UZAMSAL DİKKAT İÇEREN EVRİŞİMLİ SİNİR AĞI İLE SPİROMETRİDE ÖKSÜRÜK TESPİTİ

In the last decade, app-enabled home spirometry has become widely used for monitoring respiratory patients. This adaptation introduced a need to ensure American Thoracic Society (ATS) and European Respiratory Society (ERS) quality requirements are met without clinical supervision. Reliability of spirometry depends on correct technique and patient effort. Unlike other errors that follow rule-based definitions [1], cough lacks a standardized approach. Clinicians typically detect cough through direct observation or flow-volume curve inspection, which are inapplicable in unsupervised home testing. To address this challenge, a Convolutional Neural Network (CNN) with spatial attention mechanism has been developed. The proposed approach generates location-specific weights, helping the model focus on cough-indicative regions in flow-volume curves. To capture spatial and temporal information, a novel color-coding scheme is used: red for the FEV1 region (0-1 second) and blue for the remaining segment. This encoding enables the model to distinguish between clinically significant coughs affecting FEV1 measurements and those occurring later that may not invalidate tests. By ensuring reliable quality control, our approach could reduce invalid tests and improve remote respiratory monitoring outcomes. While developed primarily for home use, the model has potential applications in clinical settings, particularly in primary care where spirometry expertise may be limited.