睡眠多項生理檢查（polysomnography, PSG）為睡眠疾病診斷與鑑別的重要工具，其結果仰賴睡眠技師依美國睡眠醫學學會（American Academy of Sleep Medicine, AASM）準則進行睡眠分期與事件標記。然而，真實臨床個案常包含非典型波形、睡眠片段化及複雜事件，即使已有標準化規則，不同判讀者仍可能產生差異，進而影響睡眠報告與下游臨床指標。既有研究已證實雲端平台結合專家訓練可提升單一年度之 PSG 判讀一致性，但對平台長期維運、跨年度不同臨床主題之應用，以及新判讀項目與臨床指標之持續擴充，仍缺乏系統性評估。
本研究承接既有雲端睡眠判讀平台，配合 2025 與 2026 年全國睡眠判讀工作坊之臨床與教學需求進行功能強化，包括快速動眼期肌肉未失張（REM sleep without atonia, RSWA）標記與比對、多次入睡潛伏期試驗（multiple sleep latency test, MSLT）訊號、開關燈標記、經皮氧氣分壓（transcutaneous oxygen tension, PtcO₂） 與經皮二氧化碳分壓（transcutaneous carbon dioxide tension, PtcCO₂）訊號顯示，以及以 JavaScript 實作並整合至個人化報告之睡眠呼吸中止特異性缺氧負荷（sleep apnea-specific hypoxic burden, SASHB）計算模組。另分析 2021 至 2026 年六屆工作坊之完整前後測資料。各年度均採前測、專家講座與判讀回顧、後測及個人化回饋之訓練流程，參與者於相同雲端介面對該年度 PSG 個案進行前後兩次判讀，並以 30 秒 epoch 為單位與專家共識答案比對；該答案由四位資深睡眠技師完成兩輪判讀後，經多數決及諮詢專家裁決建立。共 147 筆完成前後測之年度紀錄納入睡眠分期分析，並以雙尾配對 Wilcoxon 符號等級檢定評估一致性變化。
結果顯示，2021 至 2026 年各年度整體睡眠分期一致性於後測均高於前測，改善幅度介於 4.7 至 8.9 個百分點，其中 2021 至 2025 年之前後測差異達統計顯著。年度主題事件亦呈現相應改善，其中 2022 年腿動事件、2024 年呼吸事件及 2025 年 RSWA 整體一致性分別提升 4.5、14.7 及 21.5 個百分點。多數年資組亦呈現訓練後改善，顯示此訓練流程可適用於不同判讀經驗之參與者。
綜合來說，既有雲端睡眠判讀平台可透過持續維運及臨床需求驅動之功能強化，支援不同疾病主題、訊號型態與判讀項目之訓練。專家講座、前後測與個人化回饋流程可穩定提升睡眠判讀一致性，並改善部分年度重點事件之判讀表現。SASHB 之整合使平台由傳統一致性回饋延伸至具臨床意義之指標運算。本研究成果具應用於睡眠技師繼續教育與跨機構判讀品質管理之潛力。

Polysomnography (PSG) is an important tool for diagnosing and differentiating sleep disorders. Its interpretation relies on sleep technologists performing sleep staging and event scoring according to the American Academy of Sleep Medicine (AASM) guidelines. In practice, however, clinical PSG recordings often contain atypical waveforms, fragmented sleep, and complex events, so even with standardized rules different scorers may assign different labels to the same epochs or events. These scoring differences can affect sleep reports and derived clinical indicators. Prior studies have shown that a cloud-based platform combined with expert training can improve interscorer agreement of PSG scoring within a single year. However, the long-term operation of the platform, its application to different clinical themes across years, and its continued expansion to support additional scoring categories, signal types, and clinical metrics have not yet been systematically evaluated.
Building on an existing cloud-based sleep scoring platform, this study carried out functional enhancements to meet the clinical and educational needs of the 2025 and 2026 nationwide sleep scoring workshops. These enhancements included the labeling and comparison of REM sleep without atonia (RSWA); support for loading and displaying Multiple Sleep Latency Test (MSLT) recordings together with light-off and light-on markers; the display of transcutaneous oxygen tension (PtcO₂) and transcutaneous carbon dioxide tension (PtcCO₂) signals; and a sleep apnea-specific hypoxic burden (SASHB) computation module implemented in JavaScript and integrated into the personalized report. In addition, the complete pre- and post-test data from six workshops held between 2021 and 2026 were analyzed. Each year followed a training protocol of pre-test, expert lecture and scoring review, post-test, and personalized feedback. Participants re-scored the same PSG recording for that year on the same cloud interface, and their results were compared with an expert consensus reference on a 30-second epoch basis; this reference was established by four senior sleep technologists who completed two rounds of scoring, followed by majority vote and adjudication by an expert consultant. A total of 147 annual participant records with completed pre- and post-tests were included in the sleep-staging agreement analysis, and changes in agreement were evaluated using a two-sided paired Wilcoxon signed-rank test.
