請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/57561
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 賴飛羆(Fei-Pei Lai) | |
dc.contributor.author | Guo-Hung Li | en |
dc.contributor.author | 李國弘 | zh_TW |
dc.date.accessioned | 2021-06-16T06:51:34Z | - |
dc.date.available | 2025-07-20 | |
dc.date.copyright | 2020-08-04 | |
dc.date.issued | 2020 | |
dc.date.submitted | 2020-07-20 | |
dc.identifier.citation | 1. Qureshi H, Sharafkhaneh A, Hanania NA. Chronic obstructive pulmonary disease exacerbations: latest evidence and clinical implications. Ther Adv Chronic Dis. 2014;5(5):212–227. doi:10.1177/2040622314532862 2. Yan R, Wang Y, Bo J, Li W. Healthy lifestyle behaviors among individuals with chronic obstructive pulmonary disease in urban and rural communities in China: a large community-based epidemiological study. Int J Chron Obstruct Pulmon Dis. 2017;12:3311–3321. Published 2017 Nov 13. doi:10.2147/COPD.S144978 3. GOLD - Global Initiative for Chronic Obstructive Lung Disease 4. Ambrosino, Nicolino, and Enrica Bertella. “Lifestyle interventions in prevention and comprehensive management of COPD.” Breathe (Sheffield, England) vol. 14,3 (2018): 186-194. doi:10.1183/20734735.018618 5. Adibi, Amin Sin, Don Safari, Abdollah Johnson, Kate Aaron, Shawn Fitzgerald, J Mark Sadatsafavi, Mohsen. (2020). The Acute COPD Exacerbation Prediction Tool (ACCEPT): a modelling study. The Lancet Respiratory Medicine. 10.1016/S2213-2600(19)30397-2. 6. Sanchez-Morillo, D., Fernandez-Granero, M. A., Leon-Jimenez, A. (2016). Use of predictive algorithms in-home monitoring of chronic obstructive pulmonary disease and asthma: A systematic review. Chronic Respiratory Disease, 264–283. https://doi.org/10.1177/1479972316642365 7. Hurst, JR, Donaldson, GC, Quint, JK. Domiciliary pulse-oximetry at exacerbation of chronic obstructive pulmonary disease: prospective pilot study. BMC Pulm Med 2010; 10: 52. 8. Sánchez-Morillo, D, Crespo, M, León, A. A novel multimodal tool for telemonitoring patients with COPD. Inform Health Soc Care 2013; 40: 1–22. 9. Sanders, C, Rogers, A, Bowen, R. Exploring barriers to participation and adoption of telehealth and telecare within the whole system demonstrator trial: a qualitative study. BMC Health Serv Res 2012; 12: 220. 10. Saleh L., Mcheick H., Ajami H., Mili H., Dargham J. (2017) Comparison of Machine Learning Algorithms to Increase Prediction Accuracy of COPD Domain. In: Mokhtari M., Abdulrazak B., Aloulou H. (eds) Enhanced Quality of Life and Smart Living. ICOST 2017. Lecture Notes in Computer Science, vol 10461. Springer, Cham 11. Hans Christian Riis, Morten H. Jensen, Simon Lebech Cichosz Ole K. Hejlesen (2016) Prediction of exacerbation onset in chronic obstructive pulmonary disease patients, Journal of Medical Engineering Technology, 40:1, 1-7, DOI: 10.3109/03091902.2015.1105317 12. Wang C, Chen X, Du L, Zhan Q, Yang T, Fang Z. Comparison of machine learning algorithms for the identification of acute exacerbations in chronic obstructive pulmonary disease. Comput Methods Programs Biomed. 2020;188:105267. doi:10.1016/j.cmpb.2019.105267 13. Md Juber Rahman, Ebrahim Nemati, Md Mahbubur Rahman, Viswam Nathan, Korosh Vatanparvar, Jilong Kuang, Automated assessment of pulmonary patients using heart rate variability from everyday wearables, Smart Health, Volume 15, 2020, 100081, ISSN 2352-6483, 14. Jolliffe I.T. Principal Component Analysis, Series: Springer Series in Statistics, 2nd ed., Springer, NY, 2002, XXIX, 487 p. 28 illus. ISBN 978-0-387-95442-4 15. Sharma, Himani Kumar, Sunil. (2016), A Survey on Decision Tree Algorithms of Classification in Data Mining. International Journal of Science and Research (IJSR). 5. 16. Cristóbal Esteban, Javier Moraza, Fernando Sancho, Myriam Aburto, Amaia Aramburu, Begona Goiria, Amaia Garcia-Loizaga, Alberto Capelastegui, “Machine learning for COPD exacerbation prediction”, European Respiratory Journal Sep 2015, 46 (suppl 59) OA3282; DOI: 10.1183/13993003.congress- 2015.OA3282 17. Ho, Tin Kam (2002). 'A Data Complexity Analysis of Comparative Advantages of Decision Forest Constructors'. Pattern Analysis and Applications. 5 (2): 102– 112. doi:10.1007/s100440200009. 18. Altman, Naomi S. (1992), 'An introduction to kernel and nearest-neighbor nonparametric regression,' The American Statistician. 46 (3): 175–185. doi:10.1080/00031305.1992.10475879. hdl:1813/31637. 19. Ioffe, Sergey; Szegedy, Christian (2015), 'Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,' arXiv:1502.03167 [cs.LG]. 20. He, Kaiming Zhang, Xiangyu Ren, Shaoqing Sun, Jian. (2015). Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. IEEE International Conference on Computer Vision (ICCV 2015). 1502. 