Fecha de publicación: 30/11/2024 Fuente: PubMed "honey" Comput Biol Med. 2024 Nov 29;184:109348. doi: 10.1016/j.compbiomed.2024.109348. Online ahead of print.ABSTRACTCancer, a pervasive and devastating disease, remains a leading global cause of mortality, emphasizing the growing urgency for effective detection methods. Gene Expression Microarray (GEM) data has emerged as a crucial tool in this context, offering insights into early cancer detection and treatment. While deep learning methods offer promise in detecting various cancers through GEM analysis, they suffer from high dimensionality inherent in gene sequences, preventing optimal detection performance across diverse cancer types. Additionally, existing methods often resort to synthetic features and data augmentation to enhance performance. To address these challenges and enhance accuracy, a novel Binary Honey Badger Algorithm (BHBA) integrated with the Gene Residual Network (GRNet) method has been proposed. Our approach capitalizes on BHBA's feature reduction mechanism, eliminating the need for additional preprocessing steps. Comprehensive evaluations on three well-established datasets representing lung and blood-type cancers demonstrate that our method reduces GEM data size by approximately 40 % and achieves a superior accuracy improvement of around 1 % in lung cancer types compared to state-of-the-art methods.PMID:39615230 | DOI:10.1016/j.compbiomed.2024.109348