1
|
Yan Z, Yang M. Statistical considerations in model-based dose finding for binary responses under model uncertainty. Stat Med 2024; 43:2472-2485. [PMID: 38605556 DOI: 10.1002/sim.10082] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2023] [Revised: 02/21/2024] [Accepted: 04/01/2024] [Indexed: 04/13/2024]
Abstract
The statistical methodology for model-based dose finding under model uncertainty has attracted increasing attention in recent years. While the underlying principles are simple and easy to understand, developing and implementing an efficient approach for binary responses can be a formidable task in practice. Motivated by the statistical challenges encountered in a phase II dose finding study, we explore several key design and analysis issues related to the hybrid testing-modeling approaches for binary responses. The issues include candidate model selection and specifications, optimal design and efficient sample size allocations, and, notably, the methods for dose-response testing and estimation. Specifically, we consider a class of generalized linear models suited for the candidate set and establish D-optimal designs for these models. Additionally, we propose using permutation-based tests for dose-response testing to avoid asymptotic normality assumptions typically required for contrast-based tests. We perform trial simulations to enhance our understanding of these issues.
Collapse
Affiliation(s)
- Zhiwu Yan
- Biostatistics Department, 89bio, Inc., San Francisco, California, USA
| | - Min Yang
- Department of Mathematics, Statistics, and Computer Science, University of Illinois at Chicago, Chicago, Illinois
| |
Collapse
|
2
|
Chen Y, Fries M, Leonov S. Longitudinal model for a dose-finding study for a rare disease treatment. Stat Pap (Berl) 2023. [DOI: 10.1007/s00362-023-01424-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/31/2023]
|
3
|
Optimal designs for semi-parametric dose-response models under random contamination. Comput Stat Data Anal 2023. [DOI: 10.1016/j.csda.2022.107615] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
4
|
Heidari M, Manju MA, IJzerman-Boon PC, van den Heuvel ER. D-Optimal Designs for the Mitscherlich Non-Linear Regression Function. MATHEMATICAL METHODS OF STATISTICS 2022. [DOI: 10.3103/s1066530722010033] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
5
|
Flournoy N, May C, Tommasi C. The effects of adaptation on maximum likelihood inference for nonlinear models with normal errors. J Stat Plan Inference 2021. [DOI: 10.1016/j.jspi.2021.02.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/22/2022]
|
6
|
An R-shiny application to calculate optimal designs for single substance and interaction trials in dose response experiments. Toxicol Lett 2020; 337:18-27. [PMID: 33232777 DOI: 10.1016/j.toxlet.2020.11.018] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2020] [Revised: 10/20/2020] [Accepted: 11/18/2020] [Indexed: 11/21/2022]
Abstract
BACKGROUND AND OBJECTIVE Optimal experimental design theory proposes choosing specific settings in experimental trials in order to maximize the precision of the resulting parameter estimates. In dose response experiments, this corresponds to choosing the optimal dose levels for every available observation, and can be applied both to singular dose-response relationships and to interaction experiments where two substances are given simultaneously at several different mixture ratios ("ray designs"). While the theory of experimental design for this situation is well developed, the mathematical complexity prevents widespread use in practical applications. A simple to use application making the theory accessible to practitioners is thus very desirable. METHODS Results from established optimal experimental design theory are applied to dose response applications, focusing on log-logistic and Weibull class dose response functions. Suitable optimal design algorithms to solve these problems are implemented into an R-shiny based online application. RESULTS The application provides an interface to easily calculate D-optimal designs not only for singular dose experiments, but also for interaction trials with several combination rays of substances. Furthermore, the app also allows evaluating the efficiency of existing candidate designs, and finally allows construction of designs which perform robustly under different assumptions in regard to the true parameters.
