Lung diseases, including COPD, lung cancer, and asthma, are serious global health issues, causing over seven million deaths annually. Advanced technologies, such as deep learning and the Random Forest algorithm, have been effectively utilized to detect and classify lung diseases from imaging data with high accuracy. This study aims to demonstrate the effectiveness of Random Forest in predicting lung diseases. The dataset used consists of 30,000 records with 11 attributes, collected from Kaggle and processed using Orange software version 3.36.2. The implementation of the Random Forest algorithm was conducted with 10 decision trees and six attributes considered at each split. The model was tested using Cross Validation with 10 folds. The testing results showed an AUC value of 0.993, indicating a very high level of accuracy. A confusion matrix was used to measure the model's performance through various metrics, including accuracy, precision, recall, F1-score, and AUC. This model achieved high accuracy, with ROC AUC values of 0.453 for predicting the presence of lung disease and 0.547 for predicting its absence. These results confirm that the Random Forest algorithm is an effective predictive tool for identifying lung diseases. This study makes a significant contribution to the development of more accurate and efficient diagnostic techniques, assisting medical professionals in identifying lung diseases in patients. With a deeper understanding of how this algorithm operates in the healthcare domain, it is expected to significantly enhance the quality of patient diagnosis and care.