ARCHIVES

Since lung cancer is one of the leading causes of death worldwide, early detection and risk assessment are essential for improving survival rates. This paper presents a machine learning-based approach for identifying lung cancer risk using classification techniques and an interactive web-based prediction system. A survey dataset containing patient demographic details, lifestyle habits, and clinical symptoms was used for analysis.The data preprocessing stage included handling missing values, encoding categorical variables, feature scaling, and preparing the dataset for model training. Multiple machine learning models were developed and evaluated, including Random Forest, Logistic Regression, and Support Vector Machine (SVM). Among these, the Random Forest classifier achieved the best performance with an accuracy of 94.2%.The models were assessed using confusion matrix, ROC analysis, precision, recall, and F1-score. Additionally, a prediction system was developed that allows healthcare professionals to input patient data and receive real-time lung cancer risk predictions.The proposed system demonstrates the effectiveness of machine learning in healthcare analytics and decision support, offering a practical solution for early-stage lung cancer screening and risk evaluation.