Using Naïve Bayesian Network in Predicting Diseases: A Systematic Review

Due to the improvement of technology during the last decade, using machine learning algorithms for predicting diseases has found great importance. The goal of this research was to investigate the importance of Naïve Bayesian network as the most applied algorithm in predicting diseases and classifying relevant articles related to disease prediction with data mining algorithms.
This was a systematic review study. A comprehensive search was performed from 2007 to 2017 in online databases and search engines including Scopus, Science Direct, web of science and MEDLINE.
From a total of 90 identified abstracts through the research, 27 ones were compatible with inclusion and exclusion criteria. Naïve Bayesian network was compared with other algorithms and in 92% of articles (25 articles out of 27), it had better accuracy in disease prediction. Results of this research showed effectiveness of Naïve Bayesian algorithm in disease prediction.
Naïve Bayesian network is one of the best algorithms for disease prediction in comparison with experts’ decision and other algorithms. This algorithm can be used beside physicians’ decision to improve the accuracy of disease prediction.