Combination of zero-inflated model and Dirichlet process in detection of adverse reaction signals during post-marketing surveillance

doi:10.19803/j.1672-8629.20230109

Abstract

Abstract: Objective To explore the possibility of the zero-inflated model being combined with Dirichlet process in optimizing the results of post-marketing safety signal detection of drugs. Methods By retrieving related literature, the principles of the zero-inflated model and Dirichlet process were reviewed. The current research on and strengths of the two methods were summarized. Thus, the combination of these two methods to extend technologies of signal detection was proposed. Results The zero-inflated model could minimize “excess zeros” and reduce the bias of signal detection results, while Dirichlet process could curb the false positive rate by enriching the selection of prior distribution of reporting rates of drug-adverse event pairs. Conclusion It is possible to combining the zero-inflated model with Dirichlet process to extend methods of Bayesian signal detection, and this approach deserves more study.

Key words: zero-inflated model, Dirichlet process, post-marketing surveillance, signal detection, adverse drug reaction

CLC Number:

R911
R994

CHEN Chenxin, ZHANG Pengpeng, LIU Yongmei, YE Xiaofei, HE Jia. Combination of zero-inflated model and Dirichlet process in detection of adverse reaction signals during post-marketing surveillance[J]. Chinese Journal of Pharmacovigilance, 2023, 20(6): 651-654.

References

[1] JEETU G, ANUSHA G.Pharmacovigilance: a worldwide master key for drug safety monitoring[J]. J Young Pharm, 2010, 2(3): 315-320.
[2] BLACK N.Why we need observational studies to evaluate the effectiveness of health care[J]. BMJ, 1996, 312(7040): 1215-1218.
[3] PAPANIKOLAOU PN, CHRISTIDI GD, IOANNIDIS JP.Comparison of evidence on harms of medical interventions in randomized and nonrandomized studies[J]. CMAJ, 2006, 174(5): 635-641.
[4] ZARIN DA, YOUNG JL, WEST JC.Challenges to evidence-based medicine: a comparison of patients and treatments in randomized controlled trials with patients and treatments in a practice research network[J]. Soc Psychiatry Psychiatr Epidemiol, 2005, 40(1): 27-35.
[5] DHODAPKAR MM, ROSS JS, RAMACHANDRAN R.Spontaneous reporting of post-market safety signals: what evidence should support regulatory action?[J]. BMJ, 2022, 379: 2409.
[6] MARCHENKO O, RUSSEK-COHEN E, LEVENSON M, et al.Sources of safety data and statistical strategies for design and analysis: real world insights[J]. Ther Innov Regul Sci, 2018, 52(2): 170-186.
[7] NOGUCHI Y, TACHI T, TERAMACHI H. Detection algorithms and attentive points of safety signal using spontaneous reporting systems as a clinical data source[J]. Brief Bioinform, 2021, 22(6): bbab347
[8] HEO SJ, JUNG I.Extended multi-item gamma poisson shrinker methods based on the zero-inflated Poisson model for postmarket drug safety surveillance[J]. Stat Med, 2020, 39(30): 4636-4650.
[9] VAN PUIJENBROEK EP, BATE A, LEUFKENS HG, et al.A comparison of measures of disproportionality for signal detection in spontaneous reporting systems for adverse drug reactions[J]. Pharmacoepidemiol Drug Saf, 2002, 11(1): 3-10.
[10] ROUX E, THIESSARD F, FOURRIER A, et al.Evaluation of statistical association measures for the automatic signal generation in pharmacovigilance[J]. IEEE Trans Inf Technol Biomed, 2005, 9(4): 518-527.
[11] ALMENOFF JS, LACROIX KK, YUEN NA, et al.Comparative performance of two quantitative safety signaling methods: implications for use in a pharmacovigilance department[J]. Drug Saf, 2006, 29(10): 875-887.
[12] ROLKA H, BRACY D, RUSSELL C, et al.Using simulation to assess the sensitivity and specificity of a signal detection tool for multidimensional public health surveillance data[J]. Stat Med, 2005, 24(4): 551-562.
[13] HU N, HUANG L, TIWARI RC.Signal detection in FDA FAERS database using Dirichlet process[J]. Stat Med, 2015, 34(19): 2725-2742.
[14] LAMBERT D.Zero-inflated poisson regression, with an application to defects in manufacturing[J]. Technometrics, 1992, 34(1): 1-14.
[15] FENG CX.A comparison of zero-inflated and hurdle models for modeling zero-inflated count data[J]. J Stat Distrib Appl, 2021, 8(1): 8.
[16] GREENE W.Accounting for excess zeros and sample selection in poisson and negative binomial regression models[C]. Working Paper(EC-94-10), Department of Economics, New York University, 1994.
[17] DANIEL BH.Zero-inflated poisson and binomial regression with random effects: a case study[J]. Biometrics, 2000, 56(4): 1030-1039.
[18] HUANG L, ZHENG D, ZALKIKAR J, et al.Zero-inflated poisson model based likelihood ratio test for drug safety signal detection[J]. Stat Methods Med Res, 2017, 26(1): 471-488.
[19] FERGUSON TS.A Bayesian analysis of some nonparametric problems[J]. The Annals of Statistics, 1973, 1(2): 209-230.