For a given therapy, patients, health technology assessment agencies and regulatory agencies are interested in evaluating whether the benefit outweighs the associated risks. Existing work [1] uses prioritized composite outcomes to assess benefit and risk; this manuscript extends this work. The assessment of risk is based on a derived score obtained from predefined adverse events of interest. This derived safety score incorporates full aspects of adverse events of interest. After prioritizing the components of the composite outcomes consisting of benefit and risk outcomes, the net benefit or the Wilcoxon-Mann-Whitney statistic is used to assess the composite benefit-risk outcomes. If there is no prioritization, average net benefit (also called the O’Brien method) can be used to assess the treatment differences in the composite outcomes. Via simulation, we evaluate the characteristics of these measures of benefit-risk. An existing sample size derivation is extended to the case where there is no prioritization (average net benefit). Finally, an example motivated by a plaque psoriasis study is presented.
References
[1]
Seifu, Y., Mt-Isa, S., Duke, K., Gamalo-Siebers, M., Wang, W., Dong, G., et al. (2022) Design of Paediatric Trials with Benefit-Risk Endpoints Using a Composite Score of Adverse Events of Interest (AEI) and Win-Statistics. Journal of BiopharmaceuticalStatistics, 33, 696-707. https://doi.org/10.1080/10543406.2022.2153202
[2]
Péron, J., Roy, P., Ding, K., Parulekar, W.R., Roche, L. and Buyse, M. (2015) Assessing the Benefit-Risk of New Treatments Using Generalised Pairwise Comparisons: The Case of Erlotinib in Pancreatic Cancer. BritishJournalofCancer, 112, 971-976. https://doi.org/10.1038/bjc.2015.55
[3]
Péron, J., Giai, J., Maucort-Boulch, D. and Buyse, M. (2019) The Benefit-Risk Balance of Nab-Paclitaxel in Metastatic Pancreatic Adenocarcinoma. Pancreas, 48, 275-280. https://doi.org/10.1097/mpa.0000000000001234
[4]
Buyse, M., Saad, E.D., Peron, J., Chiem, J., De Backer, M., Cantagallo, E., et al. (2021) The Net Benefit of a Treatment Should Take the Correlation between Benefits and Harms into Account. JournalofClinicalEpidemiology, 137, 148-158. https://doi.org/10.1016/j.jclinepi.2021.03.018
[5]
Backer, M.D., Sengar, M., Mathews, V., Salvaggio, S., Deltuvaite-Thomas, V., Chiêm, J., et al. (2023) Design of a Clinical Trial Using Generalized Pairwise Comparisons to Test a Less Intensive Treatment Regimen. ClinicalTrials, 21, 180-188. https://doi.org/10.1177/17407745231206465
[6]
Piffoux, M., Ozenne, B., De Backer, M., Buyse, M., Chiem, J. and Péron, J. (2024) Restricted Net Treatment Benefit in Oncology. Journal of Clinical Epidemiology, 170, Article ID: 111340. https://doi.org/10.1016/j.jclinepi.2024.111340
[7]
Buyse, M., Verbeeck, J., Saad, E.D., Backer, M.D., Deltuvaite-Thomas, V. and Molenberghs, G. (2025) Handbook of Generalized Pairwise Comparisons: Methods for Patient-Centric Analysis. Chapman and Hall/CRC.
