睡眠階段及睡眠呼吸中止症自動判讀系統

對睡眠障礙患者而言，Polysomnography(PSG)是目前最好的方式來檢查患者的睡眠階段，並藉此了解患者的睡眠品質(Sleep quality)，診斷各式睡眠疾病，例如阻塞型睡眠呼吸中止症(Obstructive sleep apnea)。然而判別睡眠階段需檢測至少八種不同的生理特徵，包含:腦電訊號、眼動訊號和肌電訊號而且人工判讀亦相當花費時間以及高成本，因此許多研究嘗試減少測量的參數以及設計適合自動判讀的演算法。雖然目前已經有很多研究提出了不同的自動判讀睡眠階段方法運用少量的參數做預測。但平均準確率大多都不及80%，且無法兼顧每種睡眠層級。直到現在尚未有一種簡易型的睡眠預測，可以在醫學上被各界認定有效且被廣泛使用。本論文提出一個舒適且簡易的方式進行睡眠階段的自動判讀。可以讓使用者在家裡就可以接受檢測，就可以達到類似於PSG的成果。此項全新的演算法僅利用2-lead的腦電訊號和1-lead的肌電訊號加上透過神經網路為基礎的決策樹(Neural-Network-based decision tree)，搭配馬可夫鏈的概念，即可將睡眠正確分期，最好的準確率為82.6%。補提藉此減少成本或工作時間。此外本論文亦提出睡眠呼吸中止症自動判讀的演算法。針對OSA患者進行檢測。透過可攜式檢測器(Portable Monitor)對使用者進行呼吸中止自動判讀，並換算成AHI指數(Apnea–Hypopnea Index)，量化OSA的嚴重程度。搭配上述的睡眠階段自動判讀系統，可以建立起完整的睡眠檢查制度，讓睡眠醫療更為方便、普及。

關鍵字

睡眠階段分期；決策樹；類神經網路；馬可夫鏈

並列摘要

For patients with sleep disorder, Polysomnography (PSG) is the best method to analyze their sleep stage and understand sleep quality. By taking a whole-night examination, the sleep laboratory can diagnose several kinds of sleep diseases such as obstructive sleep apnea. However, PSG requires at least eight different physiological signals, including EEG C3, C4, EOG and EMG, to analyze the sleep stage. Besides, manual interpretation is also costly and time-consuming. Therefore, many researches try to reduce the number of channels required to classify sleep stage automatically. Although there are several works announced that used different methods, the average accuracy is still low, mostly under 80%, and hard to give consideration to each stage’s accuracy. So far there is no portable monitor that is recommended and widely used in medical field. An automated sleep stage recognition system is proposed in this thesis. This system allow users to take the examination in their own homes. The function is very similar to PSG analysis. This novel algorithm only uses 2-lead EEG and 1-lead EMG signals. By using a neural-network-based decision tree and the Markov Model technique, our system can recognize sleep stage effectively. The accuracy is 82.6%. Furthermore, an OSA detection algorithm is also proposed in this thesis. The target is the patients who have sleep apnea. The specific Portable monitor can detect the events when sleep apnea happens and calculate the Apnea–Hypopnea Index (AHI). It can point out the severity of OSA. Combining automated sleep stage recognition and OSA detection system, we expect to develop a better sleep analysis mechanism.

並列關鍵字

sleep stage recognition ； decision tree ； Neural Network ； Markov Model

參考文獻

[27] HEAL YOURSELF AT HOME,” Different Stages of Sleep,” [Online].

[1] A. Rechtschaffen, and A Kales, A manual of standardized terminology, techniques and scoring system for sleep stages of human subject. Washington DC: US Government Printing Office, National Institute of Health Publication, 1968.

[3] N. A. Collop, W. M. Anderson, B. Boehlecke, et al.,” Clinical Guidelines for the Use of Unattended Portable Monitors in the Diagnosis of Obstructive Sleep Apnea in Adult Patients”, J Clin Sleep Med, Vol. 3, No. 7, pp. 737-747, 2007.

[5] R. Ruehland, D. Rochford, J. O'Donoghue, et al., "The new AASM criteria for scoring hypopneas: impact on the apnea hypopnea index," Sleep, Vol.32(2), pp.150–157,Feb 2009.

[6] Surgical Sleep Solutions, “Obstructive Sleep Apnea,” [Online].

國際替代計量

睡眠階段及睡眠呼吸中止症自動判讀系統

全文下載

主題瀏覽