gms | German Medical Science

GMDS 2012: 57. Jahrestagung der Deutschen Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie e. V. (GMDS)

Deutsche Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie

16. - 20.09.2012, Braunschweig

Article

Send article

Detection of possible adverse drug events using an Arden-Syntax-based rule engine

Meeting Abstract

Search Medline for

  • Dieter Kopecky - Medexter Healthcare GmbH, Wien, Österreich
  • Karsten Fehre - Medexter Healthcare GmbH, Wien, Österreich
  • Harald Mandl - Medexter Healthcare GmbH, Wien, Österreich
  • Manuela Plößnig - Salzburg Research Forschungsgesellschaft, Salzburg, Österreich
  • Bernhard Hansbauer - Paracelsus Medical University Salzburg, Österreich
  • Jochen Schuler - Gemeinnützige Salzburger Landeskliniken Betriebsgesellschaft mbH, Salzburg, Österreich
  • Christina Hofer-Dückelmann - Landesapotheke am St. Johanns-Spital, Salzburg, Österreich
  • Klaus-Peter Adlassnig - Medexter Healthcare GmbH, Wien, Österreich

GMDS 2012. 57. Jahrestagung der Deutschen Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie e.V. (GMDS). Braunschweig, 16.-20.09.2012. Düsseldorf: German Medical Science GMS Publishing House; 2012. Doc12gmds082

doi: 10.3205/12gmds082, urn:nbn:de:0183-12gmds0822

Published: September 13, 2012

© 2012 Kopecky et al.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by-nc-nd/3.0/deed.en). You are free: to Share – to copy, distribute and transmit the work, provided the original author and source are credited.

Outline

Text

Introduction: The ever increasing number of administered drugs results in an elevated risk for drug-related harm, especially in elderly patients [1], [2]. Although many countries have installed a legal commitment to report adverse drug events (ADEs), the number of reported cases – and therefore the efficacy of the reporting systems – remains low. Only about 10–20% of medication errors and 1–13% of detected ADEs are reported [3]. This is because medication errors rarely result in obvious drug-related damages or are seldom considered as primary reasons for disorders [4]. Moreover, ADE detection and reporting is a time-consuming and expensive task.

Nevertheless, it is crucial to prevent and mitigate ADEs causing damage to patients [5]. Therefore, hospitals need a more efficient way to quantify the amount and severity of ADEs for pharmacists and physicians to take corrective actions. Several studies have shown that clinical decision support systems can improve quality of care [6] and are appropriate tools to support physicians in their decisions.

Materials and Methods: Within the iMedication project [7], an intelligent ADE cockpit for detecting, monitoring, and reporting ADEs is developed. The core of the software implementation is a decision support system applying a hybrid approach combining the “IHI Global Trigger Tool”-method [5] and Morimoto’s classification [8] to detect suspected ADEs. Its knowledge base consists of medical logic modules (MLMs) [9] which encode the medical expert knowledge in Arden Syntax [9] and are executed by an Arden Syntax rule engine residing on a server [10].

The data to be processed come from various sources – the hospital information system, an electronic health record, as well as entered information – and reflects six categories: demographic data, laboratory findings, clinical symptoms, diagnoses, medications, and hospital events. The aggregated information of a single patient is delivered for interpretation to the Arden Syntax server, which returns a detailed interpretation summary for each identified ADE consisting of: (a) an ADE risk score which reflects the degree and severity of the ADE, (b) the institutions which have to be informed according to the severity of the ADE, (c) the triggers having fired, as well as (d) the complete patient information used for interpretation.

Results: Four clinically relevant situations (hyperkalemia, hyponatremia, renal failure, and over-anticoagulation) were selected as exemplary use cases. They represent some of the most relevant ADEs for internal and geriatric medicine wards. Four corresponding knowledge bases, consisting of a total of 33 MLMs covering 51 ADE triggers, were built upon these use cases in Arden Syntax in close cooperation between medical experts and knowledge engineers.

Discussion: Existing approaches for ADE detection use data mining [11], decision trees [12], ontologies [13], or product label parsing [14] to automatically generate ADE detection rules. The approach at hand formalizes operative knowledge of clinical experts into standardized machine-executable Arden Syntax, allowing the formalization of complex rules to identify ADEs.

