A Multiagent System for Integrated Detection of Pharmacovigilance Signals
Pharmacovigilance is the scientific discipline that copes with the continuous assessment of the safety profile of marketed drugs. This assessment relies on diverse data sources, which are routinely analysed to identify the so-called “signals”, i.e. potential associations between drugs and adverse effects, that are unknown or incompletely documented. Various computational methods have been proposed to support domain experts in signal detection. However, recent comparative studies illustrated that current methods exhibit high false-positive rates, significantly variable performance across different datasets used for analysis and events of interest, but also complementarity in their outcomes. In this regard, in order to reinforce accurate and timely signal detection, we elaborated through an agent-based approach towards systematic, joint exploitation of multiple heterogeneous signal detection methods, data sources and other drug-related resources under a common, integrated framework. The approach relies on a multiagent system operating based on a collaborative agent interaction protocol, aiming to implement a comprehensive workflow that comprises of method selection and execution, as well as outcomes’ aggregation, filtering, ranking and annotation. This paper presents the design of the proposed multiagent system, discusses implementation issues and demonstrates the applicability of the proposed solution in an example signal detection scenario. This work constitutes a step towards large-scale, integrated and knowledge-intensive computational signal detection.
KeywordsPharmacovigilance Computational signal detection methods Heterogeneous data sources Multiagent system Aggregation and reasoning scheme
This research was supported by a Marie Curie Intra European Fellowship within the 7th European Community Framework Programme FP7/2007-2013 under REA grant agreement no 330422 – the SAFER project.
The authors would like to express their appreciation to the reviewers for their constructive comments and suggestions.
Compliance with ethical standards
Conflict of interests
The authors declare that they have no conflicts of interest.
- 1.WHO, The Importance of Pharmacovigilance: Safety Monitoring of Medicinal Products. World Health Organization, Geneva, CH (2002)Google Scholar
- 2.Grootheest, A., and Richesson, R.: Pharmacovigilance. In: Richesson, R., and Andrews, J. (Eds.) In: Clinical Research Informatics, Health Informatics, pp. 367–387. Springer, London (2012), doi: 10.1007/978-1-84882-448-5_19
- 4.Council for International Organizations of Medical Sciences, Practical Aspects of Signal Detection in Pharmacovigilance. Report of CIOMS Working Group VIII. CIOMS, Geneva, CH (2010)Google Scholar
- 5.WHO, A Practical Handbook on the Pharmacovigilance of Antimalarial Medicines. World Health Organization, Geneva, CH (2008)Google Scholar
- 14.FDA Adverse Event Reporting System (FAERS). http://www.fda.gov/Drugs/GuidanceComplianceRegulatoryInformation/Surveillance/AdverseDrugEffects/ http://www.fda.gov/Drugs/GuidanceComplianceRegulatoryInformation/Surveillance/AdverseDrugEffects/ http://www.fda.gov/Drugs/GuidanceComplianceRegulatoryInformation/Surveillance/AdverseDrugEffects/. Accessed 13 September 2015
- 15.EudraVigilance. https://eudravigilance.ema.europa.eu/. Accessed 13 September 2015
- 16.VigiBase®. http://www.umc-products.com/. Accessed 13 September 2015
- 22.Suchard, M.A., Zorych, I., Simpson, S.E., Schuemie, M.J., Ryan, P.B., Madigan, D., Empirical performance of the self-controlled case series design: lessons for developing a risk identification and analysis system. Drug Saf 36:S83–S93, 2013. doi: 10.1007/s40264-013-0100-4.CrossRefPubMedGoogle Scholar
- 24.The Observational Medical Outcomes Partnership. http://omop.org/. Accessed 13 September 2015
- 31.van Holle, L., and Bauchau, V., Signal detection on spontaneous reports of adverse events following immunisation: a comparison of the performance of a disproportionality-based algorithm and a time-to-onset-based algorithm. Pharmacoepidemiol Drug Saf 23:178–185, 2014. doi: 10.1002/pds.3502.PubMedCentralCrossRefPubMedGoogle Scholar
- 34.Koutkias, V.G., and Jaulent, M.-C.: Leveraging post-marketing drug safety research through semantic technologies: the PharmacoVigilance Signal Detectors Ontology.. In: Proceedings of the 7th International Workshop on Semantic Web Applications and Tools for Life Sciences, CEUR Workshop Proceedings, Vol. 1320, Berlin, Germany, December 9–11 (2014)Google Scholar
- 35.Singh, M.P., and Huhns, M.N., Service-Oriented Computing: Semantics, Processes, Agents: Wiley, 2005.Google Scholar
- 38.Klusch, M., and Sycara, K.: Brokering and matchmaking for coordination of agent societies: a survey. In: Omicini, A., Zambonelli, F., Klusch, M., Tolksdorf, R. (Eds.) In: Coordination of Internet Agents, pp. 197–224. Springer-Verlag (2001)Google Scholar
- 39.Durfee, E.H.: Distributed Problem Solving and Planning. In: Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence. Cambridge, MA, MIT Press, 2000, pp. 121– 164Google Scholar
- 42.Kuhn, M., Campillos, M., Letunic, I., Juhl Jensen, L., Bork, P., A side effect resource to capture phenotypic effects of drugs. Mol. Syst. Biol. 6(1), 2010. doi: 10.1038/msb.2009.98.
