Abstract
Postmarketing drug safety surveillance is important because many potential adverse drug reactions cannot be identified in the premarketing review process. It is reported that about 5% of hospital admissions are attributed to adverse drug reactions and many deaths are eventually caused, which is a serious concern in public health. Currently, drug safety detection relies heavily on voluntarily reporting system, electronic health records, or relevant databases. There is often a time delay before the reports are filed and only a small portion of adverse drug reactions experienced by health consumers are reported. Given the popularity of social media, many health social media sites are now available for health consumers to discuss any health-related issues, including adverse drug reactions they encounter. There is a large volume of health-consumer-contributed content available, but little effort has been made to harness this information for postmarketing drug safety surveillance to supplement the traditional approach. In this work, we propose the association rule mining approach to identify the association between a drug and an adverse drug reaction. We use the alerts posted by Food and Drug Administration as the gold standard to evaluate the effectiveness of our approach. The result shows that the performance of harnessing health-related social media content to detect adverse drug reaction is good and promising.
- AdverseEvents. About us. http://www.adverseevents.com/about.php.Google Scholar
- Alan, M. H., Stephanie, J. R., Ronald, K. P., Donald, J. O. H., and Kevin, H. 2007. Using data mining to predict safety actions from FDA adverse event reporting system data. Drug Inf. J. 41, 5, 633.Google Scholar
- Benton, A., Ungar, L., Hill, S., Hennessy, S., Mao, J., Chung, A., and Holmes, J. H. 2011. Identifying potential adverse effects using the web: A new approach to medical hypothesis generation. J. Biomed. Inf. 44, 6, 989. Google ScholarDigital Library
- Benton, A., Holmes, J., Hill, S., Chung, A., and Ungar, L. 2012. Medpie: An information extraction package for medical message board posts. Bioinf. 28, 5, 743--744. Google ScholarDigital Library
- Biriell, C. and Edwards, I. R. 1997. Reasons for reporting adverse drug reactions--Some thoughts based on an international review. Pharmacoepidemiol. Drug Safety, 6, 1, 21--26.Google ScholarCross Ref
- Chee, B. W., Berlin, R., and Schatz, B. 2011. Predicting adverse drug events from personal health messages. In Proceedings of the Annual AMIA Symposium. 217--226.Google Scholar
- DuMouchel, W. 1999. Bayesian data mining in large frequency tables, with an application to the FDA spontaneous reporting system. Amer. Statist. 53, 3, 177--190.Google Scholar
- Edwards, I. R. and Aronson, J. K. 2000. Adverse drug reactions: Definitions, diagnosis, and management. Lancet 356, 9237, 1255--1259.Google Scholar
- Evans, S. J. W., Waller, P. C., and Davis, S. 2001. Use of proportional reporting ratios (PRRS) for signal generation from spontaneous adverse drug reaction reports. Pharmacoepidemiol. Drug Safety, 10, 6, 483--486.Google ScholarCross Ref
- Fox, S. 2013. Pew internet: Health. http://www.pewinternet.org/Commentary/2011/November/Pew-Internet-Health.aspx.Google Scholar
- Hakobyan, L., Haaijer-Ruskamp, F. M., De Zeeuw, D., Dobre, D., and Denig, P. 2011. A review of methods used in assessing non-serious adverse drug events in observational studies among type 2 diabetes mellitus patients. Health Qual. Life Outcomes 9, 1, 83--83.Google ScholarCross Ref
- Han, J., Kamber, M., and Pei, J. 2006. Data Mining: Concepts and Techniques. Elsevier. Google ScholarDigital Library
- Hauben, M. 2004. Early postmarketing drug safety surveillance: Data mining points to consider. Ann. Pharmacotherapy 38, 10, 1625--1630.Google ScholarCross Ref
- Hazell, L. and Shakir, S. A. W. 2006. Under-reporting of adverse drug reactions: A systematic review. Drug Safety 29, 5, 385--396.Google ScholarCross Ref
