應用資料探勘技術於尿失禁臨床病徵分析

機構典藏 > College of Engineering > Graduate Institute & Department of Computer Science and Information Engineering > Thesis > Item 987654321/94446

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/94446

Title:	應用資料探勘技術於尿失禁臨床病徵分析
Other Titles:	Using data mining in urinary incontinence clinical symptom analysis
Authors:	張紹揚;Chang, Shao-Yang
Contributors:	淡江大學資訊工程學系碩士班陳瑞發
Keywords:	骨盆底肌肉訓練;尿失禁;資料探勘;決策樹;Pelvic Floor Muscle Training;Urinary incontinence;data mining;Decision tree
Date:	2013
Issue Date:	2014-01-23 14:39:22 (UTC+8)
Abstract:	目前骨盆底肌肉訓練療程，醫師除了透過問卷內容了解患者的復健狀況外，醫師在面對不同類型的患者時，醫師只能透過醫療經驗等針對該患者提供處置方式，不容易發現其他可能影響療程等隱藏因子，故無法作出適合該患者的最佳處置。本論文主要目的在對尿失禁患者利用資料探勘中的決策樹演算法進行分類，期望能探討不同類型的患者中影響尿失禁治療結果等因子，提供醫師更清楚瞭解患者復健狀況。當有新患者需要進行復健運動時，即可透過決策樹分類模組達到預測的作用，醫師能適時給予患者協助。實作結果表明，各分類模組均可充分將目前患者資料正確地分類至各群組，有效協助醫師應用於臨床看診。 Currently, doctors in addition to the questionnaire to understand urinary incontinence through rehabilitation situation, the doctor in the face of different types of patients only by his medical experience providing for the disposition of the patient. This way is not easy to find other treatments that may affect other hidden factor, it is not appropriate for the patient to make the best deal. The purpose of this thesis is used decision tree of data mining to discuss factors which affect result of urinary incontinence treatment of different types of patients. Providing that doctor can understand patient’s situation clearly. When a new patient needs to do pelvic floor muscle training, we can predict the result of treatment by using classification model of decision tree. Doctor can give patients assistance in pelvic floor muscle training to improve the treatment effect. The experimental results show that our approach can accurately classify the data to help doctor diagnose patients.
Appears in Collections:	[Graduate Institute & Department of Computer Science and Information Engineering] Thesis

Files in This Item:

File	Size	Format
index.html	0Kb	HTML	129	View/Open

Loading...