Optimizing Skin Disease Diagnosis using Metaheuristic Algorithms: A Comparative Study

Skin disease, having a wide range of symptoms and appearances, has been putting stern challenge in the field of dermatology. In deep demand, the work reveals the potential of metaheuristic algorithms for skin disease diagnosis and aims a comparison with traditional diagnostic techniques. For the study, a real-time dataset is collected including clinical information, medical images and histopathological data of several patients affected with different skin diseases. The test dataset is reviewed to ensure its perfection and representation among several categories of diseases. Several metaheuristic algorithms are introduced like particle swarm optimization (PSO), genetic algorithm (GA), antlion optimization (ALO) and ant colony optimization (ACO) in the study. To examine the performance of the proposed metaheuristic algorithms, a comparative analysis is conducted. Furthermore, certain performance metrics such as diagnostic accuracy and results of standard deviation, mean fitness score, best fitness score, and worst fitness score are calculated. The results of our comparative analysis also indicate variations in selecting different metaheuristic algorithms. Therefore, our evaluation presents the significance of selecting the suitable algorithm for medical diagnosis based on the requirements of the clinical data and disease type.