請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/95324完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 張智星 | zh_TW |
| dc.contributor.advisor | Jyh-Shing Jang | en |
| dc.contributor.author | 王泳錡 | zh_TW |
| dc.contributor.author | Yong-Ci Wang | en |
| dc.date.accessioned | 2024-09-05T16:10:22Z | - |
| dc.date.available | 2024-09-06 | - |
| dc.date.copyright | 2024-09-05 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-08-12 | - |
| dc.identifier.citation | D. Chan, “Insight into health systems: A cross-national study of kidney disease in the united states and taiwan,” BUJBH, 2022. [Online]. Available: https://sites.brown.edu/publichealthjournal/2021/12/13/kidneys/
L. I-chia, “Chronic kidney disease costs nation NT$53.3bn,” Taipei Times, 2020. [Online]. Available: https://www.taipeitimes.com/News/taiwan/archives/2020/07/13/2003739828 M.-S. Wu, “Taiwan society of nephrology – annual report of kidney disease in taiwan,” 2021 Annual Report on Kidney Disease in Taiwan, 2021. [Online]. Available: https://www.tsn.org.tw/en/spotlight.html X.-H. Tan, “Detecting intradialytic hypotension using machine learning,”National Taiwan University, 2023. [Online]. Available: https://www.airitilibrary.com/Article/Detail/U0001-0317230802292158 Delrue, Charlotte, D. Bruyne, Sander, Speeckaert, and M. M.n, “Application of machine learning in chronic kidney disease: Current status and future prospects,” Biomedicine, pp. 1–17, 2024. [Online]. Available: https://www.mdpi.com/2227-9059/12/3/568 M. Javaid, A. Haleem, R. Pratap Singh, R. Suman, and S. Rab,“Significance of machine learning in healthcare: Features, pillars and applications,” International Journal of Intelligent Networks, pp. 58–73, 2022. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2666603022000069 H.-P. Chan, R. K. Samala, L. M. Hadjiiski, and C. Zhou, “Deep learning in medical image analysis,” Adv Exp Med Biol. 2020, pp. 3–21, 2020. [Online]. Available: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7442218 D. K. Sharma, M. Chatterjee, G. Kaur, and S. Vavilala, “3 - deep learning applications for disease diagnosis,” in Deep Learning for Medical Applications with Unique Data, D. Gupta, U. Kose, A. Khanna, and V. E. Balas, Eds. Academic Press, 2022, pp. 31–51. [Online]. Available: https://www.sciencedirect.com/science/article/pii/B9780128241455000058 M. Raparthi, “Deep learning for personalized medicine - enhancing precision health with ai,” Journal of Science amp; Technology, vol. 1, no. 1, p. 82–90, Dec. 2020. [Online]. Available: https://thesciencebrigade.com/jst/article/view/124 M. Z. Islam, R. A. Naqvi, A. Haider, and H. S. Kim, “Deep learning for automatic tumor lesions delineation and prognostic assessment in multi-modality pet/ct: A prospective survey,” Engineering Applications of Artificial Intelligence, vol. 123, pp. 106–276, 2023. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0952197623004608 V. Jain, J. M. Chatterjee, H. Hedayati, S. Krit, and O. Deperlioglu, Eds., Deep Learning for Personalized Healthcare Services. Berlin, Boston: De Gruyter, 2021. [Online]. Available: https://doi.org/10.1515/9783110708127 K. G. Dinesh, K. Arumugaraj, K. D. Santhosh, and V. Mareeswari,“Prediction of cardiovascular disease using machine learning algorithms,”International Journal of Advanced Computer Science and Applications, p. 1, 2018. [Online]. Available: https://iopscience.iop.org/article/10.1088/1742-6596/1767/1/012013/pdf doi:10.6342/NTU202403115 V. Singh, V. K. Asari, and R. Rajasekaran, “A deep neural network for early detection and prediction of chronic kidney disease,” Diagnostics, p. 1, 2022. [Online]. Available: https://www.mdpi.com/2075-4418/12/1/116 J. Ye, T. Wu, J. Li, and K. Chen, “Machine learning approaches for the neuroimaging study of alzheimer’s disease,” IEEE Computer, pp. 99–101, 2011. [Online]. Available: https://www.researchgate.net/publication/220475894 Machine Learning Approaches for the Neuroimaging Study of Alzheimer%27s Disease B. Zhang, H. Shi, and H. Wang, “Machine learning and ai in cancer prognosis, prediction, and treatment selection: A critical approach,”Journal of Multidisciplinary Healthcare, p. 1779, 2023. [Online]. Available: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10312208/ O. E. Santangelo, V. Gentile, D. Giordano, and F. Cedrone, “Machine learning and prediction of infectious diseases: A systematic review,” Machine Learning and Knowledge Extraction (MAKE), p. 175, 2023. [Online]. Available: https://www.mdpi.com/2504-4990/5/1/13 D. Kumar, P. P. Pawar, H. Gonaygunta, and G. S. Nadella, “Machine learning’s role in personalized medicine & treatment optimization,” MDPI, p. 1675, 2024. [Online]. Available: https://www.researchgate.net/publication/378550507 Machine learning’s role in personalized medicine treatment optimization H. Lee, D. Yun, J. Yoo, K. Yoo, Y. C. Kim, D. K. Kim, K.