Randomization methods Tamuno Alfred, PhD Biostatistician DataCamp - - PowerPoint PPT Presentation

▶
randomization methods
SMART_READER_LITE
LIVE PREVIEW

Randomization methods Tamuno Alfred, PhD Biostatistician DataCamp - - PowerPoint PPT Presentation

Mar 10, 2024 168 likes •693 views

DataCamp Designing and Analyzing Clinical Trials in R DESIGNING AND ANALYZING CLINICAL TRIALS IN R Randomization methods Tamuno Alfred, PhD Biostatistician DataCamp Designing and Analyzing Clinical Trials in R DataCamp Designing and

slide-1
SLIDE 1

DataCamp Designing and Analyzing Clinical Trials in R

Randomization methods

DESIGNING AND ANALYZING CLINICAL TRIALS IN R

Tamuno Alfred, PhD

Biostatistician

slide-2
SLIDE 2

DataCamp Designing and Analyzing Clinical Trials in R

slide-3
SLIDE 3

DataCamp Designing and Analyzing Clinical Trials in R

slide-4
SLIDE 4

DataCamp Designing and Analyzing Clinical Trials in R

Simple Randomization

set.seed(888) treatment <- c("A","B") simple.list <- sample(treatment, 20, replace=TRUE) cat(simple.list,sep="\n")

slide-5
SLIDE 5

DataCamp Designing and Analyzing Clinical Trials in R

Simple Randomization

set.seed(888) treatment <- c("A","B") simple.list <- sample(treatment, 20, replace=TRUE) cat(simple.list,sep="\n") table(simple.list)

slide-6
SLIDE 6

DataCamp Designing and Analyzing Clinical Trials in R

Random Permuted Blocks

slide-7
SLIDE 7

DataCamp Designing and Analyzing Clinical Trials in R

Random Permuted Blocks

library(blockrand) set.seed(888) block.list <- blockrand(n=20, num.levels = 2,block.sizes = c(2,2)) block.list

slide-8
SLIDE 8

DataCamp Designing and Analyzing Clinical Trials in R

Random Permuted Blocks

For random block sizes

block.list2 <- blockrand(n=20, num.levels = 2,block.sizes = c(1,2))

slide-9
SLIDE 9

DataCamp Designing and Analyzing Clinical Trials in R

Stratified Randomization

Balance in patient characteristics may not be achieved in small studies Common strata include age group, geographical region and disease severity Generate a randomization list for each stratum

slide-10
SLIDE 10

DataCamp Designing and Analyzing Clinical Trials in R

Stratified Randomization

slide-11
SLIDE 11

DataCamp Designing and Analyzing Clinical Trials in R

Stratified Randomization

  • ver50.severe.list <- blockrand(n=100, num.levels = 2,

block.sizes = c(1,2,3,4), stratum='Over 50, Severe', id.prefix='O50_S', block.prefix='O50_S')

slide-12
SLIDE 12

DataCamp Designing and Analyzing Clinical Trials in R

Extensions

Three or more treatment groups Can accommodate other allocation ratios, e.g. 2:1 for active drug to placebo

slide-13
SLIDE 13

DataCamp Designing and Analyzing Clinical Trials in R

Let's practice!

DESIGNING AND ANALYZING CLINICAL TRIALS IN R

slide-14
SLIDE 14

DataCamp Designing and Analyzing Clinical Trials in R

Crossover, factorial and cluster randomized trials

DESIGNING AND ANALYZING CLINICAL TRIALS IN R

Tamuno Alfred, PhD

Biostatistician

slide-15
SLIDE 15

DataCamp Designing and Analyzing Clinical Trials in R

Crossover trials

slide-16
SLIDE 16

DataCamp Designing and Analyzing Clinical Trials in R

Crossover trials

Advantages Within-patient comparisons Eliminate between-patient variability Improved treatment effect precision Fewer patients need to be recruited

slide-17
SLIDE 17

DataCamp Designing and Analyzing Clinical Trials in R

Crossover trials

Disadvantages Chronic, stable conditions Can only evaluate short-term effects There may be order effects Carryover effects Patient dropouts impact analysis

slide-18
SLIDE 18

DataCamp Designing and Analyzing Clinical Trials in R

Factorial designs

slide-19
SLIDE 19

DataCamp Designing and Analyzing Clinical Trials in R

Factorial designs

head(recovery.trial)

slide-20
SLIDE 20

DataCamp Designing and Analyzing Clinical Trials in R

Factorial designs

head(recovery.trial) recovery.trial %>% count(A, B)

slide-21
SLIDE 21

DataCamp Designing and Analyzing Clinical Trials in R

Factorial designs

recovery.trial %>% count(A, B, recover)

slide-22
SLIDE 22

DataCamp Designing and Analyzing Clinical Trials in R

Factorial designs

recovery.trial %>% count(A, B, recover) recovery.trial %>% group_by(recover) %>% filter(A=="Yes") %>% summarise (n = n()) %>% mutate(prop = n / sum(n))

slide-23
SLIDE 23

DataCamp Designing and Analyzing Clinical Trials in R

Factorial designs

Odds of recovery in A: 257/41 Odds of recovery in not A: 229/68 Odds of recovery in B: 241/58 Odds of recovery in not B: 245/51 Odds ratio of A vs. not A: (257/41)/(229/68) = 1.86 Odds ratio of B vs. not B: (241/58)/(245/51) = 0.86

slide-24
SLIDE 24

DataCamp Designing and Analyzing Clinical Trials in R

Factorial designs

library(epitools)

  • ddsratio.wald(recovery.trial$A, recovery.trial$recover)
slide-25
SLIDE 25

DataCamp Designing and Analyzing Clinical Trials in R

Cluster randomized trials

slide-26
SLIDE 26

DataCamp Designing and Analyzing Clinical Trials in R

Cluster randomized trials

Example clusters: Schools Communities Factories Hospitals General/primary care practices Geographical regions

slide-27
SLIDE 27

DataCamp Designing and Analyzing Clinical Trials in R

Let's practice!

