2. “ A clinical trial is a research activity that involves
administration of a test treatment to some experimental
unit in order to evaluate the treatment” by Meinert(1986).
Experimental unit: It is referred as the subject from the target population
under the study.
Treatment: It can be new drug with increased pharmacokinetic activity,
specificity or new therapy or new diagnostic techniques or new surgical
methods.
Evaluation: A clinical trial is done on the basis of effectiveness and safety of
the test treatment. It ensures quality of life to the target population. It also
keeps maintains the pharmacoeconimic status of the pharma companies.
3. Pre clinical
phase
Clinical
phase
Launc
h
Life cycle of clinical trial :
Rational based drug design
Chemical synthesis and
purification
Animal trials
Preliminary drug action, toxicity
and pharmacokinetic information
Phase I
• <100 healthy human volunteers
• Pharmacokinetic and pharmacodynamics study
• Determine safe drug dosage and metabolic path
followed by drug
Phase
II
• <500 patients
•Evaluate effectiveness and look
for side effects
Phase
III
•<4000 patients
•Confirm effectiveness, monitor
adverse effect for long term
•Check point before drug approval
Phase
IV
After launch 10,000-30,000
patients
Additional post-marketing test for
drug risk, benefit and optimal use
4. CONTENTS
TECHNIQUES IN CLINICAL DESIGN
CLINICAL DESIGN
TYPES OF CLINICAL TRIAL
ANALYSIS
CASE STUDY
5. TECHNIQUES USED IN
CLINICAL DESIGN:
RANDOMIZATION
Controlling bias and variability in clinical trials is very much important to ensure the
integrity of clinical trials. Thus, few techniques were introduced in clinical designs to
minimize these.
o The principle of randomization was implemented in clinical trial in
1948 by British Medial Research Council under Sir Austin Bradford
Hill.
o During subsequent analysis of the trial data, it provides a sound
statistical basis for the quantitative evaluation of the evidence
relating to treatment effects.
o It also tends to produce treatment groups in which the distribution of
prognostic factors, known and unknown, are similar.
o Some ethical considerations may also arise as some subjects
receive the treatment under study while the remaining receive the
standard treatment or the placebo.
o Randomization consist of
- random selection of subjects from the
targeted patient population
- random assignment of patients in order to
study the medicines
6. There are different randomization procedures like
1. Simple randomization
2. Restricted randomization
3. Adaptive randomization
Simple randomization:
• It is a process of drawing a sample from a population whereby the sample
participants are not known in advance.
• A simple random sample of size k is a sample determined by chance whereby
each individual in the population has the same chance of being selected.
ex- Consider tossing a coin for each subject that enters a trial, such as
Head= Active and tail= Placebo
• However, it shows imbalance randomization with lowering statistical power
when the sample size is less
Restricted randomization:
Restricted
randomization
Blocking
Unequal
allocation
Stratified
randomization
contd. TECHNIQUES USED IN
CLINICAL DESIGN:
7. o Blocking
contd. TECHNIQUES USED
IN CLINICAL DESIGN:
Block randomization ensures equal treatment numbers at certain equally spaced
points in the sequence of patient assignments.
Each random digit specifies what treatment is given to the next block of patients
o Unequal Allocation
Sometimes more participants are kept in one group compared to other.
It leads to minimize cost
Data can give a good statistical inference
It can be used for learning purpose.
o Stratified randomization
It refers to the situation in which strata are constructed based on values of
prognostic variables and a randomization scheme is performed separately within
each stratum.
The objective of stratified randomization is to ensure balance of the treatment
groups with respect to the various combinations of the prognostic variables.
Ex- if there are two prognostic variables, age and gender, such that two strata
are constructed:Gender, Age Treatment A Treatment B
Male, age <18 12 12
Male, age ≥18 13 12
Female, age <18 17 16
Female, age ≥18 35 37
8. contd. TECHNIQUES USED
IN CLINICAL DESIGN:
Adaptive randomization:
• Stratification is not applicable where too many prognostic factors are present in
the data here comes the Adaptive randomization.
• It refers to any scheme in which the probability of treatment assignment
changes according to assigned treatments of patients already in the trial.
• Randomization is adjusted dynamically to achieve the balance.
ex- if there is one “A” ball and one “B” ball in an urn and the objective of the
trial
is equal allocation between treatments A and B. Suppose that an “A” ball is blindly
selected, so that the first patient is assigned treatment A. Then the original “A” ball
and another “B” are placed in the urn so that the second patient has a 1/3 chance
of receiving treatment A and a 2/3 chance of receiving treatment b. At any point in
time with nA, “A ” balls and nB “B” balls in the urn, the probability of being
treatment A is nA/(nA+nB).
9. RANDOMIZED CLINICAL TRIAL
In most clinical trials the group of subjects (or sample) who participate is just a small portion of a
heterogeneous patient population with the intended disease.
A well-controlled randomized clinical trial is necessary to provide an unbiased and valid
assessment of the study medicine.
A well-controlled randomized trial is conducted under well-controlled experimental conditions,
usually it varies from a physician’s best clinical practice.
