Using data mining to predict safety actions from FDA adverse event reporting system data

被引:31
作者
Hochberg, Alan M. [1 ]
Reisinger, Stephanie J. [1 ]
Pearson, Ronald K. [1 ]
O'Hara, Donald J. [1 ]
Hall, Kevin [1 ]
机构
[1] ProSanos Corp, Res Dev, Harrisburg, PA 17101 USA
来源
DRUG INFORMATION JOURNAL | 2007年 / 41卷 / 05期
关键词
pharmacovigilance; data mining; drug safety; adverse event reporting system; Algorithms;
D O I
10.1177/009286150704100510
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
Purpose: To determine the value of data mining in early identification of drug safety signals from spontaneous reporting databases. Methods: A single data mining algorithm was applied to the 2001-2003 public release of Food and Drug Administration Adverse Event Reporting System (AERS) data for all therapeutic new molecular entities (NMEs) approved in 2001. The list of detected signals was compared with the list of safety-related regulatory actions for those drugs through February 2006. Results: For the 21 NMEs, 73 signals of interest were detected by data mining. In 39 cases, that signal preceded regulatory action. The median time from approval to signal detection was 11.5 months, and the median time from signal detection to action was 21 months. There were 33 actions for which no signal was detected and 34 signals with no corresponding regulatory action. Conclusion: Using AERS data 2-3 years following approval, more than half of FDA actions that occurred in the next 2-4 years were predicted by data mining, and more than half of the signals detected by data mining corresponded to an FDA action. An appropriate data mining procedure can yield meaningful safety information, Often well in advance of regulatory action.
引用
收藏
页码:633 / 643
页数:11
相关论文
共 16 条
  • [1] [Anonymous], 1993, Resampling-based multiple testing: Examples and methods for P-value adjustment
  • [2] Comparing data mining methods on the VAERS database
    Banks, D
    Woo, EJ
    Burwen, DR
    Perucci, P
    Braun, MM
    Ball, R
    [J]. PHARMACOEPIDEMIOLOGY AND DRUG SAFETY, 2005, 14 (09) : 601 - 609
  • [3] DuMouchel W., PROCEEDING C KNOWLED, P67
  • [4] Use of proportional reporting ratios (PRRs) for signal generation from spontaneous adverse drug reaction reports
    Evans, SJW
    Waller, PC
    Davis, S
    [J]. PHARMACOEPIDEMIOLOGY AND DRUG SAFETY, 2001, 10 (06) : 483 - 486
  • [5] *FOOD DRUG ADM, 2002, CDER REP NAT 2001
  • [6] Glover Janis, 2002, Medical Reference Services Quarterly, V21, P57, DOI 10.1300/J115v21n04_07
  • [7] Practical pharmacovigilance analysis strategies
    Gould, AL
    [J]. PHARMACOEPIDEMIOLOGY AND DRUG SAFETY, 2003, 12 (07) : 559 - 574
  • [8] Risk of acute myocardial infarction and sudden cardiac death in patients treated with cyclo-oxygenase 2 selective and non-selective non-steroidal anti-inflammatory drugs: nested case-control study
    Graham, DJ
    Campen, D
    Hui, R
    Spence, M
    Cheetham, C
    Levy, G
    Shoor, S
    Graham, D
    [J]. LANCET, 2005, 365 (9458) : 475 - 481
  • [9] Airway anastomosis complications in De Novo lung transplantation with sirolimus-based immunosuppression
    Groetzner, J
    Kur, F
    Spelsberg, F
    Behr, J
    Frey, L
    Bittmann, I
    Vogeser, M
    Ueberfuhr, P
    Meiser, B
    Hatz, R
    Reichart, B
    [J]. JOURNAL OF HEART AND LUNG TRANSPLANTATION, 2004, 23 (05) : 632 - 638
  • [10] Replication of the weber effect using postmarketing adverse event reports voluntarily submitted to the United States food and drug administration
    Hartnell, NR
    Wilson, JP
    [J]. PHARMACOTHERAPY, 2004, 24 (06): : 743 - 749