Discovery and identification strategy for drug safety risks based on big data monitoring of adverse reactions

doi:10.19803/j.1672-8629.20230772

Abstract

Abstract: Objective To explore how to quickly discover and accurately identify drug safety risks from a vast number of adverse reaction reports from domestic and foreign Chinese and Western medicines. The aim is also to make scientific and effective predictions and control measures for these risks. Methods Drug-induced liver injury data was taken as an example, and the process of discovering, evaluating, confirming, and controlling risks associated with drugs were discussed. Results A preliminary exploration was conducted, leading to the establishment of an integrated strategy and method system for “large-scale adverse reaction monitoring and discovery - multi-model recognition and analysis- disease-symptom-toxicology verification.” This system has been successfully applied in identifying and analyzing drug-induced liver injury. Conclusion This strategy offers a fresh perspective for the continuous development and innovation of drug safety evaluation. It also provides technical support for ensuring public safety in medication and promoting the healthy development of the Chinese and Western medicine industry.

Key words: drug adverse reactions, monitoring, big data, risk discovery, data analysis, machine learning

CLC Number:

R954
R994.11

GAO Yunjuan, ZHAO Xu, BAI Tiankai, BAI Zhaofang, WANG Jiabo, SONG Haibo, XIAO Xiaohe. Discovery and identification strategy for drug safety risks based on big data monitoring of adverse reactions[J]. Chinese Journal of Pharmacovigilance, 2024, 21(1): 1-5.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.zgywjj.com/EN/10.19803/j.1672-8629.20230772

