The effect of vitamin B12 deficiency on blood count using data mining

Abstract

Healthcare systems create vast amount of data collected from medical examination. Data mining techniques are widely used in healthcare systems to detect diseases in early stages. In this paper, we applied four data mining techniques to find the relation between vitamin B12 levels and blood cell count. Four data mining techniques were applied to real patients’ dataset: Neural Networks (MLP), Naïve Bayes, J48, and JRip. The resulting models were evaluated using the real datasets obtained from King Khalid University Hospital (KKUH), Riyadh, Saudi Arabia. Experimental results showed that both MLP and JRip techniques were capable of classifying the dataset correctly regardless of the size of the dataset.