Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences...

15
Biomedical Informatics 1 Dynamic Enhancement of Drug Product Labels Through Semantic Web Technologies (A W3C HCLS IG Use Case) Richard Boyce, University of Pittsburgh Oktie Hassanzadeh, IBM Research Jyotishman Pathak, Mayo Clinic Jodi Schneider, DERI, Galway Maria Liakata, Aberystwyh University/EMBL-EBI Anita de Waard, Elsevier Department of Biomedical Informatics

Transcript of Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences...

Page 1: Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences 2012

Biomedical Informatics1

Dynamic Enhancement of Drug Product Labels Through Semantic Web Technologies (A W3C HCLS IG Use Case)

Richard Boyce, University of PittsburghOktie Hassanzadeh, IBM ResearchJyotishman Pathak, Mayo ClinicJodi Schneider, DERI, GalwayMaria Liakata, Aberystwyh University/EMBL-EBIAnita de Waard, Elsevier

Department of Biomedical Informatics

Page 2: Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences 2012

Biomedical Informatics2

The problem• Drug product labels are a key source of

information– Drug efficacy, effectiveness, safety, use

• However, much of the information in drug product labeling is incomplete or not up to date with the scientific literature

Page 3: Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences 2012

Biomedical Informatics3

Missing drug-drug interactions• Example:

– “Both clopidogrel and ticlopidine significantly inhibited the CYP2B6-catalyzed bupropion hydroxylation. Patients receiving either clopidogrel or ticlopidine are likely to require dose adjustments when treated with drugs primarily metabolized by CYP2B6.” [1]

• Search bupropion product labels for “clopidogrel”– No mention at all in Aplenzin ER insert [2]

– Mention in the generic tablet insert [3], but refers only to hypothetical interaction

1. Turpeinen M, Tolonen A, Uusitalo J, Jalonen J, Pelkonen O, Laine K. Effect of clopidogrel and ticlopidine on cytochrome P450 2B6 activity as measured by bupropion hydroxylation. Clin Pharmacol Ther. 2005 Jun;77(6):553-9.2. http://dailymed.nlm.nih.gov/dailymed/lookup.cfm?setid=2315d6e5-144d-4163-9711-f855c759cf8e3. http://dailymed.nlm.nih.gov/dailymed/lookup.cfm?setid=e537ed50-6677-45eb-9e62-af62d3831f19

Page 4: Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences 2012

Biomedical Informatics4

Other notable incomplete information • Clinical effectiveness

– Ex: Switch to venlafaxine in adolescents: • “A switch to another SSRI was just as efficacious as a

switch to venlafaxine and resulted in fewer adverse effects.” [1]

• Age-related clearance data – Product labels rarely have this information even

when published [2]

• Metabolic inhibition– Numerous examples of missing information [3]

1. Brent D, Emslie G, Clarke G, Wagner KD, Asarnow JR, Keller M, Vitiello B, Ritz L, Iyengar S, Abebe K, irmaher B, Ryan N, Kennard B, Hughes C, DeBar L, McCracken J, Strober M, Suddath R, Spirito A, Leonard H, Melhem N, Porta G, Onorato M, Zelazny J. Switching to another SSRI or to venlafaxine with or without cognitive behavioral therapy for adolescents with SSRI-resistant depression: the TORDIA randomized controlled trial. JAMA. 2008 Feb 27;299(8):901-13.

2. Boyce RD, Handler SM, Karp JF, Hanlon JT. Age-Related Changes in Antidepressant Pharmacokinetics and Potential Drug-Drug Interactions: A Comparison of Evidence-Based Literature and Package Insert Information. Am J Geriatr Pharmacother. 2012 Apr;10(2):139-50

3. Boyce R, Harkema H, Conway M. Leveraging the semantic web and natural language processing to enhance drug-mechanism knowledge in drug product labels. In: Proceedings of the 1st ACM International Health Informatics Symposium. IHI ’10. New York, NY, USA: ACM; 2010:492–496.

Page 5: Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences 2012

Current use of product labels

Page 6: Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences 2012

Biomedical Informatics6

What are we suggesting then?

• “…build a linked open data store of scientific information that updates or elaborates on medication safety statements present in drug product labels.”

- W3C HCLS IG Use Case (http://goo.gl/wP4Mz)

Page 7: Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences 2012

Proposed innovation – take claims present in semantic web resources….

Page 8: Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences 2012

…create a linked dataset that merges those claims and identifies where they should be located in the product label….

Page 9: Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences 2012

…create customized views of the new linked dataset tailored toward various drug experts and decision support tools

Page 10: Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences 2012

Biomedical Informatics10

Proof of concept• http://tinyurl.com/c53skm4

– 29 psychotropic drug products – Created using four Semantic Web nodes

1. http://thedatahub.org/dataset/linked-structured-product-labels2. http://thedatahub.org/dataset/linkedct3. http://bioportal.bioontology.org/ontologies/471014. http://thedatahub.org/dataset/the-drug-interaction-knowledge-base

Page 11: Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences 2012

Biomedical Informatics11

Preliminary resultsDrug ClinicalTrials.gov

relevant to the Clinical Studies section

DDIs apparently novel to the Drug Interactions section

NDF-RT DIKBCritical Significant

AntidepressantsBupropion 5 2 4 0Citalopram 4 8 20 1Venlafaxine 2 6 21 3…

AntipsychoticsRisperidone 23 0 10 3Ziprasidone 1 23 55 0…

Sedative Hypnotics

Eszopiclone 3 0 2 0…

Page 12: Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences 2012

Biomedical Informatics12

Issues to be addressed• Ensuring the quality of the claims linked to the

package insert sections– Provenance is key

– Could a drug information “knowledge market” could be created?

• Technical issues with some existing linked open drug data nodes– Now is the time to improve linked open drug data

• Correct RDF mappings, accurate encodings

• Graph and data provenance

Page 13: Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences 2012

Biomedical Informatics13

Want more information?• Use Case description

– http://goo.gl/wP4Mz

• Google code project– code.google.com/p/swat-4-med-safety/

• Proof of concept– http://tinyurl.com/c53skm4

• Linked data nodes used in the proof of concept– http://thedatahub.org/dataset/linked-structured-product-labels

– http://thedatahub.org/dataset/the-drug-interaction-knowledge-base

– http://thedatahub.org/dataset/linkedct

Page 14: Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences 2012

Biomedical Informatics14

Discussion/questions

Page 15: Discussion of Dynamic Enhancement of Drug Product Labels at Data Integration in the Life Sciences 2012

Biomedical Informatics15

Acknowledgements• The Drug Interaction Knowledge Base team

– John Horn Pharm.D, Carol Collins MD, Greg Gardner, Rob Guzman

• W3C LODD Task Force• Early comments on the Use Case:

– Michel Dumontier and several others who attend W3C HCLS calls