DESIGNING AND ANALYZING CLINICAL TRIALS IN R

slide-28
SLIDE 28

DataCamp Designing and Analyzing Clinical Trials in R

Equivalence and Non- inferiority Trials

DESIGNING AND ANALYZING CLINICAL TRIALS IN R

Tamuno Alfred, PhD

Biostatistician

slide-29
SLIDE 29

DataCamp Designing and Analyzing Clinical Trials in R

Equivalence trials

Demonstrate similar efficacy between two treatments Treatments may differ in convenience of administration, e.g. pill instead of injection Check efficacy of generic drugs

slide-30
SLIDE 30

DataCamp Designing and Analyzing Clinical Trials in R

Equivalence trials

slide-31
SLIDE 31

DataCamp Designing and Analyzing Clinical Trials in R

Equivalence trials

slide-32
SLIDE 32

DataCamp Designing and Analyzing Clinical Trials in R

Equivalence trials

slide-33
SLIDE 33

DataCamp Designing and Analyzing Clinical Trials in R

Equivalence trials

library(dplyr) library(magrittr) infection.trial %>% group_by(Treatment, Infection) %>% summarise (n = n()) %>% mutate(pct = (n / sum(n))*100)

slide-34
SLIDE 34

DataCamp Designing and Analyzing Clinical Trials in R

Equivalence trials

prop.test(table(infection.trial$Treatment,infection.trial$Infection), alternative = "less", conf.level = 0.95, correct=FALSE) prop.test(table(infection.trial$Treatment,infection.trial$Infection), alternative = "greater", conf.level = 0.95, correct=FALSE)

slide-35
SLIDE 35

DataCamp Designing and Analyzing Clinical Trials in R

Equivalence trials

Two-sided 90% confidence interval excludes the delta of 12%, therefore can claim equivalence at the 5% level.

prop.test(table(infection.trial$Treatment,infection.trial$Infection), alternative = "two.sided", conf.level = 0.90, correct=FALSE)

slide-36
SLIDE 36

DataCamp Designing and Analyzing Clinical Trials in R

Non-inferiority trials

slide-37
SLIDE 37

DataCamp Designing and Analyzing Clinical Trials in R

Non-inferiority trials

One-sided 97.5% confidence interval includes the margin of 12%, therefore cannot claim non-inferiority at the 2.5% level.

prop.test(table(infection.trial$Treatment,infection.trial$Infection), alternative = "less", conf.level = 0.975, correct=FALSE)

slide-38
SLIDE 38

DataCamp Designing and Analyzing Clinical Trials in R

Caution

There are various recommendations so clearly state: Whether using one or two-sided confidence intervals Significance level Lack of superiority does not imply equivalence

slide-39
SLIDE 39

DataCamp Designing and Analyzing Clinical Trials in R

Let's practice!

DESIGNING AND ANALYZING CLINICAL TRIALS IN R

slide-40
SLIDE 40

DataCamp Designing and Analyzing Clinical Trials in R

Bioequivalence trials

DESIGNING AND ANALYZING CLINICAL TRIALS IN R

Tamuno Alfred, PhD

Biostatistician

slide-41
SLIDE 41

DataCamp Designing and Analyzing Clinical Trials in R

Bioequivalence trials

Conducted to assess whether blood concentration profiles for two formulations of a drug are similar

slide-42
SLIDE 42

DataCamp Designing and Analyzing Clinical Trials in R

Pharmacokinetics

Pharmacokinetics (PK): The study of what the body does to a drug. ADME: Absorption Distribution Metabolism Excretion

slide-43
SLIDE 43

DataCamp Designing and Analyzing Clinical Trials in R

Pharmacokinetic profiles

slide-44
SLIDE 44

DataCamp Designing and Analyzing Clinical Trials in R

Pharmacokinetic profiles

slide-45
SLIDE 45

DataCamp Designing and Analyzing Clinical Trials in R

Pharmacokinetic profiles

Crossover designs are often used

slide-46
SLIDE 46

DataCamp Designing and Analyzing Clinical Trials in R

Pharmacokinetic profiles

AUC using the linear trapezoidal method

slide-47
SLIDE 47

DataCamp Designing and Analyzing Clinical Trials in R

Pharmacokinetic profiles

AUC using the linear trapezoidal method

library(PKNCA) pk.calc.auc(PKData$plasma.conc.n, PKData$rel.time, interval=c(0.25, 12), method="linear")

slide-48
SLIDE 48

DataCamp Designing and Analyzing Clinical Trials in R

Assessing bioequivalence

90% confidence interval of the ratios should be contained within 0.8 to 1.25

slide-49
SLIDE 49

DataCamp Designing and Analyzing Clinical Trials in R

Assessing bioequivalence

slide-50
SLIDE 50

DataCamp Designing and Analyzing Clinical Trials in R

Let's practice!

DESIGNING AND ANALYZING CLINICAL TRIALS IN R

Core Hubs:
All Converters PDF Hub Video Hub Audio Hub Image Hub File Compressor