Detection and Classification Model for Respiratory Diseases Using Machine Learning Techniques

In this study, we aim to develop a respiratory disease detection and classification model using machine learning techniques. Respiratory diseases are a significant global health problem, and early detection is critical to improving patient outcomes. In this study, we collected data from multiple sources to analyze and compare the performance of several machine learning algorithms, including kNN, SVM, Gradient Boosting, Adaboost, Neural Network, Random Forest, Naïve Bayes, and Logistic Regression. These models were evaluated based on performance metrics such as Area Under the Curve (AUC), classification accuracy, Fl Score, precision, and recall. The results showed that Random Forest and Naïve Bayes models performed best in terms of accuracy and class separation ability. This study also emphasized the importance of feature analysis and correlation in improving model effectiveness. These findings are expected to contribute to the development of more accurate diagnostic tools for respiratory diseases, as well as support more timely and effective medical interventions.