雙聚類算法研究及其在我國藥品不良反應(yīng)監(jiān)測中的應(yīng)用
發(fā)布時間：2018-08-15 14:56
【摘要】：研究背景和目的:作為藥品上市后安全性監(jiān)測的重要組成部分,藥品不良反應(yīng)自發(fā)呈報系統(tǒng)可以廣泛收集不良反應(yīng)報告,實現(xiàn)對藥品不良反應(yīng)的及時監(jiān)測。我國自發(fā)呈報系統(tǒng)數(shù)據(jù)庫中數(shù)據(jù)量龐大。2009年至2016年,年報告數(shù)量已從60余萬份激增到140余萬份。利用不相稱測定方法,研究者可以從自發(fā)呈報系統(tǒng)數(shù)據(jù)中檢測出大量不良反應(yīng)信號,為藥品安全性評價提供基本依據(jù)。在檢測出不良反應(yīng)信號之后,仍需要對信號進(jìn)行評價才可以確定其是否為真實的藥品不良反應(yīng),但是大量的信號給評價工作帶來十分艱巨的挑戰(zhàn)。目前不良反應(yīng)信號評價方法主要包括將檢測出的不良反應(yīng)信號與藥品說明書數(shù)據(jù)對比、進(jìn)行專家評價等,評價效率低下。如何提高信號評價工作的效率是藥品不良反應(yīng)監(jiān)測領(lǐng)域中研究者亟需解決的問題之一。有研究指出:分析包含同一種不良反應(yīng)的多個相似信號或包含同一種藥品的多個相似信號可能可以提高信號評價效率。這為提高我國信號評價過程的效率提供了新的思路。本研究期望引入一種新的方法——雙聚類分析方法,以期識別出我國不良反應(yīng)信號數(shù)據(jù)中相似信號組合。利用組合中已確認(rèn)信號的信息對待評價信號進(jìn)行快速評價,提高信號評價工作的效率,并探索在分析我國不良反應(yīng)信號數(shù)據(jù)過程中最優(yōu)參數(shù)設(shè)置。研究方法:將Bimax雙聚類算法引入到我國不良反應(yīng)信號數(shù)據(jù)分析中。將檢測出的不良反應(yīng)信號數(shù)據(jù)構(gòu)建出原始定量數(shù)據(jù)矩陣。依據(jù)不同的區(qū)分強(qiáng)弱信號的IC值閾值將定量矩陣轉(zhuǎn)化成不同的0-1數(shù)據(jù)矩陣,并結(jié)合不同的Bimax算法參數(shù),對不同的0-1數(shù)據(jù)矩陣進(jìn)行雙聚類分析,從中識別出對應(yīng)信號值均超過閾值的多個藥品-不良反應(yīng)組合,獲取相似性信號組合信息。然后,利用秩和比綜合評價法結(jié)合平均符合比例、涉及比例兩個指標(biāo)對分析雙聚類結(jié)果進(jìn)行評價,確定最優(yōu)區(qū)分強(qiáng)弱信號的IC值閾值及最優(yōu)Bimax算法參數(shù)。最后對最優(yōu)參數(shù)設(shè)置組合下雙聚類分析結(jié)果進(jìn)行深入分析,明確雙聚類算法在我國不良反應(yīng)信號數(shù)據(jù)分析中的運用效果。研究結(jié)果:通過秩和比綜合評價法比較不同參數(shù)設(shè)置組合下雙聚類方法的分析結(jié)果,確定最優(yōu)區(qū)分強(qiáng)弱信號的閾值為IC=0.80,最優(yōu)的Bimax算法參數(shù)為最小雙簇行數(shù)3、最小雙簇列數(shù)3。在上述參數(shù)設(shè)置組合下,利用Bimax雙聚類方法可以從不良反應(yīng)信號數(shù)據(jù)中識別出4293個雙簇。雙簇平均包含23.41個信號,雙簇內(nèi)組合的平均IC值為2.38。通過分類學(xué)評價可以發(fā)現(xiàn)所包含的藥品具有相似性或所包含的不良反應(yīng)具有相似性的雙簇共有1836個,占雙簇總數(shù)的42.8%,涉及72.3%的IC值不小于0.80的待評價信號;至少包含有一個已得到藥品說明書確認(rèn)信號的雙簇有4272個,占總數(shù)的99.5%;包含的所有信號均已得到藥品說明書確認(rèn)的雙簇有193個,占總數(shù)的4.5%。在所有雙簇中出現(xiàn)頻次最多的藥品為“利培酮”,共在708個雙簇中出現(xiàn),占總數(shù)的16.5%;出現(xiàn)頻次最多的不良反應(yīng)為“肝功能異常”,共在720個雙簇中出現(xiàn),占總數(shù)的16.8%。研究結(jié)論:利用雙聚類算法分析我國不良反應(yīng)信號數(shù)據(jù)所得到的雙簇可以為潛在藥品不良反應(yīng)確認(rèn)、篩選需重點關(guān)注不良反應(yīng)信號等多個方面提供十分有價值的信息,可以促進(jìn)我國藥品不良反應(yīng)監(jiān)測中信號評價工作效率的提高。
[Abstract]:BACKGROUND AND OBJECTIVE: As an important part of post-marketing safety monitoring, ADR spontaneous reporting system can collect ADR reports extensively and realize timely monitoring of ADR. The number of ADRs surged to more than 1.4 million. Researchers can detect a large number of ADR signals from the data of the spontaneous reporting system by using the method of asymmetric measurement, which provides a basic basis for drug safety evaluation. At present, the evaluation methods of ADR signal mainly include comparing the detected ADR signal with the data of drug instructions and conducting expert evaluation. The evaluation efficiency is low. How to improve the efficiency of signal evaluation is a researcher in the field of ADR monitoring. It is pointed out that the analysis of multiple similar signals containing the same adverse reaction or multiple similar signals containing the same drug may improve the efficiency of signal evaluation. Class analysis method is used to identify the similar signal combination in the ADR signal data of our country. The information of the confirmed signals in the combination is used to evaluate the evaluation signal quickly, and the efficiency of signal evaluation is improved. The algorithm is introduced into the analysis of ADR signal data in China. The original quantitative data matrix is constructed from the detected ADR signal data. The quantitative matrix is transformed into different 0-1 data matrix according to the IC value threshold of distinguishing