近年來睡眠問題逐漸受到大家重視，睡眠呼吸中止症 (Sleep Apnea) 已成為不可忽視的健康問題之一。由於睡眠呼吸中止症的檢查過程相當繁瑣且昂貴，故本研究目標希望透過數學模型預測得病的可能性，讓有限的醫療資源能更有效運用。本研究分析病人的人體測量值與睡眠問卷資料後，使用自適性類神經模糊推論系統 (Adaptive Neural Fuzzy Inference System) 建立數學模型。研究的部分主要分為兩大部分，第一是資料分析的前處理部分，第二是自我學習的演算法部分。資料處理部分會先進行特徵 (Feature) 資料與呼吸紊亂指數 (RDI) 之間的單變數相關分析與複相關分析，找出較具影響性之項目，再匯入演算法進行學習。演算法部分使用自適性類神經模糊推論系統，並針對男性與女性不同的特徵分別建模，最後與最小平方解之線性方程式進行結果比較。結果顯示，自適性類神經模糊推論系統的預測準確度分別為72.73%(男性)及75%(女性)，優於最小平方解之線性方程式的預測準確度68.01%(男性)及43.52%。在人體測量之特徵上，本研究發現腰圍與身高的比值對於女性模型的預測影響相當顯著，優於以往使用的身體質量指數 (BMI)。

Sleep apnea has become one of the most significant health problems in recent years. However, because examinations are time consuming and involve high costs, the diagnosis of sleep apnea is limited. The purpose of this thesis is to develop a mathematical prediction model that can identify critical patients who really need to take the examination. The prediction model would be extremely helpful in increasing the effectiveness of sleep centers. This research used the questionnaire scores and clinical data of patients, which includes anthropometric measurements, then built a mathematical model using the adaptive neural fuzzy inference system (ANFIS). There are two phases in our research: data pre-processing and modeling. During data pre-processing, the correlation between features and the respiratory disturbance index (RDI) were analyzed by single variable correlation and multiple correlation. The highly correlated features were selected as the input features for the model. ANFIS models were built for males and females respectively. The performance of the ANFIS models were compared with least squared linear equation models. The results show that the accuracy of the ANFIS models for males (72.73%) and females (75%) is better than the accuracy of linear equation models for males (68.01%) and females (43.52%). Also, WC/H is more influential than BMI for predicting sleep apnea cases among females.

References

[1] Wan, Siang Cheong. "Overweight and Obesity in Asia | Gen Re." Gen Re Perspective. General Reinsurance AG, Dec. 2014. Web. 20 July 2015.

[2] Brown, Tamara, et al. "Diet and Physical Activity Interventions to Prevent or Treat Obesity in South Asian Children and Adults: A Systematic Review and Meta-Analysis." International journal of environmental research and public health 12.1 (2015): 566-594.

[3] Polat, Kemal, Şebnem Yosunkaya, and Salih Güneş. "Pairwise ANFIS approach to determining the disorder degree of obstructive sleep apnea syndrome." Journal of medical systems 32.5 (2008): 379-387.

[4] Bouloukaki, Izolde, et al. "Prediction of obstructive sleep apnea syndrome in a large Greek population." Sleep and Breathing 15.4 (2011): 657-664.

[5] Sahin, Mustafa, et al. "A Clinical Prediction Formula for Apnea-Hypopnea Index." International journal of otolaryngology 2014 (2014).

[6] Lin, I-Feng, et al. "Predicting effective continuous positive airway pressure in Taiwanese patients with obstructive sleep apnea syndrome." JOURNAL-FORMOSAN MEDICAL ASSOCIATION 102.4 (2003): 215-221.

[7] Übeyli, Elif Derya, et al. "Adaptive neuro-fuzzy inference system employing wavelet coefficients for detection of alterations in sleep EEG activity during hypopnoea episodes." Digital Signal Processing 20.3 (2010): 678-691.

[8] American Academy of Sleep Medicine. International Classification of Sleep Disorders. In: Diagnostic and Coding Manual. Second Edition. Westchester, Ill: American Academy of Sleep Medicine; 2005.

[9] Goetting, C , Downey III R. Sick, symptomatic and undiagnosed. San Antonio, TX: 2010. Paper to be presented at the Annual Meeting of the Association of Professional Sleep Society.

