Application of data mining techniques in pharmacovigilance.

AIMS To discuss the potential use of data mining and knowledge discovery in databases for detection of adverse drug events (ADE) in pharmacovigilance. METHODS A literature search was conducted to identify articles, which contained details of data mining, signal generation or knowledge discovery in relation to adverse drug reactions or pharmacovigilance in medical databases. RESULTS ADEs are common and result in significant mortality, and despite existing systems drugs have been withdrawn due to ADEs many years after licensing. Knowledge discovery in databases (KDD) is a technique which may be used to detect potential ADEs more efficiently. KDD involves the selection of data variables and databases, data preprocessing, data mining and data interpretation and utilization. Data mining encompasses a number of statistical techniques including cluster analysis, link analysis, deviation detection and disproportionality assessment which can be utilized to determine the presence of and to assess the strength of ADE signals. Currently the only data mining methods to be used in pharmacovigilance are those of disproportionality, such as the Proportional Reporting Ratio and Information Component, which have been used to analyse the UK Yellow Card Scheme spontaneous reporting database and the WHO Uppsala Monitoring Centre database. The association of pericarditis with practolol but not with other beta-blockers, the association of captopril and other angiotensin-converting enzymes with cough, and the association of terfenadine with heart rate and rhythm disorders could be identified by mining the WHO database. CONCLUSION In view of the importance of ADEs and the development of massive data storage systems and powerful computer systems, the use of data mining techniques in knowledge discovery in medical databases is likely to be of increasing importance in the process of pharmacovigilance as they are likely to be able to detect signals earlier than using current methods.

[1]  N. Laird,et al.  Incidence of Adverse Drug Events and Potential Adverse Drug Events: Implications for Prevention , 1995 .

[2]  R. Mann,et al.  Nicorandil and diabetes: a nested case-control study to examine a signal generated by prescription-event monitoring , 1999, European Journal of Clinical Pharmacology.

[3]  F. Barbone,et al.  Association of road-traffic accidents with benzodiazepine use , 1998, The Lancet.

[4]  J. Ioannidis,et al.  Completeness of safety reporting in randomized trials: an evaluation of 7 medical areas. , 2001, JAMA.

[5]  R Day,et al.  Comparison of upper gastrointestinal toxicity of rofecoxib and naproxen in patients with rheumatoid arthritis. VIGOR Study Group. , 2000, The New England journal of medicine.

[6]  B. Strom.  How Should One Perform Pharmacoepidemiology Studies? Choosing Among the Available Alternatives , 2002 .

[7]  M. Lindquist,et al.  Antipsychotic drugs and heart muscle disorder in international pharmacovigilance: data mining study , 2001, BMJ : British Medical Journal.

[8]  R. Woosley,et al.  Changes in the pharmacokinetics and electrocardiographic pharmacodynamics of terfenadine with concomitant administration of erythromycin , 1992, Clinical pharmacology and therapeutics.

[9]  M. Braun,et al.  Data mining in the US Vaccine Adverse Event Reporting System (VAERS): early detection of intussusception and other events after rotavirus vaccination. , 2001, Vaccine.

[10]  David W. Bates,et al.  Research Paper: Using Computerized Data to Identify Adverse Drug Events in Outpatients , 2001, J. Am. Medical Informatics Assoc..

[11]  J. Woodcock,et al.  The safety of newly approved medicines: do recent market removals mean there is a problem? , 1999, JAMA.

[12]  R. Meyboom,et al.  Signalling possible drug-drug interactions in a spontaneous reporting system: delay of withdrawal bleeding during concomitant use of oral contraceptives and itraconazole. , 1999, British journal of clinical pharmacology.

[13]  D. Bates,et al.  Pharmacist participation on physician rounds and adverse drug events in the intensive care unit. , 1999, JAMA.

[14]  M. Lindquist,et al.  A Data Mining Approach for Signal Detection and Analysis , 2002, Drug safety.

[15]  J. Hallas,et al.  Drug‐induced symptoms of functional dyspepsia and nausea. A symmetry analysis of one million prescriptions , 2000, Alimentary pharmacology & therapeutics.

[16]  Edwards Ir.  The accelerating need for pharmacovigilance. , 2000 .

[17]  M. Lindquist,et al.  A Retrospective Evaluation of a Data Mining Approach to Aid Finding New Adverse Drug Reaction Signals in the WHO International Database , 2000, Drug safety.

[18]  I. Edwards,et al.  Reasons for Reporting Adverse Drug Reactions—Some Thoughts Based on an International Review , 1997, Pharmacoepidemiology and drug safety.

[19]  P. Zed,et al.  Drug‐Related Visits to the Emergency Department: How Big Is the Problem? , 2002, Pharmacotherapy.

[20]  S. Shakir,et al.  Causal Association in Pharmacovigilance and Pharmacoepidemiology , 2002, Drug safety.

[21]  E. Brown,et al.  The Medical Dictionary for Regulatory Activities (MedDRA) , 1999, Drug safety.

[22]  Gobinda G. Chowdhury,et al.  Template Mining for Information Extraction from Digital Documents , 1999, Libr. Trends.

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

[24]  M. Lindquist,et al.  Signal Selection and Follow-Up in Pharmacovigilance , 2002, Drug safety.

[25]  Munir Pirmohamed,et al.  Fortnightly review: Adverse drug reactions , 1998 .

[26]  D. Bates,et al.  Effect of computerized physician order entry and a team intervention on prevention of serious medication errors. , 1998, JAMA.

[27]  P. Neuvonen,et al.  Drug-related deaths in a university central hospital , 2002, European Journal of Clinical Pharmacology.

[28]  Barbara H. Kwasnik,et al.  The Role of Classification in Knowledge Representation and Discovery , 1999, Libr. Trends.

[29]  A. Bate,et al.  Data-mining analyses of pharmacovigilance signals in relation to relevant comparison drugs , 2002, European Journal of Clinical Pharmacology.

[30]  A. Egberts,et al.  Determinants of signal selection in a spontaneous reporting system for adverse drug reactions. , 2001, British journal of clinical pharmacology.

[31]  R. O’Neill,et al.  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 , 2002, Drug safety.

[32]  W. Amery.  Signal generation from spontaneous adverse event reports , 1999, Pharmacoepidemiology and drug safety.

[33]  M. Lindquist,et al.  A comparison of measures of disproportionality for signal detection in spontaneous reporting systems for adverse drug reactions , 2002, Pharmacoepidemiology and drug safety.

[34]  E. Topol,et al.  Risk of cardiovascular events associated with selective COX-2 inhibitors. , 2001, JAMA.

[35]  Emma Heeley,et al.  Automated Signal Generation in Prescription-Event Monitoring , 2002, Drug safety.

[36]  E. Brown,et al.  Effects of Coding Dictionary on Signal Generation , 2002, Drug safety.

[37]  A. Mitchell,et al.  Signal generation and clarification: use of case–control data , 2001, Pharmacoepidemiology and drug safety.

[38]  R. Mann,et al.  Prescription-event monitoring--recent progress and future horizons. , 2002, British journal of clinical pharmacology.

[39]  C. Helma,et al.  Statistical Methods in Medical Research Knowledge Discovery and Data Mining in Toxicology , 2022 .

[40]  R. Meyboom,et al.  Use of Measures of Disproportionality in Pharmacovigilance , 2002, Drug safety.

[41]  J P Cambus,et al.  Detection and incidence of drug-induced liver injuries in hospital: a prospective analysis from laboratory signals. , 2001, British journal of clinical pharmacology.

[42]  Soumen Chakrabarti,et al.  Mining the web - discovering knowledge from hypertext data , 2002 .