BlackfordMiddleton,MD,MPH,MSc,FACP,FACMI,FHIMSS - - PowerPoint PPT Presentation

Blackford
Middleton,
MD,
MPH,
MSc,
FACP,
FACMI,
FHIMSS

 Chairman,
Center
for
Information
Technology
Leadership
 Corporate
Director,
Clinical
Informatics
Research
&
Development
 Partners
Healthcare
System
 Harvard
Medical
School
 Harvard
School
of
Public
Health


 What
is
Clinical
Decision
Support?
  The
Evidence
For
and
Against
CDS
  Current
examples
and
R&D
Projects
from
Partners
  The
Clinical
Decision
Support
Consortium


 “What
information
consumes
 is
rather
obvious:
it
 consumes
the
attention
of
its
 recipients.



• Hence
a
wealth
of
information


creates
a
poverty
of
attention,
 and
a
need
to
allocate
that
 attention
efficiently
among
the


• verabundance
of
information


sources
that
might
consume
it.”


 Changing
clinician
roles:


• From
Omniscient
Oracle…
to


Knowledge
Broker.


compiled analyzed acted upon

After B Blum, 1984

 Medical
literature
doubling
every
19
years


• Doubles
every
22
months
for
AIDS
care


 2
Million
facts
needed
to
practice
  Covell
study
of
LA
Internists:


• 2
unanswered
clinical
questions
for
every
3
pts

• 40%
were
described
as
questions
of
fact,


• 44%
were
questions
of
medical
opinion,


• 16%
were
questions
of
non‐medical
information.



Covell DG, Uman GC, Manning PR. Ann Intern Med. 1985 Oct;103(4):596-9

 Generally,
with
direct
observation,
or
interview
 immediately
after
clinical
encounters,
physicians
have
 approximately
one
question
for
every
1‐2
patients



• Independent
estimates:
0.6,
and
0.62
Q/pt

• Holds
across
PCP
and
specialty
care

• Holds
across
urban
and
rural


Gorman, 1995 Gorman and Helfand 1995

An objective measure of the amount of literature generated by medical scientists annually

Publication
 Bibliographic
databases
 Submission
 Reviews,
guidelines,
textbook


Negative





 results 


variable
 0.3
year
 6.
0
­
13.0
years
 50%
 46%
 18%
 35%
 0.6
year
 0.5
year
 9.3
years


Dickersin,
1987
 Koren,
1989
 Balas,
1995
 Poynard,
1985
 Kumar,
1992
 Kumar,
1992
 Poyer,
1982
 Antman,
1992


Negative





 results 
 Lack
of







 numbers 
 Inconsistent 
 indexing 


17:14
 Original
research
 Acceptance
 Patient
Care


17 years to apply 14% of research knowledge to patient care!

Balas
Yearbook
Medical
Informatics
2000gtre4,
courtesy
M
Overhage


Abraham
Flexner,



Medical
Education
in
the
United
States
and
Canada.
 Boston:
Merrymount
Press,
1910
 "...The curse of medical education is the excessive number of schools. The situation can improve only as weaker and superfluous schools are extinguished."

“Society reaps at this moment but a small fraction of the advantage which current knowledge has the power to confer.”

 “Instead
of
teaching
 doctors
to
be
intelligent
 map
readers,
we
have
 tried
to
teach
every
one
 to
be
a
cartographer.”

  “We
practice
healthcare
 as
if
we
never
wrote
 anything
down.

It
is
a
 spectacle
of
fragmented
 intention.”
 
 

  Larry
Weed,
M.D.


• (father
of
“S.O.A.P.”
note)


 Prone
to
error
  Lots
of
information
but
no
data
  Limited
decision
support,
or
quality
measurement
  Does
not
integrate
with
eHealthcare
  Will
not
transform
healthcare


 Medical
error,
patient
safety,
and
quality
issues


• 98,000
deaths
related
to
medical
error

• 40%
of
outpatient
prescriptions
unnecessary


• Patients
receive
only
54.9%
of
recommended
care


 Fractured
healthcare
delivery
system


• Medicare
beneficiaries
see
1.3
–
13.8
unique
providers


annually,
on
average
6.4
different
providers/yr


• Patient’s
multiple
records
do
not
interoperate


 An
‘unwired’
system


• 90%
of
the
30B
healthcare
transactions
in
the
US
every
year


are
conducted
via
mail,
fax,
or
phone



http://tr.im/sVLA

“…driven primarily by local norms that tend towards heavier use of discretionary services – such as diagnostic testing and surgical versus less invasive interventions – for which there are no clear clinical guidelines.” Peter Orszag, OMB Blog http://www.whitehouse.gov/omb/ blog/

