Abstract
Acute exacerbations of chronic obstructive pulmonary disease (AECOPD) are critical clinical events that necessitate prompt intervention, yet their detection remains challenging in primary care, especially in resource-limited regions where a lack of awareness leads to delayed diagnoses. To address this issue, we developed an AI-based AECOPD detection system that leverages standard smartphone microphones for auscultation, specifically designed for novice users and analyzing sounds to screen for AECOPD without requiring subjective patient-reported scales. Our system demonstrated robust performance, achieving an area under the curve (AUC) of 0.955 (95% CI: 0.929–0.976). A state-transition health-economic model projected per-capita net savings of 456.9 CNY (95% CI: −88.2 to 1,779.3) with a 90.3% probability of positive returns, supporting cost-effective implementation. This research highlights the potential of AI-driven solutions to enhance COPD management in underserved populations, providing a scalable tool to promote health equity where access to pulmonary specialists is constrained.
Leave a Reply