square wheels: electronic medical records for discovery research in rheumatoid arthritis
DESCRIPTION
Square wheels: electronic medical records for discovery research in rheumatoid arthritis. ^ genetic. Robert M. Plenge, M.D., Ph.D. October 30, 2009 NCRR sponsored " Using EHR Data for Discovery Research ". HARVARD MEDICAL SCHOOL. Key questions. - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/1.jpg)
Square wheels: electronic medical records for discovery research in rheumatoid arthritis
Robert M. Plenge, M.D., Ph.D.
October 30, 2009
NCRR sponsored "Using EHR Data for Discovery
Research" HARVARDMEDICAL SCHOOL
![Page 2: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/2.jpg)
Key questions
• What are the regulatory obstacles impacting your work?
• What are the resource needs required to replicate your work at other institutions?
• What are the priority short term "translational" questions in your field that would represent the most rapid payoff on investment?
![Page 3: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/3.jpg)
Key questions
How can I implement your approach, and how much
better is it?
![Page 4: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/4.jpg)
![Page 5: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/5.jpg)
genotype
phenotype
clinical care
![Page 6: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/6.jpg)
genotype
phenotype
clinical care
bottleneck
![Page 7: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/7.jpg)
Raychaudhuri et al in press Nature Genetics
October 2009: >30 RA risk loci
20031978 1987 20052004
PTPN22
2008
“shared epitope”hypothesis
HLADR4
2007
PADI4 CTLA4
TNFAIP3STAT4TRAF1-C5IL2-IL21
CD40CCL21CD244IL2RBTNFRSF14PRKCQPIP4K2CIL2RAAFF3
Latest GWAS in 25,000 case-control samples with replication in 20,000 additional samples: >10 new
loci
2009
RELBLKTAGAPCD28TRAF6PTPRCFCGR2APRDM1CD2-CD58
Together explain ~35% of the genetic burden of
disease
![Page 8: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/8.jpg)
genotype
phenotype
clinical carebottleneck
![Page 9: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/9.jpg)
Genetic predictors of response to anti-TNF
therapy in RA
PTPRC/CD45 allelen=1,283 patients
P=0.0001
Submitted to Arth & Rheum
![Page 10: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/10.jpg)
How can we collect DNA and detailed clinical data on >20,000 RA patients?
![Page 11: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/11.jpg)
What are the options for collecting clinical
data and DNA for genetic studies?
![Page 12: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/12.jpg)
Options for clinical + DNA
design Clinical
data
DNA Sample size
cost
clinical trial
+++ +++ + $$$
registry ++ +++ ++ $$
claims data
+ n/a +++ $
EMR ++ +++ +++ $
![Page 13: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/13.jpg)
• Narrative data = free-form written text– info about symptoms, medical history,
medications, exam, impression/plan
• Codified data = structured format– age, demographics, and billing codes
Content of EMRs
EMRs are increasingly utilized!
![Page 14: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/14.jpg)
Gabriel (1994) Arthritis and Rheumatism
This is not a new idea…
Sens: 89%PPV: 57%Sens: 89%PPV: 57%
![Page 15: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/15.jpg)
Gabriel (1994) Arthritis and Rheumatism
Conclusion: The sole reliance on such databases for the diagnosis of RA can result in substantial misdiagnosis.
…but EMR data are “dirty”
![Page 16: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/16.jpg)
Partners HealthCare: 4 million patients
![Page 17: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/17.jpg)
Partners HealthCare: linked by EMR
![Page 18: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/18.jpg)
Partners HealthCare: organized by i2b2
![Page 19: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/19.jpg)
4 million patients
31,171 patients
ICD9 RA and/or CCP checked(goal = high sensitivity)
3,585 RA patients
Classification algorithm(goal = high PPV)
Clinical subsetsClinical subsets
Discarded blood for DNA
![Page 20: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/20.jpg)
• Natural language processing (NLP)– disease terms (e.g., RA, lupus)– medications (e.g., methotrexate)– autoantibodies (e.g., CCP, RF)– radiographic erosions
• Codified data– ICD9 disease codes– prescription medications– laboratory autoantibodies
Our library of RA phenotypes
Qing Zeng
Concept/term Accuracy of concept presence of erosion 88% seropositive 96% CCP positive 98.7% RF positive 99.3% etanercept 100% methotrexate 100%
![Page 21: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/21.jpg)
• Natural language processing (NLP)– disease terms (e.g., RA, lupus)– medications (e.g., methotrexate)– autoantibodies (e.g., CCP, RF)– radiographic erosions
• Codified data– ICD9 disease codes– prescription medications– laboratory autoantibodies
Our library of RA phenotypes
Shawn Murphy
![Page 22: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/22.jpg)
‘Optimal’ algorithm to classify RA:
NLP + codified data
Regression model with a penalty parameter (to avoid over-fitting)
Codified data NLP data
Tianxi Cai, Kat Liao
![Page 23: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/23.jpg)
High PPV with adequate sensitivity
✪392 out of 400 (98%) had definite or possible RA!