10.1109/ICCV.2015.123 21. Goto T, Camargo CA Jr, Faridi MK, Yun BJ, Hasegawa K. Machine learning approaches for predicting disposition of asthma and COPD exacerbations in the ED. Am J Emerg Med. 2018;36(9):1650-1654. doi:10.1016/j.ajem.2018.06.062 22. Peng, J., Chen, C., Zhou, M. et al. A Machine-learning Approach to Forecast Aggravation Risk in Patients with Acute Exacerbation of Chronic Obstructive Pulmonary Disease with Clinical Indicators. Sci Rep 10, 3118 (2020). https://doi.org/10.1038/s41598-020-60042-1 23. Fernandez-Granero M.A., Sanchez-Morillo D., Lopez-Gordo M.A., Leon A. (2015) A Machine Learning Approach to Prediction of Exacerbations of Chronic Obstructive Pulmonary Disease. In: Ferrández Vicente J., Álvarez-Sánchez J., de la Paz López F., Toledo-Moreo F., Adeli H. (eds) Artificial Computation in Biology and Medicine. IWINAC 2015. Lecture Notes in Computer Science, vol 9107. Springer, Cham 24. Shah SA, Velardo C, Farmer A, Tarassenko L, Exacerbations in Chronic Obstructive Pulmonary Disease: Identification and Prediction Using a Digital Health System, J Med Internet Res 2017;19(3):e69, URL: https://www.jmir.org/2017/3/e69, DOI: 10.2196/jmir.7207, PMID: 28270380, PMCID: 5360891 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/57561 | - |
dc.description.abstract | 背景:世界衛生組織的報告指出,預計到2030 年,慢性阻塞性肺疾病(COPD) 將成為全球第三大死因和第七大罹病率。慢性阻塞性肺疾病的急性發作(AECOPD)與肺功能加速下降,生活質量下降和更高的死亡率有關。準確的早期發 現急性發作病情將有助於個人化慢性阻塞性肺疾病的醫療照護並降低死亡率。由於慢性阻塞性肺疾病患者於出院後的生活型態改變並具有較高的機率暴露於空氣 汙染、高濕度等潛在危險因子中,因此比起患者在住院期間,多數急性發作事件 發生於患者出院之後。因此,在患者出院期間進行連續性的風險評估有機會在急 性發作前提早偵測,並提醒醫師及早進行介入治療。 目的:本文旨在通過生活型態數據和症狀嚴重程度數據提出一種AE-COPD 風險 預測方法的預測模型,以預測七天內的慢性阻塞性肺病的急性發作。 方法:來自台灣大學醫院慢性阻塞性肺病的67例,排除裝有心跳節律器和妊娠 的患者組成了測試族群。使用穿戴式裝置,室內空氣質量感應設備,智慧型手機 應用程式收集生活方式和環境因素。急性發作症狀的定義來自標準化的問卷。使 用的預測模型為隨機森林、決策數、K 最近鄰居法、線性判別分析、Adaboost, 以及深度神經網路模型。 結果:本研究通過集成穿戴式裝置、室內空氣質量感應設備,智慧型手機應用程式,實現了對生活型態和環境因素的連續即時監控。在平均4 個月的持續追蹤期 間收集了67 例COPD 患者的數據,其中25 例急性發作。對未來7 天進行AECOPD 可能性評估的預測模型,其準確度達到92.1%,敏感性為94%,特異性為 90.4%。模型中權重最大的變數是步行數,樓層數和行走距離。 結論:我們使用穿戴式裝置,室內空氣質量感應設備、智慧型手機應用程式,以 及監督式學習演算法模型。在預測患者在未來的7 天內是否會急性發作,預測模 型的ROC 曲線下面積為0.9。當患者即將要急性發作時,系統能夠提前足夠的時 間做出可靠的預測。 | zh_TW |
dc.description.abstract | Background: World Health Organization anticipated that by 2030, chronic obstructive pulmonary disease (COPD) would become the third leading cause of mortality and the seventh leading cause of morbidity worldwide. Acute exacerbations of chronic obstructive pulmonary disease (AE-COPD) are associated with accelerated decline in lung function, diminished quality of life, and higher mortality. Accurate early detection of acute exacerbations will help to enable personalized chronic obstructive pulmonary disease care and reduce mortality. Objective: This paper aimed to develop a model of AE-COPD risk prediction approach using lifestyle data and severity of symptoms to achieve early prediction of AE-COPD within 7 days. Methods: This prospective study was conducted in National Taiwan University Hospital. A total of 67 COPD patients without pacemaker and pregnancy were enrolled. Lifestyle and environmental factors were collected using wearable devices, home air quality sensing devices, smartphone application. The episode of AE-COPD was evaluated by standardized questionnaire. With these input features, we evaluate the prediction performance of random forest, decision tree, kNN, linear discriminant analysis, Adaboost, and a deep neural network model. Results: The continuous real-time monitoring of lifestyle and environment factors were implemented in this study by integrating home air quality sensing devices, smartphone applications, and wearable devices. All data from 67 COPD patients were collected vi prospectively during their mean 4 months follow-up and 25 episodes of AE-COPD were detected. For prediction of AE-COPD within the next 7 days, our AE-COPD predictive model had accuracy of 92.1% , sensitivity of 94% of sensitivity and specificity of 90.4% . The most weighting variables in the model were daily walking steps, climbing stairs and daily distance. Conclusions: Using wearable devices, home air quality sensing devices, smartphone application and supervised prediction algorithms, we achieved an area under the ROC curve of 0.9x for the task of predicting whether a patient will suffer an acute exacerbation within the next seven days. The system was capable of making reliable predictions with enough time in advance when a patient is going to have an AE-COPD. | en |
dc.description.provenance | Made available in DSpace on 2021-06-16T06:51:34Z (GMT). No. of bitstreams: 1 U0001-2007202015181100.pdf: 2780647 bytes, checksum: 460607da9e70f8573a19d9bc444dbed0 (MD5) Previous issue date: 2020 | en |
