Skip navigation

DSpace

機構典藏 DSpace 系統致力於保存各式數位資料(如:文字、圖片、PDF)並使其易於取用。

點此認識 DSpace
DSpace logo
English
中文
  • 瀏覽論文
    • 校院系所
    • 出版年
    • 作者
    • 標題
    • 關鍵字
    • 指導教授
  • 搜尋 TDR
  • 授權 Q&A
    • 我的頁面
    • 接受 E-mail 通知
    • 編輯個人資料
  1. NTU Theses and Dissertations Repository
  2. 管理學院
  3. 資訊管理學系
請用此 Handle URI 來引用此文件: http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/4883
完整後設資料紀錄
DC 欄位值語言
dc.contributor.advisor盧信銘
dc.contributor.authorYu-Hsien Linen
dc.contributor.author林鈺嫻zh_TW
dc.date.accessioned2021-05-14T17:49:34Z-
dc.date.available2016-10-12
dc.date.available2021-05-14T17:49:34Z-
dc.date.copyright2015-10-12
dc.date.issued2015
dc.date.submitted2015-09-15
dc.identifier.citationY. C. Chen, W. Y. Chiou, S. K. Hung, Y. C. Su, and S. J. Hwang. 2013. Hepatitis C virus itself is a causal risk factor for chronic kidney disease beyond traditional risk factors: a 6-year nationwide cohort study across Taiwan. BMC Nephrology, 6;14:187.
W. C. Chiu, Y. T. Tsan, S. L. Tsai, C. J. Chang, J. D. Wang, P. C. Chen, and hDATa Research Group. 2014. Hepatitis C viral infection and the risk of dementia. European Journal of Neurology, 21 (8):1068-e59.
M. J. Cohen, A. D. Grossman, D. Morabito, M. M. Knudson, A. J. Butte and G. T. Manley. 2010. Identification of complex metabolic states in critically injured patients using bioinformatic cluster analysis. Critical Care, 14 (1):R10.
C. Danescu-Niculescu-Mizil, R. West, D. Jurafsky, J. Leskovec, C. Potts. 2013. No country for old members: user lifecycle and linguistic change in online communities. WWW, 307-318.
R. S. Doody, V. Pavlik, P. Massman, S. Rountree, E. Darby, and W. Chan. 2010. Predicting progression of Alzheimer’s disease. Alzheimer’s Research & Therapy, 2:2.
H. M. Fonteijn, M. Modat, M. J. Clarkson, J. Barnes, M. Lehmann, N. Z. Hobbs, R. I. Scahill, S. J. Tabrizi, S. Ourselin, N. C. Fox, and D. C. Alexander. 2012. An event-based model for disease progression and its application in familial Alzheimer’s disease and Huntington’s disease. NeuroImange, 60 (3):1880-1889.
Y. C. Hsu, J. T. Lin, H. J. Ho, Y. H. Kao, Y. T. Huang, N. W. Hsiao, M. S. Wu, Y. Y. Liu, and C. Y. Wu. 2014. Antiviral treatment for hepatitis C virus infection is associated with improved renal and cardiovascular outcomes in diabetic patients. Hepatology, 59 (4):1293-1302.
C. C. Hsu, C. H. Lee, M. L. Wahlqvist, H. L. Huang, H. Y. Chang, L. Chen, S. F. Shih, S. J. Shin, W. C. Tsai, T. Chen, C. T. Huang, J. S. Cheng. Poverty increases type 2 diabetes incidence and inequality of care despite universal health coverage. Diabetes Care, 35 (11):2286-2292.
C. H. Lin, and W. H. Sheu. 2013. Hypoglycaemic episodes and risk of dementia in diabetes mellitus: 7-year follow-up study. Journal of internal medicine, 273 (1):102-110.
D. Mould. 2012. Models for disease progression: new approaches and uses. Clinical Pharmacology & Therapeutics, 92 (1):125-131.
T. M. Post, J. I. Freijer, J. DeJongh, and M. Danhof. 2005. Disease system analysis: basic disease progression models in degenerative disease. Pharmaceutical research, 22 (7):1038-1049.
A. Raj, A. Kuceyeski, and M. Weiner. 2012. A network diffusion model of disease progression in dementia. Neuron, 73 (6):1204-1215.
X. Wang. D. Sontag, and F. Wang. 2014. Unsupervised learning of disease progression models. KDD, 85-94.
J. Yang, J. J. McAuley, J. Leskovec, P. LePendu, and N. Shah. 2014. Finding progression stages in time-evolving event sequences. WWW, 783-794.
H. T. Yeh, C. F. Hsieh, Y. W. Tsai, and W. F. Huang. 2012. Effects of thiazolidinediones on cardiovascular events in patients with type 2 diabetes mellitus after drug-eluting stent implantation: a retrospective cohort study using the national health insurance database in Taiwan. Clinical Therapy, 34 (4):885-893.