![Page 24: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/24.jpg)
This means more patients!
~25% more subjects with the complete algorithm:
3,585 subjects (3,334 with true RA)3,046 subjects (2,680 with true RA)
![Page 25: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/25.jpg)
4 million patients
31,171 patients
ICD9 RA and/or CCP checked(goal = high sensitivity)
3,585 RA patients
Classification algorithm(goal = high PPV)
Discarded blood for DNA
![Page 26: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/26.jpg)
Linking the Datamart-Crimson
NLP
data
Cod
ified
data
![Page 27: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/27.jpg)
• Over 3,000 samples collected to date– cost = $10 per sample
• DNA extracted on >2,400 Buffy coats– cost = $20 per sample– >90% had ≥1 ug of DNA– >99% had ≥5 ug of DNA after WGA
Status of i2b2 Crimson collection
genotyping of 384 SNPs (RA risk alleles, AIMs, other) is ongoing at
Broad Institute
![Page 28: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/28.jpg)
• Measured autoantibodies from plasma– 5 autoantibodies in ~380 RA patients– ~85% are CCP+, ~35% ANA+, ~15%
TPO+
• Question: are non-RA autoantibodies present at increased frequency in RA patients vs matched controls?
stay tuned…more data soon!
Status of i2b2 Crimson collection
![Page 29: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/29.jpg)
Key questions
How can I implement your approach, and how much
better is it?
![Page 30: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/30.jpg)
Key questions
• What are the regulatory obstacles impacting your work?
• What are the resource needs required to replicate your work at other institutions?
• What are the priority short term "translational" questions in your field that would represent the most rapid payoff on investment?
![Page 31: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/31.jpg)
Key questions
• What are the regulatory obstacles impacting your work?
• What are the resource needs required to replicate your work at other institutions?
• What are the priority short term "translational" questions in your fields that would represent the most rapid payoff on investment?
![Page 32: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/32.jpg)
Regulatory obstacles
• IRB approval
• De-identified vs truly anonymous
• Open question: sharing of genetic data
![Page 33: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/33.jpg)
Key questions
• What are the regulatory obstacles impacting your work?
• What are the resource needs required to replicate your work at other institutions?
• What are the priority short term "translational" questions in your fields that would represent the most rapid payoff on investment?
![Page 34: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/34.jpg)
Resources required• Building a research DataMart
– clinical EMR ≠ research EMR– multiple FTE’s to build/maintain
• NLP expertise– open-source software available– iterative process for fine-tuning
• Clinical expertise– understand nature of clinical data
![Page 35: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/35.jpg)
Resources required (cont.)
• Statistical expertise– simple algorithm is not sufficient– prepare for the unexpected!– true for narrative and codified
• Biospecimen collection, DNA extraction– varies by institution– Crimson – Broad Institute
![Page 36: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/36.jpg)
Key questions
• What are the regulatory obstacles impacting your work?
• What are the resource needs required to replicate your work at other institutions?
• What are the priority short term "translational" questions in your field that would represent the most rapid payoff on investment?
![Page 37: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/37.jpg)
4 million patients
31,171 patients
ICD9 RA and/or CCP checked(goal = high sensitivity)
3,585 RA patients
Classification algorithm(goal = high PPV)
Clinical subsetsClinical subsets
Discarded blood for DNA
![Page 38: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/38.jpg)
Characteristics
i2b2 RA CORRONA
total number 3,585 7,971
Mean age (SD) 57.5 (17.5) 58.9 (13.4)
Female (%) 79.9 74.5
Anti-CCP(%) 63 N/A
RF (%) 74.4 72.1
Erosions (%) 59.2 59.7
MTX (%) 59.5 52.8
Anti-TNF (%) 32.6 22.6
Clinical features of patients
CCP has an OR = 1.5 for predicting erosions
![Page 39: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/39.jpg)
Subset patients in clinically meaningful ways: causes of
mortality
NLP+codified data, together with statistical modeling, to define
cardiovascular disease
![Page 40: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/40.jpg)
Non-responder to anti-TNF therapy
NLP+codified data, together with statistical modeling, to define treatment
response
![Page 41: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/41.jpg)
Responder to anti-TNF therapy
NLP+codified data, together with statistical modeling, to define treatment
response
![Page 42: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/42.jpg)
Post-marketing surveillance of adverse events
NLP+codified data, together with statistical modeling, to define treatment
response
pharmacovigilance
![Page 43: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/43.jpg)
Conclusions
![Page 44: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/44.jpg)
Options for clinical + DNA
design Clinical
data
DNA Sample size
cost
clinical trial
+++ +++ + $$$
registry ++ +++ ++ $$
claims data
+ n/a +++ $
EMR ++ +++ +++ $
Conclusion: NLP + codified data, together with appropriate statistical modeling, can yield accurate clinical data.
