請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/66884完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 魏宏宇(Hung-Yu Wei) | |
| dc.contributor.author | Po-Yuan Su | en |
| dc.contributor.author | 蘇柏元 | zh_TW |
| dc.date.accessioned | 2021-06-17T01:14:15Z | - |
| dc.date.available | 2025-08-17 | |
| dc.date.copyright | 2020-08-24 | |
| dc.date.issued | 2020 | |
| dc.date.submitted | 2020-08-17 | |
| dc.identifier.citation | [1] Geert Sulter, Christel Steen, and Jacques De Keyser, “Use of the barthel index and modified rankin scale in acute stroke trials,” Stroke, vol. 30, no. 8, pp. 1538–1541, 1999. [2] 中華民國行政院衛生福利部, “108年死因統計結果分析,” June 2020. [3] William J Powers, Alejandro A Rabinstein, Teri Ackerson, Opeolu M Adeoye, Nicholas C Bambakidis, Kyra Becker, Jose ́ Biller, Michael Brown, Bart M Demaer- schalk, B Hoh, et al., “American heart association stroke council. 2018 guidelines for the early management of patients with acute ischemic stroke: a guideline for healthcare professionals from the american heart association/american stroke asso- ciation,” Stroke, vol. 49, no. 3, pp. e46–e110, 2018. [4] G Ntaios, F Gioulekas, V Papavasileiou, D Strbian, and P Michel, “Astral, dragon and sedan scores predict stroke outcome more accurately than physicians,” Euro- pean journal of neurology, vol. 23, no. 11, pp. 1651–1657, 2016. [5] Chi-Hung Liu, Yi-Chia Wei, Jr-Rung Lin, Chien-Hung Chang, Ting-Yu Chang, Kuo-Lun Huang, Yeu-Jhy Chang, Shan-Jin Ryu, Leng-Chieh Lin, Tsong-Hai Lee, et al., “Initial blood pressure is associated with stroke severity and is predictive of admission cost and one-year outcome in different stroke subtypes: a srichs registry study,” BMC neurology, vol. 16, no. 1, pp. 27, 2016. [6] Bach Xuan Tran, Carl A Latkin, Giang Thu Vu, Huong Lan Thi Nguyen, Son Nghiem, Ming-Xuan Tan, Zhi-Kai Lim, Cyrus SH Ho, and Roger Ho, “The cur- 34 rent research landscape of the application of artificial intelligence in managing cere- brovascular and heart diseases: A bibliometric and content analysis,” International journal of environmental research and public health, vol. 16, no. 15, pp. 2699, 2019. [7] Stefan Winzeck, Arsany Hakim, Richard McKinley, Jose ́ AADSR Pinto, Victor Alves, Carlos Silva, Maxim Pisov, Egor Krivov, Mikhail Belyaev, Miguel Monteiro, et al., “Isles 2016 and 2017-benchmarking ischemic stroke lesion outcome predic- tion based on multispectral mri,” Frontiers in neurology, vol. 9, pp. 679, 2018. [8] Stephen Bacchi, Luke Oakden-Rayner, Toby Zerner, Timothy Kleinig, Sandy Patel, and Jim Jannes, “Deep learning natural language processing successfully predicts the cerebrovascular cause of transient ischemic attack-like presentations,” Stroke, vol. 50, no. 3, pp. 758–760, 2019. [9] Derk L Arts, Ameen Abu-Hanna, Stephanie K Medlock, and Henk CPM van Weert, “Effectiveness and usage of a decision support system to improve stroke prevention in general practice: a cluster randomized controlled trial,” PLoS One, vol. 12, no. 2, pp. e0170974, 2017. [10] Syed Atif Ali Shah, Irfan Uddin, Furqan Aziz, Shafiq Ahmad, Mahmoud Ahmad Al-Khasawneh, and Mohamed Sharaf, “An enhanced deep neural network for pre- dicting workplace absenteeism,” Complexity, vol. 2020, 2020. [11] JoonNyung Heo, Jihoon G Yoon, Hyungjong Park, Young Dae Kim, Hyo Suk Nam, and Ji Hoe Heo, “Machine learning–based model for prediction of outcomes in acute stroke,” Stroke, vol. 50, no. 5, pp. 1263–1265, 2019. [12] Yuan Xie, Bin Jiang, Enhao Gong, Ying Li, Guangming Zhu, Patrik Michel, Max Wintermark, and Greg Zaharchuk, “Use of gradient boosting machine learning to predict patient outcome in acute ischemic stroke on the basis of imaging, demo- graphic, and clinical information,” American Journal of Roentgenology, vol. 212, no. 1, pp. 44–51, 2019. [13] Miguel Monteiro, Ana Catarina Fonseca, Ana Teresa Freitas, Teresa Pinho e Melo, Alexandre P Francisco, Jose M Ferro, and Arlindo L Oliveira, “Using machine learning to improve the prediction of functional outcome in ischemic stroke pa- tients,” IEEE/ACM transactions on computational biology and bioinformatics, vol. 15, no. 6, pp. 1953–1959, 2018. [14] JC Furlan, MDI Vergouwen, J Fang, and FL Silver, “White blood cell count is an independent predictor of outcomes after acute ischaemic stroke,” European journal of neurology, vol. 21, no. 2, pp. 215–222, 2014. [15] Yafei Wu and Ya Fang, “Stroke prediction with