El Paso McAllen TEXAS 790 mi., 1271 km

 “A
knowledge‐based
system
is
an
AI
program
whose
 performance
depends
more
on
the
explicit
presence
of
 a
large
body
of
knowledge
than
on
the
presence
of
 ingenious
computational
procedures…”


Duda RO, Shortliffe EH. Expert systems research.

• Science. 1983 Apr 15;220(4594):261-8.

 Algorithmic
  Statistical
  Pattern
Matching
  Rule‐based
(Heuristic)
  Meta‐heuristic
  Fuzzy
sets
  Neural
nets
  Bayesian


Knowledge Base Inference Engine

A B

Blois
MS.
Clinical
judgment
and
computers.
 N
Engl
J
Med.
1980
Jul
24;303(4):192‐7.


 Formatting


• Results
review,
“pocket
rounds”
reports


 Interpreting


• EKG,
PFTs,
Pap,
ABG


 Consulting


• QMR,
DxPlain,
Iliad,
Meditel,
Abd
Pain,
MI
risk


 Monitoring


• Alerts:
Critical
labs,
ABx/Surgery,
ADEs


 Critiquing


• Vent
mgmt,
anesthesia
mgmt,
HTN
Rx,
Radiology
test


selection,
Blood
products
ordering


Kuperman GJ et al. J Hlth Info Mgmt (13)2, pg 81-96

 CDS
yields
increased
adherence
to
guideline‐based
care,
enhanced
 surveillance
and
monitoring,
and
decreased
medication
errors


• (Chaudhry
et
al.,
2006)


 CDS,
at
the
time
of
order
entry
in
a
computerized
provider
order
entry
 system
can
help
eliminate
overuse,
underuse,
and
misuse.



• (Bates
et
al.,
2003;
Austin
et
al.,
1994;
Linder,
Bates
and
Lee,
2005;
Tierney


et
al.,
2003)
  For
expensive
radiologic
tests
and
procedures
this
guidance
at
the
point
of


• rdering
can
guide
physicians
toward
ordering
the
most
appropriate
and


cost
effective,
radiologic
tests.



• (Bates
et
al.,
2003;
Khorasani
et
al.,
2003)


 Showing
the
cumulative
charge
display
for
all
tests
ordered,
reminding
 about
redundant
tests
ordered,
providing
counter‐detailing
during
order
 entry,
and
reminding
about
consequent
or
corollary
orders
may
also
impact
 resource
utilization



• (Bates
and
Gawande,
2003;

Bates,
2004;
McDonald
et
al.,
2004).


 Savings
potential:
$44
billion



• reduced
medication,
radiology,
laboratory,
and


ADE‐related
expenses
  Advanced
CDS
systems



• Savings
potential
only
with
advanced
CDS

• cost
five
times
as
much
as
basic
CDS

• generate
12
times
greater
financial
return


 A
potential
reduction
of
more
than
2
million
adverse
 drug
events
(ADEs)
annually


Johnston et al., 2003

http://www.citl.org

 Han
YY
(Pediatrics
116:6,
Dec
2005)


• Analyzed
data
13
prior,
and
5
months
post,
implementation

• f
CPOE
in
critical
care

• Pre
CPOE
mortality
rate
2.8%,
Post
6.57%

• 3.28
Odds
ratio
after
multivariate
analysis
adjusting
for


covariates
  Conclusion


• Order
delay
due
to
lack
of
pre‐register

• Up
front
time
cost
to
enter
orders

• Nurses
away
from
bedside,
at
computer

• Altered
interactions
between
ICU
team
members

• Delayed
pharmacy
administration

• Problems
with
order
timing
(subsequent
doses)


