Leveraging historical control data to augment randomized control data in clinical trials has become an important strategy for improving the efficiency of statistical inference, particularly in contexts with limited sample availability. However, potential heterogeneity between historical and current datasets may introduce bias in treatment effect estimation and compromise inferential validity. This study proposes a two-stage "Fill-it-up" design for clinical trials with binary endpoints to enable the rigorous integration of historical control data under controlled statistical risk. Analytical procedures for sample size determination and practical implementation steps for both stages are provided. Simulation studies demonstrate that the family-wise error rate can be effectively controlled below the pre-specified significance level, while the average sample size is substantially reduced compared with a conventional single-stage design that excludes historical controls. The efficiency gains become more pronounced as between-group heterogeneity decreases. The proposed two-stage Fill-it-up design offers a frequentist framework for safely and efficiently incorporating historical control data into binary endpoint trials. Given that additional recruitment is required when equivalence is not established, its practical application is best suited for studies where there is strong prior confidence in the quality and comparability of historical data, such as in rare disease or pediatric settings. This design provides a pragmatic approach for enhancing the efficiency and ethical sustainability of modern clinical research.
Citation: Junjiang Zhong, Haoyun Guo, Nan Sun, Junjie Li. Two-stage Fill-it-up design method incorporating historical control data in binary endpoint clinical trials[J]. AIMS Mathematics, 2025, 10(12): 29168-29188. doi: 10.3934/math.20251283
Leveraging historical control data to augment randomized control data in clinical trials has become an important strategy for improving the efficiency of statistical inference, particularly in contexts with limited sample availability. However, potential heterogeneity between historical and current datasets may introduce bias in treatment effect estimation and compromise inferential validity. This study proposes a two-stage "Fill-it-up" design for clinical trials with binary endpoints to enable the rigorous integration of historical control data under controlled statistical risk. Analytical procedures for sample size determination and practical implementation steps for both stages are provided. Simulation studies demonstrate that the family-wise error rate can be effectively controlled below the pre-specified significance level, while the average sample size is substantially reduced compared with a conventional single-stage design that excludes historical controls. The efficiency gains become more pronounced as between-group heterogeneity decreases. The proposed two-stage Fill-it-up design offers a frequentist framework for safely and efficiently incorporating historical control data into binary endpoint trials. Given that additional recruitment is required when equivalence is not established, its practical application is best suited for studies where there is strong prior confidence in the quality and comparability of historical data, such as in rare disease or pediatric settings. This design provides a pragmatic approach for enhancing the efficiency and ethical sustainability of modern clinical research.
| [1] | Food and Drug Administration, Considerations for the design and conduct of externally controlled trials for drug and biological products, Food and Drug Administration, 2023. Available from: https://www.fda.gov/media/164960/download |
| [2] |
M. H. Chen, J. G. Ibrahim, Power prior distributions for regression models, Statist. Sci., 15 (2000), 46–60. https://doi.org/10.1214/ss/1009212673 doi: 10.1214/ss/1009212673
|
| [3] |
Y. Duan, K. Ye, E. P. Smith, Evaluating water quality using power priors to incorporate historical information, Environmetrics, 17 (2006), 95–106. https://doi.org/10.1002/env.752 doi: 10.1002/env.752
|
| [4] |
M. H. Chen, J. G. Ibrahim, P. Lam, A. Yu, Y. Zhang, Bayesian design of non-inferiority trials for medical devices using historical data, Biometrics, 67 (2011), 1163–1170. https://doi.org/10.1111/j.1541-0420.2011.01561.x doi: 10.1111/j.1541-0420.2011.01561.x
|
| [5] |
B. P. Hobbs, B. P. Carlin, S. J. Mandrekar, D. J. Sargent, Hierarchical commensurate and power prior models for adaptive incorporation of historical information in clinical trials, Biometrics, 67 (2011), 1047–1056. https://doi.org/10.1111/j.1541-0420.2011.01564.x doi: 10.1111/j.1541-0420.2011.01564.x
