This systematic review seeks to establish the application of ensemble learning approaches in lung cancer diagnosis with emphasis on 47 articles from 934 published between 2023 and 2024. The research data is collected from databases such as Science Direct, Proquest, EBSCOhost, and Google Scholar to understand the use of machine learning in medical diagnostics and enhance predictive and clinical outcomes. Our study, structured around the PRISMA framework, addresses three core research questions: First, the paper will outline the types and the frequency of Ensemble Learning techniques employed in the last lung cancer studies, the metrics applied in the evaluation of the models, and the type of data applied in these studies. These observations point to a general trend of employing more combinations of various algorithms to increase the predictive power and a particular interest in deep learning ensembles. These approaches can help enhance the diagnostic sensitivity and specificity crucial in the early detection of lung cancer. The findings of the analysis are based on the current practices of machine learning in the healthcare sector, and it maintains that ensemble learning may be a promising approach to cancer treatment. Thus, this review not only discloses the current approach and challenges but also depicts future advancements in lung cancer diagnosis.