2. This presentation will cover
1. Basics of DOE.
2. How to Select an Experimental Design?
3. Stages of DOE?
4. Exercise ONE:
Maher Alabsi R&D Center –March- 2020
4. History of DOE :
the Greek
philosopher, as
the Father of
Scientific
Method.
300 BC
Aristotle
1880
OFAT
1925 1950 1960
Sir Ronald Fisher
who actually
started DOE
the Father of
DOE.
famous person for
RSM, Response
Surface
Methodology
George Box
Sir Ron Fisher's daughter, Joan Fisher,
married George Box
passed away in
2013
One Factor At a
Time
Japanese statistician
Taguchi
His contribution
was in the robust
design
Aftermath of
the world war II
Japan was
trying to
develop better
quality products
Edison Fries
Basics of DOE.
Maher Alabsi R&D Center –March- 2020
5. History of DOE :
• The agricultural origins, 1918 – 1940s
• Firstly introduced by Ronald Fisher & his co-workers showed how valid experiments could be conduct (1920s)
• Profound impact on agricultural science
• Factorial designs, ANOVA
• The first industrial era, 1951 – late 1970s
• Box & Wilson, response surfaces
• Applications in the chemical & process industries
• The second industrial era, late 1970s – 1990
• Quality improvement initiatives in many companies • CQI and TQM were important ideas and became management goals • Taguchi and robust
parameter design, process robustness
• The modern era, economic competitiveness and globalization is driving all sectors of the
economy to be more competitive.
Basics of DOE.
Basics of DOE.
1st Gen.
2nd Gen.
Modern
Maher Alabsi R&D Center –March- 2020
8. What is Design of Experiments ?
• Design of Experiment (DOE) is a powerful statistical technique for
improving product/process designs and solving process / production
problems .
• DOE makes controlled changes to input variables in order to gain maximum
amounts of information on cause and effect relationships with a minimum
sample size.
• When analyzing a process, experiments are often used to evaluate which
process inputs have a significant impact on the process output and what the
target level the inputs should be to achieve a desired result (output).
• Design of Experiments (DOE) is also referred to as Designed Experiments or
Experimental Design
Basics of DOE.
Basics of DOE.
Maher Alabsi R&D Center –March- 2020
9. Why DOE :
• Reduce time to design/develop products & processes.
• Improve performance of existing processes.
• Improve reliability and performance of products.
• Achieve product & process robustness.
• Perform evaluation of materials, design alternatives, setting component & system
tolerances.
• Minimize Consumption.
• Improve product quality.
• Reduce manufacturing costs.
• Increase speed to develop new medicines.
Basics of DOE.
Maher Alabsi R&D Center –March- 2020
10. Planning of experiment…
• Know the different scales of experiment:
• Scale Variability Control over external factors
• Lab Large Good
• Pilot Small Medium
• Production Very small Little
• 1kg 100kg
Basics of DOE.
Maher Alabsi R&D Center –March- 2020
12. Terminology of DOE
o Factors: Factors are inputs to the process Factors can be classified as either
controllable or uncontrollable variables.
In this case, the controllable factors are Flour, Eggs, Sugar and Oven. Potential
factors can be categorized using the Cause & Effect Diagram
o Levels: Levels represent settings of each factor in the study Examples include the
oven temperature setting, no. of spoons of sugar, no. of cups of flour, and no. of
eggs .
o Response: Response is output of the experiment In the case of cake baking, the
taste, consistency, and appearance of the cake are measurable outcomes potentially
influenced by the factors and their respective levels.
Basics of DOE.
Maher Alabsi R&D Center –March- 2020
13. • Factor (Inputs)
One of the independent variables under investigation that can be set to a desired value
• k
the number of factors or variables, the effects of which are to be estimated in an experiment
• Level
the numerical value or qualitative feature of a factor
• Run (Experiments)
the act of operating the process with the factors at certain settings
• Treatment
specific combination of the levels of all factors for a given test or run
• Response (Outputs)
the numerical result of a run
Terminology of DOE
DOE Vocabulary
Basics of DOE.
Maher Alabsi R&D Center –March- 2020
14. • Experimental error
the amount of variability that may be expected in the experimental environment just by chance without
any changing of the factors being investigated
• Main Effect
the average influence on the response as a variable changes levels
• Interaction Effect
the average difference in the effect on a response of one variable dependent upon the settings of another
variable
• MSFE
Minimum Significant Factor Effect is the minimum absolute value of an effect which may be considered a
significant result
• Factorial experiment
designed to determine the effect of all possible combinations across all levels of the factors under study
• Fractional Factorial
designed to examine k factors with a fraction of the runs required for a full factorial
Terminology of DOE
DOE Vocabulary
Basics of DOE.
Maher Alabsi R&D Center –March- 2020
15. Confounding
the consequences of conducting a fractional factorial design
Blocking
a strategy for designing experiments to provide the ability to eliminate from the
experimental error a contributor of variability that is known but not under investigation
Robust
the quality of a process or output being little affected by environmental or internal
component variation
Noise
refers to variability, frequently uncontrollable or random variability in experimental
design work ANOVA a mathematical procedure testing for significant differences
between or among groups
Terminology of DOE
DOE Vocabulary
Basics of DOE.
Maher Alabsi R&D Center –March- 2020
16. FISHER’S FOUR DESIGN PRINCIPLES
1. Factorial Concept - rather than one-factor-at-a-time
2. Randomization - to avoid bias from lurking variables
3. Blocking - to reduce noise from nuisance variables
4. Replication - to quantify noise within an experiment
Basics of DOE.
FISHER’S
The father of DOE
Maher Alabsi R&D Center –March- 2020
17. Three R’s of DOE
Randomization
sequence of experiments and/or the assignment of specimens to
various treatment combinations in a purely chance manner
Replication
infers two or more runs were conducted under the same test
conditions, each run following a new set-up or resetting of the conditions
Repetition
obtaining more than one measurement or unit of output for each run
Basics of DOE.
Maher Alabsi R&D Center –March- 2020
20. KEY TERMINOLOGY
o Interaction:
Sometimes factors do not behave the same when they are looked at together
as when they are alone; this is called an interaction
Interaction plot can be used to visualize possible interactions between two
or more factors . Parallel lines in an interaction plot indicate no interaction
The greater the difference in slope between the lines, the higher the degree
of interaction
However, the interaction plot doesn't alert you if the interaction is
statistically significant
Interaction plots are most often used to visualize interactions during ANOVA
or DOE
Basics of DOE.
Maher Alabsi R&D Center –March- 2020
21. KEY TERMINOLOGY
o Randomization:
Randomization is a statistical tool used to minimize potential uncontrollable biases
in the experiment by randomly assigning material, people, order that experimental
trials are conducted, or any other factor not under the control of the experimenter
When we run designed experiments, we will use experimental templates to set
them up and to analyze them. We do not want to actually make the experimental
runs in the order shown by the template; wherever possible, we want to randomize
the experimental runs.
Randomization of the run order is needed to minimize the impact of those variables
outside of the experiment that we are not studying.
Basics of DOE.
Maher Alabsi R&D Center –March- 2020
22. KEY TERMINOLOGY
o Blocking:
Blocking is a technique used to increase the precision of an experiment
by breaking the experiment into homogeneous segments (blocks or
clusters or strata) in order to control any potential block to block
variability
Sometime we cannot totally randomize the experimental runs. Typically
this is because it will be costly or will take a long time to complete the
experiment.
Blocking means to run all combinations at one level before running all
treatment combinations at the next level.
Experimental runs within blocks must be randomized.
Basics of DOE.
Maher Alabsi R&D Center –March- 2020
23. KEY TERMINOLOGY
o Replication:
Replication is making multiple experimental runs for each
experiment combination.
This is one approach to determining the common cause variation in
the process so that we can test effects for statistical significance.
Repetition of a basic experiment without changing any factor
settings, allows the experimenter to estimate the experimental error
(noise) in the system used to determine whether observed differences
in the data are “real” or “just noise”, allows the experimenter to
obtain more statistical power.
Basics of DOE.
24. FD
CCD
e. Response Surface design (RSD)
BBD RSD
FFD
TYPES OF DOE
The most commonly designs used to
obtain an optimized formulation
commonly
الدوائ الصناعات في المستخدمة التصاميم أهمية:
Basics of DOE.
25. How do you select
an experimental design?
FD
PBD
BBD
OFAT
RSD CCD
26. A design is selected based on
• The experimental objective.
• The number of factors.
1- Comparative objective:
If there are one or more factors to be examined and the main aim is to screen
one important factor among other existent factors and its influence on the
responses, then it infers to a comparative problem which can be solved by
employing comparative designs.
2- Screening objective:
The objective of this design is to screen the more important factors among the
lesser ones. Under this objective we can select full or fraction factorial designs or
Plackett-Burman design (PBD).
