PMID- 23331232 OWN - NLM STAT- MEDLINE DCOM- 20131025 LR - 20130121 IS - 1520-5711 (Electronic) IS - 1054-3406 (Linking) VI - 23 IP - 1 DP - 2013 TI - A Bayesian group sequential approach to safety signal detection. PG - 213-30 LID - 10.1080/10543406.2013.736813 [doi] AB - Clinical safety data, usually reported as clinically manifested adverse events (AEs) according to the Medical Dictionary for Regulatory Activities (MedDRA), are routinely collected during the course of a clinical trial involving comparative groups, and periodical monitoring of the safety events is often required to determine whether excessive occurrence of a set of AEs is associated with treatment. To accommodate the structure of reported AEs with the MedDRA system, a Bayesian hierarchical model has been proposed for the analysis of clinical safety data. However, the characteristics of sequential use of the Bayesian method has not been studied. In this paper the Bayesian hierarchical model is applied in a group sequential manner for multiple interim analyses of safety events. A decision-theoretic approach is employed to determine threshold values in the safety signaling process. The proposed approach is illustrated through simulations and a real example. FAU - Chen, Wenfeng AU - Chen W AD - Department of Biostatistics, School of Public Health, Fudan University, Shanghai, China. FAU - Zhao, Naiqing AU - Zhao N FAU - Qin, Guoyou AU - Qin G FAU - Chen, Jie AU - Chen J LA - eng PT - Journal Article PL - England TA - J Biopharm Stat JT - Journal of biopharmaceutical statistics JID - 9200436 RN - 0 (Measles-Mumps-Rubella Vaccine) SB - IM MH - *Adverse Drug Reaction Reporting Systems/standards MH - Bayes Theorem MH - Humans MH - Measles-Mumps-Rubella Vaccine/adverse effects MH - Randomized Controlled Trials as Topic/adverse effects/methods MH - *Research Design/standards MH - *Signal Detection, Psychological EDAT- 2013/01/22 06:00 MHDA- 2013/10/26 06:00 CRDT- 2013/01/22 06:00 PHST- 2013/01/22 06:00 [entrez] PHST- 2013/01/22 06:00 [pubmed] PHST- 2013/10/26 06:00 [medline] AID - 10.1080/10543406.2013.736813 [doi] PST - ppublish SO - J Biopharm Stat. 2013;23(1):213-30. doi: 10.1080/10543406.2013.736813.