Spontaneous reporting system(SRS) is an important way to monitor the adverse drug reaction(ADR) and discover the ADR signal for marketed drugs. It can detect adverse reaction signals timely and effectively, and preven...Spontaneous reporting system(SRS) is an important way to monitor the adverse drug reaction(ADR) and discover the ADR signal for marketed drugs. It can detect adverse reaction signals timely and effectively, and prevent the occurrence of drug damage. Runzao Zhiyang Capsule is mainly composed of Radix Polygoni Multiflor, Radix Polygoni Multiflori Preparata, Radix Rehmanniae Recens, Radix Sophorae Flavescentis, Folium Mori and Urtica dentata Hand.-Mazz. It has the functions of nourishing blood, nourishing yin, expelling wind to relieve itching and moistening the intestines to relieve constipation. It is mainly used for skin itching, acne, constipation and other diseases caused by blood deficiency and wind dryness. The large, national SRS database of ADRs needs effective evaluation methods. We reported on the use of Bayesian confidence propagation neural network method(BCPNN) and reporting rate ratio method(PRR) with propensity score to control confounding variables. The tendency score method was used to control the hybrid bias produced by SRS data analysis. After the calculation of PRR and BCPNN, the score of "diarrhea", "rash" and "gastric dysfunction" showed that there was an early warning before and after matching. To sum up, it indicated that diarrhea, rash and gastric dysfunction were early warning signs.展开更多
目的:构建药品不良反应/事件主动监测系统,为临床提供用药安全信息,及时发现并快速上报药品不良反应(adverse drug reaction,ADR)/事件(adverse drug event,ADE),实现基于该系统的ADR/ADE真实世界研究条件。方法:联合"触发器原理&q...目的:构建药品不良反应/事件主动监测系统,为临床提供用药安全信息,及时发现并快速上报药品不良反应(adverse drug reaction,ADR)/事件(adverse drug event,ADE),实现基于该系统的ADR/ADE真实世界研究条件。方法:联合"触发器原理"与"贝叶斯置信传播神经网络法"挖掘医院信息系统的ADR/ADE信号,由药师负责建立规则、布局功能模块以及对效果进行评估验证,由软件工程师负责编写计算机程序实现。结果:建立了较全面的监测规则,实现了实时预警与回顾性研究数据快速提取,完成了ADR/ADE主动监测平台的搭建。结论:ADR/ADE实时预警有利于及时处置,减少药品危害,并提高上报效能,快速筛选数据的功能为上市后药品安全性再评价提供便利,对建立药品安全性监测与评价信息技术平台有重要意义。展开更多
Adverse Drug Reaction(ADR) is one of the major challenges to the evaluation of drug safety in the medical field. The Bayesian Confidence Propagation Neural Network(BCPNN) algorithm is the main algorithm used by the Wo...Adverse Drug Reaction(ADR) is one of the major challenges to the evaluation of drug safety in the medical field. The Bayesian Confidence Propagation Neural Network(BCPNN) algorithm is the main algorithm used by the World Health Organization to monitor ADRs. Currently, ADR reports are collected through the spontaneous reporting system. However, with the continuous increase in ADR reports and possible use scenarios, the efficiency of the stand-alone ADR detection algorithm will encounter considerable challenges. Meanwhile, the BCPNN algorithm requires a certain number of disk I/O, which leads to considerable time consumption. In this study,we propose a Spark-based parallel BCPNN algorithm, which speeds up data processing and reduces the number of disk I/O in BCPNN, and two optimization strategies. Then, the ADR data collected from the FDA Adverse Event Reporting System are used to verify the performance of the proposed algorithm and its optimization strategies.Experiments show that the parallel BCPNN can significantly accelerate data processing and the optimized algorithm has a high acceleration rate and can effectively prevent memory overflow. Finally, we apply the proposed algorithm to a dataset provided by a real medical consortium. Experiments further prove the performance and practical value of the proposed algorithm.展开更多
