Use of Logistic Regression to Combine Two Causality Criteria for Signal Detection in Vaccine Spontaneous Report Data

PurposeWe evaluated the use of logistic regression to model the probabilities of spontaneously reported vaccine–event pairs being adverse reactions following immunization (ARFI), using disproportionality and unexpectedness of time-to-onset (TTO) distributions as predictive variables and the presence of events in the global product information as a dependent variable.MethodsWe used spontaneous reports of adverse events from eight vaccines and their labels as proxies for ARFIs. Three logistic regressions were built to predict ARFIs based on different combinations of the proportional reporting ratio (PRR; disproportionality measure) and two Kolmogorov–Smirnov (KS) tests (‘between vaccines’ and the ‘between events’) of TTO distribution: model 1, using the PRR estimate and its 95 % lower confidence interval (CI) limit; model 2, using the p values of the two KS tests; and model 3, using the PRR (point estimate and lower CI limit) and both KS tests. The performance of the regressions (model fit statistics, calibration, and discrimination) was measured on 100 bootstrap samples.ResultsModel 3, using two quantified causality criteria, provided the best performance for all measures. The p value of the ‘between vaccines’ KS test was the most significant predictive factor. Model 1 had the worst performance.ConclusionsLogistic regression allows estimation of the probability of a vaccine–event pair being an ARFI using two causality criteria at the population level assessed in spontaneous report data: the strength of association (disproportionality measure) and temporality (TTO distribution tests). Logistic regression combines and weights these causality criteria based on their respective ability to predict known safety issues.

[1]  M. Lindquist,et al.  A comparison of measures of disproportionality for signal detection in spontaneous reporting systems for adverse drug reactions , 2002, Pharmacoepidemiology and drug safety.

[2]  Matthias Schroder,et al.  Logistic Regression: A Self-Learning Text , 2003 .

[3]  J. Habbema,et al.  Internal validation of predictive models: efficiency of some procedures for logistic regression analysis. , 2001, Journal of clinical epidemiology.

[4]  A. Fourrier-Réglat,et al.  A new method for assessing drug causation provided agreement with experts' judgment. , 2006, Journal of clinical epidemiology.

[5]  D. Hosmer,et al.  Applied Logistic Regression , 1991 .

[6]  D. Wooff.  Logistic Regression: a Self-learning Text, 2nd edn , 2004 .

[7]  S. Goldman,et al.  Limitations and strengths of spontaneous reports data. , 1998, Clinical therapeutics.

[8]  A Lawrence Gould,et al.  Practical pharmacovigilance analysis strategies. , 2003, Pharmacoepidemiology and drug safety.

[9]  C J McDonald,et al.  Validation of Probabilistic Predictions , 1993, Medical decision making : an international journal of the Society for Medical Decision Making.

[10]  E. Somers.  International Agency for Research on Cancer. , 1985, CMAJ : Canadian Medical Association journal = journal de l'Association medicale canadienne.

[11]  G. Niklas Norén,et al.  Improved Statistical Signal Detection in Pharmacovigilance by Combining Multiple Strength-of-Evidence Aspects in vigiRank , 2014, Drug Safety.

[12]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .

[13]  Lawrence T. DeCarlo,et al.  Signal detection theory and generalized linear models , 1998 .

[14]  Using time‐to‐onset for detecting safety signals in spontaneous reports of adverse events following immunization: a proof of concept study , 2012, Pharmacoepidemiology and drug safety.

[15]  Vincent Bauchau,et al.  Signal detection on spontaneous reports of adverse events following immunisation: a comparison of the performance of a disproportionality-based algorithm and a time-to-onset-based algorithm , 2014, Pharmacoepidemiology and drug safety.

[16]  Gaurav Deshpande,et al.  Data Mining in Drug Safety , 2010, Pharmaceutical Medicine.

[17]  F. Haramburu,et al.  An updated method improved the assessment of adverse drug reaction in routine pharmacovigilance. , 2012, Journal of clinical epidemiology.

[18]  William DuMouchel,et al.  Bayesian Data Mining in Large Frequency Tables, with an Application to the FDA Spontaneous Reporting System , 1999 .

[19]  S. Evans,et al.  Use of proportional reporting ratios (PRRs) for signal generation from spontaneous adverse drug reaction reports , 2001, Pharmacoepidemiology and drug safety.

[20]  Manfred Hauben,et al.  A conceptual approach to the masking effect of measures of disproportionality , 2014, Pharmacoepidemiology and drug safety.

[21]  V. Bauchau,et al.  The upper bound to the Relative Reporting Ratio—a measure of the impact of the violation of hidden assumptions underlying some disproportionality methods used in signal detection , 2014, Pharmacoepidemiology and drug safety.

[22]  B. Macmahon,et al.  Epidemiology: Principles and Methods , 1970 .