(Publisher of Peer Reviewed Open Access Journals)

International Journal of Advanced Computer Research (IJACR)

ISSN (Print):2249-7277    ISSN (Online):2277-7970
Volume-8 Issue-36 May-2018
Full-Text PDF
DOI:10.19101/IJACR.2018.836007
Paper Title : Decision tree-based expert system for adverse drug reaction detection using fuzzy logic and genetic algorithm
Author Name : Ayman M. Mansour
Abstract :

Early detection of unknown adverse drug reactions (ADRs) could save patient lives and prevent unnecessary hospitalizations. Current surveillance systems are not ideal for rapidly identifying rare unknown ADRs. Current methods largely rely on passive spontaneous reports, which suffer from serious underreporting, latency, and inconsistent reporting. A more effective system is needed as the electronic patient records become more and more easily accessible in various health organizations such as hospitals, medical centers and insurance companies. These data provide a new source of information that has great potentials to detect ADR signals much earlier. In this paper, we have developed a methodology that uses both decision tree and fuzzy logic to generate a decision model. The developed model is equipped with a fuzzy inference engine, which enables it to find the causal relationship between a drug and a potential ADR. This could assist healthcare professionals to early detect previously unknown ADRs. Optimizing fuzzy rule weights and fuzzy sets parameters using genetic algorithm has been embedded in the proposed system to achieve excellent performance and improve the accuracy of the developed model. To evaluate the performance of the system, we have implemented the system using Weka and FuzzyJess software packages, and generated simulation results. To conduct the experiments, clinical information on 280 patients treated at the Detroit Veterans Affairs Medical Center was used. Two physicians on the team independently reviewed the experiment results. Kappa statistics show excellent agreement between the physicians and the developed model.

