Lung cancer remains a leading cause of cancer-related deaths globally, emphasizing the need for accessible diagnostic tools. This research proposes an IoT-based machine learning lung cancer detection system, leveraging the Random Forest algorithm for real-time data monitoring and predictive analytics. Achieving 94.64% accuracy, the model outperformed K-Nearest Neighbors, Decision Trees, and Support Vector Classifier, particularly excelling in early-stage cancer detection. The system’s scalability and precision demonstrate its potential to transform lung cancer diagnostics, improve early detection rates, and extend quality healthcare to underserved areas, advancing predictive healthcare and proactive cancer management.