- 43.The DrugBank database. http://www.drugbank.ca/. Accessed 13 September 2015
- 44.The ChEMBL database. https://www.ebi.ac.uk/chembl/. Accessed 13 September 2015
- 45.Ahmed, I., and Poncet, A., PhViD: An R package for PharmacoVigilance signal Detection. R package version 1.0.6 (2013)Google Scholar
- 46.OWL 2 Web Ontology Language: Structural Specification and Functional-Style Syntax, 2nd Ed. http://www.w3.org/TR/2012/REC-owl2-syntax-20121211/. Accessed 13 September 2015
- 47.The openFDA Drug API. https://open.fda.gov/drug/event/. Accessed 13 September 2015
- 48.Europe PubMed Central RESTful Web Service. http://europepmc.org/restfulwebservice. Accessed 13 September 2015
- 49.The Twitter REST APIs. https://dev.twitter.com/rest/public. Accessed 13 September 2015
- 50.SPARQL 1.1 Overview, W3C Recommendation, 21 March 2013. Accessed 13 September 2015 (2013). http://www.w3.org/TR/sparql11-overview/
- 51.bio2RDF. http://bio2rdf.org/. Accessed 13 September 2015
- 52.Java Agent DEvelopment framework (JADE). http://jade.tilab.com/. Accessed 13 September 2015
- 53.The Foundation for Intelligent Physical Agents (FIPA). http://www.fipa.org/. Accessed 13 September 2015
- 54.Rserve - Binary R server. http://rforge.net/Rserve/. Accessed 13 September 2015
- 55.Foundation for Intelligent Physical Agents, FIPA Abstract Architecture Specification, SC00001L, http://fipa.org/specs/fipa00001/SC00001L.pdf. Accessed 13 September 2015
- 56.Foundation for Intelligent Physical Agents, FIPA ACL Message Structure Specification, SC00061G, 03/12/2002. http://www.fipa.org/specs/fipa00061/SC00061G.pdf. Accessed 13 September 2015
- 57.Foundation for Intelligent Physical Agents, FIPA Communicative Act Library Specification, SC00037J, 03/12/2002. http://www.fipa.org/specs/fipa00037/SC00037J.pdf. Accessed 13 September 2015
- 58.Foundation for Intelligent Physical Agents, FIPA SL Content Language Specification, SC00008I, 03/12/2002. http://www.fipa.org/specs/fipa00008/SC00008I.pdf. Accessed 13 September 2015
- 59.Caire, G., and Cabanillas, D.: JADE Tutorial: Application-defined Content Languages and Ontologies., 15 April 2010. http://jade.tilab.com/doc/tutorials/CLOntoSupport.pdf. Accessed 13 September 2015
- 60.The clinical Text Analysis and Knowledge Extraction System (cTAKES). http://ctakes.apache.org/. Accessed 13 September 2015
- 61.The Unified Medical Language System (UMLS). http://www.nlm.nih.gov/research/umls/. Accessed 13 September 2015
- 62.The Unstructured Information Management Architecture (UIMA). http://uima.apache.org/. Accessed 13 September 2015
- 63.The OMOP Methods Library. http://omop.org/MethodsLibrary. Accessed 13 September 2015
- 66.The Mini-Sentinel project. http://www.mini-sentinel.org/. Accessed 13 September 2015
- 67.Observational Health Data Sciences and Informatics (OHDSI) program. http://www.ohdsi.org/. Accessed 13 September 2015
- 70.Bromuri, S., Schumacher, M.I., Stathis, K., Ruiz, J.: Monitoring Gestational Diabetes Mellitus with Cognitive Agents and Agent Environments. In: Proc. of IEEE/WIC/ACM Int. Conf. on Web Intelligence and Intelligent Agent Technology (WI-IAT), Vol. 2, pp. 409–414, Lyon, France, Aug. 22-27 (2011), doi: 10.1109/WI-IAT.2011.37
- 72.Kaluža, B., et al., A multi-agent care system to support independent living. Int. J. Artif. Intell. T. 23 (1), 2014. doi: 10.1142/S0218213014400016.
- 73.Koutkias, V.G., Malousi, A., Maglaveras, N., Engineering agent-mediated integration of bioinformatics analysis tools. Multiagent Grid Syst 3(2):245–258, 2007.Google Scholar
- 78.Nyulas, C.I., O’Connor, M.J., Tu, S.W., Buckeridge, D.L., Okhmatovskaia, A., Musen, M.A.: An ontology-driven framework for deploying JADE agent systems. In: Proc. of IEEE/WIC/ACM Int. Conf. on Web Intelligence and Intelligent Agent Technology (WI-IAT), Vol. 2, pp. 573–577, Sydney, Australia, Dec. 9-12 (2008), doi: 10.1109/WIIAT.2008.25
- 79.Ferrucci, D., et al., Building Watson: an overview of the DeepQA project. AI Magazine 31(3):59–79, 2010. doi: 10.1609/aimag.v31i3.2303.
- 81.He, H., Cao, Y., Wen, J., Cheng, S.: A boost voting strategy for knowledge integration and decision making. In: Sun, F., Zhang, J., Tan, Y., Cao, J., Yu, W. (Eds.) In: Advances in Neural Networks - ISNN 2008, volume 5263 of Lecture Notes in Computer Science, pp. 472–481. Springer, Berlin (2008), doi: 10.1007/978-3-540-87732-5_53
- 82.DeployR. http://deployr.revolutionanalytics.com/. Accessed 13 September 2015
- 83.Burian, P., Multi-agent Systems and Cloud Computing for Controlling and Managing Chemical and Food Processes. J. Chem. Chem. Eng. 6:1121–1135, 2012.Google Scholar