Keywords : Adverse drug reactions, Fuzzy logic, Decision tree, Genetic algorithm.
Cite this article : Ayman M. Mansour, " Decision tree-based expert system for adverse drug reaction detection using fuzzy logic and genetic algorithm " , International Journal of Advanced Computer Research (IJACR), Volume-8, Issue-36, May-2018 ,pp.110-128.DOI:10.19101/IJACR.2018.836007
References :
[1]Edwards IR, Aronson JK. Adverse drug reactions: definitions, diagnosis, and management. The Lancet. 2000; 356(9237):1255-9.
[Crossref] [Google Scholar]
[2]http://www.fda.gov/Drugs/GuidanceComplianceRegulatoryInformation/Surveillance/AdverseDrugEffects/ucm070461.htm. Accessed 26 January 2018.
[3]Stephens MD, Talbot J, Waller P. Stephens detection of new adverse drug reactions. John Wiley & Sons; 2004.
[Google Scholar]
[4]Kaufman G. Adverse drug reactions: classification, susceptibility and reporting. Nursing Standard (2014+). 2016; 30(50):53-63.
[Crossref] [Google Scholar]
[5]Svendsen K, Halvorsen KH, Vorren S, Samdal H, Garcia B. Adverse drug reaction reporting: how can drug consumption information add to analyses using spontaneous reports?. European Journal of Clinical Pharmacology. 2018; 74(4):497-504.
[Crossref] [Google Scholar]
[6]Schmiedl S, Rottenkolber M, Szymanski J, Drewelow B, Siegmund W, Hippius M, et al. Preventable ADRs leading to hospitalization-results of a long-term prospective safety study with 6,427 ADR cases focusing on elderly patients. Expert Opinion on Drug Safety. 2018; 17(2):125-37.
[Crossref] [Google Scholar]
[7]Dormann H, Criegee-Rieck M, Neubert A, Egger T, Geise A, Krebs S, et al. Lack of awareness of community-acquired adverse drug reactions upon hospital admission. Drug Safety. 2003; 26(5):353-62.
[Crossref] [Google Scholar]
[8]Zheng Y, Lan C, Peng H, Li J. Using constrained information entropy to detect rare adverse drug reactions from medical forums. In annual international conference of the engineering in medicine and biology society 2016 (pp. 2460-3). IEEE.
[Crossref] [Google Scholar]
[9]Cazacu I, Stroe R, Dondera R, Mogosan C, Haramburu F, Fourrier?Reglat A, et al. Adverse drug reactions of analgesic medicines: analysis of the Romanian pharmacovigilance database. Fundamental Clinical Pharmacology. 2018; 32(3):330-6.
[Crossref] [Google Scholar]
[10]Stricker BH, Psaty BM. Detection, verification, and quantification of adverse drug reactions. BMJ. 2004; 329(7456):44-7.
[Crossref] [Google Scholar]
[11]Klein E, Bourdette D. Postmarketing adverse drug reactions: a duty to report?. Neurology: Clinical Practice. 2013; 3(4):288-94.
[Google Scholar]
[12]U.S. food and drug administration. https://open.fda.gov/data/faers/. Accessed 26 January 2018.
[13]U.K. Yellow Card ADR reporting system. http://yellowcard.mhra.gov.uk/. Accessed 26 January 2018.
[14]Canadian ADR reporting system. http://www.hc-sc.gc.ca/dhp-mps/medeff/databasdon/index-eng.php. Accessed 26 January 2018.
[15]Central drugs standard control organization ADR reporting system of India. http://www.cdsco.nic.in/forms. Accessed 26 January 2018.
[16]Maggo SD, Chua EW, Chin P, Cree S, Pearson J, Doogue M, et al. A New Zealand platform to enable genetic investigation of adverse drug reactions. The New Zealand Medical Journal. 2017; 130(1466):62-9.
[Google Scholar]
[17]Miller D. FDA s MedWatch program monitors drug safety, but it depends on nurses to report adverse events. ONS Connect. 2015; 30(3):49.
[Google Scholar]
[18]Rehan HS, Chopra D, Holani SN, Mishra R. An observational study to compare the contents and quality of information furnished in CDSCO ADR reporting form, yellow card, medwatch and blue form by the healthcare professionals. International Journal of Risk & Safety in Medicine. 2014; 26(1):1-8.
[Crossref] [Google Scholar]
[19]Gupta A, Woosley R, Crk I, Sarnikar S. An information technology architecture for drug effectiveness reporting and post-marketing surveillance. International Journal of Healthcare Information Systems and Informatics (IJHISI). 2007; 2(3):65-80.
[Crossref] [Google Scholar]
[20]McGee S. Evidence-based physical diagnosis E-Book. Elsevier Health Sciences; 2016.
[Google Scholar]
[21]Kelly M, Kaye KI, Davis SR, Shenfield GM. Factors influencing adverse drug reaction reporting in New South Wales teaching hospitals. Journal of Pharmacy Practice and Research. 2004; 34(1):32-5.
[Crossref] [Google Scholar]
[22]Evans SJ, Waller PC, Davis S. Use of proportional reporting ratios (PRRs) for signal generation from spontaneous adverse drug reaction reports. Pharmacoepidemiology and Drug Safety. 2001; 10(6):483-6.
[Crossref] [Google Scholar]
[23]Abin D, Mahajan TC, Bhoj MS, Bagde S, Rajeswari K. Causal association mining for detection of adverse drug reactions. In international conference on computing communication control and automation 2015 (pp. 382-5). IEEE.
[Crossref] [Google Scholar]
[24]Harpaz R, Chase HS, Friedman C. Mining multi-item drug adverse effect associations in spontaneous reporting systems. In BMC bioinformatics 2010 (p. S7). BioMed Central.
[Crossref] [Google Scholar]
[25]Kubota K, Koide D, Hirai T. Comparison of data mining methodologies using Japanese spontaneous reports. Pharmacoepidemiology and Drug Safety. 2004; 13(6):387-94.
[Crossref] [Google Scholar]
[26]Lilienfeld DE. A challenge to the data miners. Pharmacoepidemiology and Drug Safety. 2004; 13(12):881-4.
[Crossref] [Google Scholar]
[27]Giannakopoulos I, Tsoumakos D, Koziris N. A decision tree based approach towards adaptive modeling of big data applications. In international conference on Big Data. 2017 (pp. 163-72). IEEE
[Crossref] [Google Scholar]
[28]Belohlavek R, Klir GJ. Concepts and fuzzy logic. MIT Press; 2011.
[Google Scholar]
[29]Singhai R. Introduction to fuzzy logic paperback. PHI Learning; 2013.
[30]Zadeh LA. Fuzzy sets. Information and control. 1965; 8(3): 338-53.
[Crossref] [Google Scholar]
[31]Orchard R. Fuzzy reasoning in JESS: the fuzzyj toolkit and fuzzyjess. International conference on enterprise information systems 2001 (pp. 533-42). National Research Council, Canada.
[Google Scholar]
[32]University of Waikato. Weka Software. https://www.cs.waikato.ac.nz/ml/weka/. Accessed 26 January 2018.
[33]Doc N. Department of Health & Human Services.2004.
[Google Scholar]
[34]Mansour AM. A multi-agent intelligent system for monitoring health conditions of elderly people. International Journal of Electrical, Robotics, Electronics and Communications Engineering. 2014; 8(6):993-8.
[Google Scholar]
[35]U.S. food and drug administration, National Drug Code Directory, USA. http://www.fda.gov/Drugs/InformationOnDrugs/ucm142438.htm. Accessed 26 January 2018.
[36]U.S. National Library of Medicine. http://www.nlm.nih.gov. Accessed 26 January 2018.
[37]Olson D. Data mining models. Business Expert Press; 2016.
[38]Witten IH, Frank E, Hall MA, Pal CJ. Data mining: practical machine learning tools and techniques. Morgan Kaufmann; 2016.
[Google Scholar]
[39]Granger CW, Siklos PL. Systematic sampling, temporal aggregation, seasonal adjustment, and cointegration theory and evidence. Journal of Econometrics. 1995; 66(1-2):357-69.
[Crossref] [Google Scholar]
[40]Quinlan JR. C4. 5: programs for machine learning. Elsevier; 2014.
[Google Scholar]
[41]Wu X, Kumar V, Quinlan JR, Ghosh J, Yang Q, Motoda H, et al. Top 10 algorithms in data mining. Knowledge and Information Systems. 2008; 14(1):1-37.
[Google Scholar]
[42]Landis JR, Koch GG. The measurement of observer agreement for categorical data. Biometrics. 1977; 33(1):159-74.
[Crossref] [Google Scholar]