A huge innovation in diagnosis of obstructive sleep apnea syndrome: With an artificial intelligence-based algorithm, obstructive sleep apnea syndrome can now be diagnosed with pulmonary function test

Abstract

Obstructive sleep apnea syndrome (OSAS) is a life-threatening disease characterized by upper airway narrowing or obstruction. The diagnostic process is difficult, costly, and time-consuming. Many individuals with OSAS do not apply for a diagnosis or are unaware of their disease. This study aimed to develop a practical, fast, and reliable diagnostic system for early diagnosis and treatment of OSAS. For the first time, features were extracted from flow-volume curves obtained using a Pulmonary Function Test (PFT), and an Artificial Intelligence (AI)-based algorithm was developed to diagnose OSAS. Spearman correlation coefficients determined the degree of influence of the features in determining OSAS. Several models were created using different features and AI methods according to their effect levels. The models obtained by hyperparameter optimization and cross-validation were tested with unseen data, and their performance was evaluated using seven different criteria. Using only five features extracted from the flow-volume curve (TLC/PIF, PIF/PEF, TLC/FIF50, TLC/FIF25, and FIF25/FEF25), OSAS was diagnosed with 97.1% accuracy using the Neural Network (NN) algorithm. The results showed that OSAS can be diagnosed quickly and reliably using PFT available at every hospital. The features extracted from the flow-volume curve could be used as biomarkers for diagnosing OSAS. The proposed method can be adapted to PC-based spirometry devices without additional hardware developments. This is a significant innovation in both literature and practice. This method will enable early diagnosis for patients and many people unaware of their disease. This will shed light on several future studies.