Transcript No Slide Title

Critical Care Bioinformatics
at UCSF
J. Claude Hemphill III, MD, MAS
Kenneth Rainin Chair in Neurocritical Care
Associate Professor of Clinical Neurology
and Neurological Surgery
University of California, San Francisco
Director, Neurocritical Care
San Francisco General Hospital
Disclosures
Research Support: NIH/NINDS
Consulting: UCB Pharma
Stock (options): Cardium Therapeutics (Innercool Therapies), Ornim
UCSF
NEUROCRITICAL
CARE PROGRAM
So What’s the Problem?
•
Some of what we don’t know
1) Do secondary brain insults have a dose-response
relationship with outcome?
2) We treat univariate in a multivariate world
 Interaction and relationship between various
physiologic parameters?
 Event signatures?
3) How do we integrate new measures (e.g. PbtO2)?
4) How often do we need to collect physiologic data
to optimize patient care?
This is complicated
Looking at ICU Data Bedside
Paper charts in most ICUs,
electronic charts in some
ICU
Informatics
2009
Neurocritical Care Database/Informatics
GOALS
1) Identify physiological signatures to diagnose patients and
predict outcomes
2) Use real-time data to rationally drive clinical decisions and
treatment based on the specific physiologic abnormality
3) Determine dosage and delivery for commonly used NICU
medications
4) Suggest new clinically-relevant experimental research models
5) Develop user-friendly “behind the scenes” data analysis that
aids interpretability and clinical applicability
UCSF Approach to Critical Care Informatics
• Centered at SFGH
– Trauma Center
– Stroke Center
• Driven by interest of specific clinicians
– Claude Hemphill, MD,MAS - neurointensivist
– Geoff Manley, MD,PhD - neurosurgeon
– Mitch Cohen, MD – trauma surgeon
• Focus on neurotrauma
• “Ground up” approach
– Develop infrastructure
– Knowledge discovery (research driven)
– Not trying to feed back immediately into
clinical care – too early
UCSF Initial Efforts
• Gather some data
– Kiosk method
– “Home grown” software
• Analyze in novel, but simple ways
– Detection of secondary brain insults
– Improved univariate measures –
AUC (area under the curve)
• Identify and engage collaborators with
expertise (generally not clinicians)
• Publish
NICU Data Acquisition 2003
• Independent CPU
• Multiple serial ports
– Overhead monitor
(Philips)
– Ventilator (Draeger)
– Brain O2 (Licox)
– CBF (Hemedex)
• Data time-synched
• Operator must initiate
data acquisition
How Often Do We Need to Collect this Data?
ICP > 20
• Current standard
– Paper chart - Q 1 hour
and as needed
– CareVue (electronic
medical record) –
up to Q 15 min
• Study comparing Q 1 min
v. medical record (MR) for
SBI identification and
dose (n=16; 72 hours
each)
Hemphill, Physiological Measurement, 2005
Subject
# of Events
AUC in mmHg.min
Q 1 min
MR
Q 1 min
MR
1
1
1
0.5
0.1
2
10
6
13.8
9.8
3
1
0
6.1
0
6
2
10
3.0
3.0
7
9
5
76.6
73.7
8
0
1
0
0.1
9
0
1
0
1.5
10
21
12
22.1
25.6
11
0
0
0
0
12
0
14
0
25.9
13
0
0
0
0
14
7
76
4.3
33.6
15
1
11
0.4
8.5
16
4
4
7.6
13.5
17
40
23
59.9
73.7
Borrowing from Pharmacokinetics
• “Dose” is area under the curve (AUC)
39.5
39
Body Temperature
38.5
38
37.5
37
36.5
36
35.5
35
0
20
40
60
80
100
120
Hours from Hospital Admission
140
160
Does It Matter How we Define Dose?