-H. Oh, K. W. Joo, Y. S. Kim, N. Kwak, and S. S. Han, “Deep learning model for real-time prediction of intradialytic hypotension,” CJASN, pp. 396–404, 2021. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/33574056/ D. Yun, H.-L. Yang, S. G. Kim, K. Kim, D. K. Kim, K.-H. Oh, K. W. Joo, Y. S. Kim, and S. S. Han, “Real-time dual prediction of intradialytic hypotension and hypertension using an explainable deep learning model,” Sci Rep, pp. 1–9, 2023. [Online]. Available: https://doi.org/10.1038/s41598-023-45282-1 H. Zhang, S. C. Lin-Chun Wang, A. Pickering, L. Usvyat, J. Larkin, Z. K. Pete Waguespack, J. P. Kooman, F. W. Maddux, and P. Kotanko,“Real-time prediction of intradialytic hypotension using machine learning and cloud computing infrastructure,” Nephrology Dialysis Transplantation, pp. 1761–1768, 2023. [Online]. Available: https://doi.org/10.1093/ndt/gfad070 H. H. Wei, Y. Jiun-Yi, U. Chi-Hin, C. Kuan-Yu, H. Chih-Chiang, T. Rua-Huan, L. C.-C. K., C. Hsuan, and L. Hsuan-Ming, “The new method of feature selection for intradialytic hypotension prediction using machine learning,” 2021 IEEE 3rd Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS), pp. 69–70, 2021. [Online]. Available: https://ieeexplore.ieee.org/document/9510559 Y. Jiun-Yi, H. H. Wei, L. Chih-Hao, C. Kuan-Yu, U. Chi-Hin, H. Chih-Chiang, C. Chou-Cheng, L. C.-C. K., C. Hsuan, and L. Hsuan-Ming, “Differencing time series as an important feature extraction for intradialytic hypotension prediction using machine learning,” 2021 IEEE 3rd Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS), pp. 19–20, 2021. [Online]. Available: https://www.tsn.org.tw/en/spotlight.html D. Zhang, C. Yin, J. Zeng, X. Yuan, and P. Zhang, “Combining structured and unstructured data for predictive models: a deep learning approach,”MC Med Inform Decis Mak 20, 280 (2020), 2020. [Online]. Available: https://doi.org/10.1186/s12911-020-01297-6 L. Chen, Z. Yuan, I. Julie, C. Muge, A. Ryan, H. J. M., and C. Min, “Early diagnosis and prediction of sepsis shock by combining static and dynamic information,” 2018 IEEE International Conference on Healthcare Informatics (ICHI), pp. 219–228, 2018. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/8419365 A. Leontjeva and I. Kuzovkin, “Combining static and dynamic features for multivariate sequence classification,” 2016 IEEE 3rd International Conference on Data Science and Advanced Analytics (DSAA), pp. 21–30, 2016. [Online]. Available: https://www.computer.org/csdl/proceedings-article/dsaa/2016/07796887/12OmNvAiShz | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/95324 | - |
| dc.description.abstract | 本研究旨在使用傳統機器學習（Machine Learning）和深度學習（Deep Learning）模型開發一個透析中低血壓（Intradialytic Hypotension）的預測系統。數據集收集自台大醫院透析中心，涵蓋從 2016 年 1 月 1 日至 2023 年 9 月 30 日的透析記錄、生命徵象數據、患者資訊和醫療處置單。我們採用了序列特徵選擇（Sequential Feature Selection）和兩個門檻選擇標準來優化模型性能。在傳統ML模型中，XGBoost 和隨機森林均表現強勁，而在 DL 模型中，多層感知器（Multilayer Perceptron）則展現了優越的性能。我們的研究結果表明，這兩種類型的模型在預測 IDH 方面具有很強的能力。未來的工作將專注於動態調整窗口大小、整合歷史透析記錄以及開發針對個別患者定制的預測模型，以增強在實際臨床中的應用性並改善患者的治療效果。 | zh_TW |
| dc.description.abstract | This study aims to develop a predictive system for intradialytic hypotension (IDH) using conventional machine learning (ML) and deep learning (DL) models. The dataset, collected from the National Taiwan University Hospital dialysis center, includes dialysis records, vital sign data, patient information, and medical order records from January 1, 2016, to September 30, 2023. We employed Sequential Feature Selection (SFS) and two criteria for threshold selection to optimize model performance. Among conventional ML models, both Extreme Gradient Boosting (XGBoost) and Random Forest demonstrated strong performance, while Multilayer Perceptron (MLP) demonstrated superior performance among DL models. Our findings indicate strong predictive capabilities for both model types. Future work will focus on dynamic window size adjustments, integrating historical dialysis records, and developing customized prediction models to enhance real-world clinical applicability and improve patient outcomes. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-09-05T16:10:22Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-09-05T16:10:22Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Acknowledgements i
