Real Time Lung Cancer Prediction Using Lazy Learning Technique

The lungs are vital organs responsible for oxygenating the body and filtering out harmful substances. The main causes for lung cancer are smoking, Alcohol use and Air pollution. Lung cancer is crucial for improving patient predicting and reducing mortality rate. The mortality rate from lung cancer continues to rise across all age groups. The primary objective is to evaluate the effectiveness of these algorithms in early lung cancer detection which improves the patient survival rates. Machine learning revolutionizes health care by facilitating early disease detection through robust data analysis techniques. This study utilizes supervised machine learning algorithms, including Support Vector Machine (SVM), Naive Bayes, Logistic Regression and also K-Nearest Neighbors (KNN), to identify early stages of lung cancer risk. Among the tested models, Logistic Regression and also K-Nearest Neighbors (KNN) has the highest accuracy, achieving an accuracy rate of 99.99%. This models achieves highest performance and evaluated based on precision, recall, accuracy and area under the curve.