Based on the Experimental objective
Design of Experiments: Optimization and Applications in Pharmaceutical Nanotechnology Dwija Trivedi#, Veera Venkata Satyanarayana Reddy Karri#, Asha Spandana K M and Gowthamarajan-2105 Kuppusamy*
27. 3- Response surface method objective:
When there is a need of investigating the interaction between the factors,
quadratic effects or when the requirement involves the development of an idea in
relation to the shape of response surface, in such situations, a response surface
design is used.
These designs are used to troubleshoot the process problems and to make a
product more robust so as to not be affected by the non controllable influences.
The BBD and CCD are the most popular designs under this category.
Apart from all these criteria, the selection of experimental designs also depend
on the number of factors to be entered, as each design has a limitation of
entering the factors more or less of which will not be accepted.
For instance, in BBD the minimum number of numeric factors to be entered is 3
and maximum number of numeric factors to be entered is 21.
Based on the Experimental objective
Design of Experiments: Optimization and Applications in Pharmaceutical Nanotechnology Dwija Trivedi#, Veera Venkata Satyanarayana Reddy Karri#, Asha Spandana K M and Gowthamarajan-2105 Kuppusamy*
30. Summary table for choosing an experimental design for comparative,
screening, and response surface designs
Response Surface
Objective
Screening
Objective
Comparative
Objective
Number
of Factors
--1-factor completely
randomized design1
Central
composite orBox-
Behnken
Full or fractional
factorial
Randomized block
design2-4
Screen first to reduce
number of factors
Fractional
factorial orPlackett-
Burman
Randomized block
design5 or more
Based on the number of factors
31. المراد العوامل عدد على التصنيفتغيرهها:
Summary table for choosing an experimental design for comparative,
screening, and response surface designs
Response Surface
Objective
Screening
Objective
Comparative
Objective
Number
of Factors
--1-factor completely
randomized design1
Central
composite orBox-
Behnken
Full or fractional
factorial
Randomized block
design2-4
Screen first to reduce
number of factors
Fractional
factorial orPlackett-
Burman
Randomized block
design5 or more
Maher Alabsi R&D Center –March- 2020
32. The most widely used designs in pharmaceutical applications are
RSM and FD, both of which serve different purposes.
The best criteria
- Fewer runs (Experiments).
- Saves time .
- Saves money.
Optimization Strategies of
Experimental Designs
Design of Experiments: Optimization and Applications in Pharmaceutical Nanotechnology Dwija Trivedi#, Veera Venkata Satyanarayana Reddy Karri#, Asha Spandana K M and Gowthamarajan-2105 Kuppusamy*
1. Response Surface design (RSM)
Full factorial design ½ Fraction factorial design
2. Factorial design (FD)
33. Optimization Strategies
of Experimental Designs
Factorial designs (FD)
These designs help in screening the critical process parameters which can affect the process and
product with the help of interactions between the factors.
Two level factorial design (2-21 factors):
Full and fractional design will explore many factors by setting each on two levels i.e. higher and
lower. This design is helpful in identifying the most significant factors among many others that are
involved in design.
Min Run, Res V factorial designs (6-50 factors):
These class of designs containing the minimum number of trials to estimate all main effects and all
two-factor interactions (Resolution V) while maintaining treatment balance within all factors.
Min Run, Res IV factorial designs (5-50 factors):
These class of designs which has a minimum run (or with 2 extra runs), and resolution IV. This
design allows all main effects to be estimated, clear of two-factor interactions. The two- factor
interactions will be aliased with each other.
Design of Experiments: Optimization and Applications in Pharmaceutical Nanotechnology Dwija Trivedi#, Veera Venkata Satyanarayana Reddy Karri#, Asha Spandana K M and Gowthamarajan-2105 Kuppusamy*
34. Optimization Strategies of
Experimental Designs
Irregular fraction designs (4-11 factors):
It allows the estimation of main effects and two factor interactions by involving lesser
number of runs and more power of resolution than the normal fractional factorial design.
General factorial designs (1-12 factors):
These designs are used to design an experiment where each factors can have different
number of level (2-999). The layout of the design generated by this design will include
all possible combination of the factors level.
Optimal design (2-30 factors):
This design is similar to general factorial design which may produce a design with more
number of runs. The number of runs generated depends on the model you want to
estimate. These designs should be used carefully, taking into account subject matter
knowledge to decide if the design is acceptable.
