As a result of the way most people conduct their lives, we are constantly impacted by diseases. Most people’s data in the healthcare area is analyzed based on the illnesses that have affected them because of their lifestyle, and some vital information that may assist in making better decisions may be concealed in the process. In this study, we train machine learning algorithms on data derived from individuals with various lifestyle conditions. In order to forecast the progression of a disease using the decision tree and KNN algorithms, we employ data visualization tools. The term “lung cancer” refers to the cancer that kills the most people every year. As a result, the ability to identify, forecast, and diagnose lung cancer at an early stage is of paramount importance, as it streamlines and accelerates the ensuing clinical board. Machine learning methods have been used to track the development of cancer and determine the best course of treatment. The technique uses a dataset with several characteristics, including age, smoking status, family history, and carcinogen exposure, to construct a decision tree model. The dataset is preprocessed to account for missing data and extreme values. The entropy-based method used to train the decision tree prioritizes the most informative qualities at each node. The suggested method may be used by healthcare providers to identify quickly and accurately those at high risk for getting lung cancer. In addition, we need to validate the data using the training data to make predictions. For the dataset, we may gather EMRs, or electronic health records, which provide detailed information on each patient’s medical history. If we can detect the causes of most incurable diseases early on, the suggested methodology will help protect the lives of most patients.