This document discusses how big data and analytics can help simplify clinical research and make trials more cost-effective. It begins by providing context on how Henry Ford revolutionized car manufacturing using specialized machinery and standardized processes. Similarly, big data is creating a radical shift in how research is conducted by enabling the analysis of large and complex datasets. The rest of the document outlines opportunities in areas like personalized medicine, challenges like dealing with diverse and fast-changing data, and how innovation in clinical research design can help address these challenges to develop more targeted treatments.
Big Data and Analytic Strategy for Clinical Research
1. Big
data
and
analy>c
strategies:
Simplifying
Clinical
Research,
making
Trials
Cost-‐Effec>ve
Candida
Fratazzi
MD
President
Boston
Biotech
Clinical
Research,
LLC
Simplifying
Clinical
Research
www.bostonclinicalresearch.com
2. Henry
Ford
devised
a
manufacturing
system
of
mass
produc>on,
using
specialized
machinery
and
standardized
products
ü Ford
changed
the
way
we
made
cars
–
and
transformed
work
itself
Big
Data
not
only
refers
to
very
large
data
sets
and
the
tools
and
procedures
used
to
manipulate
and
analyze
them,
but
also
to
a
computa>onal
turn
in
thought
and
research
(Burkholder
1992)
ü Big
Data
creates
a
radical
shiO
in
how
we
think
about
research
3. Presenta>on’s
Map
Big Data
challenge and
opportunity
Better disease
treatments for a costefficient healthcare
Algorithm
development
Personalized
medicine
Innovation in
clinical
research
4. Big
Data
Technology
Challenge
data size
Volume
data
source
speed
of
change
Variety
Velocity
Data
complexity
5. Big
Data
Opportuni>es
• Modern
medicine
collects
huge
amounts
of
informa>on
about
pa>ents
through
imaging
technology
(CAT
scans,
MRI),
gene>c
analysis
(DNA
microarrays),
and
other
forms
of
diagnos>c
equipment
• Applying
data
mining
to
data
sets
for
large
numbers
of
pa>ents,
medical
researchers
are
gaining
fundamental
insights
into
the
gene>c
and
environmental
causes
of
diseases,
and
crea>ng
more
effec>ve
means
of
diagnosis
6. Personalized
Medicine
“……..personalized
medicine
is
a
sort
of
shorthand
used
to
represent
the
logical
next
steps
in
progression
of
medical
science
toward
greater
mechanis>c
understanding
of
health,
disease,
and
treatment.”
Janet
Woodcock
7. From
Blockbusters
to
Personalized
Medicine
• The
biggest
challenges
for
the
biotechnology
and
pharmaceu>cal
companies
is
to
develop
and
deliver
drugs
that
fit
the
individual
pa>ent’s
biology
and
pathophysiology
• Change
from
blockbuster
medicine
to
personalized
medicine
will
influence
the
way
that
drugs
are
developed,
and
prescribed
in
the
future
• Personalized
medicine
is
a
stepwise
process
to
stra>fy
pa>ents
into
different
molecular/
biological
subgroups
• Cancer
Medicine
is
expec>ng
to
deliver
in
10–15
years
many
more
drugs
using
CDx
8. Right
drug,
Right
pa>ent,
Right
dose
Adapted
from
Vikas
Kumar,
The
role
of
pharmacogenomics
in
drug
development
9. Lack
of
Efficacy
and…Side
Effects
ü
20-‐75%
of
pa>ents
do
not
receive
effec>ve
treatment
ü
>100,000
deaths
per
year
from
adverse
drug
reac>ons
in
the
US
only
10. Rheumatoid
Arthri>s
case
study
TNF-driven
IL-6-driven
Comorbidities
T cell-driven
Heterogeneity based on response
To Enbrel
B Cell-driven
11. Right
drug,
Right
pa>ent,
Right
dose
Personalized
Medicine
requires
Innova8on
in
Clinical
Research
to:
• Reduce
clinical
development
and
CRO
cost
• Improve
pa>ent
recruitment
and
accelerate
trial
execu>on
• Reduce
clinical
failure
and
generate
reproducible
data
To
create
evidence-‐based
data
driven
trials
12.
