Enhancing Anemia Prediction in Adolescents: A Study of Machine-Learning Ensembles Incorporating Gaussian Naive Bayes Algorithm, Random Forest Classifier, and Bayesian Forest Fusion

Anemia is a worldwide health concern especially common in teenagers, affecting 46.3% of teenage girls globally, according to estimates. When the body lacks the number of healthy red blood cells that source oxygen to the tissues of our body, anemia, a common blood condition, develops. Numerous factors, such as iron deficiency, malnourishment, and chronic illnesses, might contribute to it. Teenage girls are more likely to acquire anemia because of several reasons, such as growth and development, poor food, and menstruation. This proposed study explores machine learning for accurate anemia prediction by the use of three models: Naive Bayes, Random Forest, and a novel hybrid model combining both. Analyzing a dataset of teenagers collected from a diagnostic center, this proposed research analyzes each model's performance from parameters including F1 score, precision, accuracy, and recall. This study marks the way for utilizing machine learning models in early anemia detection, that enables timely intervention and improved patient outcomes.