 Information
Errors



• Assumed
dose

• Med
d/c
failure

• Procedure‐linked
med
error

• Give
now,
and
prn
d/c
error

• Antibiotic
renewal


• Diluent
option
error

• Allergy
display

• Conflict
or
duplicate
med


 HCI/Workflow
Errors


• Patient
selection

• Med
selection

• Unclear
log
on/off

• Meds
after
surgery

• Post
surgery
suspended
meds

• Time/data
loss
when
CPOE


down


• Med
delivery
error

• Timing
errors

• Delayed
nursing


documentation


• Rigid
system
design


Koppel R et al. JAMA 293:10, Mar 2005

During the Clinical Encounter

History and Physical End of Visit

After the Encounter

Results Arrive Proactive Reminders Warnings/ Feedback Templates/ Order Sets Alerts Guidelines Relevant Info Display Consequent Actions Communication Time-Based Checks

Adapted from Osherorff JA, Pifer EA, Sittig DF, Jenders RA, and Teich JM. Clinical Decision Support Implementers' Workbook. 2004.

Before the Encounter

Patient Prepares for the Visit Scheduling Record Review & Update Patient Reminders Health Information

Bates et. al. JAMA 1998.

Secure Messaging Task Management Population Management Clinical Alerts Schedule Patient Lists Knowledge Links

Information Access  Knowledge Linking

KnowledgeLink in the Workflow

Patient Disease Management

Smart
View:
 Data
Display
 Smart
 Assessment,
 Orders,
and
Plan
 Assessment
and
 recommendations
generated
from
 rules
engine
 Smart
 Documentation


• Lipids

• Anti‐platelet
therapy

• Blood
pressure

• Glucose
control

• Microalbuminuria

• Immunizations

• Smoking


• Weight

• Eye
and
foot
examinations


Medication
Orders
 Lab
Orders
 Referrals
 Handouts/Education


0%
 10%
 20%
 30%
 40%
 50%
 60%
 70%
 80%
 Up­to­date
BP
result
 Change
in
BP
therapy
if
above
goal
 Up­to­date
height
and
weight
 Change
in
therapy
if
A1C
above
goal
 Up­to­date
foot
exam
documented
 Up­to­date
eye
exam
documented
 #
of
deficiencies
addressed


Smart
Form
Used
 Control


<0.001 <0.001 <0.001 <0.001 <0.001 0.05 0.004 0.006

Targets
are
90th
percentile
for
 HEDIS
or
for
Partners
providers


Zero
defect
care:



• Aspirin

• Beta‐blockers

• Blood
pressure

• Lipids

Red,
yellow,
and
green
indicators
show
 adherence
with
targets


Discrepancy Details

Grant RW et al. Practice-linked Online Personal Health Records for Type 2 Diabetes: A Randomized Controlled Trial. Arch Intern Med. 2008 Sep 8;168(16): 1776-82. .

More medication changes in visits after diabetes journal submission:

 New
appreciation
for
potential
unintended
 consequences
of
CDS
  Knowledge
“hardwired”
into
applications
  Knowledge‐engineering
tools
assume
authors
know
 what
to
put
into
them
  Proprietary
knowledge
representation
standards:
not
 re‐usable,
not
easily
shared
  Lack
of
healthcare
leadership
or
resource
investment
 in
processes
for
knowledge
acquisition
and
 management


A
Roadmap
for
National
Action
on
Clinical
Decision
 Support
 “to
ensure
that
optimal,
usable
and
effective
clinical
 decision
support
is
widely
available
to
providers,
 patients,
and
individuals
where
and
when
they
need
it
 to
make
health
care
decisions.”

Osheroff JA, Teich JM, Middleton B, Steen EB, Wright A, Detmer DE. J. Am. Med. Inform.

• Assoc. 2007;14(2):141-145.

To
assess,
define,
demonstrate,
and
evaluate
best
 practices
for
knowledge
management
and
clinical
 decision
support
in
healthcare
information
technology
 at
scale
–
across
multiple
ambulatory
care
settings
and
 EHR
technology
platforms.
 www.partners.org/cird/cdsc

 How
do
we
improve
the
translation
of
knowledge
in
clinical
practice
guidelines
into
 actionable
CDS
in
healthcare
information
technology?
  How
do
we
optimally
represent
knowledge
and
data
required
to
make
actionable
 CDS
content
in
both
human
and
machine
readable
form?
  How
do
we
collate,
aggregate,
and
curate
knowledge
content
for
CDS
in
a
 knowledge
portal
used
by
members
of
the
CDS
Consortium?

