In this research, using a dataset of 1000 patient records that we have taken from Kaggle dataset repository, on which we have performed a thorough analysis to forecast the risk levels of lung cancer, which were divided into three categories: low, medium and high. We attempted to train and test the data for optimal predictive accuracy using sophisticated machine learning models, specifically Naive Bayes (NB), Logistic Model Tree (LMT), Random Tree (RT) and Decision Stump (DS). The Logistic Model Tree (LMT) was found to be the best performer following a thorough evaluation based on key performance indicators like accuracy, Root Absolute Error (RAE), Mean Absolute Error (MAE), Root Relative Square Error (RRSE) and Root Mean Square Error (RMSE). Notably, the LMT model outperformed the other three models with an astounding accuracy rate of 98%. To further support its effectiveness, the Random Tree (RT) model also showed minimal errors across all error metrics. The high accuracy attained by the LMT model demonstrates its exceptional performance, which forms the basis of the recommendation to use it for lung cancer risk prediction. Not only did this model perform better than the others, but its low error rates across multiple metrics also demonstrated its superior predictive power. Accurately estimating the risk of lung cancer has significant potential clinical implications, providing doctors with a useful tool for early intervention and individualized patient care. The results of this study highlight how crucial it is to use advanced machine learning methods in healthcare analytics, especially when it comes to cancer risk assessment. We believe that this research will advance predictive analytics for healthcare and lead to improved patient outcomes and a proactive approach to lung cancer management, as we recommend the use of the LMT model in lung cancer risk prediction.