Advertisement

Multimedia Tools and Applications

, Volume 77, Issue 3, pp 3493–3507 | Cite as

GA-ADE: a novel approach based on graph algorithm to improves the detection of adverse drug events

  • Xingcheng Wu
  • Jia Zhu
  • Danyang Xiao
  • Xueqin Lin
  • Rui Ding
Article

Abstract

The adverse drug event (ADE) is an unexpected and harmful consequence of drug usege. Identifying the association between the use of drugs and adverse events from biomedical literature can contribute a lot to drug safety supervision. Such identification can not only assist drug safety monitoring, but also correct known dependencies among events. In this paper,we propose a novel approach based on graph algorithm to detect adverse drug events(GA-ADE). In our approach, we first construct a graph using candidate ADE extracted from biomedical literature. We then propose a method to select important vertices from the graph as core vertices, and design a Personal Rank algorithm using the core vertices for clustering to build subgraphs. Lastly, the correlation between the drug and the event is calculated based on the subgraphs. Experiments show that our approach is feasible.

Keywords

Adverse drug events detection PersonalRank DeepWalk Graph algorithm Clustering 

Notes

Acknowledgments

This research was partially supported by the Scientfic Research Foundation of Graduate School of South China Normal University, the Natural Science Foundation of Guangdong Province, China(2015A030310509), the Public Research and Capacity Building in Guangdong Province, China(2016A030303055), the Major Science and Technology projects of Guangdong Province, China(2016B030305004, 2016B010109008, 2016B010124008) and the National Natural Science Foundation of China(61272067).