Collapse
|
7
|
Sverdlov O, Ryeznik Y, Wong WK. On Optimal Designs for Clinical Trials: An Updated Review. JOURNAL OF STATISTICAL THEORY AND PRACTICE 2019. [DOI: 10.1007/s42519-019-0073-4] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
8
|
Möllenhoff K, Bretz F, Dette H. Equivalence of regression curves sharing common parameters. Biometrics 2019; 76:518-529. [DOI: 10.1111/biom.13149] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2019] [Accepted: 09/04/2019] [Indexed: 11/28/2022]
Affiliation(s)
| | - Frank Bretz
- Novartis Pharma AGBasel Switzerland
- Center for Medical Statistics, Informatics and Intelligent SystemsMedical University of Vienna Vienna Austria
| | - Holger Dette
- Department of MathematicsRuhr‐Universität Bochum Bochum Germany
| |
Collapse
|
9
|
Yu J, Kong X, Ai M, Tsui KL. Optimal designs for dose–response models with linear effects of covariates. Comput Stat Data Anal 2018. [DOI: 10.1016/j.csda.2018.05.017] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
10
|
Zhai Y, Fang Z. Locally Optimal Designs for Some Dose-Response Models With Continuous Endpoints. COMMUN STAT-THEOR M 2018; 47:3803-3819. [PMID: 30250356 DOI: 10.1080/03610926.2017.1361996] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Abstract
We consider the problem of constructing static (or non-sequential), approximate optimal designs for a class of dose response models with continuous outcomes. We obtain conditions for a design being D-optimal or c-optimal. The designs are locally optimal in that they depend on the model parameters. The efficiency studies show that these designs have high efficiency when the mis-specification of the initial values of model parameters is not severe. A case study indicates that using an optimal design may result in a significant saving of resources.
Collapse
Affiliation(s)
- Yi Zhai
- Biostatistics Program, Louisiana State University Health Sciences Center, New Orleans, Louisiana, 70112, USA
| | - Zhide Fang
- Biostatistics Program, Louisiana State University Health Sciences Center, New Orleans, Louisiana, 70112, USA
| |
Collapse
|
11
|
Feller C, Schorning K, Dette H, Bermann G, Bornkamp B. Optimal designs for dose response curves with common parameters. Ann Stat 2017. [DOI: 10.1214/16-aos1520] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
12
|
Masoudi E, Holling H, Wong WK. Application of imperialist competitive algorithm to find minimax and standardized maximin optimal designs. Comput Stat Data Anal 2017. [DOI: 10.1016/j.csda.2016.06.014] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
13
|
Thomas N, Roy D. Analysis of Clinical Dose–Response in Small-Molecule Drug Development: 2009–2014. Stat Biopharm Res 2017. [DOI: 10.1080/19466315.2016.1256229] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
Affiliation(s)
| | - Dooti Roy
- Boehringer-Ingelheim, Ridgefield, CT
| |
Collapse
|
14
|
Hampson LV, Fisch R, Van LM, Jaki T. Asymmetric inner wedge group sequential tests with applications to verifying whether effective drug concentrations are similar in adults and children. Stat Med 2017; 36:426-441. [PMID: 27859519 DOI: 10.1002/sim.7154] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2015] [Revised: 09/19/2016] [Accepted: 10/03/2016] [Indexed: 11/08/2022]
Abstract
Extrapolating from information available on one patient group to support conclusions about another is common in clinical research. For example, the findings of clinical trials, often conducted in highly selective patient cohorts, are routinely extrapolated to wider populations by policy makers. Meanwhile, the results of adult trials may be used to support conclusions about the effects of a medicine in children. For example, if the effective concentration of a drug can be assumed to be similar in adults and children, an appropriate paediatric dosing rule may be found by 'bridging', that is, by matching the adult effective concentration. However, this strategy may result in children receiving an ineffective or hazardous dose if, in fact, effective concentrations differ between adults and children. When there is uncertainty about the equality of effective concentrations, some pharmacokinetic-pharmacodynamic data may be needed in children to verify that differences are small. In this paper, we derive optimal group sequential tests that can be used to verify this assumption efficiently. Asymmetric inner wedge tests are constructed that permit early stopping to accept or reject an assumption of similar effective drug concentrations in adults and children. Asymmetry arises because the consequences of under- and over-dosing may differ. We show how confidence intervals can be obtained on termination of these tests and illustrate the small sample operating characteristics of designs using simulation. Copyright © 2016 John Wiley & Sons, Ltd.