The results showed that overall sleep stage agreement was higher at post-test than at pre-test in every year from 2021 to 2026, with improvements ranging from 4.7 to 8.9 percentage points, and the pre-to-post difference reached statistical significance in the five years from 2021 to 2025. Agreement for the theme-specific events also improved: overall agreement for limb movement events in 2022, respiratory events in 2024, and RSWA in 2025 increased by 4.5, 14.7, and 21.5 percentage points, respectively. Most seniority groups also showed improvement after training, supporting the applicability of the training protocol across different levels of scoring experience.
In summary, an existing cloud-based sleep scoring platform can support scoring training across different disease themes, signal types, and scoring items through sustained operation and clinically driven functional enhancement. The training protocol, comprising expert lectures, pre- and post-tests, and personalized feedback, can improve the scoring agreement and enhance scoring performance for some key events. The integration of SASHB extends the platform beyond agreement-based feedback to the automated computation of a clinically meaningful index. These findings support the potential use of the platform in continuing education for sleep technologists and cross-institutional scoring quality management.

American Association of Sleep Technologists. (2018). Transcutaneous CO₂ monitoring. https://aastweb.org/Clinical-Resources/Technical-Guidelines/
Azarbarzin, A., Sands, S. A., Stone, K. L., Taranto-Montemurro, L., Messineo, L., Terrill, P. I., Ancoli-Israel, S., Ensrud, K., Purcell, S., White, D. P., Redline, S., & Wellman, A. (2019). The hypoxic burden of sleep apnoea predicts cardiovascular disease-related mortality: The Osteoporotic Fractures in Men Study and the Sleep Heart Health Study. European Heart Journal, 40(14), 1149–1157. https://doi.org/10.1093/eurheartj/ehy624
Azarbarzin, A., Sands, S. A., Taranto-Montemurro, L., Vena, D., Sofer, T., Kim, S.-W., Stone, K. L., White, D. P., Wellman, A., & Redline, S. (2020). The sleep apnea-specific hypoxic burden predicts incident heart failure. Chest, 158(2), 739–750. https://doi.org/10.1016/j.chest.2020.03.053
Benjafield, A. V., Ayas, N. T., Eastwood, P. R., Heinzer, R., Ip, M. S. M., Morrell, M. J., Nunez, C. M., Patel, S. R., Penzel, T., Pépin, J.-L., Peppard, P. E., Sinha, S., Tufik, S., Valentine, K., & Malhotra, A. (2019). Estimation of the global prevalence and burden of obstructive sleep apnoea: A literature-based analysis. The Lancet Respiratory Medicine, 7(8), 687–698. https://doi.org/10.1016/S2213-2600(19)30198-5
Berry, R. B., Quan, S. F., Abreu, A. R., Bibbs, M. L., DelRosso, L., Harding, S. M., Mao, M.-M., Plante, D. T., Pressman, M. R., Troester, M. M., & Vaughn, B. V. (2020). The AASM manual for the scoring of sleep and associated events: Rules, terminology and technical specifications. American Academy of Sleep Medicine.
Bliwise, D. L., Fairley, J., Hoff, S., Rosenberg, R. S., Rye, D. B., Schulman, D. A., & Trotti, L. M. (2018). Inter-rater agreement for visual discrimination of phasic and tonic electromyographic activity in sleep. Sleep, 41(7), zsy080. https://doi.org/10.1093/sleep/zsy080
Choo, B. P., Mok, Y., Oh, H. C., Patanaik, A., Kishan, K., Awasthi, A., Biju, S., Bhattacharjee, S., Poh, Y., & Wong, H. S. (2023). Benchmarking performance of an automatic polysomnography scoring system in a population with suspected sleep disorders. Frontiers in Neurology, 14, 1123935. https://doi.org/10.3389/fneur.2023.1123935
Chuang, L. P., Hsu, S. C., Lin, S. W., Ko, W. S., Chen, N. H., & Tsai, Y. H. (2008). Prevalence of snoring and witnessed apnea in Taiwanese adults. Chang Gung Medical Journal, 31(2), 175–181.