References

  1. 1.
    Almenoff J, Tonning JM, Gould AL, Szarfman A, Hauben M, Ouellet-Hellstrom R, Ball R, Hornbuckle K, Walsh L, Yee C (2005) Perspectives on the use of data mining in pharmaco-vigilance. Drug Safety An International Journal of Medical Toxicology & Drug Experience 28(11):981–1007CrossRefGoogle Scholar
  2. 2.
    Ahmad SR (2003) Adverse drug event monitoring at the food and drug administration. J Gen Intern Med 18(1):57–60CrossRefGoogle Scholar
  3. 3.
    Bader Gary D, Hogue Christopher Wv (2003) An automated method for finding molecular complexes in large protein interaction networks. BMC Bioinformatics 4(1):1–27CrossRefGoogle Scholar
  4. 4.
    Bate A, Evans SJ (2010) Quantitative signal detection using spontaneous adr reporting. Pharmacoepidemiol Drug Saf 18(6):427–436CrossRefGoogle Scholar
  5. 5.
    Bate A, Lindquist M, Edwards IR, Olsson S, Orre R, Lansner A, De Freitas RM (1998) A bayesian neural network method for adverse drug reaction signal generation. Eur J Clin Pharmacol 54(4):315–21CrossRefGoogle Scholar
  6. 6.
    Bianchini M, Gori M, Scarselli F (2005) Inside pagerank. ACM Trans Internet Technol 5(1):92–128CrossRefGoogle Scholar
  7. 7.
    Cao S, Lu W, Xu Q (2015) Grarep:learning graph representations with global structural information. pp 891–900Google Scholar
  8. 8.
    Center For Drug Evaluation And. Drug safety and availability - fda drug safety communication: Fda recommends not using lidocaine to treat teething pain and requires new boxed warningGoogle Scholar
  9. 9.
    Classen DC, Pestotnik SL, Evans RS, Lloyd JF, Burke JP (1997) Adverse drug events in hospitalized patients. excess length of stay, extra costs, and attributable mortality. Jama 277(4):301CrossRefGoogle Scholar
  10. 10.
    Chang X, Yi Y (2016) Semisupervised feature analysis by mining correlations among multiple tasks. IEEE Transactions on Neural Networks and Learning Systems.  https://doi.org/10.1109/TNNLS.2016.2582746
  11. 11.
    Chang Xiaojun, Yu Y-L, Yang Y, Xing EP (2017) Semantic pooling for complex event analysis in untrimmed videos. IEEE Trans Pattern Anal Mach Intell 39 (8):1617–1632CrossRefGoogle Scholar
  12. 12.
    Chang X, Ma Z, Yi Y, Zeng Z, Hauptmann Alexander G. (2017) Bi-level semantic representation analysis for multimedia event detection. IEEE Trans Cybern 47(5):1180–1197CrossRefGoogle Scholar
  13. 13.
    Chang X, Ma Z, Lin M, Yi Y, Hauptmann AG (2017) Feature interaction augmented sparse learning for fast kinect motion detection. IEEE Trans Image Process 26(8):3911–3920MathSciNetCrossRefGoogle Scholar
  14. 14.
    Chen Y, Perozzi B, Skiena S (2016) Vector-based similarity measurements for historical figures. Inf Syst 9371:179–190Google Scholar
  15. 15.
    Ding Y, Zhang Y, Zhan-Huai LI, Wang Y (2012) Research and advances on graph data mining. Journal of Computer ApplicationsGoogle Scholar
  16. 16.
    Dore DD, Seeger JD, Arnold Chan K (2009) Use of a claims-based active drug safety surveillance system to assess the risk of acute pancreatitis with exenatide or sitagliptin compared to metformin or glyburide. Curr Med Res Opin 25(4):1019CrossRefGoogle Scholar
  17. 17.
    Dumouchel W (1999) Bayesian data mining in large frequency tables, with an application to the fda spontaneous reporting system. Am Stat 53(3):177–190Google Scholar
  18. 18.
    García E., Pedroche F, Romance M (2012) On the localization of the personalized pagerank of complex networks. Linear Algebra Appl 439(439):640–652MathSciNetMATHGoogle Scholar
  19. 19.
    Grover A, Leskovec J (2016) node2vec: Scalable feature learning for networks, vol 2016Google Scholar
  20. 20.
    Harpaz R, Chase HS, Friedman C (2010) Mining multi-item drug adverse effect associations in spontaneous reporting systems. Bmc Bioinformatics 11(9):1–8Google Scholar
  21. 21.
    Haveliwala TH (2003) Topic-sensitive pagerank. In: International Conference on World Wide Web, pp 517–526Google Scholar
  22. 22.
    Healthcare Cost Utilization Project, et al. (2015) Introduction to the hcup nationwide emergency department sample (neds) 2012. 2015Google Scholar
  23. 23.
    Lazarou J, Pomeranz BH, Corey PN (1998) Incidence of adverse drug reactions in hospitalized patients: a meta-analysis of prospective studies. Jama J Am Med Assoc 279(15):1200–1205CrossRefGoogle Scholar
  24. 24.
    Li X, Xin S, Wang M (2012) Social network-based recommendation:a graph random walk kernel approach. In: Proceedings of the 12th ACM/IEEE-CS joint conference on Digital Libraries, pp 409–410Google Scholar
  25. 25.
    Luo Z, Zhang GQ, Xu R (2013) Mining patterns of adverse events using aggregated clinical trial results. Amia Jt Summits Transl Sci Proc 2013(2013):112–116Google Scholar
  26. 26.
    Ma Z, Chang X, Yi Y, Sebe N, Hauptmann AG (2017) The many shades of negativity. IEEE Trans Multimedia 19(7):1558–1568CrossRefGoogle Scholar
  27. 27.
    Metlay JP, Hennessy S, Russell Localio A, Han X, Yang W, Cohen A, Leonard CE, Haynes K, Kimmel SE, Feldman HI (2008) Patient reported receipt of medication instructions for warfarin is associated with reduced risk of serious bleeding events. J Gen Intern Med 23(10):1589–94CrossRefGoogle Scholar
  28. 28.
    Min W, Li X, Kwoh CK, Ng SK (2009) A core-attachment based method to detect protein complexes in ppi networks. BMC Bioinformatics 10(1):169CrossRefGoogle Scholar
  29. 29.
    Moore TJ, Bennett CL (2012) Underreporting of hemorrhagic and thrombotic complications of pharmaceuticals to the u.s. food and drug administration: empirical findings for warfarin, clopidogrel, ticlopidine, and thalidomide from the southern network on adverse reactions (sonar). Semin Thromb Hemost 38(8):905–7CrossRefGoogle Scholar
  30. 30.
    Nadimi MH, Mosakhani M (2015) A more accurate clustering method by using co-author social networks for author name disambiguation. 1Google Scholar