strong and weak signals, and the different 0-1 data matrix is doubly aggregated by combining different Bimax algorithm parameters. Classification analysis identifies several drug-adverse reaction combinations whose corresponding signal values exceed the threshold, and obtains the information of similarity signal combinations. Then, the rank sum ratio comprehensive evaluation method combined with the average coincidence ratio, involving two indicators of the ratio, is used to evaluate the results of the analysis of the double clustering, and the IC value threshold and the maximum value of the optimal discrimination between strong and weak signals are determined. Finally, the application effect of bi-clustering algorithm in the analysis of ADR signal data in China is clarified. The results show that the optimal region is determined by comparing the results of bi-clustering method under different parameter combinations with rank sum ratio comprehensive evaluation method. The thresholds of the strong and weak signals are IC=0.80, and the optimal parameters of the Bimax algorithm are the minimum number of rows of two clusters and the minimum number of columns of two clusters. Analogical evaluation showed that 1836 clusters, accounting for 42.8% of the total number of clusters and involving 72.3% of IC values not less than 0.80, contained similarity of drugs or adverse reactions; at least 4272 clusters, accounting for 99.5% of the total number, contained confirmation signals from the drug specifications. All the signals were confirmed by the drug instructions in 193 clusters, accounting for 4.5% of the total. Risperidone was the most frequent drug in all the clusters, accounting for 16.5% of the total 708 clusters, and liver dysfunction was the most frequent adverse reaction, accounting for 16.8% of the total 720 clusters. CONCLUSION: Bicluster analysis of ADR signal data in China can provide valuable information for identification of potential ADR, screening of ADR signal and so on. It can improve the efficiency of signal evaluation in ADR monitoring in China.
【學(xué)位授予單位】：第二軍醫(yī)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：R95
本文編號：2184552
[Abstract]:BACKGROUND AND OBJECTIVE: As an important part of post-marketing safety monitoring, ADR spontaneous reporting system can collect ADR reports extensively and realize timely monitoring of ADR. The number of ADRs surged to more than 1.4 million. Researchers can detect a large number of ADR signals from the data of the spontaneous reporting system by using the method of asymmetric measurement, which provides a basic basis for drug safety evaluation. At present, the evaluation methods of ADR signal mainly include comparing the detected ADR signal with the data of drug instructions and conducting expert evaluation. The evaluation efficiency is low. How to improve the efficiency of signal evaluation is a researcher in the field of ADR monitoring. It is pointed out that the analysis of multiple similar signals containing the same adverse reaction or multiple similar signals containing the same drug may improve the efficiency of signal evaluation. Class analysis method is used to identify the similar signal combination in the ADR signal data of our country. The information of the confirmed signals in the combination is used to evaluate the evaluation signal quickly, and the efficiency of signal evaluation is improved. The algorithm is introduced into the analysis of ADR signal data in China. The original quantitative data matrix is constructed from the detected ADR signal data. The quantitative matrix is transformed into different 0-1 data matrix according to the IC value threshold of distinguishing strong and weak signals, and the different 0-1 data matrix is doubly aggregated by combining different Bimax algorithm parameters. Classification analysis identifies several drug-adverse reaction combinations whose corresponding signal values exceed the threshold, and obtains the information of similarity signal combinations. Then, the rank sum ratio comprehensive evaluation method combined with the average coincidence ratio, involving two indicators of the ratio, is used to evaluate the results of the analysis of the double clustering, and the IC value threshold and the maximum value of the optimal discrimination between strong and weak signals are determined. Finally, the application effect of bi-clustering algorithm in the analysis of ADR signal data in China is clarified. The results show that the optimal region is determined by comparing the results of bi-clustering method under different parameter combinations with rank sum ratio comprehensive evaluation method. The thresholds of the strong and weak signals are IC=0.80, and the optimal parameters of the Bimax algorithm are the minimum number of rows of two clusters and the minimum number of columns of two clusters. Analogical evaluation showed that 1836 clusters, accounting for 42.8% of the total number of clusters and involving 72.3% of IC values not less than 0.80, contained similarity of drugs or adverse reactions; at least 4272 clusters, accounting for 99.5% of the total number, contained confirmation signals from the drug specifications. All the signals were confirmed by the drug instructions in 193 clusters, accounting for 4.5% of the total. Risperidone was the most frequent drug in all the clusters, accounting for 16.5% of the total 708 clusters, and liver dysfunction was the most frequent adverse reaction, accounting for 16.8% of the total 720 clusters. CONCLUSION: Bicluster analysis of ADR signal data in China can provide valuable information for identification of potential ADR, screening of ADR signal and so on. It can improve the efficiency of signal evaluation in ADR monitoring in China.
【學(xué)位授予單位】：第二軍醫(yī)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：R95
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 黃維佳;;淺析“毒副作用”與“不良反應(yīng)”[J];中國科技術(shù)語;2016年05期
2 朱磊;黃萍;李穎;;我國藥品不良反應(yīng)監(jiān)測現(xiàn)狀及存在問題[J];中國藥事;2016年07期
3 雷右喜;;綜合評價研究方法綜述[J];商場現(xiàn)代化;2016年02期
4 史文濤;侯永芳;葉小飛;朱田田;張?zhí)煲?吳桂芝;賀佳;;我國藥品不良反應(yīng)自發(fā)呈報系統(tǒng)中信號強(qiáng)度分級閾值的探索[J];藥物流行病學(xué)雜志;2015年08期
5 路長飛;田月潔;;基于鹽酸克林霉素注射劑不良反應(yīng)監(jiān)測數(shù)據(jù)探索聚類分析方法在藥品不良反應(yīng)監(jiān)測中的應(yīng)用[J];中國藥物警戒;2014年01期
6 樓陸軍;劉銀生;羅潔霞;朱寒根;高云;;再論我國藥品不良反應(yīng)監(jiān)測的現(xiàn)狀與完善對策[J];中國藥業(yè);2012年18期
7 張敏;戈文航;;雙聚類的研究與進(jìn)展[J];微型機(jī)與應(yīng)用;2012年04期
8 吳嘉瑞;張冰;;試論數(shù)據(jù)挖掘決策樹方法在藥物警戒研究中的應(yīng)用[J];中國藥物警戒;2012年01期
9 王志剛;陳鑫;謝麗芳;楊嘯林;張正國;;藥物功能模式相似度及其聚類[J];中國生物醫(yī)學(xué)工程學(xué)報;2011年06期
10 馮變玲;楊世民;藍(lán)夏璐;魏芬;尤海生;;心腦血管疾病用藥不良反應(yīng)與藥品品種關(guān)系的聚類分析[J];中國藥業(yè);2011年06期
相關(guān)會議論文 前1條
1 馮變玲;楊世民;尤海生;藍(lán)夏璐;魏芬;;基于數(shù)據(jù)挖掘技術(shù)的心腦血管用藥不良反應(yīng)與藥品品種間聚類分析[A];2010年中國藥學(xué)大會暨第十屆中國藥師周論文集[C];2010年
相關(guān)博士學(xué)位論文 前1條
1 于躍;基于大數(shù)據(jù)挖掘的藥品不良反應(yīng)知識整合與利用研究[D];吉林大學(xué);2016年
相關(guān)碩士學(xué)位論文 前2條
1 汪晶;我國藥品不良反應(yīng)自發(fā)呈報系統(tǒng)信號檢測中壓縮估計參數(shù)的探索[D];第二軍醫(yī)大學(xué);2015年
2 李莉;五種雙聚類算法在基因表達(dá)譜數(shù)據(jù)中的比較與評價[D];西北農(nóng)林科技大學(xué);2012年
，本文編號：2184552
本文鏈接：http://sikaile.net/yixuelunwen/yiyaoxuelunwen/2184552.html
最近更新
教材專著
