Abstract
Adverse drug events (ADEs) are a major concern and point of emphasis for the medical profession, government, and society. A diverse set of techniques from epidemiology, statistics, and computer science are being proposed and studied for ADE discovery from observational health data (e.g., EHR and claims data), social network data (e.g., Google and Twitter posts), and other information sources. Methodologies are needed for evaluating, quantitatively measuring and comparing the ability of these various approaches to accurately discover ADEs. This work is motivated by the observation that text sources such as the Medline/Medinfo library provide a wealth of information on human health. Unfortunately, ADEs often result from unexpected interactions, and the connection between conditions and drugs is not explicit in these sources. Thus, in this work, we address the question of whether we can quantitatively estimate relationships between drugs and conditions from the medical literature. This paper proposes and studies a state-of-the-art NLP-based extraction of ADEs from text.
Similar content being viewed by others
Notes
A clique in a graph is a fully connected sub-graph of the original graph. A triangle is a clique of size 3, an edge is of size 2 and a fully connected square with both diagonals if of size 4.
If there are less than 50 abstracts for a particular ADE pair, we use only the returned set of documents.
References
Bui C, Sloot PMA, van Mulligen EM, Kors J (2014) A novel feature-based approach to extract drug–drug interactions from biomedical text. Bioinformatics. Oxford University Press, Oxford
Gurwitz J, Field T, Harrold L, Rothschild J, Debellis K, Seger A (2003) Incidence and preventability of adverse drug events among older persons in the ambulatory setting. JAMA 289(9):1107–1116
White R, Tatonetti N, Shah N, Altman R, Horvitz E (2013) Web-scale pharmacovigilance: listening to signals from the crowd. JAMIA 20(3):404–408. doi:10.1136/amiajnl-2012-001482
Page D, Santos Costa V, Natarajan S, Barnard A, Peissig PL, Caldwell M (2012) Identifying adverse drug events by relational learning. AAAI
Clayton R (2013) Calculating similarity (part 1): cosine similarity [Internet]
(2010) VA/DoD clinical practice guideline for management of opioid therapy for long-term pain, D.o.D, Department of Veterans Affairs,
Pray L, Robinson S (2007) Enhancing postmarket safety monitoring. Challenges for the FDA: the future of drug safety, workshop summary. The National Academies Press, Washington
Oliveira JL, Lopes P, Nunes T, Campos D, Boyer S, Ahlberg E, Mulligen E, Kors J, Singh B, Furlong L (2013) The EU-ADR web platform: delivering advanced pharmacovigilance tools. Pharmacoepidemiology and drug safety. Wiley Online Library, New York, pp 459–467
Ang PS, Chen Z, Chan CL, Tai BC (2016) Data mining spontaneous adverse drug event reports for safety signals in Singapore—a comparison of three different disproportionality measures. Expert Opin Drug Saf
Narushima D, Kawasaki Y, Takamatsu S, Yamada H (2016) Adverse events associated with incretin-based drugs in Japanese spontaneous reports: a mixed effects logistic regression model. Peer J 4:e1753. doi:10.7717/peerj.1753.eCollection 2016
Tolies J, Lewis RJ (2016) Time-to-event analysis JAMA 315:1046–1047
Ibrahim H, Saad A, Abdo A, Sharaf Eldin A (2016) Mining association patterns of drug-interactions using post marketing FDA’s spontaneous reporting data. J Biomed Inform 60:294–308. doi:10.1016/j.jbi.2016.02.009
Baldini A, Von Korff M, Lin EH (2012) A review of potential adverse effects of long-term opioid therapy: a practitioners guide. The primary care companion to CNS disorders, vol 3, No 3. Physicians Postgraduate Press Inc
Manchikanti L, Abdi S, Atluri S, Balog CC, Benyamin RM, Boswell MV, et al (2012) American Society of Interventional Pain Physicians (ASIPP) guidelines for responsible opioid prescribing in chronic non-cancer pain: Part I-evidence assessment. Pain Physician 15(3 Suppl):S1–65
Kahan M, Wilson L, Mailis-Gagnon A, Srivastava A (2011) Canadian guideline for safe and effective use of opioids for chronic noncancer pain Clinical summary for family physicians. Part 2: special populations. Can Family Phys Coll Fam Phys Can 57(11):1269–1276
Poon H, Domingos P (2009) Unsupervised semantic parsing. In: Proceedings of the 2009 conference on empirical methods in natural language processing: vol 1. Association for computational linguistics, pp 1–10
Domingos P, Lowd D (2009) Markov logic: an interface layer for artificial intelligence. Synth Lect Artif Intel Mach Learn 3(1):1–155
Ryan P, Welebob E, Hartzema AG, Stang P, Overhage JM (2010) Surveying US observational data sources and characteristics for drug safety needs. Pharm Med 24:231–238
