基于FAERS数据库两性霉素B脱氧胆酸盐与脂质体不良事件信号挖掘研究

Adverse drug events signal mining of amphotericin B deoxycholate and amphotericin B liposome based on FAERS database

目的 利用美国食品药品监督管理局不良事件报告系统(FAERS)数据库分析两性霉素B脱氧胆酸盐(AmB-D)与两性霉素B脂质体(L-Am B)的风险信号,为临床合理用药提供参考。方法 基于FAERS数据库提取AmB-D和L-AmB2004年第1季度—2023年第4季度的不良事件报告,并导入SAS 9.4软件中进行数据清理与分析,采用报告比值比法(ROR)、比例报告比值法(PRR)、英国药品和健康产品管理局综合标准(MHRA)及贝叶斯可信区间递进神经网络法(BCPNN)进行不良事件信号挖掘。结果 分别检索到AmB-D与L-AmB的药品不良事件报告1 308、4 304份。Am B-D与L-AmB发生频次最多的不良反应均为低钾血症和急性肾损伤。Am B-D与L-Am B肾脏及泌尿系统疾病不良事件报告比例接近,提示临床可能低估了脂质体的肾毒性。并挖掘到AmB-D较强的可疑不良事件信号为免疫重建炎性综合征、白质病变;L-AmB的可疑信号为中毒性表皮坏死松解症、免疫重建炎性综合征、β2微球蛋白升高、脾损害和血管内溶血,说明书中未注明,应予以重视。结论 Am B-D与L-AmB可疑不良事件信号的挖掘,大多数与说明书记录的一致,但仍发现新的信号,需积极监测。

Objective To explore the risk signals of amphotericin B deoxycholate(AmB-D)and amphotericin B liposome(L-AmB)by using FAERS database,to provide reference for clinical rational drug use.Methods Adverse event reports of AmB-D and L-AmB from the first quarter of 2004 to the fourth quarter of 2023 were extracted based on FAERS database and imported into SAS 9.4 software for data cleaning and analysis.The adverse event signal mining was performed by ROR,PRR,MHRA,and BCPNN.Results Adverse drug event reports of AmB-D and L-AmB were 1308 and 4304,respectively.The most frequent adverse drug event of the two drugs were hypokalemia and acute kidney injury.It was found that the proportion of adverse event reports for renal and urinary diseases was similar between AmB-D and L-AmB,suggesting that the nephrotoxicity of liposomes may be underestimated in clinical practice.The suspected adverse event signal of AmB-D was found to be immune reconstructive inflammatory syndrome and white matter disease.The suspicious signals of L-AmB are toxic epidermal necrolysis,immune reconstitution inflammatory syndrome,elevatedβ2 microglobulin,spleen damage and intravascular hemolysis,which are not indicated in the instructions and should be paid attention to.Conclusion The mining of AmB-D and L-AmB suspected adverse event signals was mostly consistent with those recorded in the manual,but new signals were still found,which required active monitoring.