Detection of report signals of adverse drug reactions by fuzzy BCPNN

doi:10.19803/j.1672-8629.20210189

Abstract

Abstract: Objective To fully tap the reports of adverse drug reactions and detect adverse drug reaction signals so as to provide reference for signal verification and clinical medications. Methods The fuzzy number was introduced to quantify the fuzzy semantic information in reports of adverse reactions. The fuzzy Bayesian confidence propagation neural network (FBCPNN) method was established to be compared with the Bayesian confidence propagation neural network(BCPNN) method in order to analyze the consistency. Finally, the results of signal detection of compound osteopeptide were analyzed. Results 11 454 signals of ADR reports provided by Jiangsu ADR Monitoring Center were detected using the FBCPNN method between January 1, 2014 and December 31, 2019, including 534 new signals (not in the manual). 10 915 signals were detected using the BCPNN method, including 545 new signals. Compared with the BCPNN method algorithm, the sensitivity, specificity and Youden index of this algorithm were 0.910 3, 0.976 6 and 0.886 9 respectively. Conclusion The FBCPNN method based on uncertain information can make full use of the uncertain information of adverse reaction reports and bring about effective detection of adverse reactions.

Key words: adverse drug reaction, signal detection, fuzzy number, linguistic variable, BCPNN

CLC Number:

R911

LIU Jing, YE Guoju, WANG Qiming, LIU Wei, ZHAO Dafang, SUN Jun, LI Guoliang, WANG Xinmin, LI Ming. Detection of report signals of adverse drug reactions by fuzzy BCPNN[J]. Chinese Journal of Pharmacovigilance, 2022, 19(10): 1113-1117.

References

[1] ZHANG N, GONG L, WANG L, et al.Detection and evaluation of adverse drug reaction signals of chloroquine and hydroxychloroquine based on FDA adverse event database and designated medical event[J]. Chinese Journal of Hospital Pharmacy(中国医院药学杂志), 2020, 40(18): 1921-1928.
[2] LI SS, D YX, YIN AQ, et al. Mining and evaluation of adverse reaction signals of levofloxacin based on spontaneous reporting system in Yantai City[J]. Chinese Journal of New Drugs(中国新药杂志), 2020, 29(2): 228-231.
[3] WANG LX, XIE YM, CHENG WX, et al.Analysis of adverse reactions risk signal of Xinyuan Capsules based on national ADR monitoring spontaneous reporting system[J]. China Journal of Chinese Materia Medica(中国中药杂志), 2020, 45(10), 2310-2315.
[4] TIAN YL, BIAN GZ, CAO P, et al.Detection and evaluation of dasatinib-induced respiratory system ADR signals in post-marketing experience[J]. Chinese Journal of New Drugs(中国新药杂志), 2018, 27(2): 236-241.
[5] China Food and Drug Administration, Department of Drug Safety Supervision. National Center for ADR Monitoring, China. Handbook of Adverse Drug Reaction Reporting and Monitoring in China[G]. 2012.
[6] ZHANG L, WONG LYL, HE Y, et al.Pharmacovigilance in China: current situation, successes and challenges[J]. Drug Safety, 2014, 37(10): 765-770.
[7] BATE A, LINDQUIST M, EDWARDS IR, et al.A bayesian neural network method for adverse drug reaction signal generation[J]. European Journal of Clinical Pharmacology, 1998, 54(4): 315-321.
[8] SUN L, SUN S, WANG TL, et al.Parallel ADR detection based on spark and BCPNN[J]. Tsinghua Science and Technology, 2019, 24(2): 195-206.
[9] ZADEH LA.Fuzzy sets[J]. Information and Control, 1965, 8(3): 338-353.
[10] WANG GX.Theory and Applications of Fuzzy Numbers(模糊数理论及应用)[M]. Beijing: National Defense Industry Press, 2011.
[11] WANG GX, SHI P, WANG BP, et al.Fuzzy n-ellipsoid numbers and representations of uncertain multichannel digital information[J]. IEEE Trans Fuzzy Syst, 2014, 22(5): 1113-1126.
[12] XIE YJ.Research progress in adverse drug reaction signal detection methods[J]. Journal of Frontiers of Medicine, 2012, 2(30): 7-8.
[13] ZADEH LA.The Concept of a Linguistic Variable and its Application to Approximate Reasoning(模糊集合、语言变量及模糊逻辑)[M]. Beijing: China Science Publishing, 1984.
[14] LI LJ, HU JH, WANG Z, et al.Establishment of a new standard for evaluation of grade of adverse drug reaction severity and application of adverse drug reaction severity index[J]. Pharmaceutical Care and Research(药学服务与研究), 2008, 8(1): 9-13.
[15] WEI JX, SUN YH, ZHU YX, et al.A method for signal detection of adverse drug reactions based on mutual information[J]. Journal of Nanjing University: Natural Science(南京大学学报:自然科学版), 2010, 46(6): 705-712.
[16] National Medical Products Administration. Announcement of National Medical Products Administration on Amending the Instructions for Compound Osteopeptide Injection[EB/OL]. (2019-11-19)[2021-02-23]. https://www.nmpa.gov.cn/xxgk/ggtg/ypshmshxdgg/20191119131701629.html.
[17] CHEN WG, LI CJ, JIANG J, et al.Research of signal detection and automatic warning technology for adverse drug reaction based on BCPNN method[J]. Application Research of Computers(计算机应用研究), 2009, 26(4): 1394-1397.