Comparison of statistical methods for the analysis of recurrent adverse events in the presence of non-proportional hazards and unobserved heterogeneity: a simulation study

Noel Patson, Mavuto Mukaka, Lawrence Kazembe, Marinus J C Eijkemans, Don Mathanga, Miriam K Laufer, Tobias Chirwa, Noel Patson, Mavuto Mukaka, Lawrence Kazembe, Marinus J C Eijkemans, Don Mathanga, Miriam K Laufer, Tobias Chirwa

Abstract

Background: In preventive drug trials such as intermittent preventive treatment for malaria prevention during pregnancy (IPTp), where there is repeated treatment administration, recurrence of adverse events (AEs) is expected. Challenges in modelling the risk of the AEs include accounting for time-to-AE and within-patient-correlation, beyond the conventional methods. The correlation comes from two sources; (a) individual patient unobserved heterogeneity (i.e. frailty) and (b) the dependence between AEs characterised by time-dependent treatment effects. Potential AE-dependence can be modelled via time-dependent treatment effects, event-specific baseline and event-specific random effect, while heterogeneity can be modelled via subject-specific random effect. Methods that can improve the estimation of both the unobserved heterogeneity and treatment effects can be useful in understanding the evolution of risk of AEs, especially in preventive trials where time-dependent treatment effect is expected.

Methods: Using both a simulation study and the Chloroquine for Malaria in Pregnancy (NCT01443130) trial data to demonstrate the application of the models, we investigated whether the lognormal shared frailty models with restricted cubic splines and non-proportional hazards (LSF-NPH) assumption can improve estimates for both frailty variance and treatment effect compared to the conventional inverse Gaussian shared frailty model with proportional hazard (ISF-PH), in the presence of time-dependent treatment effects and unobserved patient heterogeneity. We assessed the bias, precision gain and coverage probability of 95% confidence interval of the frailty variance estimates for the models under varying known unobserved heterogeneity, sample sizes and time-dependent effects.

Results: The ISF-PH model provided a better coverage probability of 95% confidence interval, less bias and less precise frailty variance estimates compared to the LSF-NPH models. The LSF-NPH models yielded unbiased hazard ratio estimates at the expense of imprecision and high mean square error compared to the ISF-PH model.

Conclusion: The choice of the shared frailty model for the recurrent AEs analysis should be driven by the study objective. Using the LSF-NPH models is appropriate if unbiased hazard ratio estimation is of primary interest in the presence of time-dependent treatment effects. However, ISF-PH model is appropriate if unbiased frailty variance estimation is of primary interest.

Trial registration: ClinicalTrials.gov; NCT01443130.

Keywords: Non-proportional hazards; Randomised controlled trials; Recurrent adverse events; Unobserved heterogeneity.

Conflict of interest statement

The authors declare that they have no competing interests.

© 2022. The Author(s).

Figures

Fig. 1
Fig. 1
Average model standard errors (SE) for the frailty variance estimates across shared frailty models under varying data-generating mechanisms

