Machine Learning Based Web-App to Predict Lung Disease Using SMOTE Analysis

Lung disease pose significant health risks world-wide, encompassing a range of conditions affecting respiratory function. Leveraging machine learning, this study explores predictive models for early detection of lung disease. By analyzing the dataset encompassing symptomatology and clinical features, machine learning algorithms facilitate accurate identification of potential cases. Among various techniques, logistic regression emerges as a robust method, demonstrating high accuracy in predicting disease onset. Synthetic Minority Over-sampling Technique (SMOTE) Analysis is also been explored and is proven to be a useful tool to improve the quality of the prediction. A user-friendly interface is developed to empower individuals in monitoring their respiratory health proactively.