Abstract

Anemia is a worldwide health issue defined by diminished levels of hemoglobin in the blood, impairing its capacity to convey oxygen throughout the body. This illness may lead to numerous severe complications if not promptly detected and treated. Consequently, healthcare professionals require a rapid, precise, and data-driven diagnostic approach to facilitate informed decision-making. This study intends to implement and evaluate the efficacy of three machine learning algorithms: Random Forest (RF), Support Vector Machine (SVM), and Naive Bayes (NB), in the classification of anemic diseases utilizing clinical data. This work employs an experimental methodology encompassing data collection, preprocessing (data cleansing and normalization), model training with three techniques, and performance evaluation through accuracy measures. The experimental results indicate that the RF method outperforms both SVM and NB, achieving accuracy values of $100 \%$ each. These findings demonstrate that the Random Forest algorithm classifies anemia conditions with more efficacy and precision.

Concepts :

Access to Document

Citations by Year