How
may
we
use
such
a
 tool
to
support
knowledge
management
and
collaborative
knowledge
engineering
 for
clinical
decision
support
at
scale,
across
multiple
healthcare
delivery


• rganizations,
and
multiple
domains
of
medicine?


 How
do
we
demonstrate
broad
adoption
of
evidence‐based
CDS
at
scale
in
a
wide
 array
of
HIT
products
used
in
disparate
ambulatory
care
delivery
settings?

  Further,
how
do
we
deploy
clinical
decision
support
services
in
healthcare
 information
technology
in
a
manner
that
improves
CDS
impact?
  How
do
we
take
the
learnings
garnered
through
the
course
of
these
investigations
 and
broadly
disseminate
them
broadly
to
key
stakeholders?


1980 1990 2000 ONCOCIN EON(T-Helper) GLIF2 Arden MBTA GEODE-CM EON2 GLIF3 Asbru Oxford System

• f Medicine

DILEMMA PROforma PRESTIGE PRODIGY Decision Tables GEM PRODIGY3

• P. L. Elkin, M. Peleg, R. Lacson, E. Bernstam, S. Tu, A. Boxwala, R. Greenes, & E. H. Shortliffe.

Toward Standardization of Electronic Guidelines. MD Computing 17(6):39-44, 2000

Shahar Y, et al. JBI 2004

• 1. Knowledge Management Life Cycle
• 2. Knowledge

Specification

• 3. Knowledge Portal and

Repository

• 4. CDS Public Services

and Dashboard

• 5. Evaluation Process for each CDS Assessment and Research Area
• 6. Dissemination Process for each Assessment and Research Area

 Knowledge
management
lifecycle
  Knowledge
specification
  Knowledge
Portal
and
Repository
  CDS
Knowledge
Content
and
Public
Web
Services

  Evaluation
  Dissemination


Narrative
Recommendation
layer
 Narrative
text
of
the
recommendation
from
the
published
guideline.
 Semi‐Structured
Recommendation
layer
 Breaks
down
the
text
into
various
slots
such
as
those
for
applicable
 clinical
scenario,
the
recommended
intervention,
and
evidence
 basis
for
the
recommendation
 Standard
vocabulary
codes
for
data
and
more
precise
criteria
 (pseudocode)
 Abstract
Representation
layer


Structures
the
recommendation
for
use
in
particular
kinds
of
CDS
tools


• Reminder
and
alert
rules

• Order
sets


A
recommendation
could
have
several
different
artifacts
created
in
this
layer,


• ne
for
each
kind
of
CDS
tool


Machine
Executable
layer
 Knowledge
encoded
in
a
format
that
can
be
rapidly
integrated
into
a
 CDS
tool
on
a
specific
HIT
platform
 E.g.,
rule
could
be
encoded
in
Arden
Syntax
 A
recommendation
could
have
several
different
artifacts
created
in
this
 layer,
one
for
each
of
the
different
HIT
platforms
 Narrative
Guideline
 Semistructured
Recommendation
 Abstract
Representation
 Machine
Execution


 For
each
knowledge
representation
layer
in
CDS
stack:


• Data
standard
(controlled
medical
terminology,
concept


definitions,
allowable
values)


• Logic
specification
(statement
of
rule
logic)

• Functional
requirement
(specification
of
IT
feature


requirements
for
expression
of
rule,
etc.)


• Report
specification
(description
of
method
for
CDS
impact


 measurement
and
assessment)


Collaboration eRoom for Adult Primary Care

51

1 Oct 08 9:55pm

• How does everyone feel about this?
• Should we turn the reminder off for a

shorter period of time if “Done Elsewhere” is chosen?

Personal
Health
 Information
Network


Community
(”Crowd”)
 Medical
Professional
 Science
 Rule
builder
 Knowledge
 respository
 Rule
engine


Clin.
Inf.
System


Petter
K.
Risøe
 HSPH HPM512 2009

Patient


“I conclude that though the individual physician is not perfectible, the system of care is, and that the computer will play a major part in the perfection of future care systems.”

Clem McDonald, MD NEJM 1976

Thank you!

Blackford Middleton, MD bmiddleton1@partners.org www.partners.org/cird www.citl.org