Ensemble learning method for enhancing healthcare classification

Abstract

Ensemble learning technique is proposed in this paper for better efficiency of healthcare classification and prediction. Healthcare industry is an ever-increasing rise in the number of doctors, patients, medicines and medical records. Medical history records are beneficial for not only individual but also human society. Three popular machine learning algorithms, namely Naïve Bayes, Support Vector Machine and Decision Tree are applied on this history data as base learners. Two forms of ensemble learning namely bagging and boosting are applied with each base learner for better accuracy than using individually. Comparison results are presented and the experiments show that ensemble classifiers perform better than the base classifier alone. Cervical cancer dataset is used as case study.