Danker-Hopfe, H., Kunz, D., Gruber, G., Klösch, G., Lorenzo, J. L., Himanen, S. L., Kemp, B., Penzel, T., Röschke, J., Dorn, H., Schlögl, A., Trenker, E., & Dorffner, G. (2004). Interrater reliability between scorers from eight European sleep laboratories in subjects with different sleep disorders. Journal of Sleep Research, 13(1), 63–69. https://doi.org/10.1046/j.1365-2869.2003.00375.x
de Chazal, P. (2022). Hypoxic-Burden [Computer software]. GitHub. https://github.com/pdechazal/Hypoxic-Burden
Epstein, L. J., Plante, D. T., & Rosen, I. M. (2022). Mastery learning program to teach sleep study scoring. Journal of Clinical Sleep Medicine, 18(12), 2745–2750. https://doi.org/10.5664/jcsm.10200
Frauscher, B., Iranzo, A., Gaig, C., Gschliesser, V., Guaita, M., Raffelseder, V., Ehrmann, L., Sola, N., Salamero, M., Tolosa, E., Poewe, W., Santamaria, J., & Högl, B. (2012). Normative EMG values during REM sleep for the diagnosis of REM sleep behavior disorder. Sleep, 35(6), 835–847. https://doi.org/10.5665/sleep.1886
Hang, L.-W., Hsu, J.-Y., Chang, C.-J., Wang, H.-C., Cheng, S.-L., Lin, C.-H., Chan, M.-C., Wang, C.-C., Perng, D.-W., & Yu, C.-J. (2016). Predictive factors warrant screening for obstructive sleep apnea in COPD: A Taiwan National Survey. International Journal of Chronic Obstructive Pulmonary Disease, 11, 665–673. https://doi.org/10.2147/COPD.S96504
Krahn, L. E., Arand, D. L., Avidan, A. Y., Davila, D. G., DeBassio, W. A., Ruoff, C. M., & Harrod, C. G. (2021). Recommended protocols for the Multiple Sleep Latency Test and Maintenance of Wakefulness Test in adults: Guidance from the American Academy of Sleep Medicine. Journal of Clinical Sleep Medicine, 17(12), 2489–2498. https://doi.org/10.5664/jcsm.9620
Lee, Y.-H. (2022). 以臨床為需求的人機協同自動睡眠判讀輔助系統. Master's thesis, 國立成功大學. https://hdl.handle.net/11296/zjwtrd
Lévy, P., Kohler, M., McNicholas, W. T., Barbé, F., McEvoy, R. D., Somers, V. K., Lavie, L., & Pépin, J.-L. (2015). Obstructive sleep apnoea syndrome. Nature Reviews Disease Primers, 1, 15015. https://doi.org/10.1038/nrdp.2015.15
Liang, S.-F., Kuo, C.-E., Hu, Y.-H., & Cheng, Y.-S. (2012). A rule-based automatic sleep staging method. Journal of Neuroscience Methods, 205(1), 169–176. https://doi.org/10.1016/j.jneumeth.2011.12.022
Liao, Y.-S., Wu, M.-C., Li, C.-X., Lin, W.-K., Lin, C.-Y., & Liang, S.-F. (2024). Polysomnography scoring–related training and quantitative assessment for improving interscorer agreement. Journal of Clinical Sleep Medicine, 20(2), 271–278. https://doi.org/10.5664/jcsm.10852
Liu, G.-R., Lin, T.-Y., Wu, H.-T., Sheu, Y.-C., Liu, C.-L., Liu, W.-T., Yang, M.-C., Ni, Y.-L., Chou, K.-T., Chen, C.-H., Wu, D., Lan, C.-C., Chiu, K.-L., Chiu, H.-Y., & Lo, Y.-L. (2021). Large-scale assessment of consistency in sleep stage scoring rules among multiple sleep centers using an interpretable machine learning algorithm. Journal of Clinical Sleep Medicine, 17(2), 159–166. https://doi.org/10.5664/jcsm.8820
McEvoy, R. D., Antic, N. A., Heeley, E., Luo, Y., Ou, Q., Zhang, X., Mediano, O., Chen, R., Drager, L. F., Liu, Z., Chen, G., Du, B., McArdle, N., Mukherjee, S., Tripathi, M., Billot, L., Li, Q., Lorenzi-Filho, G., Barbe, F., . . . Anderson, C. S. (2016). CPAP for prevention of cardiovascular events in obstructive sleep apnea. The New England Journal of Medicine, 375(10), 919–931. https://doi.org/10.1056/NEJMoa1606599