References

    1. Munsaka MS. Biopharmaceutical Applied Statistics Symposium. Biostatistical analysis of clinical trials, Vol. 2. Singapore: Springer; 2018. A question-based approach to the analysis of safety data; pp. 193–216.
    1. Patson N, Mukaka M, Otwombe KN, Kazembe L, Mathanga DP, Mwapasa V, Kabaghe AN, Eijkemans MJC, Laufer MK, Chirwa T. Systematic review of statistical methods for safety data in malaria chemoprevention in pregnancy trials. Malar J. 2020;19(1):119. doi: 10.1186/s12936-020-03190-z.
    1. Phillips R, Cornelius V. Understanding current practice, identifying barriers and exploring priorities for adverse event analysis in randomised controlled trials: an online, cross-sectional survey of statisticians from academia and industry. BMJ Open. 2020;10(6):e036875. doi: 10.1136/bmjopen-2020-036875.
    1. Colopy MW, Gordon R, Ahmad F, Wang WW, Duke SP, Ball G. Statistical practices of safety monitoring: an industry survey. Ther Innov Reg Sci. 2019;53(3):293–300. doi: 10.1177/2168479018779973.
    1. Siddiqui O. Statistical methods to analyze adverse events data of randomized clinical trials. J Biopharm Stat. 2009;19(5):889–899. doi: 10.1080/10543400903105463.
    1. Hengelbrock J, Gillhaus J, Kloss S, Leverkus F. Safety data from randomized controlled trials: applying models for recurrent events. Pharm Stat. 2016;15(4):315–323. doi: 10.1002/pst.1757.
    1. Cabarrou B, Gomez-Roca C, Viala M, Rabeau A, Paulon R, Loirat D, Munsch N, Delord J-P, Filleron T. Modernizing adverse events analysis in oncology clinical trials using alternative approaches: rationale and design of the MOTIVATE trial. Investig New Drugs. 2020;38:1879–1887. doi: 10.1007/s10637-020-00938-x.
    1. Box-Steffensmeier JM, De Boef S. Repeated events survival models: the conditional frailty model. Stat Med. 2006;25(20):3518–3533. doi: 10.1002/sim.2434.
    1. Hougaard P. Analysis of multivariate survival data. New York: Springer; 2012.
    1. Duchateau L, Janssen P. The frailty model. New York: Springer; 2007.
    1. Amorim LD, Cai J. Modelling recurrent events: a tutorial for analysis in epidemiology. Int J Epidemiol. 2015;44(1):324–333. doi: 10.1093/ije/dyu222.
    1. Balan TA, Putter H. Nonproportional hazards and unobserved heterogeneity in clustered survival data: when can we tell the difference? Stat Med. 2019;38(18):3405–3420. doi: 10.1002/sim.8171.
    1. Crowther MJ. Extended multivariate generalised linear and non-linear mixed effects models. 2017.
    1. Bower H, Crowther MJ, Rutherford MJ, Andersson TM-L, Clements M, Liu X-R, et al. Capturing simple and complex time-dependent effects using flexible parametric survival models: a simulation study. Commun Stat Simul Comput. 2021;50(11):3777–93.
    1. Rutherford MJ, Crowther MJ, Lambert PC. The use of restricted cubic splines to approximate complex hazard functions in the analysis of time-to-event data: a simulation study. J Stat Comput Simul. 2015;85(4):777–793. doi: 10.1080/00949655.2013.845890.
    1. Gasparini A, Clements MS, Abrams KR, Crowther MJ. Impact of model misspecification in shared frailty survival models. Stat Med. 2019;38(23):4477–4502. doi: 10.1002/sim.8309.
    1. Cook RJ, Lawless J. The statistical analysis of recurrent events. New York: Springer; 2007.
    1. Hanagal DD. Modeling survival data using frailty models. Singapore: Springer; 2019.
    1. Andersen PK, Gill RD. Cox's regression model for counting processes: a large sample study. Ann Stat. 1982;10(4):1100–20.
    1. Kalbfleisch JD, Prentice RL. The statistical analysis of failure time data. Newyork: Wiley; 2011.
    1. Lawless JF. Statistical models and methods for lifetime data. Newyork: Wiley; 2003.
    1. Kelly PJ, Lim LLY. Survival analysis for recurrent event data: an application to childhood infectious diseases. Stat Med. 2000;19(1):13–33. doi: 10.1002/(SICI)1097-0258(20000115)19:1<13::AID-SIM279>;2-5.
    1. Babiker A, Cuzick J. A simple frailty model for family studies with covariates. Stat Med. 1994;13(16):1679–1692. doi: 10.1002/sim.4780131608.
    1. Pickles A, Crouchley R. A comparison of frailty models for multivariate survival data. Stat Med. 1995;14(13):1447–1461. doi: 10.1002/sim.4780141305.
    1. Morris TP, White IR, Crowther MJ. Using simulation studies to evaluate statistical methods. Stat Med. 2019;38(11):2074–2102. doi: 10.1002/sim.8086.
    1. Bender R, Augustin T, Blettner M. Generating survival times to simulate cox proportional hazards models. Stat Med. 2005;24(11):1713–1723. doi: 10.1002/sim.2059.
    1. Crowther MJ. Merlin-a unified modelling framework for data analysis and methods development in Stata. 2018.
    1. Crowther MJ, Lambert PC. Simulating biologically plausible complex survival data. Stat Med. 2013;32(23):4118–4134. doi: 10.1002/sim.5823.
    1. Crowther MJ, Look MP, Riley RD. Multilevel mixed effects parametric survival models using adaptive Gauss–Hermite quadrature with application to recurrent events and individual participant data meta-analysis. Stat Med. 2014;33(22):3844–3858. doi: 10.1002/sim.6191.
    1. Divala TH, Mungwira RG, Mawindo PM, Nyirenda OM, Kanjala M, Ndaferankhande M, Tsirizani LE, Masonga R, Muwalo F, Boudová S, et al. Chloroquine as weekly chemoprophylaxis or intermittent treatment to prevent malaria in pregnancy in Malawi: a randomised controlled trial. Lancet Infect Dis. 2018;18(10):1097–1107. doi: 10.1016/S1473-3099(18)30415-8.
    1. Hougaard P. Life table methods for heterogeneous populations: distributions describing the heterogeneity. Biometrika. 1984;71(1):75–83. doi: 10.1093/biomet/71.1.75.

Source: PubMed

Sponsors and Collaborators

Medical Conditions

Drug Interventions

3
Subscribe