[10] Johns, Murray W. "A new method for measuring daytime sleepiness: the Epworth sleepiness scale." sleep 14.6 (1991): 540-545.

[11] Buysse, Daniel J., et al. "The Pittsburgh Sleep Quality Index: a new instrument for psychiatric practice and research." Psychiatry research 28.2 (1989): 193-213.

[12] Buda, Andrzej, and Andrzej Jarynowski. Life time of correlations and its applications. [Vol. 1]. 2010.

[13] Cohen, Jacob. Statistical power analysis for the behavioral sciences (rev. Lawrence Erlbaum Associates, Inc, 1977.

[14] 朱經明. 教育統計學. 五南圖書出版股份有限公司, 2001.

[15] Jang, Jyh-Shing Roger. "Fuzzy Modeling Using Generalized Neural Networks and Kalman Filter Algorithm." AAAI. Vol. 91. 1991.

[16] Jang, J-SR. "ANFIS: adaptive-network-based fuzzy inference system." Systems, Man and Cybernetics, IEEE Transactions on 23.3 (1993): 665-685.

[17] Yun, Zhang, et al. "RBF neural network and ANFIS-based short-term load forecasting approach in real-time price environment." Power Systems, IEEE Transactions on 23.3 (2008): 853-858.

[18] Lei, Yaguo, et al. "Fault diagnosis of rotating machinery based on multiple ANFIS combination with GAs." Mechanical Systems and Signal Processing 21.5 (2007): 2280-2294.

[19] Boyacioglu, Melek Acar, and Derya Avci. "An adaptive network-based fuzzy inference system (ANFIS) for the prediction of stock market return: the case of the Istanbul stock exchange." Expert Systems with Applications 37.12 (2010): 7908-7912.

[20] Polat, Kemal, and Salih Güneş. "An expert system approach based on principal component analysis and adaptive neuro-fuzzy inference system to diagnosis of diabetes disease." Digital Signal Processing 17.4 (2007): 702-710.

[21] Wall, Hannah, Chris Smith, and Richard Hubbard. "Body mass index and obstructive sleep apnoea in the UK: a cross-sectional study of the over-50s." Primary Care Respiratory Journal 21.4 (2012): 371-376.

[22] Tufik, Sergio, et al. "Obstructive sleep apnea syndrome in the Sao Paulo epidemiologic sleep study." Sleep medicine 11.5 (2010): 441-446.

[23] Wolk, Robert, Abu SM Shamsuzzaman, and Virend K. Somers. "Obesity, sleep apnea, and hypertension." Hypertension 42.6 (2003): 1067-1074.

[24] Gallagher, Dympna, et al. "How useful is body mass index for comparison of body fatness across age, sex, and ethnic groups?." American journal of epidemiology 143.3 (1996): 228-239.

[25] Burkhauser, Richard V., and John Cawley. "Beyond BMI: the value of more accurate measures of fatness and obesity in social science research." Journal of health economics 27.2 (2008): 519-529.

[26] Janssen, Ian, Peter T. Katzmarzyk, and Robert Ross. "Waist circumference and not body mass index explains obesity-related health risk." The American journal of clinical nutrition 79.3 (2004): 379-384.

[27] Khoury, Michael, et al. "Role of waist measures in characterizing the lipid and blood pressure assessment of adolescents classified by body mass index." Archives of pediatrics and adolescent medicine 166.8 (2012): 719-724.

[28] BIXLER, EDWARD O., et al. "Effects of age on sleep apnea in men: I. Prevalence and severity." American Journal of Respiratory and Critical Care Medicine 157.1 (1998): 144-148.

[29] Gabbay, Itay E., and Peretz Lavie. "Age-and gender-related characteristics of obstructive sleep apnea." Sleep and Breathing 16.2 (2012): 453-460.

[30] Nieto, F. Javier, et al. "Association of sleep-disordered breathing, sleep apnea, and hypertension in a large community-based study." Jama 283.14 (2000): 1829-1836.

[31] Fletcher, Eugene C. "The relationship between systemic hypertension and obstructive sleep apnea: facts and theory." The American journal of medicine 98.2 (1995): 118-128.

[32] Lavie, Peretz, Paula Herer, and Victor Hoffstein. "Obstructive sleep apnoea syndrome as a risk factor for hypertension: population study." Bmj 320.7233 (2000): 479-482.