposed (AI), which is based on ant colony optimization (ACO) and information gain (IG). The proposed method includes two stages. First, an optimal feature subset is generated. Second, SVM is used to predict the results with three medical data sets(Wisconsin breast cancer, Pima Indians diabetes and Hepatitis). The numerical results and statistical analysis show that the proposed approach is capable of finding an optimal feature subset from a large noisy data set. In addition, AI performs significantly better than the other methods in terms of prediction accuracy with smaller subset of features.