Abstract
Since 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 safety currently depends heavily on postmarketing surveillance. Particularly, current postmarketing surveillance in the United States primarily relies on the FDA Adverse Event Reporting System (FAERS). However, the effectiveness of such spontaneous reporting systems for ADR detection is not as good as expected because of the extremely high underreporting ratio of ADRs. Moreover, it often takes the FDA years to complete the whole process of collecting reports, investigating cases, and releasing alerts. Given the prosperity of social media, many online health communities are publicly available for health consumers to share and discuss any healthcare experience such as ADRs they are suffering. Such health-consumer-contributed content is timely and informative, but this data source still remains untapped for postmarketing drug safety surveillance. In this study, we propose to use (1) association mining to identify the relations between a drug and an ADR and (2) temporal analysis to detect drug safety signals at the early stage. We collect data from MedHelp and use the FDA's alerts and information of drug labeling revision as the gold standard to evaluate the effectiveness of our approach. The experiment results show that health-related social media is a promising source for ADR detection, and our proposed techniques are effective to identify early ADR signals.
- R. Agrawal, T. Imieliński, and A. Swami. 1993. Mining association rules between sets of items in large databases. In Proceedings of the ACM SIGMOD Record. ACM, 207--216. Google ScholarDigital Library
- J. M. Ale and G. H. Rossi. 2000. An approach to discovering temporal association rules. In Proceedings of the 2000 ACM Symposium on Applied Computing-Volume 1. ACM, 294--300. Google ScholarDigital Library
- W.-H. Au and K. C. C. Chan. 2005. Mining changes in association rules: A fuzzy approach. Fuzzy Sets and Systems 149, 1 (2005), 87--104. doi:10.1016/j.fss.2004.07.018 Google ScholarDigital Library
- A. Benton, J. H. Holmes, S. Hill, A. Chung, and L. Ungar. 2012. medpie: An information extraction package for medical message board posts. Bioinformatics 28, 5 (2012), 743--744. Google ScholarDigital Library
- A. Benton, L. Ungar, S. Hill, S. Hennessy, J. Mao, A. Chung, and J. H. Holmes. 2011. Identifying potential adverse effects using the web: A new approach to medical hypothesis generation. Journal of Biomedical Informatics 44, 6 (2011), 989. doi:10.1016/j.jbi.2011.07.005 Google ScholarDigital Library
- M. Boettcher. 2011. Contrast and change mining. Wiley Interdisciplinary Reviews-Data Mining and Knowledge Discovery 1, 3 (2011), 215--230. doi:10.1002/widm.27Google ScholarCross Ref
- A. Cami, A. Arnold, S. Manzi, and B. Reis. 2011. Predicting adverse drug events using pharmacological network models. Science Translational Medicine 3, 114 (2011), 1--11. doi:10.1126/scitranslmed.3002774Google ScholarCross Ref
- B. W. Chee, R. Berlin, and B. Schatz. 2011. Predicting adverse drug events from personal health messages. In Proceedings of the AMIA Annual Symposium. 217.Google Scholar
- X. Chen and I. Petrounias. 1998. A framework for temporal data mining. In Proceedings of the Database and Expert Systems Applications. Springer, 796--805. Google ScholarDigital Library
- W. DuMouchel. 1999. Bayesian data mining in large frequency tables, with an application to the FDA spontaneous reporting system. American Statistician 53, 3 (1999), 177--190.Google Scholar
- I. R. Edwards and J. K. Aronson. 2000. Adverse drug reactions: Definitions, diagnosis, and management. Lancet 356, 9237 (2000), 1255--1259.Google Scholar
