With the world moving rapidly towards industrialization driven by economic growth and technological advancements, there is an alarming surge of air pollution leading to significant health concerns. In response, this work introduces a research-driven approach for a continuous air quality monitoring system, designed to continuously track air quality in real-time in the proximity and proactively predict potential health hazards for the user. Central to the system’s efficacy is a state-of-the-art hybrid Machine Learning model, seamlessly amalgamating the strengths of Adaptive Long Short-Term Memory (LSTM) and Auto-Regressive Integrated Moving Average (ARIMA) models, renowned for their ability in handling intricate time series data. This model is securely deployed on a cloud platform, ensuring not only accessibility but also scalability to meet current and future technological standards. The system primarily concentrates on the monitoring of air pollutants, such as PM2.5, PM10, and CO, ensuring that users have access to immediate and up-to-date insights into the air quality in their surroundings. Beyond this, the system goes a step further by employing this data to assess users’ potential risk of developing lung cancer. Through the use of Internet of Things (IoT) sensors, the system can issue timely and potentially life-saving insights, providing users with valuable information for decision-making improving their well-being. In a world, where the link between air quality and health is increasingly evident, our research-based initiative serves as a beacon for a healthier future, while also fostering environmental consciousness and public well-being.