Clinical Decision Support System for Anemia Identification and Severity Stratification

The research addresses the pervasive challenges faced by anemic individuals globally. This innovative solution goes beyond traditional approaches by incorporating real-time data collection, including critical parameters such as Complete Blood Count (CBC), age, and gender providing a dynamic and holistic view of an individual's health status. The integration of CBC data, coupled with demographic information, enhances the precision of the monitoring process, allowing for a more accurate assessment of anemia risk and severity. The collected real-time data is seamlessly transmitted to a centralized cloud platform, where advanced machine learning models, specifically recurrent neural networks (RNNs), come into play. Trained on a diverse dataset that includes CBC counts, age, and gender, these models excel in capturing temporal patterns and subtle variations associated with anemia. The result is a robust classification system that achieves a remarkable 97% accuracy, facilitating early detection and tailored interventions. By combining real-time data collection with sophisticated machine learning and deep learning models, the proposed system represents a significant advancement in addressing the challenges posed by anemia. This holistic and personalized approach not only ensures timely intervention but also contributes to improved healthcare outcomes for individuals affected by this widespread condition.