- S. J. W. Evans, P. C. Waller, and S. Davis. 2001. Use of proportional reporting ratios (PRRs) for signal generation from spontaneous adverse drug reaction reports. Pharmacoepidemiology and Drug Safety 10, 6 (2001), 483--486.Google ScholarCross Ref
- S. Fox and M. Duggan. 2013. Health Online 2013. Retrieved 5/20/2013, from http://www.pewinternet.org/2013/01/15/health-online-2013/.Google Scholar
- T. F. Gharib, H. Nassar, M. Taha, and A. Abraham. 2010. An efficient algorithm for incremental mining of temporal association rules. Data & Knowledge Engineering 69, 8 (2010), 800--815. Google ScholarDigital Library
- J. Han, M. Kamber, and J. Pei. 2006. Data Mining: Concepts and Techniques. Elsevier. Google ScholarDigital Library
- M. Hauben. 2004. Early postmarketing drug safety surveillance: Data mining points to consider. Annals of Pharmacotherapy 38, 10 (2004), 1625--1630.Google ScholarCross Ref
- L. Hazell and S. A. W. Shakir. 2006. Under-Reporting of Adverse Drug Reactions: A Systematic Review, Vol. 29, pp. 385--385. New Zealand: Adis International.Google Scholar
- A. M. Hochberg, S. J. Reisinger, R. K. Pearson, D. J. O'Hara, and K. Hall. 2007. Using data mining to predict safety actions from FDA adverse event reporting system data. Drug Information Journal 41, 5 (2007), 633.Google ScholarCross Ref
- C. Hofer-Dueckelmann, E. Prinz, W. Beindl, J. Szymanski, G. Fellhofer, M. Pichler, and J. Schuler. 2011. Adverse drug reactions (ADRs) associated with hospital admissions - elderly female patients are at highest risk. International Journal of Clinical Pharmacology and Therapeutics 49, 10 (2011), 577--586. doi:10.5414/cp201514Google ScholarCross Ref
- Y. Ji, Y. Hao, P. Dews, A. Mansour, J. Tran, R. E. Miller, and R. M. Massanari. 2011. A potential causal association mining algorithm for screening adverse drug reactions in postmarketing surveillance. IEEE Transactions on Information Technology in Biomedicine 15, 3 (2011), 428--437. Google ScholarDigital Library
- Y. Ji, R. M. Massanari, J. Ager, J. Yen, R. E. Miller, and H. Ying. 2007. A fuzzy logic-based computational recognition-primed decision model. Information Sciences 177, 20 (2007), 4338--4353. doi:10.1016/j.ins.2007.02.026 Google ScholarDigital Library
- Y. Ji, H. Ying, P. Dews, M. S. Farber, A. Mansour, J. Tran, and R. M. Massanari. 2010. A fuzzy recognition-primed decision model-based causal association mining algorithm for detecting adverse drug reactions in postmarketing surveillance. Paper presented at the 2010 IEEE International Conference on Fuzzy Systems (FUZZ). 1--8.Google Scholar
- L. Jiang and C. Yang. 2013. Using co-occurrence analysis to expand consumer health vocabularies from social media data. Paper presented at the IEEE International Conference on Healthcare Informatics, Philadelphia, PA, September 8--11, 2013. Google ScholarDigital Library
- L. Jiang, C. C. Yang, and J. Li. 2013. Discovering consumer health expressions from consumer-contributed content. In Proceedings of the Social Computing, Behavioral-Cultural Modeling and Prediction. Springer, 164--174. Google ScholarDigital Library
- H. Jin, J. Chen, H. He, C. Kelman, D. McAullay, and C. M. O'Keefe. 2010. Signaling potential adverse drug reactions from administrative health databases. IEEE Transactions on Knowledge and Data Engineering 22, 6 (2010), 839. Google ScholarDigital Library
- H. Jin, J. Chen, H. He, G. J. Williams, C. Kelman, and C. M. O'Keefe. 2008. Mining unexpected temporal associations: Applications in detecting adverse drug reactions. IEEE Transactions on Information Technology in Biomedicine 12, 4 (2008), 488--500. Google ScholarDigital Library
