慢性腎病之盛行率居高不下，為全球相當重視的健康議題。慢性腎病患者病狀進展至末期腎病階段時，需透過血液透析來治療末期腎病，完善的醫療制度與醫療品質的提升，增加了臺灣的透析發生率。血液透析過程經常伴隨著許多不良併發症，最常見的風險為透析低血壓，若發生透析低血壓，醫療人員需要立即進行調整處置，降低脫水量、降低血液流速，嚴重時須立刻中斷透析，除了影響透析品質，甚至可能引發其他併發症造成器官受損等傷害。透析低血壓發生的原因相當複雜，是醫療人員致力於防範與改善的問題，特別是在單次透析治療前半段發生之透析低血壓（早期掉壓），與臨床參數設定和較高的風險有關。
隨著醫療逐漸資訊化，醫療資訊系統與資料倉儲保存了大量醫療資料，伴隨資料探勘與機器學習技術的發展，使得大數據分析得以在醫療領域發揮價值。在機器學習中，多標籤分類方法可為一筆資料標記一個以上的類別，使預測結果貼近實際情況；隨機森林為一種分類效果良好的模型，能減少過度擬合，並能夠評估變數的重要性，幫助決策者理解變數。本研究旨在探討病患透析治療中的早期掉壓，結合臨床透析紀錄時間與兩種透析低血壓定義，發展多個標籤，並以多標籤分類與隨機森林模型深入探討病患的透析低血壓。
經由實證研究得出，分類器鏈多標籤分類模型的表現最為突出，隨機森林分類器對每個標籤各自進行特徵重要性分析。歸納早期掉壓之重要特徵，透析間病患的血壓和體重變化與早期掉壓最為相關，重要臨床參數包含：收縮壓、舒張壓、人工腎臟跨膜壓、累積交換血液容積、實際血液溫度、迴路靜脈壓與透析前淨體重。最後本研究依據醫療文獻知識，結合專業領域人員建議，探討早期掉壓的預防與控制措施。

Chronic kidney disease is a global health issue. When patients with chronic kidney disease progress to the end stage, hemodialysis is the way to maintain patients' life. While intradialytic hypotension (IDH) is the most common complication during hemodialysis the onset and pattern of intradialytic hypotension are strongly correlated to the overall and cardiovascular mortality. The patients with IDH that occurred in the first half in a single dialysis session (early IDH) have a higher risk of death than that developed later in the second half. Though there had been many studies to establish models to predict intradialytic hypotension, few were mentioning on the onset and pattern of IDH. The main purpose of this work is to develop a multi-label Classification machine learning method which could investigate the patterns and onset of IDH during hemodialysis treatment. Empirical database collected from the case hospital would be used as the basis to examine the most important features using proposed method.
Based on the 128,741 records collected, empirical results from the developed multi-label Classification model had concluded ten most important features: blood pressure, trans-membranous pressure, venous pressure of circuit, ultrafiltration volume, pre-dialysis body weight, and else. For the Class 1 and Class 3, body weight is a common feature to be observed. Medical team of the case hospital could take proper intervention to avoid intradialytic hypotension in a proactive way, based on the research findings, and decreased the burden of patients and medical staff thereafter.

