國立高雄大學圖資館 |

語系: 繁體中文

說明(常見問題)

圖資館首頁

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

基於約略集合之藥物不良反應信號偵測方法於具缺漏值之通報資料的可行性研究 ...

國立高雄大學資訊工程學系碩士班

基於約略集合之藥物不良反應信號偵測方法於具缺漏值之通報資料的可行性研究 = On the Feasibility of Rough-Set-based ADR Signaling from Spontaneous Reporting Data with Missing Values

紀錄類型:	書目-語言資料,印刷品 : 單行本
並列題名:	On the Feasibility of Rough-Set-based ADR Signaling from Spontaneous Reporting Data with Missing Values
作者:	藍琳,
其他團體作者:	國立高雄大學
出版地:	[高雄市]
出版者:	撰者;
出版年:	2014[民103]
面頁冊數:	81面圖,表 : 30公分;
標題:	藥物不良反應
標題:	Adverse drug reaction
電子資源:	http://handle.ncl.edu.tw/11296/ndltd/16226130716616540268
附註:	104年10月31日公開
附註:	參考書目：面67-70
摘要註:	藥物不良反應係指在正常用藥劑量下所引起的有害的反應(副作用)；嚴重的藥物不良反應甚至會導致病人死亡或威脅生命的後果。由於有相當多的不良反應無法在有限的臨床試驗被發現，許多先進國家乃建置自發性通報系統，盡可能地收集所有的不良反應事件，以監控上市的藥物並發掘可能的不良反應。不幸地，由於隱私問題或其他原因，通報者有時故意漏填某些欄位，造成這些通報資料含有許多的缺漏資料。這些缺漏資料多少會影響分析結果，導致結果產生偏差。大多數的不良反應偵測的研究或實際採用的作法皆採用刪除法，直接刪掉含有缺漏值的資料。目前仍未見有研究注意到並進而研究，在進行不良反應偵測的過程中將這些缺漏納入考量是否可行且效果如何的問題。本論文可視為是探索此問題的先期性的研究。我們目標在探討使用約略集合論於藥物不良反應偵測的可行性。我們提出使用基於特徵集合的估算，來計算不良反應信號的強度。我們提出了12種不同的計算方法，並且使用我們提出的兩個新的觀念，滿足性及不可分辨性，證明其中只有六種方法是適合的計算方法。經由我們使用美國食品藥物管理局(FDA)的藥物不良反應通報系統的資料所進行的實驗顯示，我們提出的方法具有和傳統的方法相似的可疑不良反應信號的定期預警能力，而且對於某些已知的不良反應，我們的方法可以產生高於門檻的信號強度值，而傳統的方法卻無法產生預期的信號。我們的研究顯示，利用約略集合理論可以將缺漏值納入不良反應信號的強度計算，且能弭補傳統的方法的不足處，因此可作為一種輔助的方法。 Adverse Drug Reactions (ADRs) are uncomfortable or harmful reactions (side effects) in normal doses of drug usage; serious ADRs may even lead to death or life-threatening outcomes of patients. Since many ADRs cannot be disclosed through limited clinical trials, most of the developed countries have established spontaneous reporting systems to collect as could as possible all adverse drug events in order to monitor the marketed drugs and to discover suspicious ADR signals. Unfortunately, due to privacy concern or other reasons, the reporters sometimes may omit consciously some attributes, causing many missing values existing in the reporting database. These missing data can reduce the accuracy of results for data analysis. Most of published research work on ADR detection or methods applied in practice simply adopted listwise deletion method to eliminate all data with missing values. No work has noticed the possibility and examined the effect of including the missing data in the process of ADR detection.This thesis represents a preliminary endeavor towards the exploration of this question. We aim at inspecting the feasibility of applying rough set theory to the ADR detection problem. We propose the concept of utilizing characteristic set based approximation to measure the strength of ADR signals. We propose twelve different rough set based measuring methods and show, in terms of two new proposed concepts, satisfiable and indistinguishable properties, only six of them are feasible for the purpose. Experimental results conducted on the FARES database show that our rough set based approach exhibits similar capability in timeline warning of suspicious ADR signals as traditional method, and sometimes can yield noteworthy measures (higher than the threshold) of some known ADR signals even when the traditional method fails. Our study concludes that rough set based ADR signal measuring method that takes missing data into account is feasible and can be regarded as an auxiliary for the traditional measuring method.