- C. Kongkaew, P. R. Noyce, and D. M. Ashcroft. 2008. Hospital admissions associated with adverse drug reactions: A systematic review of prospective observational studies. Annals of Pharmacotherapy, 42, 7 (2008), 1017--1025. doi:10.1345/aph.1L037Google ScholarCross Ref
- S. Kotsiantis and D. Kanellopoulos. 2006. Association rules mining: A recent overview. GESTS International Transactions on Computer Science and Engineering 32, 1 (2006), 71--82.Google Scholar
- K. Kubota, D. Koide, and T. Hirai. 2004. Comparison of data mining methodologies using Japanese spontaneous reports. Pharmacoepidemiology and Drug Safety 13, 6 (2004), 387--394.Google ScholarCross Ref
- K. L. Lanctot and C. A. Naranjo. 1994. Computer-assisted evaluation of adverse events using a Bayesian-approach. Journal of Clinical Pharmacology 34, 2 (1994), 142--147.Google ScholarCross Ref
- J. Lazarou, B. H. Pomeranz, and P. N. Corey. 1998. Incidence of adverse drug reactions in hospitalized patients: A meta-analysis of prospective studies. JAMA: Journal of the American Medical Association 279, 15 (1998), 1200--1205. doi:10.1001/jama.279.15.1200Google ScholarCross Ref
- R. Leaman, L. Wojtulewicz, R. Sullivan, A. Skariah, J. Yang, and G. Gonzalez. 2010. Towards Internet-age pharmacovigilance: Extracting adverse drug reactions from user posts to health-related social networks. Proceedings of the 2010 Workshop on Biomedical Natural Language Processing. ACL, 117--125. Google ScholarDigital Library
- C.-H. Lee, C.-R. Lin, and M.-S. Chen. 2001. On mining general temporal association rules in a publication database. In Proceedings of the IEEE International Conference on Data Mining (ICDM'01). IEEE, 337--344. Google ScholarDigital Library
- W.-J. Lee and S.-J. Lee. 2004. Discovery of fuzzy temporal association rules. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics 34, 6 (2004), 2330--2342. Google ScholarDigital Library
- Y. Li, P. Ning, X. S. Wang, and S. Jajodia. 2003. Discovering calendar-based temporal association rules. Data & Knowledge Engineering 44, 2 (2003), 193--218. doi:10.1016/s0169-023x(02)00135-0 Google ScholarDigital Library
- W.-Y. Lin, H.-Y. Li, J.-W. Du, W.-Y. Feng, C.-F. Lo, and V.-W. Soo. 2012. iADRs: Towards online adverse drug reaction analysis. SpringerPlus 1, 1 (2012), 1--16.Google ScholarCross Ref
- M. Lindquist, I. R. Edwards, A. Bate, H. Fucik, A. M. Nunes, and M. Stahl. 1999. From association to alert - A revised approach to international signal analysis. Pharmacoepidemiology and Drug Safety 1 (1999), 15--25.Google ScholarCross Ref
- X. Liu and H. Chen. 2013. AZDrugMiner: An information extraction system for mining patient-reported adverse drug events in online patient forums. Smart Health. Springer, 134--150. Google ScholarDigital Library
- Med Help. (1994, Last Updated 6/20/2011). Medical information, forums and communities: About us. Retrieved 1/29/2014, from http://www.medhelp.org/aboutus.htm.Google Scholar
- A. Nikfarjam and G. H. Gonzalez. 2011. Pattern mining for extraction of mentions of adverse drug reactions from user comments. AMIA Annual Symposium Proceedings 2011. 1019--1026.Google Scholar
- Y. Pouliot, A. P. Chiang, and A. J. Butte. 2011. Predicting adverse drug reactions using publicly available PubChem bioassay data. Clinical Pharmacology & Therapeutics 90, 1 (2011), 90--99.Google ScholarCross Ref
- J. F. Roddick and M. Spiliopoulou. 2002. A survey of temporal knowledge discovery paradigms and methods. IEEE Transactions on Knowledge and Data Engineering 14, 4 (2002), 750--767. Google ScholarDigital Library
- K. Shanmugapriya, D. Shanmugapriya, H. S. Parveen, and V. Niranjani. 2011. N-Unexpected temporal association rule for diagnosing adverse drug reaction from health database. International Proceedings of Computer Science and Information Technology (IPCSIT'11). 18.Google Scholar