中文文獻
台灣腎臟醫學會（2020）。2020台灣腎病年報（第一版）。財團法人國家衛生研究院。
呂執中，許文禹，林軒名，陳佳雯（2022）。應用多標籤分類機器學習方法改善透析低血壓風險。臺東大學綠色科學學刊。
林軒名（2018）。建置醫療資料探勘架構：以血液透析通路治療為例。國立成功大學。

英文文獻
Bowe, B., Xie, Y., Xu, E., & Al-Aly, Z. (2021). Kidney outcomes in long COVID. Journal of the American Society of Nephrology, 32(11), 2851-2862. doi:10.1681/ASN. 2021060734
Cedeño, S., Desco, M., Aleman, Y., Macías, N., Fernández-Pena, A., Vega, A., Abad, S., & López-Gómez, J. M. (2021). Intradialytic hypotension and relationship with cognitive function and brain morphometry, Clinical Kidney Journal, 14(4), 1156-1164, doi:10.1093/ckj/sfaa070
Chou, J. A., Kalantar-Zadeh, K., & Mathew, A. T. (2017). A brief review of intradialytic hypotension with a focus on survival. Seminars in Dialysis, 30(6), 473-480. doi:10.1111/sdi.12627
Chou, J. A., Streja, E., Nguyen, D. V., Rhee, C. M., Obi, Y., Inrig, J. K., Amin, A., Kovesdy, C. P., Sim, J. J., & Kalantar-Zadeh, K. (2018). Intradialytic hypotension, blood pressure changes and mortality risk in incident hemodialysis patients. Nephrol Dial Transplant, 33(1), 149-159. doi:10.1093/ndt/gfx037
Flythe, J. E., Xue, H., Lynch, K. E., Curhan, G. C., & Brunelli, S. M. (2015). Association of mortality risk with various definitions of intradialytic hypotension. J Am Soc Nephrol, 26(3), 724-734. doi:10.1681/ASN.2014020222
Gomez-Pulido, J. A., Gomez-Pulido, J. M., Rodriguez-Puyol, D., Polo-Luque, M. L., & Vargas-Lombardo, M. (2021). Predicting the appearance of hypotension during hemodialysis sessions using machine learning Classifiers. Int J Environ Res Public Health, 18(5). doi:10.3390/ijerph18052364
Gul, A., Miskulin, D., Harford, A., & Zager, P. (2016). Intradialytic hypotension. Curr Opin Nephrol Hypertens, 25(6), 545-550. doi:10.1097/MNH.0000000000000271
Huang, J. C.,Tsai, Y. C.,Wu, P. Y.,Lien, Y. H.,Chien, C. Y.,Kuo, C. F.,Hung, J. F.,Chen, S. C.,&Kuo, C. H. (2020). Predictive modeling of blood pressure during hemodialysis: a comparison of linear model, random forest, support vector regression, XGBoost, LASSO regression and ensemble method. Comput Methods Programs Biomed, 195, 105536.doi:10.1016/j.cmpb.2020.105536
Kanbay, M., Ertuglu, L. A., Afsar, B., Ozdogan, E., Siriopol, D., Covic, A., Basile, C., & Ortiz, A. (2020). An update review of intradialytic hypotension: concept, risk factors, clinical implications and management. Clinical Kidney Journal,13(6),981-993. doi:10.1093/ckj/sfaa078
Keane, D. F., Raimann, J. G., Zhang, H., Willetts, J., Thijssen, S., & Kotanko, P. (2021). The time of onset of intradialytic hypotension during a hemodialysis session associates with clinical parameters and mortality. Kidney International, 99(6), 1408-1417. doi:10.1016/j.kint.2021.01.018
Kohavi, R., & Provost, F. (1998). Glossary of terms. Machine Learning, 2, 271-274. https://doi.org/10.1023/A:1017181826899
Kotanko, P., Garg, A.X., Depner, T., Pierratos, A., Chan, C.T., Levin, N.W., Greene, T., Larive, B., Beck, G.J., Gassman, J., Kliger, A.S., Stokes, J.B. and (2015), Blood pressure in frequent dialysis. Hemodial Int, 19, 386-401. doi:10.1111/hdi.12255
Lee, H., Yun, D., Yoo, J., Yoo, K., Kim, Y. C., Kim, D. K., Oh, K., Joo, K. W., Kim, Y. S., Kwal, N., & Han, S. S. (2021). Deep learning model for real-time prediction of intradialytic hypotension. Clin J Am Soc Nephrol, 16(3), 396-406. doi:10.2215 /CJN.09280620
Lin, Y.-C., Lin, Y.-C., Peng, C.-C., Chen, K.-C., Chen, H.-H., Fang, T.-C., & Sung, S.-Y. (2018). Effects of cholesterol levels on mortality in patients with long-term peritoneal dialysis based on residual renal function. Nutrients, 10(3). doi:10.3390/nu10030300