  31. 31.
    Newman ME (2006) Modularity and community structure in networks. Proc Natl Acad Sci USA 103(23):8577–82CrossRefGoogle Scholar
  32. 32.
    Nie F, Wang X, Jordan MI, Huang H (2016) The constrained laplacian rank algorithm for graph-based clustering. In: Thirtieth AAAI Conference on Artificial Intelligence, pp 1969–1976Google Scholar
  33. 33.
    Nikfarjam A, Sarker A, O‘Connor K, Ginn R, Gonzalez G (2015) Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features. J Am Med Inform Assoc Jamia 22(3):671–681Google Scholar
  34. 34.
    Ochieng PJ, Kusuma WA, Haryanto T (2017) Detection of protein complex from protein-protein interaction network using markov clustering. In: In International Symposia on Bioinformatics, Chemometrics and Metabolomics, pp 1–13Google Scholar
  35. 35.
    On BW (2008) Social network analysis on name disambiguation and more. In: International Conference on Convergence and Hybrid Information Technology, pp 1081–1088Google Scholar
  36. 36.
    Ouyang L, Dai DQ, Zhang XF (2013) Protein complex detection via weighted ensemble clustering based on bayesian nonnegative matrix factorization. Plos One 8 (5):e62158CrossRefGoogle Scholar
  37. 37.
    Pan S, Jia W, Zhu X, Long G, Zhang C (2015) Finding the best not the most: regularized loss minimization subgraph selection for graph classification. Pattern Recogn 48(11):3783–3796CrossRefGoogle Scholar
  38. 38.
    Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: online learning of social representations. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 701–710Google Scholar
  39. 39.
    Phan Hang TT, Sternberg Michael J. E. (2012) Pinalog: a novel approach to align protein interaction networks—implications for complex detection and function prediction. Bioinformatics 28(9):1239– 45CrossRefGoogle Scholar
  40. 40.
    Puijenbroek EPV, Egberts ACG, Meyboom RHB, Leufkens HGM (1999) Signalling possible drug-drug interactions in a spontaneous reporting system: delay of withdrawal bleeding during concomitant use of oral contraceptives and itraconazole. Br J Clin Pharmacol 47(6):689–693CrossRefGoogle Scholar
  41. 41.
    Ryan PB, Schuemie MJ, Welebob E, Duke J, Valentine S, Hartzema AG (2013) Defining a reference set to support methodological research in drug safety. Drug Saf 36(1):33–47CrossRefGoogle Scholar
  42. 42.
    Saless F (2005) Review of fda guidance on risk management: Good pharmacovigilance practices and pharmacoepidemiologic assessment. Genet Eng News 25(18):14–0Google Scholar
  43. 43.
    Schneeweiss S (2010) A basic study design for expedited safety signal evaluation based on electronic healthcare data. Pharmacoepidemiol Drug Saf 19(8):858–868CrossRefGoogle Scholar
  44. 44.
    Shen B, Hu B, Zhang H (2016) Method for the analysis of the preferences of network users. Networks Iet 5(1):8–12CrossRefGoogle Scholar
  45. 45.
    Shetty KD, Dalal SR (2011) Using information mining of the medical literature to improve drug safety. J Am Med Inform Assoc 18(5):668–674CrossRefGoogle Scholar
  46. 46.
    Szarfman A, Machado SG, aO’Neill RT (2002) Use of screening algorithms and computer systems to efficiently signal higher-than-expected combinations of drugs and events in the us fda’s spontaneous reports database. Drug Saf 25(6):381–392CrossRefGoogle Scholar
  47. 47.
    Szarfman A, Tonning JM, Levine JG, Doraiswamy PM (2006) Atypical antipsychotics and pituitary tumors: a pharmacovigilance study. Pharmacotherapy the Journal of Human Pharmacology & Drug Therapy 26(6):748–58CrossRefGoogle Scholar
  48. 48.
    Tatonetti NP, Fernald GH, Altman RB (2012) A novel signal detection algorithm for identifying hidden drug-drug interactions in adverse event reports. J Am Med Inform Assoc Jamia 19(1):79–85CrossRefGoogle Scholar
  49. 49.
    Thakrar BT, Grundschober SB, Doessegger L (2007) Detecting signals of drug-drug interactions in a spontaneous reports database. Br J Clin Pharmacol 64 (4):489–95CrossRefGoogle Scholar
  50. 50.
    van Manen RP, Fram D, Dumouchel W (2007) Signal detection methodologies to support effective safety management. Expert Opin Drug Saf 6(4):451–64CrossRefGoogle Scholar
  51. 51.
    Wang X, Hripcsak G, Markatou M, Friedman C (2009) Active computerized pharmacovigilance using natural language processing, statistics, and electronic health records: A feasibility study. J Am Med Inform Assoc 16(3):328–337CrossRefGoogle Scholar
  52. 52.
    Winnenburg R, Sorbello A, Bodenreider O (2015) Exploring adverse drug events at the class level. J Biomed Semantics 6(1):18CrossRefGoogle Scholar
  53. 53.
    Winnenburg R, Sorbello A, Ripple A, Harpaz R, Tonning J, Szarfman A, Francis H, Bodenreider O (2015) Leveraging medline indexing for pharmacovigilance - inherent limitations and mitigation strategies. J Biomed Inform 57(C):425–435CrossRefGoogle Scholar
  54. 54.
    Yang C, Liu Z (2015) Comprehend deepwalk as matrix factorization. Computer ScienceGoogle Scholar
  55. 55.
    Yang C, Liu Z, Zhao D, Sun M, Chang EY (2015) Network representation learning with rich text information. In: International Conference on Artificial Intelligence, pp 2111–2117Google Scholar
  56. 56.
    Zhang L, Zhang Y, Zhao P, Huang SM (2009) Predicting drugdrug interactions: An fda perspective. Aaps J 11(2):300–306CrossRefGoogle Scholar
  57. 57.
    Zhu J, Xie Q, Zheng K (2015) An improved early detection method of type-2 diabetes mellitus using multiple classifier system. Inf Sci 292(292):1–14CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2017

Authors and Affiliations

  • Xingcheng Wu
    • 1
  • Jia Zhu
    • 1
  • Danyang Xiao
    • 1
  • Xueqin Lin
    • 1
  • Rui Ding
    • 1
  1. 1.School of Computer ScienceSouth China Normal UniversityGuangzhouChina

Personalised recommendations