Automated Quality Control For Respiratory Signals - Slow Vital Capacity (SVC)

Slow vital capacity (SVC) is a critical parameter in assessing lung function and diagnosing pulmonary diseases. Traditional methods for measuring SVC, while effective, often face challenges related to precision, accessibility, and patient compliance. This thesis investigates how Artificial Intelligence (AI) can enhance the accuracy, efficiency, and accessibility of SVC measurement and analysis. This study focuses on developing and validating AI-driven models using signal processing techniques combined with convolutional neural networks (CNNs) and traditional machine learning methods such as linear regression. The approach involves automated data pre-processing to extract meaningful features from the signals, followed by model training to perform accurate classifications. Despite the limitations of the dataset size, the methodology is designed to ensure reliable and consistent performance within the available data. The findings underline the potential of AI as a transformative tool in respiratory diagnostics, particularly for SVC measurement, paving the way for improved patient outcomes and resource-efficient healthcare systems. This work contributes to the growing field of AI-assisted pulmonary medicine and highlights future directions for innovation and interdisciplinary collaboration.