https://www.zgywjj.com/EN/Y2024/V21/I1/1

References

[1] TATONETTI NP, FERNALD GH, ALTMAN RB.A novel signal detection algorithm for identifying hidden drug-drug interactions in adverse event reports[J]. J Am Med Inform Assoc, 2012, 19(1): 79-85.
[2] LIU JJ, ZHENG CR, HONG YS.How machine learning empowers management research?-a comprehensive review of domestic and foreign frontiers and future prospects[J]. Journal of Management World(管理世界), 2023, 39(9): 191-216.
[3] HOOFNAGLE JH, BJÖRNSSON ES. Drug-induced liver injury-types and phenotypes[J]. New England Journal of Medicine, 2019, 381(3): 264-273.
[4] FONTANA RJ, LIOU I, REUBEN A, et al.AASLD practice guidance on drug, herbal, and dietary supplement-induced liver injury[J]. Hepatology, 2023, 77(3): 1036-1065.
[5] GAO YJ, ZHAO X, BAI ZF, et al.Prevention and control of safety risks of traditional Chinese medicine based on indirect knowledge of toxicity[J]. Chinese Journal of Pharmacovigilance(中国药物警戒), 2021, 18(11): 1004-1008.
[6] ALOMAR M, TAWFIQ AM, HASSAN N, et al.Post marketing surveillance of suspected adverse drug reactions through spontaneous reporting: current status, challenges and the future[J]. Ther Adv Drug Saf, 2020, 11: 2042098620938595.
[7] TAU N, SHOCHAT T, GAFTER-GVILI A, et al.Association between data sources and US food and drug administration drug safety communications[J]. JAMA Intern Med, 2019, 179(11): 1590-1592.
[8] NMPA. National Adverse Drug Reaction Monitoring Annual Report(2022)[EB/OL].(2021-03-26)[2023-09-01]. https://www.nmpa.gov.cn/xxgk/fgwj/gzwj/gzwjyp/20210325170127199.html.
[9] GE W.Database construction and signal detection of antibacterial adverse drug reactions based on MedDRA[D]. Xi’an: Air Force Medical University, 2022.
[10] CHEN JJ, HUO XC, WANG SX, et al.Data mining for adverse drug reaction signals of daptomycin based on real-world data: a disproportionality analysis of the US Food and Drug Administration adverse event reporting system[J]. Int J Clin Pharm, 2022, 44(6): 1351-1360.
[11] WANG FD, WANG J, CHEN L.Data-mining and analysis of adverse event signals of neurokinin-1 receptor antagonists based on FAERS database[J]. Central South Pharmacy, 2023, 21(12): 3337-3344.
[12] XIA XD, LIU PC, ZHOU M, et al. Comparative study on signal detection methods based on real world data of adverse drug reactions in H province[J]. China Food & Drug Administration Magazine(中国食品药品监管), 2023(10): 42-55.
[13] REN JT, WANG SF, HOU YF, et al.Common signal detection methods of adverse drug reaction[J]. Chinese Journal of Pharmacovigilance(中国药物警戒), 2011, 8(5): 294-298.
[14] CHEN YS, MIAO J, LIANG YM, et al.Research progress on signal detection methods for adverse drug reactions of commonly used medications[J]. Chinese Journal of Drug Dependence(中国药物依赖性杂志), 2014, 23(2): 89-92.
[15] RODRIGUES PP, FERREIRA-SANTOS D, SILVA A, et al.Causality assessment of adverse drug reaction reports using an expert-defined Bayesian network[J]. Artif Intell Med, 2018, 91: 12-22.
[16] GEORGE N, CHEN M, YUEN N, et al.Interplay of gender, age and drug properties on reporting frequency of drug-induced liver injury[J]. Regul Toxicol Pharmacol, 2018, 94: 101-107.
[17] CHEN W, YANG J, WANG HL, et al. Discovering associations of adverse events with pharmacotherapy in patients with non-small cell lung cancer using modified apriori algorithm[J/OL]. Biomed Res Int,(2018-04-23)[2023-12-12]. https://www.hindawi.com/journals/bmri/2018/1245616/.
[18] HARPAZ R, CHASE HS, FRIEDMAN C.Mining multi-item drug adverse effect associations in spontaneous reporting systems[J]. BMC Bioinformatics, 2010, 11(Suppl 9): 7.
[19] WANG T, ZHENG MJ, LIU HL, et al.Exploration and inspiration on the application of artificial intelligence in Pharmacovigilance in the USA[J]. Chinese Journal of Pharmacovigilance(中国药物警戒), 2023, 20(10): 1129-1133.
[20] BAJŽELJ B, DRGAN V. Hepatotoxicity modeling using counter-propagation artificial neural networks: handling an imbalanced classification problem[J]. Molecules, 2020, 25(3): 25030481.
[21] HOANG T, LIU J, ROUGHEAD E, et al.Supervised signal detection for adverse drug reactions in medication dispensing data[J]. Comput Methods Programs Biomed, 2018, 161: 25-38.
[22] MCMASTER C, LIEW D, KEITH C, et al.A machine-learning algorithm to optimise automated adverse drug reaction detection from clinical coding[J]. Drug Saf, 2019, 42(6): 721-725.
[23] JEONG E, PARK N, CHOI Y, et al.Machine learning model combining features from algorithms with different analytical methodologies to detect laboratory-event-related adverse drug reaction signals[J]. PLoS One, 2018, 13(11): e0207749.
[24] GAO YJ.Methods and strategies study of discovering liver injury risk signals based on ADR monitoring big data[D].Chengdu: Chengdu University of Traditional Chinese Medicine(成都中医药大学), 2023.
[25] ARNAUD M, BÉGAUD B, THURIN N, et al. Methods for safety signal detection in healthcare databases: a literature review[J]. Expert Opin Drug Saf, 2017, 16(6): 721-32.
[26] ZHOU YL.Data mining study on risk signal of triazole antifungal[D]. Chengdu: University of Electronic Science and Technology of China(电子科技大学), 2020.
[27] ZHAO Y, YU Y, WANG H, et al.Machine learning in causal inference: application in pharmacovigilance[J]. Drug Safety, 2022, 45(5): 459-476.
[28] WANG W, QI YF, BAO H, et al.Establishment of the clinical evaluation system of precision pharmacy based on medical big data[J]. Chinese Pharmaceutical Affairs(中国药事), 2017, 31(12): 1478-1482.
[29] ZHENG C, XU R.Large-scale mining disease comorbidity relationships from post-market drug adverse events surveillance data[J]. BMC Bioinformatics, 2018, 19(Suppl 17): 500.
[30] SHIN HK, CHUN HS, LEE S, et al.ToxSTAR: drug-induced liver injury prediction tool for the web environ ment[J]. Bioinformatics, 2022, 38(18): 4426-4427.
[31] CHEN M, BORLAK J, TONG W.High lipophilicity and high daily dose of oral medications are associated with significant risk for drug-induced liver injury[J]. Hepatology, 2013, 58(1): 388-396.
[32] CHEN M, BORLAK J, TONG W.A model to predict severity of drug-induced liver injury in humans[J]. Hepatology, 2016, 64(3): 931-940.
[33] XIAO XH, ZHAO X, BAI ZF, et al.New outlook on safety of traditional Chinese medicine: concept and practice[J]. China Journal of Chinese Materia Medica(中国中药杂志), 2023, 48(10): 2557-2564.
[34] WANG JB, CUI HR, BAI ZF, et al.Precision medicine-oriented safety assessment strategy for traditional Chinese medicines: disease-syndrome-based toxicology[J]. Acta Pharmaceutica Sinica(药学学报), 2016, 51(11): 1681-1688.
[35] PANG JY, BAI ZF, NIU M, et al.The toxic and protective effects of Polygonum multiflorum on normal and liver injured rats based on the symptom-based prescription theory[J]. Acta Pharmaceutica Sinica(药学学报), 2015, 50(8): 973-979.
[36] XIAO XH, BAI ZF, WANG JB, et al.Traditional Chinese medicine(TCM) safety evaluation and pharmacovigilance[J]. Chinese Science Bulletin(科学通报), 2021, 66(Z1): 407-414.
[37] BAI ZF, GAO Y, WANG JB, et al.Evaluation and risk control of idiosyncratic liver injury caused by traditional Chinese medicine[J]. Progress in Pharmaceutical Sciences(药学进展), 2020, 44(10): 724-729.