|
| [6] |
B. P. Hobbs, D. J. Sargent, B. P. Carlin, Commensurate priors for incorporating historical information in clinical trials using general and generalized linear models, Bayesian Anal., 7 (2012), 639–674. https://doi.org/10.1214/12-BA722 doi: 10.1214/12-BA722
|
| [7] |
M. Bennett, S. White, N. Best, A. Mander, A novel equivalence probability weighted power prior for using historical control data in an adaptive clinical trial design: A comparison to standard methods, Pharm. Stat., 20 (2021), 462–484. https://doi.org/10.1002/pst.2088 doi: 10.1002/pst.2088
|
| [8] |
S. Gsteiger, B. Neuenschwander, F. Mercier, H. Schmidli, Using historical control information for the design and analysis of clinical trials with overdispersed count data, Statist. Med., 32 (2013), 3609–3622. https://doi.org/10.1002/sim.5851 doi: 10.1002/sim.5851
|
| [9] |
H. Schmidli, S. Gsteiger, S. Roychoudhury, A. O'Hagan, D. Spiegelhalter, B. Neuenschwander, Robust meta-analytic-predictive priors in clinical trials with historical control information, Biometrics, 70 (2014), 1023–1032. https://doi.org/10.1111/biom.12242 doi: 10.1111/biom.12242
|
| [10] |
K. Viele, S. Berry, B. Neuenschwander, B. Amzal, F. Chen, N. Enas, et al., Use of historical control data for assessing treatment effects in clinical trials, Pharm. Stat., 13 (2014), 41–54. https://doi.org/10.1002/pst.1589 doi: 10.1002/pst.1589
|
| [11] |
W. Li, F. Liu, D. Snavely, Revisit of test-then-pool methods and some practical considerations, Pharm. Stat., 19 (2020), 498–517. https://doi.org/10.1002/pst.2009 doi: 10.1002/pst.2009
|
| [12] |
S. Wied, M. Posch, R. D. Hilgers, Evaluation of the fill-it-up-design to use historical control data in randomized clinical trials with two arm parallel group design, BMC Med. Res. Methodol., 24 (2024), 197. https://doi.org/10.1186/s12874-024-02306-2 doi: 10.1186/s12874-024-02306-2
|
| [13] |
H. I. Brunner, C. Abud-Mendoza, D. O. Viola, I. C. Penades, D. Levy, J. Anton, et al., Safety and efficacy of intravenous belimumab in children with systemic lupus erythematosus: Results from a randomized, placebo-controlled trial, Ann. Rheum. Dis., 79 (2020), 1340–1348. https://doi.org/10.1136/annrheumdis-2020-217101 doi: 10.1136/annrheumdis-2020-217101
|
| [14] |
S. V. Navarra, R. M. Guzmán, A. E. Gallacher, S. Hall, R. A. Levy, R. E. Jimenez, et al., Efficacy and safety of belimumab in patients with active systemic lupus erythematosus: A randomized, placebo-controlled, phase 3 trial, Lancet, 377 (2011), 721–731. https://doi.org/10.1016/S0140-6736(10)61354-2 doi: 10.1016/S0140-6736(10)61354-2
|
| [15] |
D. J. Schuirmann, A comparison of the two one-sided tests procedure and the power approach for assessing the equivalence of average bioavailability, J. Pharmacokinet. Biopharm., 15 (1987), 657–680. https://doi.org/10.1007/BF01068419 doi: 10.1007/BF01068419
|
| [16] |
R. L. Berger, Multiparameter hypothesis testing and acceptance sampling, Technometrics, 24 (1982), 295–300. https://doi.org/10.2307/1267823 doi: 10.2307/1267823
|
| [17] | S. C. Chow, J. Shao, H. Wang, Y. Lokhnygina, Sample size calculations in clinical research, New York: Chapman and hall/CRC, 2017. https://doi.org/10.1201/9781315183084 |
| [18] |
B. Neuenschwander, G. Capkun-Niggli, M. Branson, D. Spiegelhalter, Summarizing historical information on controls in clinical trials, Clin. Trials, 7 (2010), 5–18. https://doi.org/10.1177/1740774509356002 doi: 10.1177/1740774509356002
|
| [19] |
S. Weber, Y. Li, J. W. Seaman Ⅲ, T. Kakizume, H. Schmidli, Applying meta-analytic-predictive priors with the R Bayesian evidence synthesis tools, J. Stat. Softw., 100 (2021), 1–32. https://doi.org/10.18637/jss.v100.i19 doi: 10.18637/jss.v100.i19
|
| [20] |
G. L. Hickey, P. Philipson, A. Jorgensen, R. Kolamunnage-Dona, Joint modelling of time-to-event and multivariate longitudinal outcomes: Recent developments and issues, BMC Med. Res. Methodol., 16 (2016), 117. https://doi.org/10.1186/s12874-016-0212-5 doi: 10.1186/s12874-016-0212-5
|
| [21] |
A. H. Ekong, M. O. Olayiwola, A. G. Dawodu, A. I. Osinuga, Latent gaussian approach to joint modelling of longitudinal and mixture cure outcomes, Comput. J. Math. Stat. Sci., 4 (2025), 72–95. https://doi.org/10.21608/cjmss.2024.303748.1061 doi: 10.21608/cjmss.2024.303748.1061
|
Figures(4) / Tables(5)
Junjiang Zhong, Haoyun Guo, Nan Sun, Junjie Li. Two-stage Fill-it-up design method incorporating historical control data in binary endpoint clinical trials[J]. AIMS Mathematics, 2025, 10(12): 29168-29188. doi: 10.3934/math.20251283
DownLoad: