NON-INVASIVE DETECTION OF ANEMIA BASED ON EYE CHARACTERISTICS THROUGH MACHINE LEARNING TECHNIQUES

Abstract

Anemia, characterized by a deficiency in red blood cells or hemoglobin, poses significant health challenges globally. Traditional diagnosis relies on invasive blood tests, which may be uncomfortable and require specialized equipment. This paper investigates non-invasive detection methods using eye-related metrics and machine learning algorithms. By analysing datasets correlating eye-related metrics with anemia status, the study aims to identify patterns for early detection. Advantages over traditional methods include non-invasiveness, accessibility, early detection capabilities, and potential for automation. These findings propose a promising avenue for improving anemia screening and intervention strategies.