收稿日期: 2016-07-07
修回日期: 2016-09-02
网络出版日期: 2017-03-30
基金资助
国家自然科学基金（No.61525203，No.61572308）；上海科委项目基金（No.13441901600）资助
Screening of SAHS Snore Based on ERB Correlation Dimension
Received date: 2016-07-07
Revised date: 2016-09-02
Online published: 2017-03-30
提出一种依据鼾声录音筛查睡眠呼吸暂停低通气综合征严重程度的新方法，使用关联维数计算方法分析鼾声的非线性性质.根据听觉心理感知尺度在整个频带上划分子带，通过计算听觉子带关联维数向量，刻画睡眠呼吸症状严重程度的分布状况.提取各类鼾声的子带关联维数特征，以期训练出高斯混合模型，判断SAHS患者病情的严重程度.该方法与黄金标准多导睡眠监测诊断相比，其诊断患病严重程度的正确率为90%，相关系数为0.96（P<0.001）.实验表明该方法能有效筛查鼾症严重程度，对辅助医疗和居家监护等有积极作用.
关键词： 睡眠呼吸暂停低通气综合征; 高斯混合模型; 鼾声; 关联维数
侯丽敏, 施丹, 刘焕成, 张伟涛 . 基于听觉子带关联维数的SAHS鼾声筛查[J]. 应用科学学报, 2017 , 35(2) : 181 -192 . DOI: 10.3969/j.issn.0255-8297.2017.02.005
This paper proposes a method for screening sleep apnea hypopnea syndrome (SAHS) by recording snore sound. Based on the equivalent rectangular bandwidth (ERB) scale used in psychoacoustics, the ERB correlation dimension (ECD) of snore is used to analyze and classify snores of different severity levels. For the training group, snore episodes were manually segmented and ECD features of snores were extracted to establish a Gaussian mixture model (GMM). The nocturnal snoring sound of the test group was validated to detect SAHS snores. The apnea hypopnea index (AHI) was estimated, to determine severity of SAHS. AHI is an average number of apneic events per hour of sleep. Compared with the polysomnography diagnosis that is a gold-standard, accuracy of SAHS severity reached 90%. The proposed method is useful in accessory examination of SAHS severity and for home uses.
[1] 武海滨,王浩,胡如英,钟节鸣,钱一建,王春梅,谢开婿,陈玲俐,龚巍巍. 成年人睡眠时间与脑卒中患病关系的研究[J]. 中华流行病学杂志,2015, 36(11):1210-1215. Wu H B, Wang H, Hu R Y, Zhong J M, Qian Y J, Wang C M, Xie K X, Chen L L, Gong W W. Association between sleep duration and stroke in adults[J]. Chinese Journal of Epidemiology, 2015, 36(11):1210-1215. (in Chinese)
[2] Niiranen T J, Kronholm E, Rissanen H, Partinen M, Jula A M. Self-reported obstructive sleep apnea, simple snoring, and various markers of sleep-disordered breathing as predictors of cardiovascular risk[J]. Sleep & Breathing, 2016, 20(2):589-596.
[3] Griggdamberger M, Ralls F. Cognitive dysfunction and obstructive sleep apnea:from cradle to tomb[J]. Current Opinion in Pulmonary Medicine, 2012, 18(6):580-587.
[4] Peppard P E, Young T, Barnet J H, Palta M, Hagen E W, Hla K M. Increased prevalence of sleep-disordered breathing in adults[J]. American Journal of Epidemiology, 2013, 177(9):1006-1014.
[5] 齐家超,林其昌,林新,陈晓. 睡眠呼吸暂停患者内脏脂肪指数与转氨酶水平及非酒精性脂肪肝发生的相关性[J]. 中华医学杂志,2015, 95(42):3420-3423. Qi J C, Lin Q C, Lin X, Chen X. Relationship of visceral adiposity index with serum aminotransferase and nonalcoholic fatty liver disease in patients with sleep apnea[J]. National Medical Journal of China, 2015, 95(42):3420-3423. (in Chinese)
[6] Beck R, Odeh M, Oliven A, Gavriely N. The acoustic properties of snores[J]. European Respiratory Journal, 1995, 8(12):2120-2128.
[7] Dafna E, Tarasiuk A, Zigel Y. Automatic detection of whole night snoring events using non-contact microphone[J]. PLoS ONE, 2013, 8(12):1-14.
[8] Camacho M, Robertson M, Abdullatif J, Certal V, Kram Y A, Ruoff C M, Brietzke S E, Capasso R. Smartphone apps for snoring[J]. Journal of Laryngology & Otology, 2015, 129(10):974-979.
[9] 杨弋,秦永,黄魏宁,彭好,许辉杰. 阻塞性睡眠呼吸暂停低通气综合征患者鼾声的声学特征研究[J]. 临床耳鼻咽喉头颈外科杂志,2012, 27(8):360-363. Yang Y, Qin Y, Huang W N, Peng H, Xu H J. Acoustic characteristics of snoring sound in patients with obstructive sleep apnea hypopnea syndrome[J]. Journal of Clinical Otorhinolaryngology Head and Neck Surgery, 2012, 27(8):360-363. (in Chinese)
[10] Ng A K, Koh T S, Baey E, Lee T K, Abeyratne U R, Puvanendran K. Could formant frequencies of snore signals be an alternative means for the diagnosis of obstructive sleep apnea?[J]. Sleep Medicine, 2008, 9(8):894-898.
