Data Mining Techniques for Predictive Classification of Anemia Disease Subtypes

Abstract

Anemia, characterized by insufficient red blood cells or reduced hemoglobin, hinders oxygen transport in the body. Understanding the different types of anemia is vital to tailor effective prevention and treatment. This research explores the role of data mining in predicting and classifying anemia types, focusing on complete blood count (CBC) and demographic data. Data mining is the key to building models that help healthcare professionals diagnose and treat anemia. Employing the cross-industry standard process for data mining (CRISP-DM), with its six phases, facilitates this effort. Our study compared Naïve Bayes, J48 Decision Tree, and Random Forest algorithms using RapidMiner tools, evaluating precision, mean recall, and mean precision. The J48 decision tree outperformed the others, highlighting the importance of algorithm choice in anemia classification models. Furthermore, our analysis identified renal disease-related and chronic anemia as the most prevalent types, with greater occurrence among females. Recognizing gender disparities in the prevalence of anemia informs customized healthcare decisions. Understanding demographic factors in specific types of anemia is crucial to effective care strategies.