Improving Classification Accuracy Using Hybrid Machine Learning Algorithm on Clinical Datasets

Abstract

In the present era, maintaining a healthy and disease-free life is complex due to multiple personal and environmental impacts. Early identification and diagnosis will help human beings lead a sustainable life. However, to achieve this, health care data has to be processed in an efficient manner with more accuracy. Thus, the impacts of diseases or future impacts can be predicted or detected and proper medication can be provided by the physicians. Machine learning (ML) has been shown to be effective in assisting in making decisions and predictions from the large quantity of data produced by the healthcare industry. In this paper we have studied and implemented many traditional machine learning algorithms which are K-Nearest Neighbor algorithm (KNN), Support Vector Machine (SVM), Decision Tree (DT) AND Artificial Neural Network (ANN). Based on output we have implemented hybrid model by combining the above mentioned algorithms to archive more accuracy. Accuracy measure has been used to compare the effectiveness and performance of the individual algorithms and the proposed hybrid approach. We have observed that the classification accuracy has been improved for different clinical datasets with the proposed hybrid model using a stacking classifier technique.