Computational Intelligence Techniques for Disease Prediction

Abstract

Objective: The aim of the study is to examine the performance of six Machine Learning algorithms for reducing the complexity and cost of chronic disease diagnosis by prediction. Methods: I used six machine learning techniques for the classification of chronic disease datasets including Breast Cancer, Chronic Kidney Disease and Liver Patient datasets. SVM, NB, KNN, RF, DT and LR were used for prediction and diagnosis of chronic disease. The performance of the used techniques was evaluated with sensitivity, specificity, f 1 measure and total accuracy. Results: All the machine learning classifiers show the accuracy level above 95% for both of the kidney disease and breast cancer prediction. Hence, the accuracy level nearly of 75% for liver disease prediction using all classification classifiers. In Kidney disease datasets, NB and RF has achieved the best performance than the other classification techniques in terms of accuracy by obtaining the highest accuracy as 100% respectively. The performance of analyzing breast cancer datasets, SVM achieved the highest performance with maximum classification accuracy of 97.07% while second highest classification accuracy is achieved by NB and RF (97%). Moreover, in the terms of accuracy for analyzing liver disease datasets, LR achieved the highest accuracy (i.e. 0.75%) and NB achieved the worst performance (i.e. 0.53%). Conclusion: My findings showed that the NB, RF outperformed for analyzing the kidney datasets. NB, RF, SVM achieves best performance for performing experiment on breast cancer. In addition, LR have shown the utmost performance on liver disease datasets. In summary, our study has emphasized the research trends and scope in relation to chronic disease and clinical research fields by machine learning techniques, which has an effective impact in bio-medical fields.