International Research Journal of Education and Technology

In our daily lives, remarkable advancements in the healthcare industry are creating essential data. This data must be processed in order to extract valuable information for analysis, forecasting, providing suggestions, and making decisions. Using data mining and machine learning approaches turn existing data into useful knowledge. In medicine, accurate illness prediction is critical for both preventive and effective treatment planning. A lack of accuracy might be fatal on occasion. Using CBC (Complete Blood Count) data from the Pathology Center, this study investigates monitored basic Bayes, random forest, and decision tree machine learning algorithms for predicting anemia. The results reveal that the Naive Bayes technique outperforms C4.5 and Random Forest in terms of accuracy.

Key Words:  Anemia, Classification Algorithms, Complete Blood Count (CBC), Decision Making.