Design of Experiments: Optimization and Applications in Pharmaceutical Nanotechnology Dwija Trivedi#, Veera Venkata Satyanarayana Reddy Karri#, Asha Spandana K M and Gowthamarajan-2105 Kuppusamy*
35. Optimization Strategies of
Experimental Designs
Plackett-Burman designs (up to 31 factors):
These are highly confounding designs. The main useful application of this design is for
validation where one can hope to find no or very little effect on the responses due to any
factors.
Taguchi orthogonal array designs (up to 63 factors)
Response surface design (RSD)
RSM quantifies the relationship between several explanatory variable and one or more
responses. It helps in finding the ideal process settings to achieve optimal performance.
Central composite design (CCD):
The most popular design used in response surface methodology. Regular central
composite designs have 5 levels for each factor, although this can be modified by
choosing alpha value 1.0, a face centered CCD. The face-centered design has only three
levels for each factor. This design is insensitive to missing data and has been created to
estimate quadratic model.
Design of Experiments: Optimization and Applications in Pharmaceutical Nanotechnology Dwija Trivedi#, Veera Venkata Satyanarayana Reddy Karri#, Asha Spandana K M and Gowthamarajan-2105 Kuppusamy*
36. Optimization Strategies of
Experimental Designs
Box behnken design (BBD):
This is also a popular design among response surface designs; this design has 3 levels
for each factor and generates a lesser number of trials in comparison to central
composite design. This design is sensitive to the missing data and provides strong
coefficient estimates near the center of the design space (where the presumed
optimum is), but weaker at the corners of the cube (where there are no design points).
One factor at a time (OFAT):
This design is used where only one continuous factor is meant to be estimated.
Categoric factor can be added to this design for each categoric combination design is
duplicated.
User defined: This design is user friendly and allows selecting all classes of candidate
points as per requirement; vertices, centre of edges etc. One can select the number of
factors and levels and can add constraints to limit the factor space to reasonable
combination. One can even select the model desired to fit by using this design.
Design of Experiments: Optimization and Applications in Pharmaceutical Nanotechnology Dwija Trivedi#, Veera Venkata Satyanarayana Reddy Karri#, Asha Spandana K M and Gowthamarajan-2105 Kuppusamy*
37. Optimization Strategies of
Experimental Designs
Mixture design
This design is applied when the factors are proportion of blend.
Combined designs
Combined designs are optimal and user defined. While working with categoric factor in
addition to continuous factors or when there are constraints on experiment optimal
design, this is used to minimize the number of trials.
Studies on Different Types of Nanoparticles Optimized Using DoE.
Design of Experiments: Optimization and Applications in Pharmaceutical Nanotechnology Dwija Trivedi#, Veera Venkata Satyanarayana Reddy Karri#, Asha Spandana K M and Gowthamarajan-2105 Kuppusamy*
38. Examples of DoE application in medicinal product development and pharmaceutical
processes
Design of experiments (DoE) in pharmaceutical development - Stavros N. Politis, Paolo Colombo, Gaia Colombo & Dimitrios M. Rekk -2017
39. Examples of DoE application in medicinal product development and pharmaceutical
processes
Design of experiments (DoE) in pharmaceutical development - Stavros N. Politis, Paolo Colombo, Gaia Colombo & Dimitrios M. Rekk -2017
40. The Response surface design (RSD) and factorial designs (FD) are the
most commonly employed designs in pharmaceutical industry. [1]
- The Box-behnken design (BBD) is the most popular among all response surface
methodology (RSM) because it requires fewer runs in 3 factor experimental design than all
other RSM designs [1]
Which design used in pharmaceutical industry?
1.Wang F, Chen L, Jiang S, He J, Zhang X, Peng J, J Liposome Res, 2014, 24, 171.
Optimization Strategies of Experimental Designs [8]
There are various designs and plots are available in DoE to obtain an optimized formulation. The most widely
used designs in pharmaceutical applications are RSM and FD, both of which serve different purposes. The best
criteria to select a design is that which can give an optimized formulation in fewer runs that in turn saves time as
well as money.
41. Examples of DoE application in medicinal product development and pharmaceutical
processes
Design of experiments (DoE) in pharmaceutical development - Stavros N. Politis, Paolo Colombo, Gaia Colombo & Dimitrios M. Rekk -2017
44. Designed experiments are usually carried out in five stages:
• Planning
• Planning Optimization
• Robustness testing
• Verification.
Stages of DOE
Planning
Planning
Optimizat
ion
Robustnes
s
Verification.