[11] Karunajeewa A S, Abeyratne U R, Hukins C. Multi-feature snore sound analysis in obstructive sleep apnea-hypopnea syndrome[J]. Physiological Measurement, 2011, 32(1):83-97.
[12] Solà-Soler J, Fiz J A, Morera J, Jane R. Multiclass classification of subjects with sleep apnoea-hypopnoea syndrome through snoring analysis[J]. Medical Engineering & Physics, 2012, 34(9):1213-1220.
[13] Dafna E, Tarasiuk A, Zigel Y. OSA severity assessment based on sleep breathing analysis using ambient microphone[C]//35th Annual International Conference of Engineering in Medicine and Biology Society. IEEE, 2013:2044-2047.
[14] Ben-Israel N, Tarasiuk A, Zigel Y. Obstructive apnea hypopnea index estimation by analysis of nocturnal snoring signals in adults[J]. Sleep, 35(9):1299-1305.
[15] Herath D L, Abeyratne U R, Hukins C. Hidden Markov modelling of intra-snore episode behavior of acoustic characteristics of obstructive sleep apnea patients[J]. Physiological Measurement, 2015, 36(12):2379-2404.
[16] Sakakura A. Acoustic analysis of snoring sounds with chaos theory[C]//Proceedings of the International Congress Series, 2003, 1257:227-230.
[17] Mikami T. Detecting nonlinear properties of snoring sounds for sleep apnea diagnosis[C]//2nd International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2008. IEEE, 2008:1173-1176.
[18] Anki?an H, Yilmaz D. Comparison of SVM and ANFIS for snore related sounds classification by using the largest Lyapunov exponent and entropy[J]. Computational & mathematical Methods in Medicine, 2013:1-13.
[19] Grassberger P, Procaccia I. Dimension and entropy of strange attractors from a fluctuating dynamic approach[J]. Physica D:Nonlinear Phenomena, 1984, 13(1/2):34-54.
[20] Rosenstein M T, Collins J, De L C. Reconstruction expansion as a geometry-based framework for choosing proper delay times[J]. Physica D:Nonlinear Phenomena, 1994, 73(1/2):82-98.
[21] Kennel M B, Brown R, Abarbanel H D. Determining embedding dimension for phase space reconstruction using a geometrical construction[J]. Physical Review A, 1992, 45(6):3403-3411.
[22] Cao L. Practical method for determining the minimum embedding dimension of a scalar time series[J]. Physical D:Nonlinear Phenomena, 1997, 110(1/2):43-50.
[23] Moore B C J, Glasberg B R. Suggested formulae for calculating auditory-filter bandwidths and excitation patterns[J]. Journal of the Acoustical Society of America, 1983, 74(3):750-753.
[24] Glasberg B R, Moore B C J. Derivation of auditory filter shapes from notched-noise data[J]. Hearing Research, 1990, 47(1/2):103-138.
[25] 中华耳鼻咽喉头颈外科杂志编辑委员会. 阻塞性睡眠呼吸暂停低通气综合症诊断和外科治疗指南[J]. 中华耳鼻咽喉头颈外科杂志,2009, 44(2):95-96. Editor Committee of Chinese Journal of Otorhinolaryngology Head and Neck Surgery. Guideline for the diagnosis and surgical treatment of obstructive sleep apea hypopnea syndrome[J]. Chinese Journal of Otorhinolaryngology Head and Neck Surgery, 2009, 44(2):95-96. (in Chinese)
[26] Yegnanarayana B, Kishore S P. Aann:an alternative to GMM for pattern recognition[J]. Neural Networks, 2002, 15(3):459-469.
[27] Nakamura K, Toda T, Saruwatari H, Shikano K. Speaking-aid systems using GMM-based voice conversion for electrolaryngeal speech[J]. Speech Communication, 2012, 54(1):134-146.
[28] 侯丽敏,张长恒,殷善开,易红良,孟丽丽. 一种基于鼾声筛查OSAHS的装置,中国:CN103735267A[P], 2014.
[29] Hou L M, Wang C, Zhang C H, Meng L L, Yi H L, Yin S K. Calculating AHI combine oximetery and snore sound source[C]//2015 IEEE China Summit and International Conference on Signal and Information Processing. IEEE, 2015:69-73.
[30] Zollanvari A, Braga-Neto U M, Dougherty E R. On the sampling distribution of resubstitution and leave-one-out error estimators for linear classifiers[J]. Pattern Recognition, 2009, 42(11):2705-2723.
[31] Braga-Neto U, Hashimoto R, Dougherty E R, Nguyen D V, Carroll R J. Is crossvalidation better than resubstitution for ranking genes?[J]. Bioinformatics, 2004, 20(2):253-258.
[32] Clancy E A. Factors influencing the resubstitution accuracy in multivariate classification analysis:implications for study design in ergonomics[J]. Ergonomics, 2010, 1(4):417-427.
[33] Xu H J, Wei S, Yi H L, Hou L M, Zhang C H, Chen B, Chen Y Q, Yin S K. Nocturnal snoring sound analysis in the diagnosis of obstructive sleep apnea in the Chinese Han population[J]. Sleep & Breathing, 2015, 19(2):599-605.
/
| 〈 |
|
〉 |
