Comparative Evaluation of Machine Learning Models for Medical Recommendation Systems

Advancing medical diagnosis and patient treatment relies heavily on the development of effective recommendation systems. This research investigates the performance of various Machine Learning algorithms, such as Random Forest Classifier, Stacking (LGBMClassifier + kNN), and XGBoost, when applied to medical datasets. The models are assessed using standard metrics like accuracy, precision, recall, and F1-score, revealing that XGBoost demonstrates the most superior results. Although stacking demonstrates promising performance, it lags slightly behind XGBoost. Random Forest, on the other hand, provides a solid benchmark. These results emphasize XGBoost's effectiveness for medical recommendation systems, advancing the use of Machine Learning in healthcare and ultimately leading to improved decision- making and patient care.