Comparative Analysis Of The Data Mining Classification Algorithms For The Diagnosis Of Malaria

ABSTRACT

Data mining is the process of determining patterns, discovering correlations, trends or relationships in the area with large data sets Information Technology, medical science, biology, education, and human resources. In Healthcare, DM is useful in medical data to anticipate novel, useful and potential knowledge that can save a life, lessen treatment cost, increases diagnostic and prediction accuracy as well as save human resources. Data mining contains several techniques such as anomaly detection, classification, regression, clustering, time series analysis, association rule, and summarization.Classification is the most important application of data mining. In this study, we use classification technique in determine the best data mining algorithms to efficiently diagnose malaria.For the purpose of this study, the framework was developed and trained using Malaria data acquired from hospital. To achieve the objective of this study different experiments have been conducted to compare the performance of the five most effective algorithms in human disease diagnosis using Malaria patients‟ data set, and tested for performance accuracy using accuracy, sensitivity and specificity. The study concludes by describing best performing algorithm for the data mining Malaria diagnosis; Where among Artificial Neural Networks (ANN), Decision Trees, Naïve Bayes, and Support Vector Machines (SVM) the K Nearest Neighbors (K-NN) was selected to be the best algorithm with the highest score of 82% accuracy, 82% specificity and 84% sensitivity. Finally, the author provides recommendations for future research in the application of data mining to facilitate decisions relevant to Malaria diagnosis.