Machine Learning Approaches for Enhanced Diagnosis of Hematological Disorders

This research examined the feasibility of utilizing ML algorithms to improve the initial detection and classification of anemia and other blood disorders. The following study employed several traditional machine learning models: additional ML and AI methods were subsequently evaluated including - LightGB, CatBoost, Decision Tree, Gradient Boosting, Random Forest and XGBoost to blood-based features (RBC, WBC, HGB, and PLT). The results demonstrated that LightGB had the highest accuracy of 98.38%, then followed by CatBoost at 98.37%. The Decision Tree and Gradient Boosting models respectively demonstrated an accuracy of 98.05%. The accuracy of Random Forest and XGBoost was 97.72%. These results show the possibility of ML techniques being able to uncover higher-level complex patterns in medical data to improve accuracy, particularly for anemia. The study presented new evidence and baseline models to promote ML to expedite clinical decision making to provide timely intervention and develop personalized health care. The study provided evidence and potential usages for ML models to enable better clinical decision and action. The findings of this study explained that in the future using advanced technologies or deep learning, or addressing concerns relating to explainable AI methods, the capabilities in clinical use should be optimized and expanded.