Mokhlesi, B., Masa, J. F., Brozek, J. L., Gurubhagavatula, I., Murphy, P. B., Piper, A. J., Tulaimat, A., Afshar, M., Balachandran, J. S., Dweik, R. A., Grunstein, R. R., Hart, N., Kaw, R., Lorenzi-Filho, G., Pamidi, S., Patel, B. K., Patil, S. P., Pépin, J. L., Soghier, I., . . . Teodorescu, M. (2019). Evaluation and management of obesity hypoventilation syndrome: An official American Thoracic Society clinical practice guideline. American Journal of Respiratory and Critical Care Medicine, 200(3), e6–e24. https://doi.org/10.1164/rccm.201905-1071ST
Peker, Y., Glantz, H., Eulenburg, C., Wegscheider, K., Herlitz, J., & Thunström, E. (2016). Effect of positive airway pressure on cardiovascular outcomes in coronary artery disease patients with nonsleepy obstructive sleep apnea: The RICCADSA randomized controlled trial. American Journal of Respiratory and Critical Care Medicine, 194(5), 613–620. https://doi.org/10.1164/rccm.201601-0088OC
Penzel, T., & Salanitro, M. (2025). Emerging challenges in the transition from manual to automated sleep scoring [Editorial]. Sleep, 48(10), zsaf202. https://doi.org/10.1093/sleep/zsaf202
Puligheddu, M., Figorilli, M., Congiu, P., Lecca, R., Casaglia, E., Tamburrino, L., Orrù, R., Meloni, F., & Ferri, R. (2023). Quantification of REM sleep without atonia: A review of study methods and meta-analysis of their performance for the diagnosis of RBD. Sleep Medicine Reviews, 68, 101745. https://doi.org/10.1016/j.smrv.2023.101745
Rosenberg, R. S., & Van Hout, S. (2013). The American Academy of Sleep Medicine inter-scorer reliability program: Sleep stage scoring. Journal of Clinical Sleep Medicine, 9(1), 81–87. https://doi.org/10.5664/jcsm.2350
Rosenberg, R. S., & Van Hout, S. (2014). The American Academy of Sleep Medicine inter-scorer reliability program: Respiratory events. Journal of Clinical Sleep Medicine, 10(4), 447–454. https://doi.org/10.5664/jcsm.3630
Sánchez-de-la-Torre, M., Sánchez-de-la-Torre, A., Bertran, S., Abad, J., Duran-Cantolla, J., Cabriada, V., Mediano, O., Masdeu, M. J., Alonso, M. L., Masa, J. F., Barceló, A., de la Peña, M., Mayos, M., Coloma, R., Montserrat, J. M., Chiner, E., Perelló, S., Rubinós, G., Mínguez, O., . . . Barbé, F. (2020). Effect of obstructive sleep apnoea and its treatment with continuous positive airway pressure on the prevalence of cardiovascular events in patients with acute coronary syndrome (ISAACC study): A randomised controlled trial. The Lancet Respiratory Medicine, 8(4), 359–367. https://doi.org/10.1016/S2213-2600(19)30271-1
Sutherland, K., Sadr, N., Bin, Y. S., Cook, K., Dissanayake, H. U., Cistulli, P. A., & de Chazal, P. (2022). Comparative associations of oximetry patterns in obstructive sleep apnea with incident cardiovascular disease. Sleep, 45(12), zsac179. https://doi.org/10.1093/sleep/zsac179
Taiwan Society of Sleep Medicine. (2019, March 30). 2019 年台灣睡眠醫學學會年度調查：輪班工作者慢性失眠盛行率及睡眠問題大調查 [2019 annual survey of the Taiwan Society of Sleep Medicine: Prevalence of chronic insomnia and sleep problems among shift workers] [Press release]. https://tssm.org.tw/file/1563864454.pdf
Taiwan Society of Sleep Medicine. (2025). 臺灣睡眠醫學學會「專業睡眠機構」認證施行細則 [Implementation rules for accreditation of professional sleep facilities]. https://tssm.org.tw/certi.php?key=certi02
Trzepizur, W., Blanchard, M., Ganem, T., Balusson, F., Feuilloy, M., Girault, J.-M., Meslier, N., Oger, E., Paris, A., Pigeanne, T., Racineux, J.-L., Sabil, A., Gervès-Pinquié, C., & Gagnadoux, F. (2022). Sleep apnea-specific hypoxic burden, symptom subtypes, and risk of cardiovascular events and all-cause mortality. American Journal of Respiratory and Critical Care Medicine, 205(1), 108–117. https://doi.org/10.1164/rccm.202105-1274OC
Wu, M.-C. (2021). 智慧睡眠輔助判讀系統應用於睡眠技師評估訓練與人機協同自動判讀. Master's thesis, 國立成功大學. https://hdl.handle.net/11296/p9hz79
Wu, S.-B. (2023). 基於形態學的睡眠慢波及k複合波自動偵測方法. Master's thesis, 國立成功大學. https://hdl.handle.net/11296/j6cw56