Early Diagnosis of Lung Cancer Using Hyperparameter-Tuned Machine Learning Models

Globally, lung cancer is the leading cause of cancer-related deaths. Improving survival depends on early and precise identification, which is still mostly accomplished using antiquated techniques that are frequently ineffective and erroneous. In this study, we used patient demographic and clinical data to create a machine learning-based risk prediction model that aims to diagnose lung cancer early and accurately. To verify the performance on our lung cancer data set, we employed important machine learning algorithms such as logistic regression, random forest, and support vector machines (SVM). PCA for feature selection, resampling to balance classes, and handling missing values were all examples of preprocessing. Among models, Random Forest shown excellent efficiency in risk detection, while SVM ultimately.