Collapse
Affiliation(s)
- Lisa V Hampson
- Medical and Pharmaceutical Statistics Research Unit, Department of Mathematics and Statistics, Lancaster University, Lancaster, LA1 4YF, U.K
| | - Roland Fisch
- Biostatistical Science and Pharmacometrics, Novartis Pharma AG, Basel, CH-4002, Switzerland
| | - Linh M Van
- Biostatistical Science and Pharmacometrics, Novartis Pharmaceutical, Cambridge, 02139, MA, U.S.A
| | - Thomas Jaki
- Medical and Pharmaceutical Statistics Research Unit, Department of Mathematics and Statistics, Lancaster University, Lancaster, LA1 4YF, U.K
| |
Collapse
|
15
|
Kao LJ, Chen TY, Chang KC. Efficient Mixture Design Fitting Quadratic Surface with Quantile Responses Using First-degree Polynomial. COMMUN STAT-SIMUL C 2016. [DOI: 10.1080/03610918.2013.833228] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
16
|
|
17
|
Magnusdottir BT. Optimal designs for a multiresponse Emax model and efficient parameter estimation. Biom J 2015; 58:518-34. [DOI: 10.1002/bimj.201400203] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2014] [Revised: 07/28/2015] [Accepted: 08/20/2015] [Indexed: 11/06/2022]
|
18
|
Dette H, Titoff S, Volgushev S, Bretz F. Dose response signal detection under model uncertainty. Biometrics 2015; 71:996-1008. [DOI: 10.1111/biom.12357] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2014] [Revised: 05/01/2015] [Accepted: 05/01/2015] [Indexed: 12/15/2022]
Affiliation(s)
- Holger Dette
- Ruhr-Universität Bochum; Fakultät für Mathematik; 44780 Bochum Germany
| | - Stefanie Titoff
- Continentale Krankenversicherung a.G. Ruhrallee 92; 44139 Dortmund Germany
| | | | - Frank Bretz
- Novartis Pharma AG, Lichtstrasse 35, 4002 Basel; Switzerland and Shanghai University of Finance and Economics; People's Republic of China
| |
Collapse
|
19
|
Dette H, Kiss C. Optimal Designs for Rational Regression Models. JOURNAL OF STATISTICAL THEORY AND PRACTICE 2015. [DOI: 10.1080/15598608.2014.910480] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
20
|
Hu L, Yang M, Stufken J. Saturated locally optimal designs under differentiable optimality criteria. Ann Stat 2015. [DOI: 10.1214/14-aos1263] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
21
|
Kim Y, Jang DH, Yi S. The Maximin Robust Design for the Uncertainty of Parameters of Michaelis-Menten Model. KOREAN JOURNAL OF APPLIED STATISTICS 2014. [DOI: 10.5351/kjas.2014.27.7.1269] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
|
22
|
Kim Y, Jang DH, Yi S. Some Examples of Constrained Optimal Experimental Design for Nonlinear Models. KOREAN JOURNAL OF APPLIED STATISTICS 2014. [DOI: 10.5351/kjas.2014.27.7.1151] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
|
23
|
Sverdlov O, Wong WK. Novel Statistical Designs for Phase I/II and Phase II Clinical Trials With Dose-Finding Objectives. Ther Innov Regul Sci 2014; 48:601-612. [DOI: 10.1177/2168479014523765] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
|
24
|
Thomas N, Sweeney K, Somayaji V. Meta-Analysis of Clinical Dose–Response in a Large Drug Development Portfolio. Stat Biopharm Res 2014. [DOI: 10.1080/19466315.2014.924876] [Citation(s) in RCA: 21] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
25
|
Burghaus I, Dette H. Optimal designs for nonlinear regression models with respect to non-informative priors. J Stat Plan Inference 2014. [DOI: 10.1016/j.jspi.2014.05.009] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
26
|
Lange MR, Schmidli H. Optimal design of clinical trials with biologics using dose-time-response models. Stat Med 2014; 33:5249-64. [DOI: 10.1002/sim.6299] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2013] [Revised: 07/31/2014] [Accepted: 08/20/2014] [Indexed: 12/23/2022]
