Mining Internet Conversations for Evidence of Herbal-Associated Adverse Events Abstract This application addresses broad Challenge Area (10), Information Technology for Processing Health Care Data and specific Challenge Topic 10-LM-102: Informatics for Post- Marketing Surveillance. Often, users of online resources such as discussion boards seek advice about topics they are hesitant to discuss with providers. One such topic is the use of herbal supplements. Relatively little is known about the use and effects of these supplements, primarily due to patient and provider reticence, but also owing to the lack of a formal reporting mechanism. As a result, adverse events and interactions possibly related to herbal use are difficult to evaluate in a population-based investigation. The potential impact for monitoring side effects and adverse events associated with herbal use as well as prescription drug interactions with herbals is highly important. The goal of this project is to develop, apply, and evaluate computational intelligence tools for mining conversational text for evidence of adverse events and side effects of herbals and prescription drugs reported by users of online communication resources relating to breast and prostate cancer. This project will use these informatics tools as the cornerstone of a new approach to post-marketing surveillance, and has been determined by the National Library of Medicine to be responsive to the stated Challenge Topic. This project will be conducted at the University of Pennsylvania School of Medicine, which contributes substantially to the local economy. In 2008, the School created 37,000 jobs and $5.4 billion in regional economic activity. This project will create or retain eight jobs. The School's ability to fill these positions is evident: in 2008, Penn received more than 24,600 applications for just 840 open staff research positions. Mining Internet Conversations for Evidence of Herbal-Associated Adverse Events There has been increasing discussion about the use of herbals with the advent of online resources such as message boards, blogs, and chat rooms. In mining the text from such online, new information about side effects and adverse events associated with herbal use as well as prescription drug interactions with herbals will be discovered. This is highly important for the health of the public, as it stands to create the framework for an herbal sentinel network system.

Public Health Relevance

Mining Internet Conversations for Evidence of Herbal-Associated Adverse Events There has been increasing discussion about the use of herbals with the advent of online resources such as message boards, blogs, and chat rooms. In mining the text from such online, new information about side effects and adverse events associated with herbal use as well as prescription drug interactions with herbals will be discovered. This is highly important for the health of the public, as it stands to create the framework for an herbal sentinel network system.

Agency
National Institute of Health (NIH)
Institute
National Library of Medicine (NLM)
Type
NIH Challenge Grants and Partnerships Program (RC1)
Project #
1RC1LM010342-01
Application #
7820824
Study Section
Special Emphasis Panel (ZRG1-RPHB-E (58))
Program Officer
Florance, Valerie
Project Start
2009-09-30
Project End
2011-09-29
Budget Start
2009-09-30
Budget End
2010-09-29
Support Year
1
Fiscal Year
2009
Total Cost
$482,925
Indirect Cost
Name
University of Pennsylvania
Department
Biostatistics & Other Math Sci
Type
Schools of Medicine
DUNS #
042250712
City
Philadelphia
State
PA
Country
United States
Zip Code
19104
Mao, Jun J; Chung, Annie; Benton, Adrian et al. (2013) Online discussion of drug side effects and discontinuation among breast cancer survivors. Pharmacoepidemiol Drug Saf 22:256-62
Benton, A; Holmes, J H; Hill, S et al. (2012) medpie: an information extraction package for medical message board posts. Bioinformatics 28:743-4
Benton, Adrian; Hill, Shawndra; Ungar, Lyle et al. (2011) A system for de-identifying medical message board text. BMC Bioinformatics 12 Suppl 3:S2
Benton, Adrian; Ungar, Lyle; Hill, Shawndra et al. (2011) Identifying potential adverse effects using the web: a new approach to medical hypothesis generation. J Biomed Inform 44:989-96
Hill, Shawndra; Mao, Jun; Ungar, Lyle et al. (2011) Natural supplements for H1N1 influenza: retrospective observational infodemiology study of information and search activity on the Internet. J Med Internet Res 13:e36