LUNG CANCER PREDICTION SYSTEM

Lung cancer is one of the leading causes of cancer-related deaths worldwide. Early diagnosis plays a crucial role in improving the survival rate of patients. Conventional diagnostic methods such as CT scans, MRI scans, chest X-rays, and biopsy procedures require specialized equipment and expert medical interpretation, making early detection challenging in many healthcare settings. Machine Learning techniques have emerged as an efficient solution for analyzing medical data and predicting diseases with high accuracy. The proposed Lung Cancer Prediction System utilizes supervised machine learning algorithms to analyze patient symptoms, demographic information, and lifestyle factors such as smoking habits, coughing, chest pain, wheezing, fatigue, shortness of breath, and chronic diseases. The collected data undergoes preprocessing, feature selection, and model training before predicting whether a patient is at high or low risk of developing lung cancer. Multiple algorithms including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Naïve Bayes are evaluated using performance metrics such as Accuracy, Precision, Recall, and F1-Score. Among these algorithms, Random Forest achieves the highest prediction accuracy due to its ensemble learning capability. The proposed system supports healthcare professionals by providing quick, reliable, and cost-effective predictions that encourage early diagnosis and timely medical intervention. [1]–[4]

Keywords: Lung Cancer, Machine Learning, Artificial Intelligence, Random Forest, Disease Prediction, Healthcare Analytics