Today, metaheuristic algorithms are considered powerful tools for solving complex problems and optimization. These algorithms are widely used, especially in the fields of optimization, machine learning, engineering, and computer science. The particle swarm optimization (PSO) algorithm is one of the popular metaheuristic algorithms that was introduced by Kennedy and Eberhardt in 1995 and quickly attracted the attention of researchers in various fields. This paper examines the PSO algorithm and its applications in the medical and healthcare fields. It explains and investigates the principles of PSO and its related parameters, followed by a review of various applications in the literature, highlighting its integration with techniques such as neural networks and machine learning. Applications of PSO include disease diagnosis, image processing, feature selection, drug discovery, medication scheduling, and bioinformatics. Notably, PSO has proven effective for the early detection of cardiovascular diseases, COVID-19, and the identification of polyps and cancer. Additionally, PSO is significant in optimizing therapeutic nanoparticles and treatment planning for radiation therapy. These results demonstrate PSO's capabilities in enhancing accuracy and efficiency in disease diagnosis and treatment, serving as a foundation for future research. A comparative analysis of PSO, Ant Colony Optimization (ACO), and Artificial Bee Colony (ABC) algorithms for medical image segmentation shows comparable performance accuracy, with some strengths or weaknesses in specific metrics.