Lin, C. J., Chen, Y. Y., Pan, C. F., Wu, V., & Wu, C. J. (2019). Dataset supporting blood pressure prediction for the management of chronic hemodialysis. Sci Data, 6(1), 313.doi:10.1038/s41597-019-0319-8
Liu, Y. S., Yang, C. Y., Chiu, P. F., Lin, H. C., Lo, C. C., Lai, A. S., Chang, C., & Lee, O. K. (2021). Machine learning analysis of time-dependent features for predicting adverse events during hemodialysis therapy: model development and validation study. J Med Internet Res, 23(9), e27098. doi:10.2196/27098
Maxwell, A., Li, R., Yang, B., Weng, H., Ou, A., Hong, H., Zhou, Z., Gong, P., & Zhang, C. (2017). Deep learning architectures for multi-label Classification of intelligent health risk prediction. BMC Bioinformatics, 18 (14), 523. doi:10.1186/s12859-017-1898-z
Pliakos, K., Geurts, P., & Vens, C. (2018). Global multi-output decision trees for interaction prediction. Machine Learning,107(8-10), 1257-1281. doi:10.1007/s10994-018-5700-x
Pliakos, K., Vens, C., & Tsoumakas, G. (2021). Predicting drug-target interactions with multi-label Classification and label partitioning. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 18(4), 1596-1607. doi:10.1109/TCBB. 2019.2951378
Read, J., Pfahringer, B., Holmes, G., & Frank, E. (2011). Classifier chains for multi-label Classification. Machine Learning, 85(3), 333-359. doi:10.1007/s10994-011-5256-5
Reilly, R. F. (2014). Attending rounds: A patient with intradialytic hypotension. Clinical Journal of the American Society of Nephrology, 9(4), 798-803. doi:10.2215/ CJN.09930913
Sands, J.J., Usvyat, L.A., Sullivan, T., Segal, J.H., Zabetakis, P., Kotanko, P., Maddux, F.W. & Diaz-Buxo, J.A. (2014). Intradialytic hypotension: frequency, sources of variation and correlation with clinical outcome. Hemodialysis international, 18(2), 415-422. doi:10.1111/hdi.12138
Saran, R., Bragg-Gresham, J. L., Levin, N. W., Twardowski, Z. J., Wizemann, V., Saito, A., Kimata, N., Gillespie, B.W., Combe, C., Bommer, J., Akiba, T., Mapes, D. L., Young, E.W., &Port, F.K. (2006). Longer treatment time and slower ultrafiltration in hemodialysis: associations with reduced mortality in the DOPPS. Kidney International, 69(7), 1222-1228. doi:10.1038/sj.ki. 5000186
Shoji, T., Tsubakihara, Y., Fujii, M., & Imai, E. (2004). Hemodialysis-associated hypotension as an independent risk factor for two-year mortality in hemodialysis patients. Kidney International, 66(3), 1212-1220. doi:10.1111/j.1523-1755.2004. 00812.x
Sohn, P., Narasaki, Y., & Rhee, C. M. (2021). Intradialytic hypotension: is timing everything? Kidney International, 99(6), 1269-1272. doi: 10.1016/j.kint.2021.03.012
Stefánsson, B. V., Brunelli, S. M., Cabrera, C., Rosenbaum, D., Anum, E., Ramakrishnan, K., Jensen, D. E., & Stalhammar, N. O. (2014). Intradialytic hypotension and risk of cardiovascular disease. Clin J Am Soc Nephrol, 9(12), 2124-2132. doi:10.2215 /CJN.02680314
USRDS. (2020), End Stage Renal Disease: Chapter 11 International Comparisons. https://adr.usrds. org/2020/end-stage-renal-disease/11-international-comparisons
Webster, A. C., Nagler, E. V., Morton, R. L., & Masson, P. (2017). Chronic kidney disease. The Lancet, 389(10075), 1238-1252.
Zhang, M.-L., & Zhou, Z.-H. (2014). A review on multi-label learning algorithms. IEEE Transactions on Knowledge and Data Engineering, 26(8), 1819-1837. doi:10.1109/tkde. 2013.39
Zhou, L., Zheng, X., Yang, D., Wang, Y., Bai, X., & Ye, X. (2021). Application of multi-label Classification models for the diagnosis of diabetic complications. BMC Med Inform Decis Mak, 21(1), 182. doi:10.1186/s12911-021-01525-7
Zou, Q., Qu, K., Luo, Y., Yin, D., Ju, Y., & Tang, H. (2018). Predicting diabetes mellitus with machine learning techniques. Front Genet, 9, 515. doi:10.3389/fgene. 2018.00515