Yiming Ding1,2,3, Jiaxi Wang4, Jiandong Gao4,5, Qiang Fang6, Yanru Li1,2,3, Wen Xu1,2,3, Ji Wu7,8, Demin Han9,10,11. 1. Beijing Tongren Hospital, Capital Medical University, 1, Dongjiaominxiang Street, Dongcheng District, Beijing, 100730, People's Republic of China. 2. Obstructive Sleep Apnea-Hypopnea Syndrome Clinical Diagnosis and Therapy and Research Centre, Capital Medical University, Beijing, 100730, People's Republic of China. 3. Key Laboratory of Otolaryngology Head and Neck Surgery, Ministry of Education, Capital Medical University, Beijing, 100730, People's Republic of China. 4. Department of Electronic Engineering, Tsinghua University, Room 8301, Luomu Building, Beijing, China. 5. Center for Big Data and Clinical Research, Institute for Precision Medicine, Tsinghua University, Room 8301, Luomu Building, Beijing, China. 6. Institute of Linguistics, Chinese Academy of Social Sciences, Beijing, China. 7. Department of Electronic Engineering, Tsinghua University, Room 8301, Luomu Building, Beijing, China. wuji_ee@mail.tsinghua.edu.cn. 8. Center for Big Data and Clinical Research, Institute for Precision Medicine, Tsinghua University, Room 8301, Luomu Building, Beijing, China. wuji_ee@mail.tsinghua.edu.cn. 9. Beijing Tongren Hospital, Capital Medical University, 1, Dongjiaominxiang Street, Dongcheng District, Beijing, 100730, People's Republic of China. deminhan_ent@hotmail.com. 10. Obstructive Sleep Apnea-Hypopnea Syndrome Clinical Diagnosis and Therapy and Research Centre, Capital Medical University, Beijing, 100730, People's Republic of China. deminhan_ent@hotmail.com. 11. Key Laboratory of Otolaryngology Head and Neck Surgery, Ministry of Education, Capital Medical University, Beijing, 100730, People's Republic of China. deminhan_ent@hotmail.com.
Abstract
PURPOSE: There are upper airway abnormalities in patients with obstructive sleep apnea (OSA), and their speech signal characteristics are different from those of unaffected people. In this study, the severity of OSA was evaluated automatically by machine learning technology based on the speech signals of Chinese people. METHODS: In total, 151 adult male Mandarin native speakers who had suspected OSA completed polysomnography to assess the severity of the disease. Chinese vowels and nasal sounds were recorded in sitting and supine positions, and the accuracy of predicting the apnea-hypopnea index (AHI) of the participants using a machine learning method was analyzed based on features extracted from the speech signals. RESULTS: 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 collected from participants recorded in the sitting and supine positions and by using a linear support vector machine (SVM); we classified the participants 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. CONCLUSION: This study constructed a severity evaluation model of OSA based on speech signal processing and machine learning, which can be used as an effective method to screen patients with OSA. In addition, it was found that Chinese pronunciation can be used as an effective feature to predict OSA.
PURPOSE: There are upper airway abnormalities in patients with obstructive sleep apnea (OSA), and their speech signal characteristics are different from those of unaffected people. In this study, the severity of OSA was evaluated automatically by machine learning technology based on the speech signals of Chinese people. METHODS: In total, 151 adult male Mandarin native speakers who had suspected OSA completed polysomnography to assess the severity of the disease. Chinese vowels and nasal sounds were recorded in sitting and supine positions, and the accuracy of predicting the apnea-hypopnea index (AHI) of the participants using a machine learning method was analyzed based on features extracted from the speech signals. RESULTS: 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 collected from participants recorded in the sitting and supine positions and by using a linear support vector machine (SVM); we classified the participants 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. CONCLUSION: This study constructed a severity evaluation model of OSA based on speech signal processing and machine learning, which can be used as an effective method to screen patients with OSA. In addition, it was found that Chinese pronunciation can be used as an effective feature to predict OSA.
Entities:
Keywords:
Machine learning; Obstructive sleep apnea (OSA); Speech signal processing
Authors: Y Finkelstein; D Wexler; E Horowitz; G Berger; A Nachmani; M Shapiro-Feinberg; D Ophir Journal: Laryngoscope Date: 2001-04 Impact factor: 3.325
Authors: Virend K Somers; David P White; Raouf Amin; William T Abraham; Fernando Costa; Antonio Culebras; Stephen Daniels; John S Floras; Carl E Hunt; Lyle J Olson; Thomas G Pickering; Richard Russell; Mary Woo; Terry Young Journal: J Am Coll Cardiol Date: 2008-08-19 Impact factor: 24.094
Authors: Warren R Ruehland; Peter D Rochford; Fergal J O'Donoghue; Robert J Pierce; Parmjit Singh; Andrew T Thornton Journal: Sleep Date: 2009-02 Impact factor: 5.849
Authors: Richard B Berry; Rohit Budhiraja; Daniel J Gottlieb; David Gozal; Conrad Iber; Vishesh K Kapur; Carole L Marcus; Reena Mehra; Sairam Parthasarathy; Stuart F Quan; Susan Redline; Kingman P Strohl; Sally L Davidson Ward; Michelle M Tangredi Journal: J Clin Sleep Med Date: 2012-10-15 Impact factor: 4.062