Lung cancer prediction: A performance analysis of machine learning classifiers

Lung cancer remains one of the most prevalent and deadly forms of cancer worldwide, necessitating advanced and accurate diagnostic tools to improve patient outcomes. The major factors that contribute to it are smoking, drinking, shortness of breath and many more. This study conducts a comprehensive performance analysis of various machine learning classifiers for the prediction of lung cancer. The classifiers evaluated include Decision Trees, Random Forests, Support Vector Machines, k-Nearest Neighbors, and Neural Networks. Utilizing a publicly available dataset, we preprocess the data to address imbalances and missing values, ensuring robustness in our analysis. The classifiers are assessed based on key performance metrics such as accuracy, precision, recall, F1-score, and area under the ROC curve (AUC- ROC). Our results indicate that ensemble methods, particularly Random Forests, exhibit superior predictive accuracy and reliability compared to other models. Additionally, the study highlights the importance of feature selection and hyperparameter tuning in enhancing model performance. This research underscores the potential of machine learning classifiers in lung cancer prediction, providing a foundation for future work aimed at integrating these models into clinical practice for early detection and personalized treatment planning. The implementation of this research utilizes Python programming language along with popular libraries such as scikit-learn and TensorFlow for machine learning and natural language processing tasks.