Developing a Predictive Model for Early Asthma Detection

Asthma is a chronic respiratory disease that significantly affects quality of life and increases healthcare burden worldwide. Early detection remains challenging, as traditional diagnostic methods are often reactive and fail to capture complex risk factors. This work presents a predictive model for early asthma detection using machine learning techniques. By integrating local clinical data with diverse online datasets, the study improves model generalizability and predictive accuracy.Three algorithms-Random Forest, Support Vector Machine, and Neural Networks-were implemented and evaluated using standard performance metrics. Results show that Random Forest and Support Vector Machine achieved the highest accuracy of 95%, demonstrating strong reliability, while Neural Networks achieved 92%.The study highlights the effectiveness of combining diverse datasets and classical machine learning models for accurate disease prediction. It provides a practical framework for early asthma detection, supporting improved clinical decision-making, timely intervention, and better patient outcomes.