Early Detection of Sickle Cell Anemia in Nilgiri Tribes Using a Hybrid Swin Transformer-Based RNN with Improved Weighted Quantum Monkey Optimization Algorithm Optimization

Background: Early detection of Sickle Cell Anemia (SCA) is crucial for timely intervention and effective disease management, particularly in vulnerable populations like the Nilgiri tribes. Traditional diagnostic methods can be time-consuming and require specialized expertise. Deep learning techniques have shown promise in automating early-stage detection, but there is a need for improved models to enhance accuracy and efficiency. This study aims to develop a novel deep learning model that leverages a Hybrid Swin Transformer-Based Recurrent Neural Network (RNN) integrated with an Improved Weighted Quantum Monkey Optimization (IWQMO) algorithm for early-stage prediction of SCA in the Nilgiri tribes. Methods: The proposed hybrid model combines the Swin Transformer’s hierarchical feature extraction with an RNN's temporal pattern recognition capabilities. The IWQMO algorithm is utilized to optimize feature selection, ensuring the most relevant attributes are prioritized for classification. The model is trained and evaluated on a dataset of 300 Nilgiri tribespeople's medical records provided by the NAWA-Nilgiri Adivasi Welfare Association. Performance metrics, including accuracy, precision, recall, and F1 score, were used to evaluate model efficacy. Results: The hybrid model demonstrated superior performance compared to traditional approaches. The Swin Transformer enhanced feature extraction, while the RNN improved temporal prediction. The IWQMO algorithm effectively selected the most pertinent features, contributing to a more accurate SCA classification. The model’s performance was benchmarked against existing techniques, showing improved accuracy, precision, and recall. Conclusion: The Hybrid Swin Transformer-RNN model integrated with the IWQMO algorithm significantly improves early prediction of SCA, outperforming traditional diagnostic methods. This approach has the potential to provide more timely and accurate predictions, leading to better healthcare outcomes for the Nilgiri tribes. The findings underscore the potential of deep learning techniques for advancing public health initiatives in vulnerable populations.