English  |  正體中文  |  简体中文  |  Items with full text/Total items : 49287/83828 (59%)
Visitors : 7152543      Online Users : 49
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/87979


    Title: 利用決策樹與統計t檢定分析子宮內膜異位症病患之治療方式比較
    Other Titles: Comparison of endometriosis treatment using decision tree and t-test
    Authors: 黃炳維;Huang, Ping-Wei
    Contributors: 淡江大學資訊工程學系碩士班
    陳俊豪
    Keywords: 子宮內膜異位症;CART決策樹;t-test;Endometriosis;CART decision tree
    Date: 2012
    Issue Date: 2013-04-13 11:55:07 (UTC+8)
    Abstract: 在國內外的婦女不孕症醫療統計上,約有20%的不孕症病患同時為子宮內膜異位症的患者,隨著醫療技術的進步,子宮內膜異位症的病患已可藉由手術或藥物的治療方式獲得治癒而成功懷孕,這些手術或藥物的治療方式有許多種,若以酒精滯留手術來治療,目前以酒精滯留在病患體內7分鐘以上,並視病患手術過後的情況給予用藥或針劑治療為主流的治療方式。然而,酒精滯留在病患體內的時間不同對於不同狀況病患的療效會有所不同,手術後不同的藥物治療方式也會對不同狀況的病患帶來不同的治療效果,因此找出對於哪一種狀況的病患採用哪一種治療方式具有較佳的療效便是我們的目標。若只採用傳統的t檢定或變異數分析等統計方法來分析,則如何將病患資料切割出適合這些統計方法分析的資料群組將成為一個困難而麻煩的問題,因此本論文改採用CART決策樹來產生出各種狀況的病患,統計這些狀況下的病患接受各種治療方式而治療成功或失敗的人數,並透過治癒率、治療率比以及統計t檢定比較各治療方式間的療效差異程度,藉以了解在該狀況下的病患採用何種治療方式具有較佳的療效。實驗結果顯示,我們的方法能夠找出對於各種狀況的病患具較佳療效的治療方式,進而成為輔佐醫師制訂醫療決策時的參考知識。
    According to statistical research studied by WHO, there’re approximately 20% of infertility female patients who had been affected by endometriosis. But these patients can be healed by medicated or surgery treatment due to improvement of medical technology. At present, “7 minutes or above” treat time became the main treatment if the injection of 95% ethanol was chosen to be the surgery treatment, meanwhile, doctors would use medicated treatment after surgery likely according to the patient’s status. However, the effect of both medicated and surgery treatment can be different due to the difference of patient’s status. Therefore, the goal of this paper is to find out which treatment would be better rest with patient’s certain status. If we only use statistical way (ANOVA, t-test, etc) to solve this problem, how to partition the medical data properly would be a serious circumstance. Therefore, CART decision tree was used to generate different patient’s status in this paper, then, compare population, cure rate and magnificent difference of t-test between different treatments, after that, the better medical treatment can be found. According to the experiment result in this paper, the better medical treatment can be found out by purposed method.
    Appears in Collections:[資訊工程學系暨研究所] 學位論文

    Files in This Item:

    File SizeFormat
    index.html0KbHTML130View/Open

    All items in 機構典藏 are protected by copyright, with all rights reserved.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - Feedback