dc.description.tableofcontents | 國立臺灣大學(碩)博士學位論文............................................................................... i 口試委員會審定書........................................................................................................... i 誌謝 .................................................................................................................................. ii 中文摘要 ......................................................................................................................... iii Abstract.............................................................................................................................. v CONTENTS ................................................................................................................... vii LIST OF FIGURES ......................................................................................................... ix LIST OF TABLES............................................................................................................. x Chapter1. Introduction .............................................................................................. 1 Chapter2. Methods..................................................................................................... 3 2.1. Data Collection ............................................................................................... 3 2.2. System Architecture........................................................................................ 5 2.3. Feature Selection and Feature Engineering .................................................... 9 2.4. Imbalanced Data ........................................................................................... 11 2.5. Missing Data ................................................................................................. 13 2.6. Feature Distribution ...................................................................................... 14 2.7. K-Fold Validation ......................................................................................... 19 2.8. Principal Component Analysis ..................................................................... 19 2.9. Classification Model ..................................................................................... 20 2.9.1. Linear Discriminant Analysis .............................................................. 21 2.9.2. Decision Tree....................................................................................... 21 2.9.3. AdaBoost ............................................................................................. 22 2.9.4. Random Forest .................................................................................... 23 2.9.5. K Nearest Neighbor ............................................................................. 23 2.9.6. Deep Neural Network.......................................................................... 24 2.10. Acute Exacerbation Prediction ..................................................................... 27 2.11. Model Assessment ........................................................................................ 27 Chapter3. Results ..................................................................................................... 28 3.1. Lifestyle and Environment ........................................................................... 28 3.2. AE-COPD Prediction Model ........................................................................ 28 3.3. Deployment................................................................................................... 31 3.4. Feature Importance ....................................................................................... 31 Chapter4. Discussion ................................................................................................ 33 4.1. Comparison of Feature Sets .......................................................................... 33 4.2. System Architecture Analysis ....................................................................... 38 Chapter5. Limitation ............................................................................................... 40 Chapter6. Conclusions ............................................................................................. 41 Abbreviations ........................................................................................................... 42 References 43 | |
dc.language.iso | en | |
dc.title | 基於穿戴式裝置之慢性肺阻塞急性發作機器學習預測系統 | zh_TW |
dc.title | Chronic Obstructive Pulmonary Disease with Acute Exacerbation Prediction System Using Wearable Device and Machine Learning and Deep Learning | en |
dc.type | Thesis | |
dc.date.schoolyear | 108-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 郭律成(Lu-Cheng Kuo),簡榮彥(Jung-Yien Chien),李妮鍾(Ni-Chung Lee),胡務亮(Wuh-Liang Hwu) | |
dc.subject.keyword | 慢性阻塞性肺疾病,臨床決策支持系統,健康風險評估,穿戴式裝置,監督式機器學習, | zh_TW |
dc.subject.keyword | chronic obstructive pulmonary disease,clinical decision support systems,health risk assessment,wearable device,supervised machine learning, | en |
dc.relation.page | 46 | |
dc.identifier.doi | 10.6342/NTU202001652 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2020-07-21 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 生醫電子與資訊學研究所 | zh_TW |
顯示於系所單位: | 生醫電子與資訊學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
U0001-2007202015181100.pdf 目前未授權公開取用 | 2.72 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。