An IoMT based Ensemble Classification Framework to Predict Treatment Response in Hepatitis C Patients
Taher M. Ghazal, Sagheer Abbas, Munir Ahmad, Shabib Aftab
Abstract
Hepatitis C is considered a deadly disease as mortality rate in the patients suffering from this disease is very high, if not properly treated. This research proposes an IOMT based ensemble classification framework for the prediction of treatment response of a drug: “L-Ornithine-L-Aspartate” (LOLA) in hepatitis c patients. The treatment with this drug is called LOLA therapy which is significant for the patients to recover from the effects of hepatitis c disease. To implement the proposed framework, we used the medical data of hepatitis c patients who are being treated with LOLA therapy. The proposed framework integrates the predictive accuracy of two supervised machine learning techniques: Support Vector Machine (SVM) and Decision Tree (DT) by using Voting ensemble technique. The results reflect that the proposed ensemble framework performed well as compared to other published techniques on the prediction of treatment response for hepatitis c disease.