<![CDATA[Lung disease is a serious respiratory disorder that requires early detection for proper treatment. The advancement of data mining technology enables the diagnostic process by analyzing patient behavioral data to predict the likelihood of developing lung disease. This study applies the Random Forest algorithm using data obtained from Kaggle, containing information such as age, gender, smoking habits, activities, and pre-existing conditions. The dataset was processed using the RapidMiner application through a data preprocessing phase, separating labeled and unlabeled data. A total of 998 records were used for model training and 29,002 for prediction. The model evaluation employed the Performance operator to measure prediction accuracy. The results show that the Random Forest algorithm achieved 94.33% accuracy with high precision and recall values, proving its effectiveness in handling large datasets and supporting early detection of lung disease.]]>
Copyrights © 2025
