Anemia Prediction Based on Eye Condition Data Using Machine Learning

Anemia, a prevalent global health issue, can significantly impact an individual's well-being. This study explores the predictive capability of machine learning algorithms—Naive Bayes, Random Forest, and Decision Tree in diagnosing anemia based on eye condition data. Leveraging a dataset encompassing diverse eye-related parameters and anemia status, the models were trained and evaluated to classify whether an individual is affected by anemia. The research aimed to discern patterns and relationships between eye conditions and anemia, contributing to early detection and intervention strategies. Through rigorous analysis and experimentation, the models demonstrated promising accuracy in predicting anemia based on ocular features. The findings highlight the potential of utilizing non-invasive eye-related metrics for efficient anemia screening, offering a feasible approach for healthcare practitioners to enhance diagnostic procedures and facilitate timely intervention.

 Keywords: Decision tree , Random forest and Naïve Bayes and Machine learning techniques