Therefore it is a concern whether the clinical results observed from the well-controlled
randomized clinical trial can be applied on the patient population with the disease.
Feasibility and generalization of well-controlled randomized trials are important issue in public
health.
COMPLICATIONS IN RCT
RCT
NON
COMPILANCE
MISSING
OUTCOMES
10. contd. RCT
One potential solution to this problem is a statistical concept called Intention-To
Treat(ITT) analysis.
ITT analysis includes every subject who is randomized according to randomized
treatment assignment.
It ignores noncompliance, protocol deviations, withdrawal and anything that
happens after randomization.
Principle: “Once Randomized, Always Randomized”
11. contd. TECHNIQUES USED
IN CLINICAL DESIGN:
BLINDING/MASKING
• Blinding is defined as an experimental condition in which various groups of the
individuals involved with the trial are withheld from the knowledge of the treatments
assigned to patients and corresponding relevant information.
• The purpose of blinding is to eliminate bias in subjective judgment due to
knowledge of the treatment.
• Since the subjective and judgmental bias is directly or indirectly related to
treatment, it can seriously distort statistical inference on the treatment effect.
• Therefore, it is important to remove such type of bias.
BLINDING
OPEN
LABEL
SINGLE
BLINDING
DOUBLE
BLINDING
TRIPLE
BLINDIN
G
12. contd. TECHNIQUES USED
IN CLINICAL DESIGN:
o Open label:
• In this technique no blinding is employed.
• Ethical consideration is always an important factor, and thus a trial study is
conducted in an open label fashion.
Ex- phase I dose-escalating studies for determination of the maximum tolerable
dose of drugs in treating terminally ill cancer patients are usually open labeled,
evaluation of the effectiveness and safety of new surgical procedure is also
open labeled
o Single blinding:
• It is a technique in which either the patient or
investigator is unaware of the assigned treatment
• As compared with open-label trials, single-blind
studies offer a certain degree of control and the
assurance of the validity of clinical trials.
• However, it retains the chances of bias as the
investigator is mostly exposed to the treatment
assigned to the subject.
13. contd. TECHNIQUES USED
IN CLINICAL DESIGN:
o Double blinding:
• A double-blind trial is a trial in which
neither the patients nor the investigator is
aware of patient’s treatment assignment.
• This is done to minimize the bias
compared to single blinding.
o Triple blinding:
• A triple-blind study with respect to blindness can
provide the highest degree for the validity of a
controlled clinical trial.
• Hence it provides the most conclusive unbiased
evidence for the evaluation of the effectiveness
and safety of the therapeutic intervention under
investigation.
Carefully chosen study design with appropriate
randomization method
A proper control should be given according to the
study
A sufficient statistical power should come
Patient compliance should be cared
Appropriate statistical methods for data analysis
14. STUDY DESIGN
Primary objective
Secondary
objective
Objective All medical questions should be formulated
Based on same subject number, events, duration of events, check point of
each event, end point of each event and evaluation should be done
It is achieved by drawing a comparison between new drug/therapy and
current drug/therapy
It can be demonstrated by using parallel or randomized group trial
It decides the conclusion of clinical trial
It shows survival rate, response time, response rate, dosages and
toxicity
The selection of patients for trials should be done according to the study. They
should actually represent the targeted population
Each trial should be unbiased with minimum or no variability
15. contd. study design
PARALLEL GROUP DESIGN:
It is a complete randomized design in which subjects are distributed
randomly within two or more groups and each group should receive only
one type of treatment parallel to the other groups
Each group should contain equal number of subjects
Most commonly used design
Before a patient undergo any clinical trial he must undergo placebo
effect(Run in), so that the investigator can have baseline data to compare
with the end of clinical trial for analysis of the research study
R
U
N
I
N
16. contd. study design
CROSSOVER DESIGN:
It is a modified randomized block design in which each design in which each block
receives more than one treatment at different dosing periods.
A block can be a patient or a group of patients.
Patients in each group receive different sequences of treatment
*Each block under the investigation should receive all treatment.
It is not necessary that the number of treatments in each sequence be greater than or equal
to the number of treatments to be compared.
It allows a within patient comparison between treatments, since each patient serves as his
or her own treatment.
It removes the interpatient variability from the comparison between treatments
With a proper randomization of patients to the treatment sequences, it provides the best
unbiased estimates for differences between treatments
Applicable Objective measures and interpretable data for both efficacy and
safety are obtained
Chronic disease are under study
Relatively short treatment periods are considered
Baseline and washout periods are feasible
Patient
s
Block
A
Rando
mization
Block
B
PERIOD
W
A
S
H
O
U
T
BLOCK
A
BLOCK B
TEST CONTROL
CONTR
OL
TEST (ex- two period cross over design)
17. contd. study design
TITRATION
DESIGN:For phase I safety and tolerance studies, Rodda et al. (1998) classify traditional
designs as follows:
1. Rising single-dose design
2. Rising single-dose crossover design
3. Alternative- panel rising single-dose design
4. Alternative-panel rising single-dose crossover design
5. Parallel-panel rising multiple-dose design
6. Alternative-panel rising multiple-dose design
CLUSTER RANDOMIZED
DESIGNS: The randomization unit is same as the analysis unit as the experimental unit for
statistical unit(Fisher;1947).