- Hofer-Dueckelmann, C., Prinz, E., Beindl, W., Szymanski, J., Fellhofer, G., Pichler, M., and Schuler, J. 2011. Adverse drug reactions (ADRS) associated with hospital admissions - Elderly female patients are at highest risk. Int. J. Clinical Pharmacol. Therapeutics 49, 10, 577--586.Google ScholarCross Ref
- Ji, Y., Massanari, R. M., Ager, J., Yen, J., Miller, R. E., and Ying, H. 2007. A fuzzy logic-based computational recognition-primed decision model. Inf. Sci. 177, 20, 4338--4353. Google ScholarDigital Library
- Ji, Y., Ying, H., Dews, P., Farber, M. S., Mansour, A., Tran, J., and Massanari, R. M. 2010. A fuzzy recognition-primed decision model-based causal association mining algorithm for detecting adverse drug reactions in postmarketing surveillance. In Proceedings of the IEEE International Conference on Fuzzy Systems (FUZZ’10). 1--8.Google Scholar
- Ji, Y., Hao, Y., Dews, P., Mansour, A., Tran, J., Miller, R. E., and Massanari, R. M. 2011a. A Potential causal association mining algorithm for screening adverse drug reactions in postmarketing surveillance. IEEE Trans. Inf. Technol. Biomed. 15, 3, 428--437. Google ScholarDigital Library
- Ji, Y., Ying, H., Dews, P., Mansour, A., Tran, J., Miller, R. E., and Massanari, R. M. 2011b. A potential causal association mining algorithm for screening adverse drug reactions in postmarketing surveillance. IEEE Trans. Inf. Technol. Biomed. 15, 3, 428--437. Google ScholarDigital Library
- Jin, H., Chen, J., He, H., Williams, G. J., Kelman, C., and O’Keefe, C. M. 2008. Mining unexpected temporal associations: Applications in detecting adverse drug reactions. IEEE Trans. Inf. Technol. Biomed. 12, 4, 488--500. Google ScholarDigital Library
- Kohn, L. T., Corrigan, J., and Donaldson, M. S., Eds. 2000. To Err is Human: Building a Safer Health System. National Academy Press, Washington, D.C.Google Scholar
- Kongkaew, C., Noyce, P. R., and Ashcroft, D. M. 2008. Hospital admissions associated with adverse drug reactions: A systematic review of prospective observational studies. Ann. Pharmacotherapy, 42, 7, 1017--1025.Google ScholarCross Ref
- Kubota, K., Koide, D., and Hirai, T. 2004. Comparison of data mining methodologies using japanese spontaneous reports. Pharmacoepidemiol. Drug Safety, 13, 6, 387--394.Google ScholarCross Ref
- Lanctot, K. L. and Naranjo, C. A. 1994. Computer-assisted evaluation of adverse events using a bayesian-approach. J. Clinical Pharmacol. 34, 2, 142--147.Google ScholarCross Ref
- Lazarou, J., Pomeranz, B. H., and Corey, P. N. 1998. Incidence of adverse drug reactions in hospitalized patients: A meta-analysis of prospective studies. J. Amer. Med. Assoc. 279, 15, 1200--1205.Google ScholarCross Ref
- Leaman, R., Wojtulewicz, L., Sullivan, R., Skariah, A., Yang, J., and Gonzalez, G. 2010. Towards internet-age pharmacovigilance: Extracting adverse drug reactions from user posts to health-related social networks. In Proceedings of the Workshop on Biomedical Natural Language Processing (ACL’10). 117--125. Google ScholarDigital Library
- Lindquist, M., Edwards, I. R., Bate, A., Fucik, H., Nunes, A. M., and Stahl, M. 1999. From association to alert - A revised approach to international signal analysis. Pharmacoepidemiol. Drug Safety 1, 15--25.Google ScholarCross Ref
- MedHelp. 1994. Medical information, forums and communities. http://www.medhelp.org/aboutus.htm.Google Scholar
- Nikfarjam, A. and Gonzalez, G. H. 2011. Pattern mining for extraction of mentions of adverse drug reactions from user comments. In Proceedings of the AMIA Annual Symposium. 1019--1026.Google Scholar
- Park, M. Y., Yoon, D., Lee, K., Kang, S. Y., Park, I., Lee, S. H., and Kim, J. H. 2011. A novel algorithm for detection of adverse drug reaction signals using a hospital electronic medical record database. Pharmacoepidemiol. Drug Safety 20, 6, 598--607.Google ScholarCross Ref
- Pouliot, Y., Chiang, A. P., and Butte, A. J. 2011. Predicting adverse drug reactions using publically available pubchem bioassay data. Clinical Pharmacol. Therapeutics 90, 1, 90--99.Google ScholarCross Ref
