Harnessing Machine Learning Techniques for Intelligent Disease Prediction

Abstract

Anemia, a prevalent medical illness characterized by a deficiency in red blood cells or hemoglobin, remains a substantial global health issue. The significance of timely identification and intervention in minimizing adverse health effects cannot be stressed. This research study provides a comprehensive analysis focused on the prediction of anemia utilizing three distinct machine learning (ML) algorithms: Logistic Regression (LR), K-Nearest Neighbors (KNN), and Naive Bayes (NB). The results of this research indicate that the logistic regression algorithm exhibits exceptional predictive capabilities, achieving a notable accuracy rate of 98.95%. The empirical results support the LR technique's superior performance in comparison to the KNN and NB algorithms within the specific context of anemia prediction. This work makes substantial contributions to comprehending the potential advantages of data-driven approaches in enhancing the timely identification of anemia. These findings' benefits are significant in expediting medical procedures and ultimately improving the overall quality of patient care.