machine learning methods among older chinese,” International journal of environmental research and public health, vol. 17, no. 6, pp. 1828, 2020. [16] Ellery Wulczyn, David F Steiner, Zhaoyang Xu, Apaar Sadhwani, Hongwu Wang, Isabelle Flament-Auvigne, Craig H Mermel, Po-Hsuan Cameron Chen, Yun Liu, and Martin C Stumpe, “Deep learning-based survival prediction for multiple cancer types using histopathology images,” PloS one, vol. 15, no. 6, pp. e0233678, 2020. [17] Ning Xie, Gabrielle Ras, Marcel van Gerven, and Derek Doran, “Explainable deep learning: A field guide for the uninitiated,” arXiv preprint arXiv:2004.14545, 2020. [18] Leilani H Gilpin, David Bau, Ben Z Yuan, Ayesha Bajwa, Michael Specter, and Lalana Kagal, “Explaining explanations: An overview of interpretability of machine learning,” in 2018 IEEE 5th International Conference on data science and advanced analytics (DSAA). IEEE, 2018, pp. 80–89. [19] Jin Cho, Alnour Alharin, Zhen Hu, Nancy Fell, and Mina Sartipi, “Predicting post-stroke hospital discharge disposition using interpretable machine learning ap- proaches,” in 2019 IEEE International Conference on Big Data (Big Data). IEEE, 2019, pp. 4817–4822. [20] Tingting Chen, Jun Xu, Haochao Ying, Xiaojun Chen, Ruiwei Feng, Xueling Fang, Honghao Gao, and Jian Wu, “Prediction of extubation failure for intensive care unit patients using light gradient boosting machine,” IEEE Access, vol. 7, pp. 150960– 150968, 2019. [21] Cameron Chen, Yun Liu, and Lily Peng, “How to develop machine learning models for healthcare,” Nature Materials, 2019. [22] Laurens van der Maaten and Geoffrey Hinton, “Visualizing data using t-sne,” Jour- nal of machine learning research, vol. 9, no. Nov, pp. 2579–2605, 2008. [23] GuolinKe,QiMeng,ThomasFinley,TaifengWang,WeiChen,WeidongMa,Qiwei Ye, and Tie-Yan Liu, “Lightgbm: A highly efficient gradient boosting decision tree,” in Advances in Neural Information Processing Systems 30, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, Eds., pp. 3146– 3154. Curran Associates, Inc., 2017. [24] Sergey Ioffe and Christian Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” arXiv preprint arXiv:1502.03167, 2015. [25] GeoffreyEHinton,NitishSrivastava,AlexKrizhevsky,IlyaSutskever,andRuslanR Salakhutdinov, “Improving neural networks by preventing co-adaptation of feature detectors,” arXiv preprint arXiv:1207.0580, 2012. [26] Nitesh V Chawla, Kevin W Bowyer, Lawrence O Hall, and W Philip Kegelmeyer, “Smote: synthetic minority over-sampling technique,” Journal of artificial intelli- gence research, vol. 16, pp. 321–357, 2002. [27] Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin, “” why should i trust you?” explaining the predictions of any classifier,” in Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, 2016, pp. 1135–1144. [28] Scott M Lundberg and Su-In Lee, “A unified approach to interpreting model predic- tions,” in Advances in neural information processing systems, 2017, pp. 4765–4774. [29] G Ntaios, M Faouzi, J Ferrari, W Lang, K Vemmos, and P Michel, “An integer- based score to predict functional outcome in acute ischemic stroke: the astral score,” Neurology, vol. 78, no. 24, pp. 1916–1922, 2012. [30] Tsong-Hai Lee, Chien-Hung Chang, Yeu-Jhy Chang, Ku-Chou Chang, Jacky Chung, Chang Gung Medical System Stroke Registry Group, et al., “Establish- ment of electronic chart-based stroke registry system in a medical system in taiwan,” Journal of the Formosan Medical Association, vol. 110, no. 8, pp. 543–547, 2011. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/66884 | - |
| dc.description.abstract | 腦血管疾病在台灣是主要的死亡原因之一，及時準確的結果預測在治療決策重要作用，在本篇論文中，我們建立機器學習模型並進行驗證和分析，以預測出院時的雷氏量表分數及惡化。以ROC曲線下面積（AUC）評估，隨機森林在兩個目標中均表現最佳，在對於病房中惡化（目標不平衡）的預測模型訓練中，我們進行重新採樣的實驗。整體而言，我們觀察到，過去中風的量表，包含：雷氏量表、NIHSS、巴氏量表，是預測的關鍵，同時也指出添加更多預測因子，可以略微增加模型的AUC，最後，本篇論文也示範了以SHAP及LIME解釋模型重要因子，並確認模型的可靠性。 | zh_TW |
