Optimizing Anemia Detection Using Effective Computational Techniques

Abstract

Worldwide, anemia is the most common blood disease. The World Health Organization (WHO) defines anemia as the lack of red blood cells, which prevents the body from carrying enough oxygen to satisfy its requirements. Anemia is characterized by decreased erythrocyte mass, blood hemoglobin, and hemocrit levels. Early detection and accurate diagnosis are essential for effective management and therapy. The study's goal is to develop an algorithm for optimizing anemia detection utilizing an effective computational technique. The study proposed a brand-new Dynamic Gannet-tuned Light Gradient Boosting Machine (DG-LGBM) model for the detection of anemia in typical clinical practice settings. In this study, anemia data is collected from a publicly available dataset from Kaggle. The data was preprocessed using data cleaning and normalization for the obtained data. The study aims to improve the predicted accuracy and efficiency of anemia diagnosis by utilizing clinical and biochemical markers. The results demonstrate that, in comparison to traditional methods, the DG-LGBM model performed better in terms of anemia detection rates, highlighting the potential of computational tools to completely transform anemia screening practices. In a comparative analysis, the proposed model is validated using precision (92%), recall (91.71%) f1-score (93.07%), and accuracy (91.06%) values. In addition to advancing the area of medical diagnostics, this study highlights the significance of technology in enhancing healthcare outcomes for impacted communities.