[8]
Péron, J., Roy, P., Ozenne, B., Roche, L. and Buyse, M. (2016) The Net Chance of a Longer Survival as a Patient-Oriented Measure of Treatment Benefit in Randomized Clinical Trials. JAMAOncology, 2, 901-905. https://doi.org/10.1001/jamaoncol.2015.6359
[9]
Buyse, M. (2010) Generalized Pairwise Comparisons of Prioritized Outcomes in the Two-Sample Problem. StatisticsinMedicine, 29, 3245-3257. https://doi.org/10.1002/sim.3923
[10]
Dong, G., Huang, B., Wang, D., Verbeeck, J., Wang, J. and Hoaglin, D.C. (2020) Adjusting Win Statistics for Dependent Censoring. PharmaceuticalStatistics, 20, 440-450. https://doi.org/10.1002/pst.2086
[11]
Ramchandani, R., Schoenfeld, D.A. and Finkelstein, D.M. (2016) Global Rank Tests for Multiple, Possibly Censored, Outcomes. Biometrics, 72, 926-935. https://doi.org/10.1111/biom.12475
[12]
Verbeeck, J., Spitzer, E., de Vries, T., van Es, G.A., Anderson, W.N., Van Mieghem, N.M., et al. (2019) Generalized Pairwise Comparison Methods to Analyze (Non)prioritized Composite Endpoints. StatisticsinMedicine, 38, 5641-5656. https://doi.org/10.1002/sim.8388
[13]
Deltuvaite-Thomas, V. and Burzykowski, T. (2021) Operational Characteristics of Generalized Pairwise Comparisons for Hierarchically Ordered Endpoints. PharmaceuticalStatistics, 21, 122-132. https://doi.org/10.1002/pst.2156
[14]
Niebecker, R., Maas, H., Staab, A., Freiwald, M. and Karlsson, M.O. (2019) Modeling Exposure-Driven Adverse Event Time Courses in Oncology Exemplified by Afatinib. CPT: Pharmacometrics&SystemsPharmacology, 8, 230-239. https://doi.org/10.1002/psp4.12384
[15]
Evans, S.R., Rubin, D., Follmann, D., Pennello, G., Huskins, W.C., Powers, J.H., et al. (2015) Desirability of Outcome Ranking (DOOR) and Response Adjusted for Duration of Antibiotic Risk (RADAR). ClinicalInfectiousDiseases, 61, 800-806. https://doi.org/10.1093/cid/civ495
[16]
Fay, M.P. and Malinovsky, Y. (2018) Confidence Intervals of the Mann-Whitney Parameter That Are Compatible with the Wilcoxon-Mann-Whitney Test. Statistics in Medicine, 37, 3991-4006. https://doi.org/10.1002/sim.7890
[17]
Gasparyan, S.B., Kowalewski, E.K., Folkvaljon, F., Bengtsson, O., Buenconsejo, J., Adler, J., et al. (2021) Power and Sample Size Calculation for the Win Odds Test: Application to an Ordinal Endpoint in COVID-19 Trials. Journal of BiopharmaceuticalStatistics, 31, 765-787. https://doi.org/10.1080/10543406.2021.1968893
[18]
CIOMS Working Group (2023) Benefit-Risk Balance for Medical Products.
[19]
Ozenne, B. and Peron, J. (2024) BuyseTest: Implementation of the Generalized Pairwise Comparisons. R Package Version 3.0.2.
[20]
Noether, G.E. (1987) Sample Size Determination for Some Common Nonparametric Tests. JournaloftheAmericanStatisticalAssociation, 82, 645-647. https://doi.org/10.1080/01621459.1987.10478478
[21]
Kornacki, A., Bochniak, A. and Kubik-Komar, A. (2017) Sample Size Determination in the Mann-Whitney Test. BiometricalLetters, 54, 175-186. https://doi.org/10.1515/bile-2017-0010
[22]
Zhou, T.J., LaValley, M.P., Nelson, K.P., Cabral, H.J. and Massaro, J.M. (2022) Calculating Power for the Finkelstein and Schoenfeld Test Statistic for a Composite Endpoint with Two Components. Statistics in Medicine, 41, 3321-3335. https://doi.org/10.1002/sim.9419
[23]
Gordon, K.B., Strober, B., Lebwohl, M., Augustin, M., Blauvelt, A., Poulin, Y., et al. (2018) Efficacy and Safety of Risankizumab in Moderate-to-Severe Plaque Psoriasis (Ultimma-1 and Ultimma-2): Results from Two Double-Blind, Randomised, Placebo-Controlled and Ustekinumab-Controlled Phase 3 Trials. TheLancet, 392, 650-661. https://doi.org/10.1016/s0140-6736(18)31713-6
[24]
Verbeeck, J., Dirani, M., Bauer, J.W., Hilgers, R., Molenberghs, G. and Nabbout, R. (2023) Composite Endpoints, Including Patient Reported Outcomes, in Rare Diseases. OrphanetJournalofRareDiseases, 18, Article No. 262. https://doi.org/10.1186/s13023-023-02819-x
[25]
Deltuvaite-Thomas, V., De Backer, M., Parker, S., Deneux, M., Polgreen, L.E., O’Neill, C., et al. (2023) Generalized Pairwise Comparisons of Prioritized Outcomes Are a Powerful and Patient-Centric Analysis of Multi-Domain Scores. OrphanetJournalofRareDiseases, 18, Article No. 321. https://doi.org/10.1186/s13023-023-02943-8
[26]
Yuan, S.S., Seifu, Y., Wang, W. and Colopy, M. (2021) Estimands in Safety and Benefit-Risk Evaluation. In: QuantitativeDrugSafetyandBenefit-RiskEvaluation: Practical and Cross-Disciplinary Approaches, Chapman and Hall/CRC, 317-349. https://doi.org/10.1201/9780429488801-18
