Wart Treatment Decision Support Using Support Vector Machine

Warts are noncancerous benign tumors caused by the Human Papilloma Virus (HPV). The success rates of cryotherapy and immunotherapy, two common treatment methods for cutaneous warts, are 44% and 72%, respectively. The treatment methods, therefore, fail to cure a significant percentage of the patients. This study aims to develop a reliable machine learning model to accurately predict the success of immunotherapy and cryotherapy for individual patients based on their demographic and clinical characteristics. We employed support vector machine (SVM) classifier utilizing a dataset of 180 patients who were suffering from various types of warts and received treatment either by immunotherapy or cryotherapy. To balance the minority class, we utilized three different oversampling methods- synthetic minority oversampling technique (SMOTE), borderline-SMOTE, and adaptive synthetic (ADASYN) sampling. F-score along with sequential backward selection (SBS) algorithm were utilized to extract the best set of features. For the immunotherapy treatment method, SVM with radial basis function (RBF) kernel obtained an overall classification accuracy of 94.6% (sensitivity = 96.0%, specificity = 89.5%), and for the cryotherapy treatment method, SVM with polynomial kernel obtained an overall classification accuracy of 95.9% (sensitivity = 94.3%, specificity = 97.4%). The obtained results are competitive and comparable with the congeneric research works available in the literature, especially for the immunotherapy treatment method, we obtained 4.6% higher accuracy compared to the existing works. The developed methodology could potentially assist the dermatologists as a decision support tool by predicting the success of every unique patient before starting the treatment process.