It needs minimum sample size and generates highest power, hence it becomes
most efficient
Units such as patients of a disease, athletes, hospitals , communities etc. act
as cluster
Randomization is done at cluster level instead of subject level
However, clinical trial needs inference at subject level, hence, the standard
sample size calculation and data analysis considering subject as analysis unit is
not appropriate
It is important for the analysis of intracluster, intercluster and ICC variations.
18. contd. study design
FACTORIAL
DESIGN:• Two or more treatments are evaluated simultaneously through the use of
varying combinations of the treatments.
• The simplest example is the 2×2 factorial design in which subjects are randomly
allocated to one of the four possible combinations of two treatments, A and B
say.
These are: A alone; B alone; both A and B; neither A nor B.
• In many cases this design is used for the specific purpose of examining the
interaction of A and B.
• The statistical test of interaction may lack power to detect an interaction if the
sample size was calculated based on the test for main effects.
• This consideration is important when this design is used for examining the joint
effects of A and B, in particular, if the treatments are likely to be used together
20. ANALYSIS
When designing a clinical trial the principle features of the eventual statistical
analysis of the data should be described in the statistical section of the
protocol. This section should include all the principle features of the proposed
confirmatory analysis of the primary variable(s) and the way in which analysis
problems will be handled.
The important considerations for Analysis of the study data are as follows:
Analysis sets: If all subjects randomized into a clinical trial satisfied all entry
criteria, followed all trial procedures perfectly with no losses to follow-up, and
provided complete data records, then the set of subjects to be included in the
analysis would be self-evident. The design and conduct of a trial should aim to
approach this ideal as closely as possible, but, in practice, it is doubtful if it can ever
be fully achieved. Hence, the statistical section of the protocol should address
anticipated problems prospectively in terms of how these affect the subjects and
data to be analyzed.
Missing Values and Outliers : Missing values represent a potential source of bias
in a clinical trial. Hence, every effort should be undertaken to fulfill all the
requirements of the protocol concerning the collection and management of data. In
reality, however, there will almost always be some missing data. A trial may be
regarded as valid, provided the methods of dealing with missing values are sensible,
and particularly if those methods are pre-defined in the protocol.
Data Transformation: The decision to transform key variables prior to which
analysis is made should be done based on similar design of the trial from data of
earlier clinical trials.
21. contd.
ANALYSISEstimation, Confidence Intervals and Hypothesis Testing: The statistical section of the
protocol should specify the hypothesis that are to be tested and/or the treatment effects
which are to be estimated in order to satisfy the primary objectives of the trial. The
statistical methods to be used to accomplish these tasks should be described for the
primary (and preferably the secondary) variables, and the underlying statistical model
should be made clear. Estimates of treatment effects should be accompanied by
confidence intervals, whenever possible, and the way in which these will be calculated
should be identified.
Adjustment of Significance and Confidence Levels: When multiplicity is present, the
usual approach to the analysis of clinical trial data may necessitate an adjustment to the
type I error. Multiplicity may arise, for example, from multiple primary variables, multiple
comparisons of treatments, repeated evaluation over time and/or interim analysis.
Subgroups, Interactions and Covariates: The primary variable(s) is often systematically
related to other influences apart from treatment. For example, there may be relationships
between two covariates such as age and sex, or there may be differences between
specific subgroups of subjects such as those treated at the different centers of a
multicenter trial. The treatment effect itself may also vary with subgroup or covariate - for
example, the effect may decrease with age or may be larger in a particular diagnostic
category of subjects. Pre-trial deliberations should identify those covariates and factors
expected to have an important influence on the primary variable(s), and should consider
how to account for these in the analysis in order to improve precision and to compensate
for any lack of balance between treatment groups.
22. contd.
ANALYSIS
contd.
Analysis
The different methods for calculating data analysis are as follows:
Graphical Data Analysis: The technical basis of graphical data analysis is
simultaneous display of both magnitudes and frequencies of individual data values in
order to characterize data distribution.
Data Analysis with Summary Measures: Bar charts are good for showing
magnitudes, and line-scatter plots are good for showing trends. Commonly used
summary measures are the number of observations, mean, median, standard
deviation, average deviation, and standard error.
Analysis of Variance (ANOVA): The analysis of variance summarizes data with the
mean, and the quality of summarization is measured with the standard error. The
major use is simultaneous evaluation of multiple interrelated factors. The basic
operation is grouping and curve fitting.
Nonparametric Analysis: The word, nonparametric, really means no involvement of
mathematical distributions. The most commonly performed “nonparametric” analyses
are essentially the traditional analysis of variance on transformed data.
Statistical Sampling and Estimation: Sometimes the size of the entire population
to be studied is so large that measuring a particular parameter (say population mean
X) becomes to time consuming and costly. To deal with this problem researchers can
draw a sample of the population at random and then calculate the mean X of that
population. This parameter becomes an estimate of the population parameter that
needs to be measured.
Statistical Tests of Significance: Tests of significance try to find out whether there
is a real relation between two events or the relation appears by chance only. One of