ABSTRACT
Automatic discovery of medical knowledge using data mining has great potential benefit in improving population health and reducing healthcare cost. Discovering adverse drug reaction (ADR) is especially important because of the significant morbidity of ADRs to patients. Recently, more and more patients describe the ADRs they experienced and seek for help through online health forums, creating great opportunities for these forums to discover previously unknown ADRs.
In this paper, we propose a novel unsupervised approach to tap into the increasingly available health forums to mine the side effect symptoms of drugs mentioned by forum users. Our approach is based on a novel probabilistic mixture model of symptoms, where the side effect symptoms and disease symptoms are explicitly modeled with two separate component models, and discovery of side effect symptoms can be achieved in an unsupervised way through fitting the mixture model to the forum data. Extensive experiments on online health forums demonstrate that our proposed model is effective for discovering the reported ADRs on forums in a completely unsupervised way. The mined knowledge using our model is directly useful for increasing our understanding of more challenging ADRs, such as long-term side effects, drug-drug interactions, and rare side effects. Since our approach is unsupervised, it can be applied to mining large amounts of growing forum data to discover new knowledge about ADRs, helping many patients become aware of possible ADRs.
- D. W. Bates and et al. Incidence of adverse drug events and potential adverse drug events. JAMA, 274(1):29--34, 1995.Google ScholarCross Ref
- D. W. Bates and et al. The costs of adverse drug events in hospitalized patients. JAMA, 277(4):307--311, 1997.Google ScholarCross Ref
- D. M. Blei, A. Y. Ng, and M. I. Jordan. Latent dirichlet allocation. JMLR, 3:993--1022, 2003. Google ScholarDigital Library
- O. Bodenreider. The unified medical language system (umls): integrating biomedical terminology. Nucleic acids research, 32(suppl 1):D267--D270, 2004.Google Scholar
- U. A. Boelsterli. Diclofenac-induced liver injury: a paradigm of idiosyncratic drug toxicity. Toxicology and applied pharmacology, 192(3):307--322, 2003.Google Scholar
- B. W. Chee, R. Berlin, and B. Schatz. Predicting adverse drug events from personal health messages. In AMIA, volume 2011, page 217. American Medical Informatics Association, 2011.Google Scholar
- R. Crenshaw. Prozac and premature ejaculation. In Annual Meeting of the American Association of Sex Educators, Counselors and Therapists, Orlando, FL, 1992.Google Scholar
- J. Davidson. Seizures and bupropion: a review. The Journal of clinical psychiatry, 50(7):256--261, 1989.Google Scholar
- eHealthMe. Review: could ativan(r) cause high blood sugar? http://www.ehealthme.com/ds/Ativan(R)/high+blood+sugar, 2014.Google Scholar
- eHealthMe. Review: could phentermine cause bone and joint pain? http://www.ehealthme.com/ds/phentermine/bone+and+joint+pain, 2014.Google Scholar
- C. for Disease Control, P. (CDC, et al. Adverse events associated with ephedrine-containing products--texas, december 1993-september 1995. MMWR. Morbidity and mortality weekly report, 45(32):689, 1996.Google Scholar
- C. Friedman. Discovering novel adverse drug events using natural language processing and mining of the electronic health record. In Artificial Intelligence in Medicine, pages 1--5. Springer, 2009. Google ScholarDigital Library
- K. M. Giacomini and et al. When good drugs go bad. Nature, 446(7139):975--977, 2007.Google ScholarCross Ref
- T. Hofmann. Probabilistic latent semantic indexing. In SIGIR'99, pages 50--57. ACM, 1999. Google ScholarDigital Library
- S. Hornby. Effects of methadone with xanax. http://www.livestrong.com/article/260570-effects-of-methadone-with-xanax/, 2010.Google Scholar
- Y. Jiang, Q. V. Liao, Q. Cheng, R. B. Berlin, and B. R. Schatz. Designing and evaluating a clustering system for organizing and integrating patient drug outcomes in personal health messages. In AMIA Annual Symposium Proceedings, volume 2012, page 417. American Medical Informatics Association, 2012.Google Scholar
- S. J. Kish. Pharmacologic mechanisms of crystal meth. Canadian Medical Association Journal, 178(13):1679--1682, 2008.Google ScholarCross Ref
- R. Leaman, L. Wojtulewicz, R. Sullivan, A. Skariah, J. Yang, and G. Gonzalez. Towards internet-age pharmacovigilance: extracting adverse drug reactions from user posts to health-related social networks. In 2010 workshop on biomedical natural language processing, pages 117--125. ACL, 2010. Google ScholarDigital Library
- R. Leone and et al. Drug-related deaths. Drug Safety, 31(8):703--713, 2008.Google ScholarCross Ref
