Decision tree-based expert system for adverse drug reaction detection using fuzzy logic and genetic algorithm

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.

[1]  Surendra Sarnikar,et al.  An Information Technology Architecture for Drug Effectiveness Reporting and Post-Marketing Surveillance , 2007 .

[2]  Bruce M Psaty,et al.  Detection, verification, and quantification of adverse drug reactions , 2004, BMJ : British Medical Journal.

[3]  Yi Zheng,et al.  Using constrained information entropy to detect rare adverse drug reactions from medical forums , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[4]  Karen I Kaye,et al.  Factors Influencing Adverse Drug Reaction Reporting in New South Wales Teaching Hospitals , 2004 .

[5]  G. Kaufman.  Adverse drug reactions: classification, susceptibility and reporting. , 2016, Nursing standard (Royal College of Nursing (Great Britain) : 1987).

[6]  David E. Lilienfeld.  A challenge to the data miners , 2004, Pharmacoepidemiology and drug safety.

[7]  Philip S. Yu,et al.  Top 10 algorithms in data mining , 2007, Knowledge and Information Systems.

[8]  National drug code directory. , 1969, Hospitals.

[9]  P. Waller,et al.  Stephens' detection of new adverse drug reactions , 2004 .

[10]  J. Pearson,et al.  A New Zealand platform to enable genetic investigation of adverse drug reactions. , 2017, The New Zealand medical journal.

[11]  David L. Olson,et al.  Data Mining Models , 2016 .

[12]  Robert Orchard,et al.  Fuzzy Reasoning in JESS: The Fuzzyj Toolkit and Fuzzyjess , 2001, ICEIS.

[13]  Ritu Mishra,et al.  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. , 2014, The International journal of risk & safety in medicine.

[14]  Mihai Nadin,et al.  Concepts and fuzzy logic , 2012, Int. J. Gen. Syst..

[15]  Dimitrios Tsoumakos,et al.  A decision tree based approach towards adaptive modeling of big data applications , 2017, 2017 IEEE International Conference on Big Data (Big Data).

[16]  S. Evans,et al.  Use of proportional reporting ratios (PRRs) for signal generation from spontaneous adverse drug reaction reports , 2001, Pharmacoepidemiology and drug safety.

[17]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[18]  Ayman M. Mansour,et al.  A Multi-Agent Intelligent System for Monitoring Health Conditions of Elderly People , 2014 .

[19]  Clive W. J. Granger,et al.  Systematic sampling, temporal aggregation, seasonal adjustment, and cointegration theory and evidence , 1995 .

[20]  Carol Friedman,et al.  Mining multi-item drug adverse effect associations in spontaneous reporting systems , 2010, BMC Bioinformatics.

[21]  A. Schuchat.  DEPARTMENT OF HEALTH & HUMAN SERVICES , 2015 .

[22]  Khichar Shubhakaran,et al.  Postmarketing adverse drug reactions: A duty to report? , 2014, Neurology. Clinical practice.

[23]  M. Hippius,et al.  Preventable ADRs leading to hospitalization — results of a long-term prospective safety study with 6,427 ADR cases focusing on elderly patients , 2018, Expert opinion on drug safety.

[24]  I. Edwards,et al.  Adverse drug reactions: definitions, diagnosis, and management , 2000, The Lancet.

[25]  Kay Brune,et al.  Lack of Awareness of Community-Acquired Adverse Drug Reactions Upon Hospital Admission , 2003, Drug safety.

[26]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[27]  Robert LIN,et al.  NOTE ON FUZZY SETS , 2014 .

[28]  Daisuke Koide,et al.  Comparison of data mining methodologies using Japanese spontaneous reports , 2004, Pharmacoepidemiology and drug safety.

[29]  A. Fourrier-Réglat,et al.  Adverse drug reactions of analgesic medicines: analysis of the Romanian pharmacovigilance database , 2018, Fundamental & clinical pharmacology.

[30]  Deepa Abin,et al.  Causal Association Mining for Detection of Adverse Drug Reactions , 2015, 2015 International Conference on Computing Communication Control and Automation.

[31]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[32]  K. Halvorsen,et al.  Adverse drug reaction reporting: how can drug consumption information add to analyses using spontaneous reports? , 2018, European Journal of Clinical Pharmacology.