Abstract ii Contents iv List of Tables vii List of Figures viii 1 Introduction 1 1.1 Background 1 1.2 Motivation 2 1.3 Outlines 2 2 Literature Review 4 2.1 Machine Learning and Deep Learning 4 2.1.1 Machine Learning 4 2.1.2 Types of Machine Learning 5 2.1.3 Deep Learning 6 2.1.4 Types of Deep Learning 7 2.2 Application in Medical Prediction 8 2.2.1 Cardiovascular Diseases 8 2.2.2 Kidney and Urinary Systems 8 2.2.3 Brain and Central Nervous Systems 9 2.2.4 Other Applications 9 2.3 ML and DL Approaches for Intradialytic Hypotension Prediction 9 2.3.1 Deep Learning Model for Real-Time Prediction of Intradialytic Hypotension 10 2.3.2 Real-Time Dual Prediction of Intradialytic Hypotension and Hypertension Using an Explainable Deep Learning Model 10 2.3.3 Real-Time Prediction of Intradialytic Hypotension Using Machine Learning and Cloud Computing Infrastructure 11 2.3.4 Feature Selection and Engineering for IDH Prediction 12 2.4 Integration of Dynamic and Static Data in Medical Predictions 12 3 Methodology 14 3.1 Data Introduction 14 3.1.1 Data Description 14 3.2 Data preprocessing 16 3.2.1 Groundtruth Definition 16 3.2.2 Feature Deletion 17 3.2.3 Null Value Processing 17 3.2.4 Feature Engineering 18 3.2.5 Task Introduction and Data Arrangement 19 3.2.6 Data Splitting 19 3.2.7 Data Resampling 20 3.2.8 Feature Selection 21 3.3 Model Selection 23 3.3.1 Conventional Machine Learning Models 23 3.3.2 Deep Learning Models 24 3.4 Summary 25 4 Experimental Setup 26 4.1 Dataset 26 4.2 Evaluation Metrics 27 4.2.1 True Positive (TP), True Negative (TN), False Positive (FP), False Negative (FN) 27 4.2.2 Sensitivity and Specificity 27 4.2.3 Threshold Selection 28 4.2.4 The performance of Feature Selection 30 4.3 Experimental Environment 30 4.4 Experimental Parameter Setting 30 4.4.1 Convenional ML Model 31 4.4.2 Deep Learning Model 32 4.4.3 Loss Function 33 4.5 Experimental Roadmap 33 4.5.1 Conventional ML Training Procedure 34 4.5.2 DL Training Process 35 5 Experimental Results 36 5.1 Introduction 36 5.2 Performance Comparison of Conventional ML Models 36 5.2.1 Model Performance with Fixed Window Size (w = 3) 37 5.2.2 Sequential Feature Selection (SFS) Results for Each Model 39 5.2.3 Optimal Window Size Selection for Conventional ML Models 44 5.3 Performance Comparison of DL Models 45 5.3.1 Model Performance with Fixed Window Size (w = 3) 45 5.3.2 Optimal Window Size Selection for DL Models 46 5.4 Ablation Study 47 5.4.1 The Result of Ablation Study 48 5.4.2 Conclusion of Ablation Study 48 5.5 Performance Comparison between Conventional ML and DL Models 49 5.6 Predictive System Implementation 50 5.6.1 Implementation Details 50 6 Conclusions and Future Work 52 6.1 Research Summary 52 6.2 Comparison with Previous Work 52 6.3 Future Work 53 Bibliography 55 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 透析中低血壓 | zh_TW |
| dc.subject | 預測系統 | zh_TW |
| dc.subject | 序列特徵選擇 | zh_TW |
| dc.subject | machine learning | en |
| dc.subject | clinical application | en |
| dc.subject | patient data integration | en |
| dc.subject | Sequential Feature Selection | en |
| dc.subject | predictive modeling | en |
| dc.subject | deep learning | en |
| dc.subject | Intradialytic Hypotension | en |
| dc.title | 機器學習用於血液透析中低血壓的檢測與分析 | zh_TW |
| dc.title | Machine Learning for Detection and Analysis of Intradialytic Hypotension in Hemodialysis | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 盧彥文;周鈺翔 | zh_TW |
| dc.contributor.oralexamcommittee | Yen-Wen Lu;Yu-Hsiang Chou | en |
| dc.subject.keyword | 機器學習,深度學習,透析中低血壓,預測系統,序列特徵選擇, | zh_TW |
| dc.subject.keyword | Intradialytic Hypotension,machine learning,deep learning,predictive modeling,Sequential Feature Selection,patient data integration,clinical application, | en |
| dc.relation.page | 59 | - |
| dc.identifier.doi | 10.6342/NTU202403115 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2024-08-13 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊工程學系 | - |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf 未授權公開取用 | 13.09 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。