Maher Alabsi R&D Center –March- 2020
45. Planning
It is important to carefully plan for the course of experimentation before
embarking upon the process of testing and data collection. A thorough and
precise objective identifying the need to conduct the investigation, an
assessment of time and resources available to achieve the objective and an
integration of prior knowledge to the experimentation procedure are a few
of the goals to keep in mind at this stage. A team composed of individuals
from different disciplines related to the product or process should be used to
identify possible factors to investigate and determine the most appropriate
response(s) to measure. A team-approach promotes synergy that gives a
richer set of factors to study and thus a more complete experiment. Carefully
planned experiments always lead to increased understanding of the product
or process.
Maher Alabsi R&D Center –March- 2020
46. Screening
Screening experiments are used to identify the important factors
that affect the system under investigation out of the large pool of
potential factors. These experiments are carried out in conjunction
with prior knowledge of the system to eliminate unimportant
factors and focus attention on the key factors that require further
detailed analyses. Screening experiments are usually efficient
designs requiring a few executions where the focus is not on
interactions but on identifying the vital few factors.
Maher Alabsi R&D Center –March- 2020
47. Optimization
Once attention is narrowed down to the important factors affecting
the process, the next step is to determine the best setting of these
factors to achieve the desired objective. Depending on the product
or process under investigation, this objective may be to either
maximize, minimize or achieve a target value of the response.
Maher Alabsi R&D Center –March- 2020
48. Robustness Testing
Once the optimal settings of the factors have been determined, it
is important to make the product or process insensitive to
variations that are likely to be experienced in the application
environment. These variations result from changes in factors that
affect the process but are beyond the control of the analyst. Such
factors as humidity, ambient temperature, variation in material,
etc. are referred to as noise factors. It is important to identify
sources of such variation and take measures to ensure that the
product or process is made insensitive (or robust) to these factors.
Maher Alabsi R&D Center –March- 2020
49. Verification
This final stage involves validation of the best settings of the factors
by conducting a few follow-up experiment runs to confirm that the
system functions as desired and all objectives are met.
Maher Alabsi R&D Center –March- 2020
51. Exercise ONE: Pharm Tech, May 1998
• “A Systematic Formulation Optimization Process for a Generic
Pharmaceutical Tablet.”
• Hwang, R.; Gemoules, M; Ramlose, D. and Thomasson, C.
Maher Alabsi R&D Center –March- 2020
52. Objective
• “ … optimizing an immediate release tablet formulation for a generic
pharmaceutical product.”
• Develop a generic tablet with a disintegration time of 6-12 minutes,
5 minute dissolution of 40-60% and 45 minute dissolution of greater
than 90%.
Maher Alabsi R&D Center –March- 2020
53. 1. API particle size Small Large
2. API % 5% 10%
3. Lactose MCC ratio. 1:3 3:1
4. MCC particle size Small Large
5. MCC density Low High
6. Disintegrant. Cornstarch, Glycolate
7. Disintegrant % 1% 5%
8. Talc 0% 5%
9. Mag Sterate 0.5% 1%
Treatments
(Factors) (Inputs)
2 levels
Upper Lower
limit limit
9 Factors
Maher Alabsi R&D Center –March- 2020
54. Responses
(Outputs)
• Blend homogeneity
• Compression force %RSD
• Ejection force
• Tablet weight %RSD
• Tablet hardness
• Tablet friability
• Tablet disintegration time
• Tablet dissolution at 5 minutes
• Tablet dissolution at 45 minutes
Maher Alabsi R&D Center –March- 2020
55. Statistical Design
• 9 factors each at two levels
• 16 runs
• Design is a 29-5 fractional factorial
• Resolution III
Maher Alabsi R&D Center –March- 2020
56. The best formulation:
• API 7.14%
• Fast-Flo lactose 60.74%
• Avicel PH-302 30.37%
• Talc 1%
• Mag Stearate 0.75%
Maher Alabsi R&D Center –March- 2020
57. Conclusion
• “The formulation was successfully scaled up to a 120 kg batch size
and the manufacturability and product quality were confirmed.”
• “This study has demonstrated the efficiency and effectiveness of
using a systematic formulation optimization process … “
Maher Alabsi R&D Center –March- 2020
58. Maher Alabsi R&D Center –March- 2020
Maher Alabsi
R&D Formulator at R&D Center- Global & Modern Pharma.
https://www.linkedin.com/in/maher-al-absi-5579009b/