- M. Lindquist and et al. A retrospective evaluation of a data mining approach to aid finding new adverse drug reaction signals in the who international database. Drug Safety, 23(6):533--542, 2000.Google ScholarCross Ref
- J. Liu, A. Li, and S. Seneff. Automatic drug side effect discovery from online patient-submitted reviews: Focus on statin drugs. In IMMM 2011, pages 91--96, 2011.Google Scholar
- X. Liu and H. Chen. Azdrugminer: an information extraction system for mining patient-reported adverse drug events in online patient forums. In Smart Health, pages 134--150. Springer, 2013. Google ScholarDigital Library
- Y. Lu and C. Zhai. Opinion integration through semi-supervised topic modeling. In WWW'08, pages 121--130. ACM, 2008. Google ScholarDigital Library
- J. R. Nebeker, P. Barach, and M. H. Samore. Clarifying adverse drug events: a clinician's guide to terminology, documentation, and reporting. Annals of internal medicine, 140(10):795--801, 2004.Google Scholar
- C. Parker. Zoloft drug interactions. http://www.drugsdb.com/rx/zoloft/zoloft-drug-interactions/, 2012.Google Scholar
- M. Pirmohamed, A. M. Breckenridge, N. R. Kitteringham, and B. K. Park. Fortnightly review: adverse drug reactions. BMJ: British Medical Journal, 316(7140):1295, 1998.Google ScholarCross Ref
- J. C. Prather and et al. Medical data mining: knowledge discovery in a clinical data warehouse. In AMIA, page 101. American Medical Informatics Association, 1997.Google Scholar
- D. Ramage, D. Hall, R. Nallapati, and C. D. Manning. Labeled lda: A supervised topic model for credit attribution in multi-labeled corpora. In EMNLP: Volume 1-Volume 1, pages 248--256. ACL, 2009. Google ScholarDigital Library
- P. Sondhi, J. Sun, H. Tong, and C. Zhai. Sympgraph: a framework for mining clinical notes through symptom relation graphs. In KDD'12, pages 1167--1175. ACM, 2012. Google ScholarDigital Library
- T. Ulrich. Drug safety and side effects: Detection, or prediction? http://vectorblog.org/2012/01/drug-safety-and-side-effects-detection-or-prediction/, 2012.Google Scholar
- C. S. van Der Hooft and et al. Adverse drug reaction-related hospitalisations. Drug Safety, 29(2):161--168, 2006.Google ScholarCross Ref
- B. J. Welch and et al. Biochemical and stone-risk profiles with topiramate treatment. American journal of kidney diseases, 48(4):555--563, 2006.Google Scholar
- R. W. White and E. Horvitz. Studies of the onset and persistence of medical concerns in search logs. In SIGIR'12, pages 265--274. ACM, 2012. Google ScholarDigital Library
- H. Wu, H. Fang, and S. J. Stanhope. An early warning system for unrecognized drug side effects discovery. In Proceedings of the 21st international conference companion on World Wide Web, pages 437--440. ACM, 2012. Google ScholarDigital Library
- T.-Y. Wu and et al. Ten-year trends in hospital admissions for adverse drug reactions in england 1999--2009. Journal of the Royal Society of Medicine, 103(6):239--250, 2010.Google ScholarCross Ref
- A. Yates and N. Goharian. Adrtrace: detecting expected and unexpected adverse drug reactions from user reviews on social media sites. In Advances in Information Retrieval, pages 816--819. Springer, 2013. Google ScholarDigital Library
- A. Yates, N. Goharian, and O. Frieder. Extracting adverse drug reactions from forum posts and linking them to drugs. In Proceedings of the 2013 ACM SIGIR Workshop on Health Search and Discovery, 2013.Google Scholar
- Q. Zeng, S. Kogan, N. Ash, R. Greenes, and A. Boxwala. Characteristics of consumer terminology for health information retrieval. Methods of information in medicine, 41(4):289--298, 2002.Google Scholar
Index Terms
- SideEffectPTM: an unsupervised topic model to mine adverse drug reactions from health forums
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 ...
A High Performance Agent-Based System for Reporting Suspected Adverse Drug Reactions
ITNG '12: Proceedings of the 2012 Ninth International Conference on Information Technology - New GenerationsAdverse drug reactions (ADRs) represent a serious worldwide problem. Current post-marketing ADR detection approaches largely rely on spontaneous reports filed by various healthcare professionals such as physicians, pharmacists et.al.. Underreporting is ...
Extraction of Clinical Phenotypic Information from Online Heterogeneous Healthcare Networks
ICHI '15: Proceedings of the 2015 International Conference on Healthcare InformaticsMillions of patients are affected by adverse drug reactions (ADRs) every year. It represents a substantial burden on healthcare resources. Pharmacovigilance using text and data analytics has drawn substantial attention in the recent years. These ...
Comments