Implementasi Random Forest dalam Klasifikasi Kanker Paru-Paru

Abstract

Lung cancer is a serious disease that threatens global health due to its high morbidity and mortality rates. To reduce lung cancer mortality, a more precise diagnostic approach is needed. The aim of this study was to improve the sensitivity and specificity in detecting lung cancer, to support early detection efforts and more effective management. The research method involved a series of steps from data collection to model performance evaluation. Data was collected, cleaned, and analyzed for correlation before going through the preprocessing stage. Model training was conducted using the Random Forest Classifier algorithm, which proved effective in modeling the complexity of lung cancer data. The results prove that the model used can achieve an accuracy rate of 78%. The uniqueness of this research lies in the application of machine learning techniques to improve lung cancer diagnosis. By combining ADASYN oversampling with the Random Forest Classifier algorithm, this research has proven potential in the sensitivity and specificity of detecting the disease. These findings provide an important foothold in the development of more advanced and efficient diagnostic methods for lung cancer, paving the way for more effective early detection efforts and better disease management.