Improving Sickle Cell Anaemia Classification in Nilgiri Tribes through Multimodal RBC Spot Extraction Using Optimized Deep Stacking Network Algorithm

Sickle Cell Anemia (SCA) is a prevalent genetic blood disorder that disproportionately affects the health of the Nilgiri tribes. Early and accurate diagnosis is pivotal for effective management of the disease. This research proposes an innovative approach to Multimodal RBC Spot Extraction using Optimized Deep Stacking Network (MRSE-ODSN) Algorithm to classify SCA diagnosis within this community by harnessing the synergies of multimodal Red Blood Cell (RBC) image analysis. The MRSE-ODSN framework begins with acquiring diverse RBC images encompassing brightfield microscopy, phase-contrast imaging, and fluorescence microscopy. Each imaging modality captures distinctive aspects of RBC morphology and function. The sample data were collected from the NAWA-Nilgiri Adivasi Welfare Association in Nilgris, which contains data from 300 patients with 14 features related to SCA that were acquired. Rigorous preprocessing and augmentation techniques ensure data quality and resilience. A sophisticated architecture tailored for sequential feature extraction from multimodal RBC images. ODSN expertly integrates with CNN to classify sickle cell anemia efficiently within the Nilgiri tribes. The proposed model obtained 98.01 percent accuracy. By employing MRSE-ODSN, healthcare practitioners can potentially offer timely interventions, personalized treatments, and enhanced disease management strategies, thereby positively impacting the health and well-being of the Nilgiri tribes.