Applying particle swarm optimization-based decision tree classifier for wart treatment selection

Abstract Wart is a disease caused by human papillomavirus with common and plantar warts as general forms. Commonly used methods to treat are immunotherapy cryotherapy. The selection of proper treatment vital cure warts. This paper establishes classification regression tree (CART) model based on particle swarm optimisation help patients choose between proposed can accurately predict the response two methods. Using an improved algorithm (PSO) optimise parameters instead traditional pruning algorithm, more concise accurate obtained. Two experiments conducted verify feasibility model. On hand, five benchmarks performance PSO algorithm. other experiment wart datasets conducted. Results show that effective. method classifies better than k-nearest neighbour, C4.5 logistic regression. It also performs conventional for CART Moreover, decision established in this study interpretable understandable. Therefore, doctors reduce medical cost improve quality healing operation.