On estimands and the analysis of adverse events in the presence of varying follow‐up times within the benefit assessment of therapies

The analysis of adverse events (AEs) is a key component in the assessment of a drug's safety profile. Inappropriate analysis methods may result in misleading conclusions about a therapy's safety and consequently its benefit‐risk ratio. The statistical analysis of AEs is complicated by the fact that the follow‐up times can vary between the patients included in a clinical trial. This paper takes as its focus the analysis of AE data in the presence of varying follow‐up times within the benefit assessment of therapeutic interventions. Instead of approaching this issue directly and solely from an analysis point of view, we first discuss what should be estimated in the context of safety data, leading to the concept of estimands. Although the current discussion on estimands is mainly related to efficacy evaluation, the concept is applicable to safety endpoints as well. Within the framework of estimands, we present statistical methods for analysing AEs with the focus being on the time to the occurrence of the first AE of a specific type. We give recommendations which estimators should be used for the estimands described. Furthermore, we state practical implications of the analysis of AEs in clinical trials and give an overview of examples across different indications. We also provide a review of current practices of health technology assessment (HTA) agencies with respect to the evaluation of safety data. Finally, we describe problems with meta‐analyses of AE data and sketch possible solutions.

[1]  Tim Friede,et al.  Meta‐analysis of two studies in the presence of heterogeneity with applications in rare diseases , 2016, Biometrical journal. Biometrische Zeitschrift.

[2]  Tim Friede,et al.  Random‐effects meta‐analysis of few studies involving rare events , 2018, Research synthesis methods.

[3]  G. Rücker,et al.  Simpson's paradox visualized: The example of the Rosiglitazone meta-analysis , 2008, BMC medical research methodology.

[4]  Claudia Schmoor,et al.  Statistical issues in the analysis of adverse events in time‐to‐event data , 2016, Pharmaceutical statistics.

[5]  T. Friede,et al.  Hartung-Knapp-Sidik-Jonkman approach and its modification for random-effects meta-analysis with few studies , 2015, BMC Medical Research Methodology.

[6]  O Kuss,et al.  Statistical methods for meta‐analyses including information from studies without any events—add nothing to nothing and succeed nevertheless , 2015, Statistics in medicine.

[7]  E. Scott.  Modelling Survival Data in Medical Research , 1995 .

[8]  Norbert Benda,et al.  Choosing Appropriate Estimands in Clinical Trials , 2015, Therapeutic innovation & regulatory science.

[9]  Dankmar Böhning,et al.  Meta-analysis of Binary Data Using Profile Likelihood , 2008 .

[10]  J. Pearl,et al.  Causal Inference , 2011, Twenty-one Mental Models That Can Change Policing.

[11]  M. Cowie.  National Institute for Health and Care Excellence. , 2015, European heart journal.

[12]  Chikayuki Naito,et al.  Ethnic Factors in the Acceptability of Foreign Clinical Data , 1998 .

[13]  Craig Mallinckrodt,et al.  Preventing and Treating Missing Data in Longitudinal Clinical Trials: A Practical Guide , 2013 .

[14]  J. Ioannidis,et al.  Better Reporting of Harms in Randomized Trials: An Extension of the CONSORT Statement , 2004, Annals of Internal Medicine.

[15]  D G Altman,et al.  Statistics notes: Absence of evidence is not evidence of absence , 1995 .

[16]  P. Kaatsch,et al.  [Position paper of the Society of Pediatric Oncology and Hematology (GPOH) on (long-term) surveillance, (long-term) follow-up and late effect evaluation in pediatric oncology patients]. , 2007, Klinische Padiatrie.

[17]  Erik T Parner,et al.  Causal inference in survival analysis using pseudo‐observations , 2017, Statistics in medicine.

[18]  Ren Johansen.  An Empirical Transition Matrix for Non-homogeneous Markov Chains Based on Censored Observations , 1978 .

[19]  Ai Jian.  Guidance for industry premarketing risk assessment(I) , 2006 .

[20]  S. Duffy,et al.  Are adverse effects incorporated in economic models? An initial review of current practice. , 2009, Health technology assessment.

[21]  Claudia Wild,et al.  BEST PRACTICE IN UNDERTAKING AND REPORTING HEALTH TECHNOLOGY ASSESSMENTS , 2002, International Journal of Technology Assessment in Health Care.

[22]  M. A. Best.  Bayesian Approaches to Clinical Trials and Health‐Care Evaluation , 2005 .

[23]  Brenda J. Crowe,et al.  Current Practices, Challenges, and Statistical Issues With Product Safety Labeling , 2013 .

[24]  M. Schemper,et al.  The estimation of average hazard ratios by weighted Cox regression , 2009, Statistics in medicine.

[25]  Markus Pauly,et al.  Weak Convergence of the Wild Bootstrap for the Aalen–Johansen Estimator of the Cumulative Incidence Function of a Competing Risk , 2013 .

[26]  Martin Schumacher,et al.  Competing Risks and Multistate Models with R , 2011 .

[27]  Tim Friede,et al.  Meta‐analysis of few small studies in orphan diseases , 2016, Research synthesis methods.

[28]  Robert Gray,et al.  A Proportional Hazards Model for the Subdistribution of a Competing Risk , 1999 .

[29]  Peter W Lane,et al.  Graphical approaches to the analysis of safety data from clinical trials , 2008, Pharmaceutical statistics.

