Bayesian optimization design for finding a maximum tolerated dose combination in phase I clinical trials
-
Ami Takahashi
and
Taiji Suzuki
Abstract
The development of combination therapies has become commonplace because potential synergistic benefits are expected for resistant patients of single-agent treatment. In phase I clinical trials, the underlying premise is toxicity increases monotonically with increasing dose levels. This assumption cannot be applied in drug combination trials, however, as there are complex drug–drug interactions. Although many parametric model-based designs have been developed, strong assumptions may be inappropriate owing to little information available about dose–toxicity relationships. No standard solution for finding a maximum tolerated dose combination has been established. With these considerations, we propose a Bayesian optimization design for identifying a single maximum tolerated dose combination. Our proposed design utilizing Bayesian optimization guides the next dose by a balance of information between exploration and exploitation on the nonparametrically estimated dose–toxicity function, thereby allowing us to reach a global optimum with fewer evaluations. We evaluate the proposed design by comparing it with a Bayesian optimal interval design and with the partial-ordering continual reassessment method. The simulation results suggest that the proposed design works well in terms of correct selection probabilities and dose allocations. The proposed design has high potential as a powerful tool for use in finding a maximum tolerated dose combination.
Acknowledgement
TS was partially supported by JSPS Kakenhi (18K19793, 18H03201, and 20H00576), Japan Digital Design, and JST-CREST.
-
Author contribution: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
-
Research funding: None declared.
-
Conflict of interest statement: The authors declare no conflicts of interest regarding this article.
References
1. Zhang, L, Yuan, Y. A practical Bayesian design to identify the maximum tolerated dose contour for drug combination trials. Stat Med 2016;35:4924–36. https://doi.org/10.1002/sim.7095.Search in Google Scholar PubMed PubMed Central
2. Liu, S, Yuan, Y. Bayesian optimal interval designs for phase I clinical trials. J Roy Stat Soc C Appl Stat 2015;64:507–23. https://doi.org/10.1111/rssc.12089.Search in Google Scholar
3. Yuan, Y, Hess, KR, Hilsenbeck, SG, Gilbert, MR. Bayesian optimal interval designs: a simple and well-performing design for phase I oncology trials. Clin Canc Res 2016;22:4291–301. https://doi.org/10.1158/1078-0432.ccr-16-0592.Search in Google Scholar PubMed PubMed Central
4. Lin, R, Yin, G. Bayesian optimal interval design for dose finding in drug-combination trials. Stat Methods Med Res 2017;26:2155–67. https://doi.org/10.1177/0962280215594494.Search in Google Scholar PubMed
5. Wages, NA, Conaway, MR, O’Quigley, J. Continual reassessment method for partial ordering. Biometrics 2011;67:1555–63. https://doi.org/10.1111/j.1541-0420.2011.01560.x.Search in Google Scholar PubMed PubMed Central
6. Wages, NA, Conaway, MR. Specifications of a continual reassessment method design for phase I trials of combined drugs. Pharm Stat 2013;12:217–24. https://doi.org/10.1002/pst.1575.Search in Google Scholar PubMed PubMed Central
7. O’Quigley, J, Pepe, M, Fisher, L. Continual reassessment method: a practical design for phase I clinical trials in cancer. Biometrics 1990;46:33–48.10.2307/2531628Search in Google Scholar
8. Yin, G, Yuan, Y. Bayesian dose finding in oncology for drug combinations by copula regression. J Roy Stat Soc C Appl Stat 2009;58:211–24. https://doi.org/10.1111/j.1467-9876.2009.00649.x.Search in Google Scholar
9. Riviere, M-K, Yuan, Y, Dubois, F, Zohar, S. A Bayesian dose-finding design for drug combination clinical trials based on the logistic model. Pharm Stat 2014;13:247–57. https://doi.org/10.1002/pst.1621.Search in Google Scholar PubMed
10. Diniz, MA, Li, Q, Tighiouart, M. Dose finding for drug combination in early cancer phase I trials using conditional continual reassessment method. J Biometrics Biostat 2017;8:381.Search in Google Scholar
11. Riviere, M-K, Dubois, F, Zohar, S. Competing designs for drug combination in phase I dose-finding clinical trials. Stat Med 2015;34:1–12. https://doi.org/10.1002/sim.6094.Search in Google Scholar PubMed
12. Hirakawa, A, Wages, NA, Sato, H, Matsui, S. A comparative study of adaptive dose-finding designs for phase I oncology trials of combination therapies. Stat Med 2015;34:3194–213. https://doi.org/10.1002/sim.6533.Search in Google Scholar PubMed PubMed Central
13. Mockus, J. On Bayesian methods for seeking the extremum. In: Optimization techniques IFIP technical conference. Springer, Berlin, Heidelberg; 1975:400–4.10.1007/978-3-662-38527-2_55Search in Google Scholar
14. Shahriari, B, Swersky, K, Wang, Z, Adams, RP, Freitas, ND. Taking the human out of the loop: a review of Bayesian optimization. Proc IEEE 2016;104:148–75. https://doi.org/10.1109/jproc.2015.2494218.Search in Google Scholar
15. Jimenez, JL, Tighiouart, M, Gasparini, M. Cancer phase I trial design using drug combinations when a fraction of dose limiting toxicities is attributable to one or more agents. Biom J 2019;61:319–32. https://doi.org/10.1002/bimj.201700166.Search in Google Scholar PubMed PubMed Central
16. Neal, RM. Monte Carlo implementation of Gaussian process models for Bayesian regression and classification. Technical Report. Department of Statistics, University of Toronto; 1997.10.1007/978-1-4612-0745-0_3Search in Google Scholar
17. Schneider, P-I, Santiago, XG, Rockstuhl, C, Burger, S. Global optimization of complex optical structures using Bayesian optimization based on Gaussian processes. In: Proceedings of SPIE, digital optical technologies. 2017, Vol. 10335;103350O.10.1117/12.2270609Search in Google Scholar
