整合決策樹與統計分析超音波抽取注入酒精在子宮內膜異位症療效

機構典藏 > College of Engineering > Graduate Institute & Department of Computer Science and Information Engineering > Thesis > Item 987654321/52407

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/52407

Title:	整合決策樹與統計分析超音波抽取注入酒精在子宮內膜異位症療效
Other Titles:	Statistical and decision tree analysis of effectiveness of ultrasound-guided aspiration of ovarian endometriomas
Authors:	莊斯婷;Chuang, Ssu-ting
Contributors:	淡江大學資訊工程學系碩士班蔣定安;Chiang, Ding-an
Keywords:	資料探勘;決策樹;CART;統計t test;子宮內膜異位症;data mining;Decision tree;CART;t test of Statistical;ovarian endometriomas
Date:	2010
Issue Date:	2010-09-23 17:36:30 (UTC+8)
Abstract:	在醫療統計上，有許多學者證實了“超音波抽取注入酒精治療注入酒精時間在十分鐘以上至不抽出，有較佳的療效”，但是卻很少學者探討“不同狀況患者對酒精治療時間長短與復癒率之間的關係”，所以本論文以資料探勘的方式探討此問題。而決策樹演算法在規則表現以樹狀方式呈現，因此在知識的透明度上有很好的表現，且決策樹可針對目標類別同時分析類別屬性與數值屬性欄位，找出對於最佳屬性切點。但決策樹分類的結構是屬於區域的特性且有過度擬合(over-fitting)問題。故在本文中，擬利用決策樹CART演算法產生規則，將決策樹規則的節點重新組合產生所有可能的規則，再結合統計t test驗證規則的顯著，以找出未被發掘而有意義的知識。實驗結果表明，我們的做法可以找到子宮內膜異位症不同狀況患者對酒精治療時間長短與復癒率的一些新知識。 Although several researchers have performed statistical methods to prove that aspiration followed by injection of 95% ethanol left in situ (retention) is an effective treatment of ovarian endometriomas, very few of them discuss the different conditions that could generate different recovery rate for the patients. Therefore, this study adopts the statistical method and decision tree techniques together to analyze the postoperative status of ovarian endometriosis patients under the conditions. Since our collected data set is small, only contains 212 records, we use all of these data as the training data. Therefore, instead of using a resultant tree to generate rules directly, we use the value of each node as a cut point to generate all possible rules to the tree first. Then, using t test to verify rules to discover some useful description rules after all possible rules to the tree are generated. The experimental results show that our approach can find some new interesting knowledge about the recurrent ovarian endometriomas under the different conditions.
Appears in Collections:	[Graduate Institute & Department of Computer Science and Information Engineering] Thesis

Files in This Item:

File	Size	Format
index.html	0Kb	HTML	201	View/Open

Loading...