Affiliation(s)
- Markus R. Lange
- Statistical Methodology, Development; Novartis Pharma AG; Basel Switzerland
- Hannover Medical School; Institute for Biometry; Hannover Germany
| | - Heinz Schmidli
- Statistical Methodology, Development; Novartis Pharma AG; Basel Switzerland
| |
Collapse
|
27
|
Dette H, Müller WG. Optimal Designs for Regression Models With a Constant Coefficient of Variation. JOURNAL OF STATISTICAL THEORY AND PRACTICE 2013. [DOI: 10.1080/15598608.2013.781833] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/27/2022]
|
28
|
Dette H, Kiss C, Benda N, Bretz F. Optimal designs for dose finding studies with an active control. J R Stat Soc Series B Stat Methodol 2013. [DOI: 10.1111/rssb.12030] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Affiliation(s)
| | | | - Norbert Benda
- Federal Institute for Drugs and Medical Devices; Bonn Germany
| | - Frank Bretz
- Novartis Pharma; Basel Switzerland
- and Shanghai University of Finance and Economics; People's Republic of China
| |
Collapse
|
29
|
|
30
|
Dette H, Bornkamp B, Bretz F. On the efficiency of two-stage response-adaptive designs. Stat Med 2012; 32:1646-60. [DOI: 10.1002/sim.5555] [Citation(s) in RCA: 17] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2011] [Accepted: 07/03/2012] [Indexed: 11/08/2022]
Affiliation(s)
| | - Björn Bornkamp
- Novartis Pharma AG; Lichtstrasse 35; 4002 Basel; Switzerland
| | - Frank Bretz
- Novartis Pharma AG; Lichtstrasse 35; 4002 Basel; Switzerland
| |
Collapse
|
31
|
Affiliation(s)
- Holger Dette
- a Ruhr-Universität Bochum , 44780 , Bochum , Germany
| | - Matthias Trampisch
- b Department of Mathematics , Ruhr-Universität Bochum , 44780 , Bochum , Germany
| |
Collapse
|
32
|
Bartroff J. A new characterization of Elfving's method for high dimensional computation. J Stat Plan Inference 2012. [DOI: 10.1016/j.jspi.2011.10.009] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
33
|
Bornkamp B, Bretz F, Dette H, Pinheiro J. Response-adaptive dose-finding under model uncertainty. Ann Appl Stat 2011. [DOI: 10.1214/10-aoas445] [Citation(s) in RCA: 34] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
34
|
Bretz F, Dette H, Pinheiro JC. Practical considerations for optimal designs in clinical dose finding studies. Stat Med 2010; 29:731-42. [PMID: 20213708 DOI: 10.1002/sim.3802] [Citation(s) in RCA: 52] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Abstract
A key objective in the clinical development of a medicinal drug is the determination of an adequate dose level and, more broadly, the characterization of its dose response relationship. If the dose is set too high, safety and tolerability problems are likely to result, while selecting too low a dose makes it difficult to establish adequate efficacy in the confirmatory phase, possibly leading to a failed program. Hence, dose finding studies are of critical importance in drug development and need to be planned carefully. In this paper, we focus on practical considerations for establishing efficient study designs to estimate relevant target doses. We consider optimal designs for estimating both the minimum effective dose and the dose achieving a certain percentage of the maximum treatment effect. These designs are compared with D-optimal designs for a given dose response model. Extensions to robust designs accounting for model uncertainty are also discussed. A case study is used to motivate and illustrate the methods from this paper.
Collapse
Affiliation(s)
- Frank Bretz
- Novartis Pharma AG, CH-4002 Basel, Switzerland.
| | | | | |
Collapse
|