Advancing lung cancer diagnosis with bio-inspired algorithms: a comprehensive assessment

Lung cancer is a prevalent and deadly disease with a high global incidence rate. For efficient treatment with a positive prognosis for patients, early identification with precise subtype categorization of lung cancer is essential. Bio-inspired algorithms have emerged as promising tools for solving complex medical problems in recent years. This paper comprehensively reviews bio-inspired algorithms used for lung cancer prediction and classification. The current study investigates the use of several bio-inspired algorithms for identifying and forecasting problems involving lung cancer, such as genetic algorithms, particle swarm optimization, artificial neural networks, and ant colony optimization. These algorithms mimic the behaviour of natural systems to optimize model parameters, improve feature selection, and dimensionality reduction methods and enhance prediction accuracy.