Abstract :

Air Pollution Has Evolved Into One Of The Most Critical Public-health Challenges Of The Decade, Directly Influencing Respiratory And Cardiovascular Disease Burdens Across Urban And Semi-urban Regions. While Massive Environmental Datasets Are Now Available, Most Existing Monitoring Platforms Only Visualize Pollutant Levels And Fail To Convert This Information Into Actionable Health-risk Insights. Traditional Systems Rely Heavily On Static Thresholds Or Rule-based Estimates, Which Cannot Adapt To Dynamic Pollution Patterns, Seasonal Variations, Or Complex Pollutant Interactions. These Approaches Offer Limited Predictive Accuracy, Lack Automated Forecasting, And Provide No Deep Correlation Between Airquality Indicators And Real Health Impact Metrics Such As Asthma Or Cardiovascular Case Surges. To Address These Shortcomings, There Is A Clear Need For An Intelligent, Data-driven System That Can Continuously Learn From Environmental And Medical Datasets And Produce Real-time, User-friendly Health-risk Predictions. The Proposed System Introduces A Full-stack Machine Learning Platform Capable Of Classifying Health-impact Severity And Predicting Disease Case Counts Using A Hybrid Modeling Approach. The Backend Integrates Random Forests (RF), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost), And A Hybrid Deep Quality Network-Random Forest (DQN-RF) Architecture To Capture Both Linear And Non-linear Dependencies Within Pollution Data. The System Performs Classification Of Health-impact Categories And Regression-based Forecasting For Respiratory And Cardiovascular Cases. Advanced Preprocessing, Feature Scaling, Automated Training, Performance Evaluation, And Batch Prediction Pipelines Ensure Reliability And Scalability. A Flask-based Web Interface Enables Real-time Predictions For Both Individual Readings And Entire Datasets. This Hybrid Prediction Framework Significantly Enhances Public-health Readiness By Transforming Raw Air-quality Data Into Early-warning Health Indicators. The System’s Ability To Detect High-risk Pollution Patterns, Forecast Potential Disease Surges, And Deliver Actionable Insights Makes It Valuable For Environmental Agencies, Healthcare Planners, And Smart-city Applications Aiming To Minimize Pollution-related Health Impacts.

Published:

22-6-2026

Issue:

Vol. 26 No. 6 (2026)

Page Nos:

1287-1296

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite