請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85950完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 周呈霙(Cheng-Ying Chou) | |
| dc.contributor.author | Ting-Chia Kuo | en |
| dc.contributor.author | 郭庭嘉 | zh_TW |
| dc.date.accessioned | 2023-03-19T23:30:09Z | - |
| dc.date.copyright | 2022-09-26 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-09-20 | |
| dc.identifier.citation | [1] Shih-Cheng Huang, Anuj Pareek, Saeed Seyyedi, Imon Banerjee, and Matthew P Lungren. Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines. NPJ Digital Medicine, 3(1):1–9, 2020. [2] Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q Weinberger. Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4700–4708, 2017. [3] National Health Service (NHS). Intensive care. https://www.nhs.uk/conditions/intensive-care/. Accessed: 2021-11-08. [4] Tim Wenham and Alison Pittard. Intensive care unit environment. Continuing Education in Anaesthesia Critical Care & Pain, 9(6):178–183, 12 2009. [5] National Health Service (NHS). Acute respiratory distress syndrome. https://www.nhs.uk/conditions/acute-respiratory-distress-syndrome/. Accessed:2021-11-08. [6] Michael A Matthay, Rachel L Zemans, Guy A Zimmerman, Yaseen M Arabi, Jeremy R Beitler, Alain Mercat, Margaret Herridge, Adrienne G Randolph, and Carolyn S Calfee. Acute respiratory distress syndrome. Nature reviews Disease primers, 5(1):1–22, 2019. [7] Niall D Ferguson, Eddy Fan, Luigi Camporota, Massimo Antonelli, Antonio Anzueto, Richard Beale, Laurent Brochard, Roy Brower, Andrés Esteban, Luciano Gattinoni, et al. The berlin definition of ARDS: an expanded rationale, justification, and supplementary material. Intensive Care Medicine, 38(10):1573–1582, 2012. [8] Vito Fanelli, Aikaterini Vlachou, Shirin Ghannadian, Umberto Simonetti, Arthur S Slutsky, and Haibo Zhang. Acute respiratory distress syndrome: new definition, current and future therapeutic options. Journal of Thoracic Disease, 5(3):326, 2013. [9] Giacomo Bellani, John G Laffey, Tài Pham, Eddy Fan, Laurent Brochard, Andres Esteban, Luciano Gattinoni, Frank Van Haren, Anders Larsson, Daniel F McAuley, et al. Epidemiology, patterns of care, and mortality for patients with acute respiratory distress syndrome in intensive care units in 50 countries. JAMA, 315(8):788–800, 2016. [10] Giacomo Bellani, Tài Pham, and John G Laffey. Missed or delayed diagnosis of ards: a common and serious problem. Intensive Care Medicine, 46(6):1180–1183, 2020. [11] George D Magoulas and Andriana Prentza. Machine learning in medical applications. In Advanced Course on Artificial Intelligence, pages 300–307. Springer, 1999. [12] Akbar K Waljee and Peter DR Higgins. Machine learning in medicine: a primer for physicians. American Journal of Gastroenterology, 105(6):1224–1226, 2010. [13] Cesar Trillo-Alvarez, Rodrigo Cartin-Ceba, Daryl J Kor, Marija Kojicic, Rahul Kashyap, Sweta Thakur, Lokendra Thakur, V Herasevich, M Malinchoc, and O Gajic. Acute lung injury prediction score: derivation and validation in a population-based sample. European Respiratory Journal, 37(3):604–609, 2011. [14] Graciela J Soto, Daryl J Kor, Pauline K Park, Peter C Hou, David A Kaufman, Mimi Kim, Hemang Yadav, Nicholas Teman, Michael Hsu, Tatyana Shvilkina, et al. Lung injury prediction score in hospitalized patients at risk of acute respiratory distress syndrome. Critical Care Medicine, 44(12):2182, 2016. [15] Zachary M Bauman, Marika Y Gassner, Megan A Coughlin, Meredith Mahan, and Jill Watras. Lung injury prediction score is useful in predicting acute respiratory distress syndrome and mortality in surgical critical care patients. Critical Care Research and Practice, 2015, 2015. [16] Paul E Pepe, Ronald G Thomas, Marie Anne Stager, Leonard D Hudson, and C James Carrico. Early prediction of the adult respiratory distress syndrome by a simple scoring method. Annals of Emergency Medicine, 12(12):749–755, 1983. [17] Mengyuan Liang, Miao He, Jian Tang, Xinliang He, Zhijun Liu, Siwei Feng, Ping Chen, Hui Li, Yu＇e Xue, Tao Bai, et al. Novel risk scoring system for predicting acute respiratory distress syndrome among hospitalized patients with coronavirus disease 2019 in wuhan, china. BMC infectious Diseases, 20(1):1–10, 2020. [18] Pengcheng Yang, Taihu Wu, Ming Yu, Feng Chen, Chunchen Wang, Jing Yuan, Jiameng Xu, and Guang Zhang. A new method for identifying the acute respiratory distress syndrome disease based on noninvasive physiological parameters. PLOS ONE, 15(2):e0226962, 2020. [19] Sidney Le, Emily Pellegrini, Abigail Green-Saxena, Charlotte Summers, Jana Hoffman, Jacob Calvert, and Ritankar Das. Supervised machine learning for the early prediction of acute respiratory distress syndrome (ards). Journal of Critical Care, 60:96–102, 2020. [20] Xian-Fei Ding, Jin-Bo Li, Huo-Yan Liang, Zong-Yu Wang, Ting-Ting Jiao, Zhuang Liu, Liang Yi, Wei-Shuai Bian, Shu-Peng Wang, Xi Zhu, et al. Predictive model for acute respiratory distress syndrome events in icu patients in china using machine learning algorithms: a secondary analysis of a cohort study. Journal of Translational Medicine, 17(1):1–10, 2019. [21] Daniel Zeiberg, Tejas Prahlad, Brahmajee K Nallamothu, Theodore J Iwashyna, Jenna Wiens, and Michael W Sjoding. Machine learning for patient risk stratification for acute respiratory distress syndrome. PLOS ONE, 14(3):e0214465, 2019. [22] Yang Fei, Kun Gao, and Wei-qin Li. Prediction and evaluation of the severity of acute respiratory distress syndrome following severe acute pancreatitis using an artificial neural network algorithm model. HPB, 21(7):891–897, 2019. [23] Lakshya Singhal, Yash Garg, Philip Yang, Azade Tabaie, A Ian Wong, Akram Mohammed, Lokesh Chinthala, Dipen Kadaria, Amik Sodhi, Andre L Holder, et al. eards: A multi-center validation of an interpretable machine learning algorithm of early onset acute respiratory distress syndrome (ards) among critically ill adults with covid-19. PLOS ONE, 16(9):e0257056, 2021. [24] Narathip Reamaroon, Michael W Sjoding, Jonathan Gryak, Brian D Athey, Kayvan Najarian, and Harm Derksen. Automated detection of acute respiratory distress syndrome from chest x-rays using directionality measure and deep learning features. Computers in Biology and Medicine, 134:104463, 2021. [25] Michael W Sjoding, Daniel Taylor, Jonathan Motyka, Elizabeth Lee, Ivan Co, Dru Claar, Jakob I McSparron, Sardar Ansari, Meeta Prasad Kerlin, John P Reilly, et al. Deep learning to detect acute respiratory distress syndrome on chest radiographs: a retrospective study with external validation. The Lancet Digital Health, 2021. [26] Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, and Andrew Y Ng. Multimodal deep learning. In ICML, 2011. [27] Jabeen Summaira, Xi Li, Amin Muhammad Shoib, Songyuan Li, and Jabbar Abdul. Recent advances and trends in multimodal deep learning: A review. arXiv preprint arXiv:2105.11087, 2021. [28] Aleksei Tiulpin, Stefan Klein, Sita MA Bierma-Zeinstra, Jérôme Thevenot, Esa Rahtu, Joyce van Meurs, Edwin HG Oei, and Simo Saarakkala. Multimodal machine learning-based knee osteoarthritis progression prediction from plain radiographs and clinical data. Scientific Reports, 9(1):1–11, 2019. [29] Shih-Cheng Huang, Anuj Pareek, Roham Zamanian, Imon Banerjee, and Matthew P Lungren. Multimodal fusion with deep neural networks for leveraging ct imaging and electronic health record: a case-study in pulmonary embolism detection. Scientific Reports, 10(1):1–9, 2020. [30] Jordan Yap, William Yolland, and Philipp Tschandl. Multimodal skin lesion classification using deep learning. Experimental Dermatology, 27(11):1261–1267, 2018. [31] Adam Yala, Constance Lehman, Tal Schuster, Tally Portnoi, and Regina Barzilay. A deep learning mammography-based model for improved breast cancer risk prediction. Radiology, 292(1):60–66, 2019. [32] Alistair Johnson, Lucas Bulgarelli, Tom Pollard, Steven Horng, Leo Anthony Celi, and Roger Mark. MIMIC-IV, 2021. [33] Alistair EW Johnson, Tom J Pollard, Seth J Berkowitz, Nathaniel R Greenbaum, Matthew P Lungren, Chih-ying Deng, Roger G Mark, and Steven Horng. Mimiccxr, a de-identified publicly available database of chest radiographs with free-text reports. Scientific Data, 6(1):1–8, 2019. [34] Accountability Act. Health insurance portability and accountability act of 1996. Public law, 104:191, 1996. [35] Connor Shorten and Taghi M Khoshgoftaar. A survey on image data augmentation for deep learning. Journal of Big Data, 6(1):1–48, 2019. [36] Dina Elreedy and Amir F. Atiya. A comprehensive analysis of synthetic minority oversampling technique (smote) for handling class imbalance. Information Sciences, 505:32–64, 2019. [37] Yan-Yan Song and LU Ying. Decision tree methods: applications for classification and prediction. Shanghai Archives of Psychiatry, 27(2):130, 2015. [38] Gérard Biau and Erwan Scornet. A random forest guided tour. TEST, 25(2):197–227, 2016. [39] Tianqi Chen and Carlos Guestrin. XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, pages 785–794, 2016. [40] Jürgen Schmidhuber. Deep learning in neural networks: An overview. Neural Networks, 61:85–117, 2015. [41] Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255. IEEE, 2009. [42] Payam Refaeilzadeh, Lei Tang, and Huan Liu. Cross-validation. Encyclopedia of Database Systems, 5:532–538, 2009. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85950 | - |
| dc.description.abstract | 急性呼吸窘迫症候群是病人進入加護病房的常見原因之一，並且有很高的死亡率，雖然現今已經有很多研究運用臨床資料和機器學習方法探討及時診斷與提前預測的模型，但幾乎沒有研究同時考慮了數值資料及影像資料。本研究使用了公開資料集(MIMIC-IV 以及 MIMIC-CXR)以獲取病人的臨床資料及胸部X光片影像資料，應用機器學習方法建立決策樹(Decision Tree)、隨機森林(Random Forest)、極限梯度提升(XGBoost)、神經網路(Neural Network)等多種模型，並應用了多模態機器學習分析，比較單模態與多模態模型的表現。使用晚期融合的多模態模型在診斷及12小時、24小時及48小時前的預測，接受者操作特徵曲線下面積(AUROC)約為0.7951至0.8502，與單模態模型相比約可以提高6.0%至9.3%的模型表現，這個研究將可以協助急性呼吸窘迫症候群的診斷及早期預測。 | zh_TW |
| dc.description.abstract | Acute respiratory distress syndrome (ARDS) is one of the most common causes of admission to the intensive care unit and has a high mortality rate. Although there were several studies applying machine learning techniques to the issue of ARDS prediction, few studies combined numerical and image data. This study collected clinical data and chest radiograph images from publicly available databases (MIMIC-IV and MIMIC-CXR) and applied machine learning methods to establish models such as Decision Tree, Random Forest, XGBoost, and Neural Networks. Moreover, multimodal machine learning were applied and the performance of single- and multi-modality models were compared. The multi-modality models with late-level fusion demonstrated the AUROC of 0.7951~0.8502 for onset identification, 12-, 24-, and 48-hr prediction, which improved about 6.0%~9.3% compared with the single-modality models. This study can assist improved prediction and early recognition of ARDS. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T23:30:09Z (GMT). No. of bitstreams: 1 U0001-0807202219464500.pdf: 9530003 bytes, checksum: ff8b0470e9918c12758cf42a40f93737 (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | 摘要 i Abstract iii Contents v List of Figures ix List of Tables xi Denotation xiii Chapter 1 Introduction 1 1.1 Background 1 1.2 Purpose of Research 3 1.3 Thesis Organization 4 Chapter 2 Literature Reviews 7 2.1 ARDS Prediction 7 2.2 Multimodal Deep Learning 11 Chapter 3 Materials 15 3.1 Data Source 15 3.1.1 MIMIC-IV 15 3.1.2 MIMIC-CXR 17 3.2 Data Processing 18 3.2.1 Data extraction 18 3.2.2 Feature selection 19 3.2.3 Patient selection 22 3.3 Data Analysis 24 Chapter 4 Methods 29 4.1 Data Standardization 29 4.2 Data Augmentation 30 4.3 Imbalanced Data 31 4.4 Models 33 4.4.1 Decision tree 33 4.4.2 Random forest 34 4.4.3 Extreme gradient boosting 35 4.4.4 Convolutional neural network 36 4.5 Fusion Strategies of Multi-modality 39 Chapter 5 Model Evaluation 43 5.1 Evaluation Metrics 43 5.2 Stratified Cross-Validation 45 Chapter 6 Results 49 6.1 Single-modality Models 49 6.2 Multi-modality Models 54 6.3 Model Comparison 55 Chapter 7 Discussion and Conclusion 59 7.1 Discussion 59 7.2 Limitations 60 7.3 Conclusion 61 References 63 Appendix A — Cross-validation Results 71 | |
| dc.language.iso | en | |
| dc.subject | 極限梯度提升 | zh_TW |
| dc.subject | 晚期融合 | zh_TW |
| dc.subject | 胸部X光片 | zh_TW |
| dc.subject | 多模態機器學習 | zh_TW |
| dc.subject | 急性呼吸窘迫症候群 | zh_TW |
| dc.subject | Late-level Fusion | en |
| dc.subject | Acute Respiratory Distress Syndrome | en |
| dc.subject | Multimodal Machine Learning | en |
| dc.subject | Chest Radiograph | en |
| dc.subject | eXtreme Gradient Boosting | en |
| dc.title | 應用多模態機器學習於急性呼吸窘迫症候群之預測 | zh_TW |
| dc.title | Applying Multimodal Machine Learning for Early Prediction of Acute Respiratory Distress Syndrome | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 110-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 王偉仲(Weichung Wang),陳定立(Ting-Li Chen) | |
| dc.subject.keyword | 急性呼吸窘迫症候群,多模態機器學習,胸部X光片,極限梯度提升,晚期融合, | zh_TW |
| dc.subject.keyword | Acute Respiratory Distress Syndrome,Multimodal Machine Learning,Chest Radiograph,eXtreme Gradient Boosting,Late-level Fusion, | en |
| dc.relation.page | 74 | |
| dc.identifier.doi | 10.6342/NTU202201359 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2022-09-22 | |
| dc.contributor.author-college | 共同教育中心 | zh_TW |
| dc.contributor.author-dept | 統計碩士學位學程 | zh_TW |
| dc.date.embargo-lift | 2022-09-26 | - |
| 顯示於系所單位： | 統計碩士學位學程 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-0807202219464500.pdf | 9.31 MB | Adobe PDF | 檢視/開啟 |
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。