- A. Szarfman, J. M. Tonning, and P. M. Doraiswamy. 2004. Pharmacovigilancein the 21st century: New systematic tools for an old problem. Pharmacotherapy 24, (2004), 1099--1104.Google Scholar
- E. P. van Puijenbroek, A. C. G. Egberts, R. H. B. Meyboom, and H. G. M. Leufkens. 1999. Signalling possible drug--drug interactions in a spontaneous reporting system: Delay of withdrawal bleeding during concomitant use of oral contraceptives and itraconazole. British Journal of Clinical Pharmacology 47, (1999), 689--693.Google ScholarCross Ref
- H. Wactlar, M. Pavel, and W. Barkis. 2011. Can computer science save healthcare? IEEE Intelligent Systems 26, 5 (2011), 79.Google Scholar
- X. Wang, G. Hripcsak, M. Markatou, and C. Friedman. 2009. Active computerized pharmacovigilance using natural language processing, statistics, and electronic health records: A feasibility study. JAMIA: Journal of the American Medical Informatics Association 16, 3 (2009), 328--337. doi:10.1197/jamia.M3028Google ScholarCross Ref
- R. W. White, N. P. Tatonetti, N. H. Shah, R. B. Altman, and E. Horvitz. 2013. Web-scale pharmacovigilance: listening to signals from the crowd. Journal of the American Medical Informatics Association 20, 3 (2013), 404.Google ScholarCross Ref
- E. Winarko and J. F. Roddick. 2007. ARMADA--an algorithm for discovering richer relative temporal association rules from interval-based data. Data & Knowledge Engineering 63, 1 (2007), 76--90. Google ScholarDigital Library
- A. J. J. Wood. 2000. Thrombotic thrombocytopenic purpura and clopidogrel—A need for new approaches to drug safety. New England Journal of Medicine 342, 24 (2000), 1824--1826. doi:10.1056/nejm200006153422410Google ScholarCross Ref
- C. C. Yang, L. Jiang, H. Yang, and X. Tang. 2012. Detecting signals of adverse drug reactions from health consumer contributed content in social media. Proceedings of ACM SIGKDD Workshop on Health Informatics, Beijing, August 12, 2012.Google Scholar
- C. C. Yang, H. Yang, L. Jiang, and M. Zhang. 2012. Social media mining for drug safety signal detection. Proceedings of ACM CIKM International Workshop on Smart Health and Wellbeing, Maui, Hawaii, October 29, 2012. Google ScholarDigital Library
- Q. Zeng, S. Kogan, N. Ash, R. A. Greenes, and A. A. Boxwala. 2002. Characteristics of consumer terminology for health information retrieval. Methods of Information in Medicine 41, 4 (2002), 289--298.Google ScholarCross Ref
- Q. Zeng, S. Kogan, N. Ash, and R. A. Greenes. 2001. Patient and clinician vocabulary: How different are they? Studies in Health Technology Information (2001), 399--403.Google Scholar
- Q. T. Zeng and T. Tse. 2006. Exploring and developing consumer health vocabularies. JAMIA: Journal of the American Medical Informatics Association 13, 1 (2006), 24--29. doi:10.1197/jamia.M1761Google ScholarCross Ref
- Q. T. Zeng, T. Tse, J. Crowell, G. Divita, L. Roth, and A. C. Browne. 2005. Identifying consumer-friendly display (CFD) names for health concepts. AMIA Annual Symposium Proceedings (2005), 859--863.Google Scholar
- Q. T. Zeng, T. Tse, G. Divita, A. Keselman, J. Crowell, and A. C. Browne. 2006. Exploring lexical forms: First-generation consumer health vocabularies. AMIA Annual Symposium Proceedings (2006), 1155--1155.Google Scholar
Index Terms
- Using Health-Consumer-Contributed Data to Detect Adverse Drug Reactions by Association Mining with Temporal Analysis
Recommendations
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 ...
Postmarketing Drug Safety Surveillance Using Publicly Available Health-Consumer-Contributed Content in Social Media
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 ...
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