A Harmful Disorder: Predictive and Comparative Analysis for fetal Anemia Disease by Using Different Machine Learning Approaches

Abstract

Anemia is a major issue for public health with significant implications for national development, it remains a largely neglected health problem in many developing countries. Iron deficiency is responsible for at least 50% of all cases of anemia and kills nearly 1 million people each year. Africa and Southeast Asia account for three quarters of these deaths. Surprisingly, one of the top ten risk factors that contributes to the global burden of disease is iron deficiency anemia (IDA). This study investigated the use of machine learning models to predict anemia. The study compared the performance of five different machine learning models: K-Nearest Neighbors, Logistic Regression, Support Vector Machines, Gaussian Naive Bayes, and Light Gradient Boosting Machines. These models are combined using a voting classifier method to improve prediction accuracy. The study highlights the importance of accurately predicting diseases in the medical field. The ability to predict anemia at the right time is essential for effective prevention and treatment. This study demonstrates the potential of machine learning models to predict anemia and improve disease prevention and treatment. Using advanced algorithms and data processing techniques can help doctors make accurate predictions and make decisions, leading to better patient outcomes. This research result shows that the voting classifier achieved 99.95% accuracy.