18. Jones, DR, Schonlau, M, Welch, WJ. Efficient global optimization of expensive black-box functions. J Global Optim 1998;13:455–92. https://doi.org/10.1023/a:1008306431147.10.1023/A:1008306431147Search in Google Scholar
19. Nguyen, V, Gupta, S, Rana, S, Li, C, Venkatesh, S. Regret for expected improvement over the best-observed value and stopping condition. In: Proceedings of machine learning research 2017;77:279–94.Search in Google Scholar
20. Qin, C, Klabjan, D, Russo, D. Improving the expected improvement algorithm. In: NIPS’17: Proceedings of the 31st international conference on neural information processing systems; 2017;5387–97.Search in Google Scholar
21. Snoek, J, Larochelle, H, Adams, RP. Practical Bayesian optimization of machine learning algorithms. In: NIPS’12: Proceedings of the 25th international conference on neural information processing systems. 2012, Vol. 2:2951–9.Search in Google Scholar
22. Bull, AD. Convergence rates of efficient global optimization algorithms. J Mach Learn Res 2011;12:2879–904.Search in Google Scholar
23. Wang, K, Ivanova, A. Two-dimensional dose finding in discrete dose space. Biometrics 2005;61:217–22. https://doi.org/10.1111/j.0006-341x.2005.030540.x.Search in Google Scholar
24. Wages, NA. Identifying a maximum tolerated contour in two-dimensional dose finding. Stat Med 2017;36:242–53. https://doi.org/10.1002/sim.6918.Search in Google Scholar PubMed PubMed Central
25. Yan, F, Zhang, L, Zhou, Y, Pan, H, Liu, S, Yuan, Y. BOIN: an R package for designing single-agent and drug-combination dose-finding trials using Bayesian optimal interval designs. J Stat Software 2020;94:1–32. https://doi.org/10.18637/jss.v094.i13.Search in Google Scholar
26. Zhou, Y. Choice of designs and doses for early phase trials. Fund Clin Pharmacol 2004;18:373–8. https://doi.org/10.1111/j.1472-8206.2004.00226.x.Search in Google Scholar PubMed
27. Hirakawa, A, Sato, H, Gosho, M. Effect of design specifications in dose-finding trials for combination therapies in oncology. Pharm Stat 2016;15:531–40.10.1002/pst.1770Search in Google Scholar PubMed
28. Tighiouart, M, Rogatko, A. Dose finding with escalation with overdose control (EWOC) in cancer clinical trials. Stat Sci 2010;25:217–26. https://doi.org/10.1214/10-sts333.Search in Google Scholar
29. Fedorov, VV, Leonov, SL. Optimal design for nonlinear response models. Boca Raton, FL: CRC Press; 2013.10.1201/b15054Search in Google Scholar
Supplementary Material
The online version of this article offers supplementary material (https://doi.org/10.1515/ijb-2020-0147).
© 2021 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Research Articles
- Integrating additional knowledge into the estimation of graphical models
- Asymptotic properties of the two one-sided t-tests – new insights and the Schuirmann-constant
- Bayesian optimization design for finding a maximum tolerated dose combination in phase I clinical trials
- A Bayesian mixture model for changepoint estimation using ordinal predictors
- Power prior for borrowing the real-world data in bioequivalence test with a parallel design
- Bayesian approaches to variable selection: a comparative study from practical perspectives
- Bayesian adaptive design of early-phase clinical trials for precision medicine based on cancer biomarkers
- More than one way: exploring the capabilities of different estimation approaches to joint models for longitudinal and time-to-event outcomes
- Designing efficient randomized trials: power and sample size calculation when using semiparametric efficient estimators
- Power formulas for mixed effects models with random slope and intercept comparing rate of change across groups
- The effect of data aggregation on dispersion estimates in count data models
- A zero-inflated non-negative matrix factorization for the deconvolution of mixed signals of biological data
- Multiple scaled symmetric distributions in allometric studies
- Estimation of semi-Markov multi-state models: a comparison of the sojourn times and transition intensities approaches
- Regularized bidimensional estimation of the hazard rate
- The effect of random-effects misspecification on classification accuracy
- The area under the generalized receiver-operating characteristic curve
Articles in the same Issue
- Frontmatter
- Research Articles
- Integrating additional knowledge into the estimation of graphical models
- Asymptotic properties of the two one-sided t-tests – new insights and the Schuirmann-constant
- Bayesian optimization design for finding a maximum tolerated dose combination in phase I clinical trials
- A Bayesian mixture model for changepoint estimation using ordinal predictors
- Power prior for borrowing the real-world data in bioequivalence test with a parallel design
- Bayesian approaches to variable selection: a comparative study from practical perspectives
- Bayesian adaptive design of early-phase clinical trials for precision medicine based on cancer biomarkers
- More than one way: exploring the capabilities of different estimation approaches to joint models for longitudinal and time-to-event outcomes
- Designing efficient randomized trials: power and sample size calculation when using semiparametric efficient estimators
- Power formulas for mixed effects models with random slope and intercept comparing rate of change across groups
- The effect of data aggregation on dispersion estimates in count data models
- A zero-inflated non-negative matrix factorization for the deconvolution of mixed signals of biological data
- Multiple scaled symmetric distributions in allometric studies
- Estimation of semi-Markov multi-state models: a comparison of the sojourn times and transition intensities approaches
- Regularized bidimensional estimation of the hazard rate
- The effect of random-effects misspecification on classification accuracy
- The area under the generalized receiver-operating characteristic curve
