PREDICTIVE MODELLING FOR EARLY DETECTION OF LUNG CANCER USING MACHINE LEARNING

Abstract

Lung cancer remains a leading cause of mortality worldwide, and early detection is of crucial importance to maximize patient survival. In this study, machine learning techniques are employed to predict the presence of lung cancer from the data. After pre-processing the dataset based on the missing values and choosing salient features, two different supervised learning algorithms, Random Forest and Logistic Regression, will be applied for classifying instances into cancerous or non-cancerous cases. Their performance will be evaluated and compared on accuracy, precision, recall, and F1-score metrics. Experimental results show that the Random Forest classifier outperforms Logistic Regression, providing higher prediction accuracy in detecting lung cancer at an early stage. The findings support the potential capacity of machine learning methods to assist in medical diagnosis and clinical decision-making.