Ryan P, Madigan D, Stang P, Overhage J, Racoosin J, Hartzema A (2012) Empirical assessment of methods for risk identification in healthcare data: results from the experiments of the observational medical outcomes partnership. Stat Med 31(30):4401–4415
Navigli R, Velardi P, Faralli S (2011) A graph-based algorithm for inducing lexical taxonomies from scratch. In: Proceedings of the twenty-second international joint conference on artificial intelligence, vol 3. AAAI Press, Barcelona, pp 1872–1877
Boella G, Caro LD, Ruggeri A, Robaldo L (2014) Learning from syntax generalizations for automatic semantic annotation. J Intell Inf Syst 43(2):231–246
Mooney RJ, Bunescu R (2005) Mining knowledge from text using information extraction. SIGKDD Explor Newsl 7(1):3–10
Mintz M, Bills S, Snow R, Jurafsky D (2009) Distant supervision for relation extraction without labeled data. In: Proceedings of the joint conference of the 47th annual meeting of the ACL and the 4th international joint conference on natural language processing of the AFNLP, vol 2, Association for Computational Linguistics, PA pp 1003–1011
Gurulingappa H, Fluck J, HofmannApitius M, Toldo L (2011) Identification of adverse drug event assertive sentences in medical case reports. In: First international workshop on knowledge discovery in health care and medicine
Friedman C (2009) Discovering novel adverse drug events using natural language processing and mining of the electronic health record. In: Proceedings of the 12th conference on artificial intelligence in medicine, AIME ’09, pp 1–5
Shetty K, Dalal S (2011) Using information mining of the medical literature to improve drug safety. JAMIA 18(5):668–674
Bian J, Topaloglu U, Yu F (2012) Towards Large-scale twitter mining for drug-related adverse events. In: Proceedings of the 2012 international workshop on smart health and wellbeing, pp 25–32
Lafferty JD, McCallum A, Pereira F (2001) Conditional random fields: probabilistic models for segmenting and labeling sequence data. Proceedings of the Eighteenth International Conference on Machine Learning. ICML ’0. Morgan Kaufmann Publishers Inc., San Francisco, pp 282–289
Niu F, Ré C, Doan A, Shavlik J (2011) Tuffy: scaling up statistical inference in markov logic networks using an rdbms. Proc VLDB Endow VLDB 4(6):373–384
Riedel S, Chun H, Takagi T, Tsujii J (2009) A markov logic approach to bio-molecular event extraction. In: Proceedings of the workshop on current trends in biomedical natural language processing: shared task, association for computational linguistics, pp 41–49
Poon H, Vanderwende L (2010) Joint inference for knowledge extraction from biomedical literature. In: Human language technologies: the 2010 annual conference of the North American chapter of the association for computational linguistics, pp 813–821
Riedel S, McCallum A (2011) Robust biomedical event extraction with dual decomposition and minimal domain adaptation. In: Proceedings of the BioNLP shared task 2011 workshop, association for computational linguistics, pp 46–50
Riedel S, McClosky D, Surdeanu M, McCallum A, Manning CD (2011) Model combination for event extraction in BioNLP 2011. In: Proceedings of the BioNLP shared task 2011 workshop, association for computational linguistics, pp 51–55
Bergstrom CT, West JD, Wiseman MA (2008) The Eigenfactor metrics. J Neurosci 28(45):11433–11434
Finkel J, Grenager T, Manning C (2005) Incorporating non-local information into information extraction systems by Gibbs sampling. In: Proceedings of the 43rd annual meeting on association for computational linguistics, pp 363–370
Klein D, Manning C (2003) Accurate unlexicalized parsing. In: Proceedings of the 41st annual meeting on association for computational linguistics, vol 1, pp 423–430
Khot T, Natarajan S, Kersting K, Shavlik J (2011) Learning markov logic networks via functional gradient boosting. In: International conference in data mining
Natarajan S, Khot T, Kersting K, Gutmann B, Shavlik J (2012) Gradient-based boosting for statistical relational learning: the relational dependency network case. Mach Learn J 86(1):25–56
J Davis, M Goadrich (2006) The relationship between Precision-Recall and ROC curves. ICML
Tatonetti NP, Fernald GH, Altman RB (2012) A novel signal detection algorithm for identifying hidden drug-drug interactions in adverse event reports. JAMIA 19(1):79–85
Acknowledgments
The authors gratefully acknowledge National Institute of Health Grant Number NIGMS 5R01GM097618 for the support.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Natarajan, S., Bangera, V., Khot, T. et al. Markov logic networks for adverse drug event extraction from text. Knowl Inf Syst 51, 435–457 (2017). https://doi.org/10.1007/s10115-016-0980-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10115-016-0980-6