Can obstructive sleep apnea be detected in speech signal characteristics? There is a recent study (Ding Y, et al., Sleep Breath. 2021 Jun;25(2):787-795. doi: 10.1007/s11325-020-02168-0), involving machine learning, which suggests yes.
In this study, conducted in Beijing’s Capital Medical University, 151 adult male subjects who had suspected OSA completed polysomnography to assess the severity of the syndrome, and were then assessed for vowel and nasal sounds, in sitting and supine positions; the accuracy of predicting the apnea-hypopnea index (AHI) of the participants using a machine learning method was analyzed against the speech signals.
Among the 151 participants, 75 had AHI > 30 events/h, and 76 had AHI ≤ 30 events/h. Various features, including linear prediction cepstral coefficients (LPCC), were extracted from the data with a linear support vector machine (SVM); participants were classified with thresholds of AHI = 30 and AHI = 10 events/h. The accuracies of the classifications were both 78.8%, the sensitivities were 77.3% and 79.1%, and the specificities were 80.3% and 78.0%, respectively.
There emerged a severity evaluation model of OSA based on speech signal processing and machine learning, which is validated for screening patients with OSA.
MyoNews from BreatheWorksTM is a report on trends and developments in oromyofunctional disorder and therapy. These updates are not intended as diagnosis, treatment, cure or prevention of any disease or syndrome.