Impact of ED episodes and dose of hypotension on risk
of in-hospital death after severe TBI (n=107)
SBI
Odds Ratio
95% CI
P
Any hypotension (n=26)
3.39
1.34-8.56
.009
1 episode of hypotension
2.05
0.67-6.23
0.21
≥ 2 episodes of hypotension
8.07
1.63-39.9
0.01
Minimal dose hypotension
(< 1 mmHg*minute)
1.35
0.28-6.4
0.71
Moderate dose hypotension
(1-100 mmHg*minutes)
3.14
0.85-11.6
0.087
High dose hypotension
(> 100 mmHg*minutes)
12.55
1.5-107
0.021
* Manley, Arch Surg, 2001
+Barton,
Acad Emerg Med, 2005
*
+
Mannitol Dose-Response
Sorani J Neurotrauma 2008
Physiology Cluster Analysis
SBP
DBP
MAP
PbtO2
ETCO2
Self-organizing map reduces high-dimensional
information to a two-dimensional grid
Sorani Neurocritical Care 2007
UCSF Next (and Current) Efforts
• Create group identity
– C-BICC – Center for Biomedical Informatics in Critical Care
• Obtain funding
• Develop data warehouse
• Undertake advanced informatics and statistical analyses to
– Remove artifacts
– Identify event signatures
– Improve data visualization
• Allow some use for hospital QA
(helps with administrative buy-in)
• Publish
NeuroICU Physiological Informatics
• Collaborative Project
– Admit it: this is beyond bedside clinicians
– Clinicians, computer scientists, informatics,
industry
• UC Discovery Grant
– Pilot project between UCSF, UC Berkeley, Intel
– Two years: develop data warehouse methods,
pilot data analysis
– Expand to multi-center project (will require large
numbers of patients with long-term outcome)
• NIH/NINDS SBIR – Scott Winterstein, PhD
– Data acquisition methodology and device library
NICU Data Acquisition 2009
•
The primary data are:
1. Bedside physiological data (Aristein-”homemade”)
2. ICU Patient Care Chart (Carevue-Philips)
3. Lifetime Clinical Record (Invision-Siemens)
•
•
No kiosk – each bed with networked data acquisition
Bedside physiological data collected continuously
(Q1 minute) and automatically into Data Registry
Server
•
Must have contextual data (e.g. medications and
timing) in order to make sense
of physiological data
NICU Data Acquisition 2009
D a ta S o u rc e s
D a ta T ra n sm itte d
to Q B 3
S y ste m S e rv e rs
Ca re V u e
P hilip s
ISM D a ta m a rt
N u rsin g
D o cu m e n ta tio n
Sto ra g e A rea
N etw o rk
Sto ra g e
D e-id en tified
d ata
A riste in
A riste in
A ristein SQ L
B io in fo rm a tics
P h ysio lo gy
Sta g in g
Server
SF G H
F irew a ll
P e rso n a l
H e a lth
I n fo rm a tio n
In visio n
S ie m e n s
D e m o gra p h ics
In visio n SQ L
ET L
Server
QB3
Server
M eta da ta
W a reh o use
Query Building Screen
Number of patients in data set
(current test data)
Data sources and filters
Invision LCR
•
Aristein high
frequency
physiology
CareVue
Nursing documentation of medications, treatments,
assessments, laboratory values, IV solutions administered
Once filters have been selected, the user clicks
on show patients to see preliminary data.
Current database
– CareVue data on
~11,000 patients
– Physiology data on
~1000 patients
Number of patients meeting selection
Sample data. Data displayed in a spreadsheet format.
Shows subset of available variables from 3 data sources
Preliminary results show the
number of rows of data per variable
per patient. The 3 data sources
provide 60 possible variables. This
screen shot shows only a subset of
physiologic variables.
Data are integrated by date/time stamp.
A = physiology
M = medication data
I = Intake or Output data
C = nursing documentation of treatments or assessments
Rows of data for this patient and this variable.
User can download data into a csv file for a single
patient or all patients at one time.
Novel Data Visualization Tools
• Viewing large amounts of data in
clinically useful way
• Medications and events
• Compressed time scales
• Physiological “signatures”
Patient Applications: Data Visualization
36 days of continuous physiological data
Acetaminophen
then antibiotics
Pattern Recognition
State 1
State 2
State 3 State 4 States 5,6 State 7
PHYSIOLOGIC SIGNATURES
Dynamic Bayesian Networks
We treat patients as if we are practicing DBN state theory.
No really, we do.
Our Problems
• Paying for all this
– Personnel
– Data warehousing (ongoing)
– Business models of for-profit companies
(“just contract with Oracle”) don’t currently
work for research needs
• Balance
– Just like doctors have different specialties,
so do engineers, programmers,
database/informatics experts, statisticians,
computer scientists
– Clinical coordination – responsible for
publishing in clinical journals
Evidence-based Neurocritical Care
• Expertise matters
• Pronovost, JAMA, 2002 – systematic review of 26 studies
– Presence of intensivist ass. w/ better outcomes
– Only 1 neuroICU studied
• Neurointensivists – improved outcome
– Suarez, Critical Care Medicine, 2004
– Varelas, Critical Care Medicine, 2004
» Semi-closed unit; 30% TBI
• Understanding
– Why expertise makes a difference even without a specific
obvious treatment
– How to harness and “export” expertise
UCSF ICU Informatics – Guiding Principles
• NeuroICU monitoring tools have advanced beyond our current
ability to understand how to use them
• This is due to the disconnect between data generation and data
analysis
• Advances in real-time user-friendly data analysis must
accompany advances in neuromonitoring techniques
• This will be a “long haul”
• This is a large-scale collaborative effort across institutions
• Avoid the temptations to
–
–
–
–
–
Be impatient and give up
Assume the data we want is easily obtained/acquired
Expect big answers right away
Read too much into early simple analyses
Assume large companies will provide us with the solutions
• Publish – interim experience and results must be disseminated
Acknowledgements
UCSF Neurosurgery
Geoff Manley, MD, PhD
Diane Morabito, RN MPH
Guy Rosenthal, MD
Michele Meeker, RN
Scott Winterstein, PhD
UCSF Neurology
Wade Smith, MD,PhD
UCSF Medical Informatics
Marco Sorani
UC Berkeley Computer Science
Stuart Russell
Norm Aleks
Intel Corporation
Doug Busch
Kevin Conlon
UCSF Neuroradiology
Pratik Mukherjee, MD PhD
Alisa Gean, MD
UC Berkeley Neuroscience Institute
Robert Knight, MD
Brain Trauma Foundation
Jam Ghajar, MD PhD
NIH R01NS050173, CDC R49CE000460,
NIH K23NS041240 , NIH U10NS058931,
NIH R43NS056639 , UC Discovery Program,
McDonnell-Pew Foundation