S C I O
Strategic
Clinical
Innova>on
Organiza>on
a
new
class
of
service
B o s t o n
B i o t e c h
C l i n i c a l
R e s e a r c h
13. Finding
the
Meaning
in
“
Meaningful
Use
”
Trial
Protocol
Variables
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
Product
(Drug,
device,
or
diagnos>c)
MOA
Disease
pathology
Unmet
medical
needs
Disease
incidence
and
geography
Compe>>on
and
products
in
development
Select
subset
pa>ent
popula>on
likely
to
show
a
significant
improvement
considering
MOA
Iden>fy
clinically
meaningful
endpoint/s
Control
for
co-‐morbidi>es
Consider
selec>ng
an
ac>ve
control
to
assist
in
pharmaco-‐economic
support
for
reimbursement
Select
meaningful
outcomes
and
define
the
clinically
significant
minimal
difference
14. Innova>on
in
Clinical
Research
Design
Endpoints
PK/PD
Diagnostics
Biomarkers
Regulators
SCIO
Patients’
stratification
Safety
Market
analysis
Disease
staging
CRO
Discovery
/
Pre-‐Clinical
Drug-Target
Study
protocol
15. Cytokine
Signaling
Pathways
relevant
to
NFarly
RA
E B
SYK, (& BTK)
K
signalling
cascade
signalling
cascade
MAPK
signalling
cascade
JAK
signalling
cascade
Lipid
messengers
Syk
PI3K
PI3K
PI3K
PI3K
BTK
Kinases
e.g.
MKK3,
MKK6
JAK
Second
messengers
IKK
JAK
STAT
Kinases
STAT
JNK
ERK
NFκB
STAT
p38
Gene
transcrip>on
STAT
CYTOPLASM
NUCLEUS
Adapted from Mavers M, et al. Curr Rheum Rep 2009; 11: 378–385; and Rommel C, et al. Nat Rev Immunol 2007; 7: 191–201.
18.
Dis>lling
Meaning
from
Big
Data
Metabolomics
ü
ü
ü
ü
Blood
Urine
Fluids
Tissue
Proteomics
Genomics
Epigene>cs
Microbiome
Imaging
A n
a l g o r i t h m
t o
d i s 8 l l
a
c o h e r e n t
p i c t u r e
o f
d i s e a s e
f r o m
a
w i d e
r a n g e
o f
d i s p a r a t e
d a t a
ü
ü
ü
ü
RNA
Protein
Metabolites
Images
A p p r o x i m a t e l y 4 0 0 0 N e w Te s t s / n e x t 1 0 y e a r s
19. There
is
No
App
for
Clinical
Research
INNOVATION
Tech
solu>ons
alone
are
not
enough
!!
• Applying
new
technology
to
old
development
models
is
not
good
enough
• Use
of
technology
alone
cannot
innovate
clinical
research
• Technology
advancement
is
key
to
improve
Variety,
Volume
and
Velocity
management
• Clinical
Research
INNOVATION
requires
algorithm/s
that
dis>lls
meanings
from
big
data
22. The
Ul>mate
Goal
• Simplifying
Clinical
Research
meets
the
requirements
of
investors,
partners
and
regulators
• Strategizing
Clinical
Plan
accelerates
value
crea>on
from
phase
I
and
II
of
clinical
trials
• Genera8ng
Evidence-‐based
Medicine
reduces
clinical
risk
and
maximizing
the
chance
of
a
successful
outcome
• Design
Focused
Trials
results
in
cost-‐effec>ve
clinical
trials
• Develop
Algorithm/s
to
integrate
Big
Data
for
decision
making
26. Simplifying
Clinical
Research
affects
Healthcare
• Personalized
medicine
is
poised
to
transform
healthcare
• New
diagnos>c
and
prognos>c
tools
will
increase
our
ability
to
predict
drug
therapy
outcomes
• Expanded
use
of
biomarkers
will
result
in
targeted
drug
development
Treatments
developed
for
Personalized
Medicine
improve
Healthcare
Quality
and
make
Healthcare
Cost-‐effec>ve