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

利用合作訓練與集成學習法檢測藥物不良反應事件通報系統中之重複記錄 = C...

國立高雄大學資訊工程學系碩士班

利用合作訓練與集成學習法檢測藥物不良反應事件通報系統中之重複記錄 = Co-Training and Ensemble Learning for Duplicate Detection in Adverse Drug Event Reporting Systems

紀錄類型:	書目-語言資料,印刷品 : 單行本
並列題名:	Co-Training and Ensemble Learning for Duplicate Detection in Adverse Drug Event Reporting Systems
作者:	羅喬楓,
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:	2013[民102]
面頁冊數:	59面圖，表 : 30公分;
標題:	藥物不良反應事件
標題:	Adverse drug events
電子資源:	http://handle.ncl.edu.tw/11296/ndltd/16706898753512263382
附註:	參考書目：面44-49
附註:	103年12月16日公開
附註:	內容為英文
摘要註:	藥物不良反應檢測在對於大眾健康以及製藥的發展，是個非常重要的議題。由於藥物被批准上市場前的臨床樣本數不足以確定潛在的藥物不良反應，許多國家都建立各種自發性通報系統（SRSs），以便監控上市後的藥品並收集數據用於檢測未知的藥物不良反應。由於自發性通報系統的數據來自於不同的呈報來源，就導致重複通報的問題。不幸的是，就算只有少量的重複報告，也會造成藥物不良反應檢測的偏差。雖然已有很多重複值檢測的文獻，但是很少有針對藥物不良反應的資料集做重複值檢測，而且這些研究皆未考慮資料中存在的後續追蹤報告。因此目前藥物不良反應報告中重複值偵測的方法皆無法區分一份報告是屬於重複的紀錄或是後續追蹤的連結。在本研究中，我們探討在藥物不良反應報告中存在後續追蹤紀錄的情形下，如何進行重複記錄偵測的問題，並提出一種基於合作訓練與集成學習的檢測方法。此種方法能檢測出一份報告是否為重複的報告或是初始報告的後續追蹤紀錄。 Adverse drug reactions detection is a very important topic in the public health as well as the development of modern pharmaceutical industry. Since the number of samples in clinical trials is not enough to identify potential adverse drug reactions before the drugs are approved for marketing, many countries have established various spontaneous reporting systems (SRSs) to facilitate postmarketing surveillance of listed drugs and collect enough data for detecting unknown adverse drug reactions. Unfortunately, due to data in SRSs coming from different sources of reporters, there heralds the problem of duplicate reporting; even a small amount of duplicate records would bias the detection results. Although lots of works have been conducted on duplicate record detection, very few of them have been devoted to dataset about adverse drug reactions, and none of them have considered the existence of follow-up reports. Thus contemporary methods tailored to detecting duplicate ADR report are inept to discriminate real duplicate from follow-up linkage. In this study, we investigated the problem of identifying duplicate ADR reports in SRSs with the presence of follow-ups. We propose an ensemble and co-training based detection method that is capable of detecting for a given report not only its duplicates but also its initial or earlier linkage cases.

利用合作訓練與集成學習法檢測藥物不良反應事件通報系統中之重複記錄 = Co-Training and Ensemble Learning for Duplicate Detection in Adverse Drug Event Reporting Systems
羅, 喬楓

利用合作訓練與集成學習法檢測藥物不良反應事件通報系統中之重複記錄 = Co-Training and Ensemble Learning for Duplicate Detection in Adverse Drug Event Reporting Systems / 羅喬楓撰 - [高雄市] : 撰者, 2013[民102]. - 59面 ; 圖，表 ; 30公分.
參考書目：面44-49103年12月16日公開內容為英文.
藥物不良反應事件Adverse drug events

利用合作訓練與集成學習法檢測藥物不良反應事件通報系統中之重複記錄 = Co-Training and Ensemble Learning for Duplicate Detection in Adverse Drug Event Reporting Systems
LDR:04001nam0a2200301 450 001 389690
005 20170214092848.0
009 389690
010 0 $b 精裝
010 0 $b 平裝
100 $a 20170214d2013 k y0chiy05 b
101 1 $a eng $d chi $d eng
102 $a tw
105 $a ak am 000yy
200 1 $a 利用合作訓練與集成學習法檢測藥物不良反應事件通報系統中之重複記錄 $d Co-Training and Ensemble Learning for Duplicate Detection in Adverse Drug Event Reporting Systems $z eng $f 羅喬楓撰
210 $a [高雄市] $c 撰者 $d 2013[民102]
215 0 $a 59面 $c 圖，表 $d 30公分
300 $a 參考書目：面44-49
300 $a 103年12月16日公開
300 $a 內容為英文
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 藥物不良反應檢測在對於大眾健康以及製藥的發展，是個非常重要的議題。由於藥物被批准上市場前的臨床樣本數不足以確定潛在的藥物不良反應，許多國家都建立各種自發性通報系統（SRSs），以便監控上市後的藥品並收集數據用於檢測未知的藥物不良反應。由於自發性通報系統的數據來自於不同的呈報來源，就導致重複通報的問題。不幸的是，就算只有少量的重複報告，也會造成藥物不良反應檢測的偏差。雖然已有很多重複值檢測的文獻，但是很少有針對藥物不良反應的資料集做重複值檢測，而且這些研究皆未考慮資料中存在的後續追蹤報告。因此目前藥物不良反應報告中重複值偵測的方法皆無法區分一份報告是屬於重複的紀錄或是後續追蹤的連結。在本研究中，我們探討在藥物不良反應報告中存在後續追蹤紀錄的情形下，如何進行重複記錄偵測的問題，並提出一種基於合作訓練與集成學習的檢測方法。此種方法能檢測出一份報告是否為重複的報告或是初始報告的後續追蹤紀錄。 Adverse drug reactions detection is a very important topic in the public health as well as the development of modern pharmaceutical industry. Since the number of samples in clinical trials is not enough to identify potential adverse drug reactions before the drugs are approved for marketing, many countries have established various spontaneous reporting systems (SRSs) to facilitate postmarketing surveillance of listed drugs and collect enough data for detecting unknown adverse drug reactions. Unfortunately, due to data in SRSs coming from different sources of reporters, there heralds the problem of duplicate reporting; even a small amount of duplicate records would bias the detection results. Although lots of works have been conducted on duplicate record detection, very few of them have been devoted to dataset about adverse drug reactions, and none of them have considered the existence of follow-up reports. Thus contemporary methods tailored to detecting duplicate ADR report are inept to discriminate real duplicate from follow-up linkage. In this study, we investigated the problem of identifying duplicate ADR reports in SRSs with the presence of follow-ups. We propose an ensemble and co-training based detection method that is capable of detecting for a given report not only its duplicates but also its initial or earlier linkage cases.
510 1 $a Co-Training and Ensemble Learning for Duplicate Detection in Adverse Drug Event Reporting Systems $z eng
610 0 $a 藥物不良反應事件 $a 重複紀錄檢測 $a 集成學習法 $a 合作訓練學習法 $a 藥物事件通報系統 $a 後續追蹤 $a 自發性通報系統
610 1 $a Adverse drug events $a duplicate records detection $a ensemble learning $a co-training learning $a drug event reporting system $a follow-up $a spontaneous reporting systems
681 $a 008M/0019 $b 464103 6024 $v 2007年版
700 1 $a 羅 $b 喬楓 $4 撰 $3 614550
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 NUK $c 20141204 $g CCR
856 7 $z 電子資源 $2 http $u http://handle.ncl.edu.tw/11296/ndltd/16706898753512263382