- SideEffective. 2014. SideEffective - The voice of web about medications. http://www.sideeffective.com/about/.Google Scholar
- Szarfman, A., Tonning, J. M., and Doraiswamy, P. M. 2004. Pharmacovigilancein the 21st century: New systematic tools for an old problem. Pharmacotherapy, 24, 1099--1104.Google ScholarCross Ref
- Tatonetti, N., Denny, J., Murphy, S., Fernald, G., Krishnan, G., Castro, V., and Roden, D. 2011. Detecting drug interactions from adverse-event reports: Interaction between paroxetine and pravastatin increases blood glucose levels. Clinical Pharmacol. Therapeutics, 90, 1, 133--142.Google ScholarCross Ref
- Treato. 2013. Treato: Patient intelligence based on real-life experiences. http://treato.com/about/.Google Scholar
- van Puijenbroek, E. P., Egberts, A. C. G., Meyboom, R. H. B., and Leufkens, H. G. M. 1999. Signalling possible drug--Drug interactions in a spontaneous reporting system: Delay of withdrawal bleeding during concomitant use of oral contraceptives and itraconazole. Brit. J. Clinical Pharmacol. 47, 689--693.Google ScholarCross Ref
- Wang, X., Hripcsak, G., Markatou, M., and Friedman, C. 2009. Active computerized pharmacovigilance using natural language processing, statistics, and 22 electronic health records: A feasibility study. J. Amer. Med. Inf. Assoc. 16, 3, 328--337.Google ScholarCross Ref
- White, R. W., Tatonetti, N. P., Shah, N. H., Altman, R. B., and Horvitz, E. 2013. Web-scale pharmacovigilance: Listening to signals from the crowd. J. Amer. Med. Informatics Assoc. 20, 3, 404--408.Google ScholarCross Ref
- Wood, A. J. J. 2000. Thrombotic thrombocytopenic purpura and clopidogrel --- A need for new approaches to drug safety. New England J. Med. 342, 24, 1824--1826.Google ScholarCross Ref
- Wu, Y. T. and Makuch, R. W. 2006. Detecting rare adverse events in postmarketing studies: Sample size considerations. Drug Inf. J. 40, 1, 89--98.Google ScholarCross Ref
- Yang, C. C., Jiang, L., Yang, H., and Tang, X. 2012. Detecting signals of adverse drug reactions from health consumer contributed content in social media. In Proceedings of the ACM SIGKDD Workshop on Health Informatics.Google Scholar
- Zeng, Q. T. and Tse, T. 2006. Exploring and developing consumer health vocabularies. J. Amer. Med. Inf. Assoc. 13, 1, 24--29.Google ScholarCross Ref
- Zeng, Q. T., Tse, T., Divita, G., Keselman, A., Crowell, J., and Browne, A. C. 2006. Exploring lexical forms: First-generation consumer health vocabularies. In Proceedings of the AMIA Annual Symposium. 1155--1155.Google Scholar
Index Terms
- Postmarketing Drug Safety Surveillance Using Publicly Available Health-Consumer-Contributed Content in Social Media
Recommendations
Using Health-Consumer-Contributed Data to Detect Adverse Drug Reactions by Association Mining with Temporal Analysis
Regular Papers and Special Section on Intelligent Healthcare InformaticsSince adverse drug reactions (ADRs) represent a significant health problem all over the world, ADR detection has become an important research topic in drug safety surveillance. As many potential ADRs cannot be detected though premarketing review, drug ...
Social media mining for drug safety signal detection
SHB '12: Proceedings of the 2012 international workshop on Smart health and wellbeingAdverse Drug Reactions (ADRs) represent a serious problem all over the world. They may complicate a patient's medical conditions and increase the morbidity, even mortality. Drug safety currently depends heavily on post-marketing surveillance, because ...
Identifying Unknown Adverse Drug Reaction Signal Pairs in Postmarketing Surveillance Using an Active Multi-agent System Approach
CITWORKSHOPS '08: Proceedings of the 2008 IEEE 8th International Conference on Computer and Information Technology WorkshopsDiscovering unknown adverse drug reactions (ADRs) in postmarketing surveillance as early as possible is of great importance. The current approach to postmarketing surveillance primarily relies on spontaneous reporting. It is passive and suffers from ...
Comments