Enhanced Classification of Lyme Disease Rashes Through Deep Attribute Blending Techniques

Lyme disease, caused by Borrelia burgdorferi and transmitted by tick bites, often presents with distinctive rashes that can be challenging to diagnose accurately. This study explores the application of deep attribute blending techniques to enhance the classification of Lyme disease rashes using three Convolutional Neural Network (CNN) architectures: ResNet, SqueezeNet, and Xception called Deep Attribute Blending (DAB) ensemble machine learning algorithm. Constructed an ensemble model that leverages the strengths of each architecture to improve classification performance. The results demonstrate that the ensemble model achieved an accuracy of 96.28% and an F1 score of 0.97, significantly outperforming individual models. The findings highlight the potential of deep learning approaches in supporting clinical diagnosis and improving patient outcomes in Lyme disease.