1. Designs for Clinical Trials

2. Chapter 5 Reading Instructions 5.1: Introduction 5.2: Parallel Group Designs (read) 5.3: Cluster Randomized Designs (less important) 5.4: Crossover Designs (read+copies) 5.5: Titration Designs (read) 5.6: Enrichment Designs (less important) 5.7: Group Sequential Designs (read include 10.6) 5.8: Placebo-Challenging Designs (less important) 5.9: Blinded Reader Designs (less important) 5.10: Discussion

3. Design issues ?

4. Objective Research question Design, Variables Control Ethics Feasibility Cost Statistics Variability Confounding Statistical optimality not enough! Use simulation models!

5. Parallel Group Designs R Test Control 1 Control 2 Easy to implement Accepted Easy to analyse Good for acute conditions

6. Where does the varation go? 8 week blood pressure Placebo Drug X Anything we can explainUnexplained

7. Between and within subject variation Baseline 8 weeks Placebo Drug X DBP mmHg Female Male

8. What can be done? Stratify: More observations per subject: Run in period: Randomize by baseline covariate and put the covariate in the model. Baseline More than 1 obsservation per treatment Ensure complience, diagnosis

9. Parallell group design with baseline R Test Control 1 Control 2 Baseline8 weeks Compare bloodpressure for three treatments, one test and two control. Model: Observation Treatment Subject Treatment effect Subject effect Random error

10. Change from baseline The variance of an 8 week value is Change from baseline The variance of change from baseline is Usually

11. Baseline as covariate R Test Control 1 Control 2 Baseline8 weeks Subject Treatment Treatment effect Random error Baseline value Model:

12. Baseline as covariate x=baseline Model:

13. Crossover studies All subject gets more that one treatment Comparisons within subject R Wash out A AB B Period 1Period 2 Sequence 1 Sequence 2 AB BA Within subject comparison Reduced sample size Good for cronic conditions Good for pharmaceutical studies

14. Model for a cross over study Obs=Period+sequence+subject+treament+carryover+error

15. 2 by 2 Crossover design Effect of treatment and carry over can not be separated!

16. Matrix formulation Model: Sum to zero: Matrix formulation

17. Parameter estimate: Estimates independent and

18. Alternatives to 2*2 Compare AB BA AB BA B A to Same model but with 3 periods and a carry over effect

19. Parameters of the AAB, BBA design

20. Matrix again Effect of treatment and carry over can be estimated independently!

21. Other 2 sequence 3 period designs AB BA B A AA BB B A AB BA A B AA BB A B 1 2 3 4 12341234 0.190.750.25N/A 0.251.001.00N/A 0.00.870.50N/A

22. Comparing the AB, BA and the ABB, BBA designs AB BA B A AB BA Can’t include carry over Carry over estimable 2 treatments per subject3 treatments per subject Shorter duration Longer duration Excercise: Find the best 2 treatment 4 period design

23. More than 2 treatments Tools of the trade: AB BC C A CA AC B B BA CB C A AB BD C A D C CA DC D B B A Investigate Define the model AB BC CA AC BC CB Watch out for drop outs!

24. Titration Designs Increasing dose panels (Phase I): SAD (Single Ascending Dose) MAD (Multiple Ascending Dose) Primary Objective: Establish Safety and Tolerability Estimate Pharmaco Kinetic (PK) profile Increasing dose panelse (Phase II): Dose - response

25. Titration Designs (SAD, MAD) X on drug Y on Placebo Dose: Z 1 mg X on drug Y on Placebo Dose: Z 2 mg X on drug Y on Placebo Dose: Z k mg Stop if any signs of safety issues VERY careful with first group!

26. Titration Designs Which dose levels? Start dose based on exposure in animal models. Stop dose based on toxdata from animal models. Doses often equidistant on log scale. Which subject? Healty volunteers Young Male How many subjects? Rarely any formal power calculation. Often 2 on placebo and 6-8 on drug.

27. Titration Designs Not mandatory to have new subject for each group. Gr. 1Gr. 2Gr. 3Gr. 1Gr. 2Gr. 4 X 1 mgX 2 mgX 3 mgX 4 mgX 5 mgX Y mg 12+2 Slighty larger groups to have sufficiently many exposed. Dose in fourth group depends on results so far. Possible to estimate within subject variation.

28. Factorial design Evaluation of a fixed combination of drug A and drug B A placebo B placebo A active B placebo A placebo B active A active B active The U.S. FDA’s policy (21 CFR 300.50) regarding the use of a fixed-dose combination The agency requires: Each component must make a contribution to the claimed effect of the combination. Implication: At specific component doses, the combination must be superior to its components at the same respective doses P BAB A

29. Factorial design Usually the fixed-dose of either drug under study has been approved for an indication for treating a disease. Nonetheless, it is desirable to include placebo (P) to examine the sensitivity of either drug give alone at that fixed-dose (comparison of AB with P may be necessary in some situations). Assume that the same efficacy variable is used for studying both drugs (using different endpoints can be considered and needs more thoughts).

30. Factorial design Sample mean Y i ∼ N( μ i, σ2/n ), i = A, B, AB n = sample size per treatment group (balanced design is assumed for simplicity). H0: μ AB ≤ μ A or μ AB ≤ μ B H1: μ AB > μ A and μ AB > μ B j=A, B Min test and critical region:

31. Group sequential designs A large study is a a huge investment, $, ethics What if the drug doesn’t work or is much better than expected? Could we take an early look at data and stop the study is it look good (or too bad)?

32. Repeated significance test Let: Test: Test statistic: ForIf Stop, reject otherwise Continue to group IfStop, reject otherwise stop accept

33. True type I error rate Repeat testing until H 0 rejected

34. Pocock’s test Suppose we want to test the null hypothesis 5 times using the same critical value each time and keep the overall significance level at 5% ForIf Stop, reject otherwise Continue to group IfStop, reject otherwise stop accept ChooseSuch that After group K

35. Pocock’s test All tests has the same nominal significance level A group sequential test with 5 interrim tests has level

36. Pocock’s test 2.413 -2.413

37. O’Brian & Flemmings test ForIf Stop, reject otherwise Continue to group If Stop, reject otherwise stop accept ChooseSuch that After group K : : Increasing nominal significance levels

38. O’Brian & Flemmings test Critical values and nominal significance levels for a O’Brian Flemming test with 5 interrim tests. Rather close to 5%

39. O’Brian & Flemmings test 0.000005 0.0013 0.0084 0.0225 0.0413

40. Comparing Pocock and O’Brian Flemming

42. Group Sequential Designs Efficiency Gain (Decreasing marginal benefit) Establish efficacy earlier Detect safety problems earlier Smaller safety data base Complex to run Need to live up to stopping rules! Pros: Cons:

43. Selection of a design The design of a clinical study is influenced by: Number of treatments to be compared Characteristics of the treatment Characteristics of the disease/condition Study objectives Inter and intra subject variability Duration of the study Drop out rates

44. Backup Back up: