Phase II clinical trials are commonly conducted as pilot studies to evaluate the efficacy and safety of the investigational drug in the targeted patient population with the disease or condition to be treated or prevented. When designing such a trial considering efficacy conclusions, people naturally think as follows: if efficacy evidence is very strong, a go decision should be made; if efficacy evidence is very weak, a no-go decision should be made; if the efficacy evidence is neither strong nor weak, no decision can be made (inconclusive). The designs presented in this paper match this natural thinking process with go/no-go/inconclusive outcomes. Both two-/three-stage designs are developed with three outcomes. Additionally, a general approach based on conditional error function is implemented such that new decision boundaries can be calculated to handle mid-course sample size change which results in either ‘over-running’ or ‘under-running’ and ensure the control of overall type I error. A free open-source R package tsdf that calculates the proposed two-/three-stage designs is available on CRAN.

References

• Brannath, W., Koenig, F., & Bauer, P. (2007). Multiplicity and flexibility in clinical trials. Pharmaceutical Statistics, 6(3), 205–216. https://doi.org/10.1002/pst.302 
• Demets, D. L., & Lan, K. K. G. (1994). Interim analysis: The alpha spending function approach. Statistics in Medicine, 13(13–14), 1341–1352. https://doi.org/10.1002/(ISSN)1097-0258
• Englert, S., & Kieser, M. (2012). Improving the flexibility and efficiency of phase II designs for oncology trials. Biometrics, 68(3), 886–892. https://doi.org/10.1111/j.1541-0420.2011.01720.x
• Englert, S., & Kieser, M. (2015). Methods for proper handling of overrunning and underrunning in phase II designs for oncology trials. Statistics in Medicine, 34(13), 2128–2137. https://doi.org/10.1002/sim.v34.13 
• Guo, W., Hui, J., & Zhong, B. (2019). TSDF: Two-/three-stage designs for phase 1&2 clinical trials. R package version 1.1-7.
• Hong, S., & Wang, Y. (2007). A three-outcome design for randomized comparative phase ii clinical trials. Statistics in Medicine, 26(19), 3525–3534. https://doi.org/10.1002/(ISSN)1097-0258 
• Hwang, I. K., Shih, W. J., & De Cani, J. S. (1990). Group sequential designs using a family of type i error probability spending functions. Statistics in Medicine, 9(12), 1439–1445. https://doi.org/10.1002/(ISSN)1097-0258
• Jennison, C., & Turnbull, B. W. (2000). Group sequential methods with applications to clinical trials, Chapman and Hall. 
• Koyama, T., & Chen, H. (2008). Proper inference from Simon's two-stage designs. Statistics in Medicine, 27(16), 3145–3154. https://doi.org/10.1002/sim.v27:16
• Li, G., Shih, W. J., Xie, T., & Lu, J. (2002). A sample size adjustment procedure for clinical trials based on conditional power. Biostatistics, 3(2), 277–287. https://doi.org/10.1093/biostatistics/3.2.277 
• O'Brien, P. C., & Fleming, T. R. (1979). A multiple testing procedure for clinical trials. Biometrics, 35(3), 549–556. https://doi.org/10.2307/2530245 
• Proschan, M. A., & Hunsberger, S. A. (1995). Designed extension of studies based on conditional power. Biometrics, 51(4), 1315–1324. https://doi.org/10.2307/2533262
• Sargent, D. J., Chan, V., & Goldberg, R. M. (2001). A three-outcome design for phase ii clinical trials. Controlled Clinical Trials, 22(2), 117–125. https://doi.org/10.1016/S0197-2456(00)00115-X 
• Shan, G., & Chen, J. J. (2018). Optimal inference for Simon's two-stage design with over or under enrollment at the second stage. Communications in Statistics -- Simulation and Computation, 47(4), 1157–1167. https://doi.org/10.1080/03610918.2017.1307398
• Simon, R. (1989). Optimal two-stage designs for phase II clinical trials. Controlled Clinical Trials, 10(1), 1–10. https://doi.org/10.1016/0197-2456(89)90015-9 
• Whitehead, J. (1992). Overrunning and underrunning in sequential clinical trials. Controlled Clinical Trials, 13(2), 106–121. https://doi.org/10.1016/0197-2456(92)90017-T 
• Zhong, B. (2012). Single-arm phase IIa clinical trials with go/no-go decisions. Contemporary Clinical Trials, 33(6), 1272–1279. https://doi.org/10.1016/j.cct.2012.07.006 
• Zhong, W., & Zhong, B. (2013). One-sample proportion testing procedure for hypothesis of inequality. Journal of Biopharmaceutical Statistics, 23(3), 604–617. https://doi.org/10.1080/10543406.2012.756501 

To cite this article: Wenchuan Guo, Jianan Hui & Bob Zhong (2023): Single-arm phase II threeoutcome designs with handling of over-running/under-running, Statistical Theory and Related Fields, DOI: 10.1080/24754269.2023.2189348

To link to this article: https://doi.org/10.1080/24754269.2023.2189348