基金funded by National Science and Technology Major Project of New Important Drug Creation (2015ZX09501004-001-002)The National Natural Science Foundation of China (81473798):Study on allergic reaction mechanism of Chinese medicine injections with active monitoring and network target monitoring+1 种基金Project of "One Belt, One Road" for Traditional Chinese Medicine of China Academy of Chinese Medical Sciences (GH2017-04)Construction of China-US Major Disease Clinical Research Center (GH2017-04-01)
文摘Spontaneous reporting system(SRS) is an important way to monitor the adverse drug reaction(ADR) and discover the ADR signal for marketed drugs. It can detect adverse reaction signals timely and effectively, and prevent the occurrence of drug damage. Runzao Zhiyang Capsule is mainly composed of Radix Polygoni Multiflor, Radix Polygoni Multiflori Preparata, Radix Rehmanniae Recens, Radix Sophorae Flavescentis, Folium Mori and Urtica dentata Hand.-Mazz. It has the functions of nourishing blood, nourishing yin, expelling wind to relieve itching and moistening the intestines to relieve constipation. It is mainly used for skin itching, acne, constipation and other diseases caused by blood deficiency and wind dryness. The large, national SRS database of ADRs needs effective evaluation methods. We reported on the use of Bayesian confidence propagation neural network method(BCPNN) and reporting rate ratio method(PRR) with propensity score to control confounding variables. The tendency score method was used to control the hybrid bias produced by SRS data analysis. After the calculation of PRR and BCPNN, the score of "diarrhea", "rash" and "gastric dysfunction" showed that there was an early warning before and after matching. To sum up, it indicated that diarrhea, rash and gastric dysfunction were early warning signs.
文摘目的:构建药品不良反应/事件主动监测系统,为临床提供用药安全信息,及时发现并快速上报药品不良反应(adverse drug reaction,ADR)/事件(adverse drug event,ADE),实现基于该系统的ADR/ADE真实世界研究条件。方法:联合"触发器原理"与"贝叶斯置信传播神经网络法"挖掘医院信息系统的ADR/ADE信号,由药师负责建立规则、布局功能模块以及对效果进行评估验证,由软件工程师负责编写计算机程序实现。结果:建立了较全面的监测规则,实现了实时预警与回顾性研究数据快速提取,完成了ADR/ADE主动监测平台的搭建。结论:ADR/ADE实时预警有利于及时处置,减少药品危害,并提高上报效能,快速筛选数据的功能为上市后药品安全性再评价提供便利,对建立药品安全性监测与评价信息技术平台有重要意义。
基金supported in part by the Science and Technology Innovation Action Plan Project of Science and Technology Commission of Shanghai Municipality(No.18511102703)the Scientific Research Plan Project of Science and Technology Commission of Shanghai Municipality(No.16JC1400803)
文摘Adverse Drug Reaction(ADR) is one of the major challenges to the evaluation of drug safety in the medical field. The Bayesian Confidence Propagation Neural Network(BCPNN) algorithm is the main algorithm used by the World Health Organization to monitor ADRs. Currently, ADR reports are collected through the spontaneous reporting system. However, with the continuous increase in ADR reports and possible use scenarios, the efficiency of the stand-alone ADR detection algorithm will encounter considerable challenges. Meanwhile, the BCPNN algorithm requires a certain number of disk I/O, which leads to considerable time consumption. In this study,we propose a Spark-based parallel BCPNN algorithm, which speeds up data processing and reduces the number of disk I/O in BCPNN, and two optimization strategies. Then, the ADR data collected from the FDA Adverse Event Reporting System are used to verify the performance of the proposed algorithm and its optimization strategies.Experiments show that the parallel BCPNN can significantly accelerate data processing and the optimized algorithm has a high acceleration rate and can effectively prevent memory overflow. Finally, we apply the proposed algorithm to a dataset provided by a real medical consortium. Experiments further prove the performance and practical value of the proposed algorithm.