![Page 45: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/45.jpg)
Options for clinical + DNA
design Clinical
data
DNA Sample size
cost
clinical trial
+++ +++ + $$$
registry ++ +++ ++ $$
claims data
+ n/a +++ $
EMR ++ +++ +++ $
Conclusion: We can collect DNA and plasma in a high-throughput manner.
![Page 46: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/46.jpg)
Options for clinical + DNA
design Clinical
data
DNA Sample size
cost
clinical trial
+++ +++ + $$$
registry ++ +++ ++ $$
claims data
+ n/a +++ $
EMR ++ +++ +++ $
Conclusion: The cost is reasonable...even for >20,000 RA patients!
![Page 47: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/47.jpg)
genotype
phenotype
clinical care
![Page 48: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/48.jpg)
AcknowledgmentsZak KohaneSusanne ChurchillVivian GainerKat LiaoTianxi CaiShawn MurphyQing ZingSoumya RaychaudhuriBeth KarlsonPete SzolovitsLee-Jen WeiLynn Bry (Crimson)Sergey GoryachevBarbara Mawn & many others !
Namaste!
![Page 49: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/49.jpg)
![Page 50: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/50.jpg)
Narrative data (NLP text extractions)
Codified data (ICD9 codes, etc)
![Page 51: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/51.jpg)
Run specific queries
![Page 52: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/52.jpg)
Visualize results in a timeline
![Page 53: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/53.jpg)
Identifying RA patients in our i2b2 RA DataMart
1993 2008
Signs and symptomsDiseases that mimick RA
Medications specific to RANotes (including whether seen by a rheumatologist)
diagnostic codes for RA
Shawn Murphy, Vivian Gainer, others
![Page 54: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/54.jpg)
signs and symptoms c/w RA
RA without other diseases
Specific RA meds, including MTX
Seen by rheumatology
Many diagnostic codes for RA
1993 2008
Identifying RA patients in our i2b2 RA DataMart
![Page 55: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/55.jpg)
Probability of RA: all 31K subjects
Probability of RA
Freq
uen
cy
not RA RA (n=3,585)
![Page 56: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/56.jpg)
ROC curves for algorithms
sensi
tivit
y
1 - specificity
97% specificity
codified + NLP
NLP only
codified only
![Page 57: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/57.jpg)
Other algorithms to classify RA
NLP OnlyCodified only
Portability!
![Page 58: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/58.jpg)
Classification of RA cases (and not RA)
1.00
0.80
0.60
0.40
0.20
0.00
Pro
bab
ility
R
A
Not RA possible Yes RA
threshold
0.29
???
![Page 59: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/59.jpg)
Diagnosis = Ankylosing Spondylitis
(but many RA codes)
A few signs and symptoms c/w RA
NLP with few mentions of RA Specific meds
Visits to BWH/MGH
diagnostic codes for RA
Probability RA = 0.78
![Page 60: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/60.jpg)
Diagnosis = JRA (but many RA codes)
signs and symptoms c/w RA
NLP with “RA” and “JRA”
Specific meds
Visits to the RA Center at BWH
Many diagnostic codes for RA
![Page 61: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/61.jpg)
Probability RA = 0.33
Diagnosis not clear initially…
signs and symptoms c/w RA
NLP without much “RA”, few specific meds (MTX x 1)
…and few diagnostic codes for RA, despite multiple LMR notes, including visits to the BWH Arthritis Center
![Page 62: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/62.jpg)
Now the false negatives…
![Page 63: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/63.jpg)
Diagnosed in 1992, little follow-up
For some reason few RA diagnostic codes
Probability RA = 0.11
![Page 64: Square wheels: electronic medical records for discovery research in rheumatoid arthritis](https://reader036.vdocuments.mx/reader036/viewer/2022062408/5681389e550346895da05724/html5/thumbnails/64.jpg)
Enbrel (etanercept)codified: 1,628NLP: 3,796
overlap: 1,612 (99%)
Note: review of 50 NLPoccurrences shows that 38 out of 50 actively on Enbrel
Medications: codified data vs. NLP