J. Zhou, J. Liu, V. A. Narayan, and J. Ye.. 2012. Modeling disease progression via fused sparse group lasso. KDD, 1095-1103.
J. Zhou, L. Yuan, J. Liu, J. Ye.. 2011. A multi-task learning formulation for predicting disease progression. KDD, 814-822.
dc.identifier.urihttp://tdr.lib.ntu.edu.tw/jspui/handle/123456789/4883-
dc.description.abstract由許多事件組合而成的連續序列資料中,可能隱含一些像是病況的嚴重程度,或是病情加重的速度等資訊。舉例來說,像是在醫院中的病人的看診資料,如果把每次看診的疾病代碼當作是一個事件,每位病人的病例就能夠看成是一序列資料。而隨時間累積而成的序列有兩個獨特的特性。第一個特性是序列能夠根據不同的演化速度或事件組合而被區分成不同的類別(class),另一個特性是可以根據序列中發生的事件順序來推算目前此序列所在的階段(stage)。而因為序列之間會有不同的序列長度和演化速度,因此要來預測序列的類別與階段是有難度的。以慢性病病人來說,他們的病歷資料就會有上述的那些特性。因此我們能利用建立模型來分析資料,藉以從模型的產出找到有用的資訊來預測或是預防疾病的發展。從前人的研究得到的結果可以知道,利用疾病發展模型不只可以預測疾病的發展,連疾病的共病和藥物作用都可以被預測,也因此這些研究的結果能夠廣泛的運用在醫療之中。
在本研究中,我們使用資料導向(data-driven)的方法來分析健保資料中的糖
尿病患者病歷,並且從資料中擷取出疾病發展的不同階段。本研究的結果顯示,用
於研究中的模型預測能力跟前人的研究結果類似,而從分析模型產出的類別也發現,從這些類別中可以推測出兩種不同類別的糖尿病患。這些從本研究中得到的資訊可以讓我們更加了解糖尿病患的發展模式與其中的差異,並且可以提供給後人參考。
zh_TW
dc.description.abstractA series of events, such as a patient’s medical records, have two natural features, class and stage that are not easy to find. Since each event sequence may have different length, and different progression speed. Especially for chronic diseases patients, they may suffer with these diseases for a long time. The development of model to estimate the disease progression can help to provide information for them. From previous findings, their results suggested that by modeling disease progression, not only disease progression rate can be predicted but disease’s comorbidities and drug effect.
In this paper, we present a data-driven approach to analyze the health insurance claim records to extract the disease progression stages of diabetic patients. Our experiments suggested that our model’s performance is consistent with previous finding. And the progression classes learned from our model have revealed different types of diabetic patients.
en
dc.description.provenanceMade available in DSpace on 2021-05-14T17:49:34Z (GMT). No. of bitstreams: 1
ntu-104-R02725035-1.pdf: 1972707 bytes, checksum: fa5c83920dffa567502cc2cda9abe27f (MD5)
Previous issue date: 2015
en
dc.description.tableofcontents致謝 II
摘要 III
ABSTRACT IV
1 INTRODUCTION 1
2 LITERATURE REVIEW 3
2.1 PROGRESSION MODELS WITH DOMAIN KNOWLEDGE 3
2.2 PROGRESSION MODELS WITHOUT DOMAIN KNOWLEDGE 5
3 DATASET AND MODEL 8
3.1 DATASET 8
3.2 MODEL 11
3.2.1 Problem definition 11
3.2.2 Model description 13
3.2.3 Model iteration 14
3.2.4 Cross validation 18
3.2.5 Model initialization 18
4 EXPERIMENTS 19
4.1 CROSS VALIDATION 19
4.2 PREDICTING ACCURACY 20
4.3 THETA INSPECTION 21
4.4 PATIENT EXAMPLES 24
4.5 CROSS ENTROPY 26
5 CONCLUSIONS 27
6 REFERENCES 28
dc.language.isoen
dc.subject事件序列zh_TW
dc.subject資料導向zh_TW
dc.subject疾病發展模型zh_TW
dc.subject時間序列zh_TW
dc.subject非監督式學習zh_TW
dc.subjectdata-drivenen
dc.subjectevent sequenceen
dc.subjectdisease progression modelen
dc.subjecttime seriesen
dc.subjectunsupervised learningen
dc.title用非監督學習建立疾病進展模型zh_TW
dc.titleModels of Disease Progression:
An Unsupervised Learning Approach
en
dc.typeThesis
dc.date.schoolyear104-1
dc.description.degree碩士
dc.contributor.oralexamcommittee孔令傑,曹承礎
dc.subject.keyword事件序列,疾病發展模型,時間序列,非監督式學習,資料導向,zh_TW
dc.subject.keywordevent sequence,disease progression model,time series,unsupervised learning,data-driven,en
dc.relation.page30
dc.rights.note同意授權(全球公開)
dc.date.accepted2015-09-16
dc.contributor.author-college管理學院zh_TW
dc.contributor.author-dept資訊管理學研究所zh_TW
顯示於系所單位:資訊管理學系

文件中的檔案:
檔案 大小格式 
ntu-104-1.pdf1.93 MBAdobe PDF檢視/開啟
顯示文件簡單紀錄


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。

社群連結
聯絡資訊
10617臺北市大安區羅斯福路四段1號
No.1 Sec.4, Roosevelt Rd., Taipei, Taiwan, R.O.C. 106
Tel: (02)33662353
Email: ntuetds@ntu.edu.tw
意見箱
相關連結
館藏目錄
國內圖書館整合查詢 MetaCat
臺大學術典藏 NTU Scholars
臺大圖書館數位典藏館
本站聲明
© NTU Library All Rights Reserved