基於約略集合之藥物不良反應信號偵測方法於具缺漏值之通報資料的可行性研究 = On the Feasibility of Rough-Set-based ADR Signaling from Spontaneous Reporting Data with Missing Values
藍, 琳

基於約略集合之藥物不良反應信號偵測方法於具缺漏值之通報資料的可行性研究 = On the Feasibility of Rough-Set-based ADR Signaling from Spontaneous Reporting Data with Missing Values / 藍琳撰 - [高雄市] : 撰者, 2014[民103]. - 81面 ; 圖,表 ; 30公分.
104年10月31日公開參考書目：面67-70.
藥物不良反應Adverse drug reaction

基於約略集合之藥物不良反應信號偵測方法於具缺漏值之通報資料的可行性研究 = On the Feasibility of Rough-Set-based ADR Signaling from Spontaneous Reporting Data with Missing Values
LDR:05285nam0a2200289 450 001 430142
005 20170214095230.0
009 430142
010 0 $b 精裝
010 0 $b 平裝
100 $a 20170214y2014 k y0chiy50 b
101 1 $a eng $d chi $d eng
102 $a tw
105 $a ak am 000yy
200 1 $a 基於約略集合之藥物不良反應信號偵測方法於具缺漏值之通報資料的可行性研究 $d On the Feasibility of Rough-Set-based ADR Signaling from Spontaneous Reporting Data with Missing Values $z eng $f 藍琳撰
210 $a [高雄市] $c 撰者 $d 2014[民103]
215 0 $a 81面 $c 圖,表 $d 30公分
300 $a 104年10月31日公開
300 $a 參考書目：面67-70
314 $a 指導教授：林文揚博士
328 $a 碩士論文--國立高雄大學資訊工程學系碩士班
330 $a 藥物不良反應係指在正常用藥劑量下所引起的有害的反應(副作用)；嚴重的藥物不良反應甚至會導致病人死亡或威脅生命的後果。由於有相當多的不良反應無法在有限的臨床試驗被發現，許多先進國家乃建置自發性通報系統，盡可能地收集所有的不良反應事件，以監控上市的藥物並發掘可能的不良反應。不幸地，由於隱私問題或其他原因，通報者有時故意漏填某些欄位，造成這些通報資料含有許多的缺漏資料。這些缺漏資料多少會影響分析結果，導致結果產生偏差。大多數的不良反應偵測的研究或實際採用的作法皆採用刪除法，直接刪掉含有缺漏值的資料。目前仍未見有研究注意到並進而研究，在進行不良反應偵測的過程中將這些缺漏納入考量是否可行且效果如何的問題。本論文可視為是探索此問題的先期性的研究。我們目標在探討使用約略集合論於藥物不良反應偵測的可行性。我們提出使用基於特徵集合的估算，來計算不良反應信號的強度。我們提出了12種不同的計算方法，並且使用我們提出的兩個新的觀念，滿足性及不可分辨性，證明其中只有六種方法是適合的計算方法。經由我們使用美國食品藥物管理局(FDA)的藥物不良反應通報系統的資料所進行的實驗顯示，我們提出的方法具有和傳統的方法相似的可疑不良反應信號的定期預警能力，而且對於某些已知的不良反應，我們的方法可以產生高於門檻的信號強度值，而傳統的方法卻無法產生預期的信號。我們的研究顯示，利用約略集合理論可以將缺漏值納入不良反應信號的強度計算，且能弭補傳統的方法的不足處，因此可作為一種輔助的方法。 Adverse Drug Reactions (ADRs) are uncomfortable or harmful reactions (side effects) in normal doses of drug usage; serious ADRs may even lead to death or life-threatening outcomes of patients. Since many ADRs cannot be disclosed through limited clinical trials, most of the developed countries have established spontaneous reporting systems to collect as could as possible all adverse drug events in order to monitor the marketed drugs and to discover suspicious ADR signals. Unfortunately, due to privacy concern or other reasons, the reporters sometimes may omit consciously some attributes, causing many missing values existing in the reporting database. These missing data can reduce the accuracy of results for data analysis. Most of published research work on ADR detection or methods applied in practice simply adopted listwise deletion method to eliminate all data with missing values. No work has noticed the possibility and examined the effect of including the missing data in the process of ADR detection.This thesis represents a preliminary endeavor towards the exploration of this question. We aim at inspecting the feasibility of applying rough set theory to the ADR detection problem. We propose the concept of utilizing characteristic set based approximation to measure the strength of ADR signals. We propose twelve different rough set based measuring methods and show, in terms of two new proposed concepts, satisfiable and indistinguishable properties, only six of them are feasible for the purpose. Experimental results conducted on the FARES database show that our rough set based approach exhibits similar capability in timeline warning of suspicious ADR signals as traditional method, and sometimes can yield noteworthy measures (higher than the threshold) of some known ADR signals even when the traditional method fails. Our study concludes that rough set based ADR signal measuring method that takes missing data into account is feasible and can be regarded as an auxiliary for the traditional measuring method.
510 1 $a On the Feasibility of Rough-Set-based ADR Signaling from Spontaneous Reporting Data with Missing Values $z eng
610 0 $a 藥物不良反應 $a 列聯表 $a 缺漏值 $a 藥物安全監測 $a 約略集合論 $a 自發性通報資料
610 1 $a Adverse drug reaction $a contingency table $a missing data $a pharmacovigilance $a rough set theory $a spontaneous reporting data
681 $a 008M/0019 $b 464103 4414.2 $v 2007年版
700 1 $a 藍 $b 琳 $4 撰 $3 673365
712 0 2 $a 國立高雄大學 $b 資訊工程學系碩士班 $3 353878
801 0 $a tw $b 國立高雄大學 $c 20151023 $g CCR
856 7 $z 電子資源 $2 http $u http://handle.ncl.edu.tw/11296/ndltd/16226130716616540268