HCI-Driven Machine Learning for Early Detection of Lung Cancer: An Ensemble Approach

Lung cancer is one of the deadliest cancers worldwide, resulting in millions of deaths annually. Early detection of lung nodules from the patient's case history and lifestyle is critical to treating this disease effectively. We proposed an innovative approach to predicting lung cancer diseases by utilizing a combination of four supervised classification machine learning algorithms and principal component analysis (PCA). The proposed model employs decision tree classifiers, random forest, KNN, and support vector machines (SVM) to classify patients into categories of having lung cancer or not. The study found that SVM and random forest had the highest accuracy of 94% among the algorithms used. PCA was employed to reduce the dimensionality of the data, and the model's performance was evaluated using precision, recall, and F1-Score. Beyond the technical aspects, our approach integrates Human-Computer Interaction (HCI) principles for a user-friendly web application seamlessly fitting into healthcare workflows. This tool not only assists healthcare practitioners but also contributes to predictive healthcare technology, with a focus on accessibility and an improved user experience. Its adaptability specifically extends to predicting lung cancer, promoting early detection, and enhancing overall healthcare outcomes.