COPD Detection Using Respiratory Sounds and Convolutional Neural Network

Chronic obstructive pulmonary disease (COPD) is a progressive and debilitating lung disease that affects millions of people worldwide. Early detection and diagnosis of COPD are critical to improving patient outcomes and reducing healthcare costs. Machine learning algorithms have shown promise in accurately identifying COPD using acoustics. We will explore feature extraction technique, such as Mel-frequency cepstral coefficients (MFCCs) to extract discriminative acoustic features. The extracted features will then be used to train various ML algorithm, Convolutional neural networks. Our results demonstrate that transfer learning significantly improves the accuracy, sensitivity, and specificity of COPD detection, outperforming all other models tested. Our findings suggest that transfer learning has great potential for COPD detection and may lead to earlier diagnosis, better management, and improved patient outcomes.