The proposed implementation is suitable for various applications, including quality assurance by retrospective evaluation of clinical data regarding suspected ADEs, active feedback for clinicians during patient treatment, and pharmacovigilance reporting.

Outline

References

1.
Hofer-Dueckelmann C, Prinz E, Beindl W, Szymanski J, Fellhofer G, Pichler M, et al. Adverse drug reactions (ADRs) associated with hospital admissions – elderly female patients are at highest risk. Int J Clin Pharmacol Ther. 2011;10:577-86.
2.
Schuler J, Dückelmann C, Beindl W, Prinz E, Michalski T, Pichler M. Polypharmacy and inappropriate prescribing in elderly internal-medicine patients in Austria. Wien Klin Wochenschr. 2008;120:733-41.
3.
Zafar A, Hickner J, Pace W, Tierney W. An Adverse Drug Event and Medication Error Reporting System for Ambulatory Care (MEADERS). AMIA Annu Symp Proc. 2008:839-43.
4.
Pirmohamed M, James S, Meakin S, Green Ch, Scott A, Walley T, et al. Adverse drug reactions as cause of admission to hospital: prospective analysis of 18 820 patients. BMJ. 2004;239:15-9.
5.
Griffin FA, Resar RK. IHI Global Trigger Tool for Measuring Adverse Events. 2nd edition. Cambridge, Massachusetts: Institute for Healthcare Improvement; 2009. (IHI Innovation Series white paper)
6.
Garg A, Adhikari N, McDonald H, Rosas-Arellano M, Devereaux P, Beyene J, et al. Effects of Computerized Clinical Decision Support Systems on Practitioner Performance and Patient Outcomes. JAMIA. 2005;293(10):1223-38.
7.
Plößnig M, Schuler J, Hansbauer B, Stroka S, Engel T, Hofer-Dückelmann C, et al. Semi-Automated Identification of Potential Adverse Drug Events. In: Proceedings of eHealth; 2012 Mai 10-11; Vienna, Austria.
8.
Morimoto T, Gandhi TK, Seger AC, Hsieh TC, Bates DW. Adverse drug events and medication errors: detection and classification methods. Qual Saf Health Care. 2004;13:306-14.
9.
Samwald M, Fehre K, De Bruin J, Adlassnig KP. The Arden Syntax Standard for Clinical Decision Support: Experiences and Directions. J Biomed Inform. 2012. DOI: 10.1016/j.jbi.2012.02.001 External link
10.
Fehre K, Adlassnig KP. Service-Oriented Arden-Syntax-Based Clinical Decision Support. In: Schreier G, Hayn D, Ammenwerth E, editors. Tagungsband der eHealth 2011 – Health Informatics meets eHealth – von der Wissenschaft zur Anwendung und zurück, Grenzen überwinden – Continuity of Care. Wien: Österreichische Computer Gesellschaft; 2011. p. 123-8.
11.
Chazard E, Preda C, Merlin B, Ficheur G; the PSIP consortium, Beuscart R. Data-Mining-Based Detection of Adverse Drug Events. Stud Health Technol Inform. 2009;150:552-6.
12.
Chazard E, Baceanu A, Marcilly R, Bernonville S, Ficheur G, Beuscart R. A Web Tool for Automated Adverse Drug Events Detection: the ADE Scorecards. In: Moen A, Andersen S, Aarts J, Hurlen P, editors. User Centered Networked Health Care: Proceedings of MIE 2011, 23rd International Conference of the European Federation for Medical Informatics; Oslo, Norway; 2008.
13.
Cao F, Sun X, Wang X, Li B, Li J, Pan Y. Ontology-based Knowledge Management for Personalized Adverse Drug Events Detection. Stud Health Technol Inform. 2011;169:699-703.
14.
Duke JD, Friedlin J. ADESSA: A Real-Time Decision Support Service for Delivery of Semantically Coded Adverse Drug Event Data. AMIA Annu Symp Proc. 2010; 2010: 177-81.
15.
Adlassnig KP, Rappelsberger A. Medical Knowledge Packages and their Integration into Health-Care Information Systems and the World Wide Web. In: Andersen SK, Klein GO, Schulz S, Aarts J, Mazzoleni MC, editors. eHealth Beyond the Horizon – Get IT There Proceedings of the 21st International Congress of the European Federation for Medical Informatics (MIE 2008); Amsterdam: IOS Press; 2008. p. 121-6.