| dc.description.abstract | Cerebrovascular disease is a leading cause of death in Taiwan. Timely and accurate outcome prediction plays an important role in guiding treatment decision. In this work we focus on the ML development, validation and model analysis for predicting mRS at discharge and deterioration. Random forest performs the best in both target evaluated with Area Under the ROC Curve(AUC). For deterioration during ward, which target is imbalanced, experiment with re-sampling is also included. We observe that by features obtained by assessment like mRS, NIHSS, BI are key for predicting. We conclude that not only the random forest could be the best model to use for prediction, but also point out adding more features, like blood test result, can slightly increase AUC of models. Interpretation for prediction is also described in this work. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T01:14:15Z (GMT). No. of bitstreams: 1 U0001-1608202023044800.pdf: 2245302 bytes, checksum: 80daee61b7fcc2f4c9d59f0940f91751 (MD5) Previous issue date: 2020 | en |
| dc.description.tableofcontents | 中文摘要....................................... i 英文摘要....................................... ii 1 Introduction.................................... 1 1.1 Motivation.................................. 1 1.2 RelatedWork ................................ 2 1.3 Research Direction ............................. 3 1.4 Contribution................................. 3 1.5 Chapter Arrangement............................ 4 2 Background Knowledge.............................. 5 2.1 Unsupervised clustering and Visualization . . . . . . . . . . . . . . . . . 5 2.1.1 t-SNE................................ 5 2.2 Machine Learning Models ......................... 5 2.2.1 Support Vector Machine ...................... 5 2.2.2 Random Forest ........................... 6 2.2.3 LightGBM ............................. 7 2.2.4 Deep Neural Network ....................... 7 2.3 Resampling and SMOTE .......................... 9 2.4 Feature Importance ............................. 9 2.4.1 LIME................................ 10 2.4.2 SHAP................................ 10 2.5 Stroke Related Index ............................ 11 3 Experiment for Predicting DischargemRS .................... 13 3.1 DataDescription .............................. 13 3.1.1 DataSource............................. 13 3.1.2 Unsupervised clustering ...................... 14 3.2 Method ................................... 15 3.2.1 Binary, Multi-classification, and Regression models . . . . . . . . 16 3.2.2 Experiment for Data Volume.................... 17 3.3 Results.................................... 17 3.3.1 Experiment for Data Volume.................... 17 3.3.2 Group by different bin of data ................... 19 3.4 Model Analysis ............................... 21 3.4.1 Experiment for features....................... 21 3.4.2 Feature importance......................... 21 3.4.3 Explanation for samples ...................... 23 3.5 Chapter Conclusion............................. 24 4 Experiment for Predicting Deterioration ..................... 27 4.1 Data Description .............................. 27 4.2 Data Resampling .............................. 28 4.3 Results.................................... 30 4.4 Feature Importance ............................. 30 4.5 Chapter Conclusion............................. 31 5 Conclusion and Future Works........................... 33 5.1 Contribution and Discussion ........................ 33 5.2 FutureWorks ................................ 33 Reference....................................... 34 Appendix ....................................... 39 1 Features...................................... 39 | |
| dc.language.iso | en | |
| dc.subject | 中風預測 | zh_TW |
| dc.subject | 雷氏量表 | zh_TW |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | 重新抽樣 | zh_TW |
| dc.subject | 預測因子 | zh_TW |
| dc.subject | Predictor | en |
| dc.subject | Stroke Prediction | en |
| dc.subject | mRS | en |
| dc.subject | Machine Learning | en |
| dc.subject | Re-sampling | en |
| dc.title | 基於機器學習的中風患者離院時之修改過的雷氏量表及惡化預測 | zh_TW |
| dc.title | Machine Learning Based Discharge-mRS and Deterioration Prediction for Stroke Patients | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 108-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 林澤(Che Lin),柯拉飛(Rafael Kaliski),王志宇(Chih-Yu Wang),林忠緯(Chung-Wei Lin) | |
| dc.subject.keyword | 中風預測,雷氏量表,機器學習,重新抽樣,預測因子, | zh_TW |
| dc.subject.keyword | Stroke Prediction,mRS,Machine Learning,Re-sampling,Predictor, | en |
| dc.relation.page | 41 | |
| dc.identifier.doi | 10.6342/NTU202003633 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2020-08-17 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
| 顯示於系所單位： | 電機工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-1608202023044800.pdf 未授權公開取用 | 2.19 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。