In today's digital era, email spam may lead to phishing scams, malware infections, and even identity theft, making email security a top priority. Spam detection algorithms that are based on machine learning have seen widespread application, and their effectiveness may be improved with the help of bio-inspired metaheuristic algorithms. This study provides, how bio- inspired metaheuristic algorithms may be used in conjunction with machine learning models for spam identification. We talk about how to optimize the parameters of machine learning models for spam detection using genetic algorithms, particle swarm optimization, and ant colony optimization. Additionally, we discuss the significance of feature selection and extraction in the development of effective spam detection models. Finally, we shed light on how bio-inspired metaheuristic algorithms may be used to improve email security by strengthening spam detection systems' precision and efficacy.