Advancements in technology and data analysis are crucial for developing non-invasive methods for early lung cancer detection. This paper proposes a novel system integrating wireless-enabled machine learning, specifically logistic regression models, with electronic nose volatile organic compound (VOC) sensors to enhance the accuracy of lung cancer detection. The electronic nose enables rapid and non-invasive analysis of VOC profiles, while logistic regression models offer robust classification capabilities. Wireless communication integration facilitates remote monitoring and data transmission, ensuring seamless implementation in clinical settings. A logistic regression model utilizing a comprehensive dataset of VOC profiles from lung cancer patients and healthy individuals demonstrates significant accuracy, sensitivity, and specificity in distinguishing between VOC profiles associated with lung cancer and those of healthy individuals. This integrated approach aims to enable earlier diagnosis and improve patient outcomes.