[30]  R. Guthrie.  Canagliflozin and cardiovascular and renal events in type 2 diabetes , 2018, Postgraduate medicine.

[31]  John O'Quigley,et al.  Proportional Hazards Regression , 2008 .

[32]  D. Kleinbaum,et al.  Survival Analysis: A Self-Learning Text. , 1996 .

[33]  Iris Pigeot,et al.  Multivariate time‐to‐event analysis of multiple adverse events of drugs in integrated analyses , 2007, Statistics in medicine.

[34]  S. Ruberg,et al.  Estimands in clinical trials – broadening the perspective , 2017, Statistics in medicine.

[35]  J. Hanley,et al.  Recovering the raw data behind a non-parametric survival curve , 2014, Systematic Reviews.

[36]  D. Rubin,et al.  Principal Stratification in Causal Inference , 2002, Biometrics.

[37]  Simon G Thompson,et al.  Predicting the extent of heterogeneity in meta-analysis, using empirical data from the Cochrane Database of Systematic Reviews , 2012, International journal of epidemiology.

[38]  J Crowley,et al.  Estimation of failure probabilities in the presence of competing risks: new representations of old estimators. , 1999, Statistics in medicine.

[39]  Allan Wailoo,et al.  Using health state utility values in models exploring the cost-effectiveness of health technologies. , 2012, Value in health : the journal of the International Society for Pharmacoeconomics and Outcomes Research.

[40]  T. Friede,et al.  Discrete Approximation of a Mixture Distribution via Restricted Divergence , 2016, 1602.04060.

[41]  R. O’Neill.  Statistical Analyses of Adverse Event Data from Clinical Trials , 1987, Drug information journal.

[42]  Judea Pearl,et al.  Causal Inference , 2010 .

[43]  C. Chuang-Stein,et al.  Reporting cumulative proportion of subjects with an adverse event based on data from multiple studies , 2011, Pharmaceutical statistics.

[44]  Jesse A. Berlin,et al.  Meta-analysis of clinical trial safety data in a drug development program: Answers to frequently asked questions , 2013, Clinical trials.

[45]  F. Bretz,et al.  Estimands and Their Role in Clinical Trials , 2017 .

[46]  David J Spiegelhalter,et al.  A re-evaluation of random-effects meta-analysis , 2009, Journal of the Royal Statistical Society. Series A,.

[47]  J. Berlin,et al.  Recommendations to improve adverse event reporting in clinical trial publications: a joint pharmaceutical industry/journal editor perspective , 2016, British Medical Journal.

[48]  Mei-Jie Zhang,et al.  The proportional odds cumulative incidence model for competing risks , 2015, Biometrics.

[49]  Ralf Bender,et al.  Methods for evidence synthesis in the case of very few studies , 2018, Research synthesis methods.

[50]  Ohidul Siddiqui,et al.  Statistical Methods to Analyze Adverse Events Data of Randomized Clinical Trials , 2009, Journal of biopharmaceutical statistics.

[51]  Tim Friede,et al.  Random‐effects meta‐analysis of few studies involving rare events , 2018, Research synthesis methods.

[52]  Niels Keiding,et al.  Interpretability and importance of functionals in competing risks and multistate models , 2012, Statistics in medicine.

[53]  Alan Agresti,et al.  Categorical Data Analysis , 2003 .

[54]  Jonathan J Deeks,et al.  Much ado about nothing: a comparison of the performance of meta‐analytical methods with rare events , 2007, Statistics in medicine.

[55]  O. Aalen,et al.  Survival and Event History Analysis: A Process Point of View , 2008 .

[56]  Stuart G. Baker,et al.  Analysis of Survival Data from a Randomized Trial with All-or-None Compliance: Estimating the Cost-Effectiveness of a Cancer Screening Program , 1998 .

[57]  J. Larkin,et al.  Pembrolizumab versus Ipilimumab in Advanced Melanoma. , 2015, The New England journal of medicine.

[58]  Damian McEntegart,et al.  Pooling in Integrated Safety Databases , 2000 .

[59]  D. Spiegelhalter,et al.  Bayesian Approaches to Clinical Trials and Health-Care Evaluation: Spiegelhalter/Clinical Trials and Health-Care Evaluation , 2004 .

[60]  D. Pieper,et al.  Methodological approaches in conducting overviews: current state in HTA agencies , 2014, Research synthesis methods.

[61]  Scott M Berry,et al.  Accounting for Multiplicities in Assessing Drug Safety: A Three‐Level Hierarchical Mixture Model , 2004, Biometrics.

[62]  Christy Chuang-Stein,et al.  Recent Advancements in the Analysis and Presentation of Safety Data , 2001 .

[63]  Nicky J Welton,et al.  Enhanced secondary analysis of survival data: reconstructing the data from published Kaplan-Meier survival curves , 2012, BMC Medical Research Methodology.

[64]  Mike Clarke,et al.  Individual Participant Data (IPD) Meta-analyses of Randomised Controlled Trials: Guidance on Their Use , 2015, PLoS medicine.

[65]  Peter Congdon,et al.  Survival and Event History Analysis , 2007 .

[66]  Niels Keiding,et al.  Statistical Models Based on Counting Processes , 1993 .

[67]  R. Bender,et al.  Biometrical issues in the analysis of adverse events within the benefit assessment of drugs , 2016, Pharmaceutical statistics.