Lung cancer is the leading cause of cancer-related mortality worldwide. Early cancer identification has shown to be very beneficial for effectively treating the illness. Using current advances in artificial intelligence, it is possible to create a lung cancer therapy prototype without negatively impacting the environment. It will save time and money since fewer resources will be squandered, and less labor will be needed to perform manual tasks. We proposed LCP-ML Framework for early lung cancer prediction using ML algorithms. The dataset has been collected from the Kaggle repository. The raw images are denoising using a multi-layer perception (MLP) algorithm. The image histogram equalization has been utilized with CLAHE. The segmentation part has been executed with Robert Operator. Finally, the image classification has been utilized with Random Forest (RF), K-Nearest Neighbor (KNN), Decision Tree (DT), and Naïve Bayes (NB) algorithms. The experimental results indicate that the classification accuracy of the approach proposed in this research can reach 87% using the Naïve Bayes algorithm.