Ivor Ralph Edwards

A Bayesian neural network method for adverse drug reaction signal generation

AbstractObjective: The database of adverse drug reactions (ADRs) held by the Uppsala Monitoring Centre on behalf of the 47 countries of the World Health Organization (WHO) Collaborating Programme for International Drug Monitoring contains nearly two million reports. It is the largest database of this sort in the world, and about 35 000 new reports are added quarterly. The task of trying to find new drug–ADR signals has been carried out by an expert panel, but with such a large volume of material the task is daunting. We have developed a flexible, automated procedure to find new signals with known probability difference from the background data. Method: Data mining, using various computational approaches, has been applied in a variety of disciplines. A Bayesian confidence propagation neural network (BCPNN) has been developed which can manage large data sets, is robust in handling incomplete data, and may be used with complex variables. Using information theory, such a tool is ideal for finding drug–ADR combinations with other variables, which are highly associated compared to the generality of the stored data, or a section of the stored data. The method is transparent for easy checking and flexible for different kinds of search. Results: Using the BCPNN, some time scan examples are given which show the power of the technique to find signals early (captopril–coughing) and to avoid false positives where a common drug and ADRs occur in the database (digoxin–acne; digoxin–rash). A routine application of the BCPNN to a quarterly update is also tested, showing that 1004 suspected drug–ADR combinations reached the 97.5% confidence level of difference from the generality. Of these, 307 were potentially serious ADRs, and of these 53 related to new drugs. Twelve of the latter were not recorded in the CD editions of The physicians Desk Reference orMartindales Extra Pharmacopoea and did not appear in Reactions Weekly online. Conclusion: The results indicate that the BCPNN can be used in the detection of significant signals from the data set of the WHO Programme on International Drug Monitoring. The BCPNN will be an extremely useful adjunct to the expert assessment of very large numbers of spontaneously reported ADRs.

Causal or Casual? The Role of Causality Assessment in Pharmacovigilance

SummaryAs with any other study method, ‘spontaneous reporting’ in pharmacovigilance is a process of data acquisition, assessment, presentation and interpretation. The provision of information (i.e. of interpreted data) concerning previously unknown, or otherwise important adverse drug reactions is a major goal. The assessment of case reports in spontaneous reporting takes place in 2 steps: first the assessment of each case individually, and secondly the interpretation of the aggregated data. The latter step is only completed for a minority of case reports, such as when actions or measures are deemed necessary.Uncertainty in case reports regarding the involvement of the suspected drugs is an inherent drawback of spontaneous reporting. Standardised case-causality assessment has become a routine at pharmacovigilance centres around the world. It aims at a decrease in ambiguity of the data and plays a role in data exchange and the prevention of erroneous conclusions. A variety of systems for standardised causality assessment have been developed, ranging from short questionnaires to comprehensive algorithms. Since none of the available assessment systems has been validated (i.e. shown to consistently and reproducibly produce a fair approximation of the truth), causality assessment has only limited scientific value. Causality assessment neither eliminates nor quantifies uncertainty but, at best, categorises it in a semiquantitative way.Routine causality assessment is usually part of the first step in case assessment, and is based on a general system that is intended for all reactions and all drugs. During the subsequent phase of aggregated assessment, causality assessment is likely to be repeated and the use of a specific aetiological-diagnostic system may be more appropriate. It may be recommended to restrict case-causality assessment to selected case reports that are likely to play an active role in pharmacovigilance and to use specific systems, adapted to the reaction or problem involved.It is an inherent limitation of spontaneous reporting that, with the exception of rare proof-positive case reports, conclusive evidence cannot usually be produced. Standardised causality assessment has not really changed this situation. As a rule, confirmation of the connection between a drug and an adverse reaction requires further analytical or experimental study.

Antipsychotic drugs and heart muscle disorder in international pharmacovigilance: data mining study

Abstract Objectives: To examine the relation between antipsychotic drugs and myocarditis and cardiomyopathy. Design: Data mining using bayesian statistics implemented in a neural network architecture. Setting: International database on adverse drug reactions run by the World Health Organization programme for international drug monitoring. Main outcome measures: Reports mentioning antipsychotic drugs, cardiomyopathy, or myocarditis. Results: A strong signal existed for an association between clozapine and cardiomyopathy and myocarditis. An association was also seen with other antipsychotics as a group. The association was based on sufficient cases with adequate documentation and apparent lack of confounding to constitute a signal. Associations between myocarditis or cardiomyopathy and lithium, chlorpromazine, fluphenazine, haloperidol, and risperidone need further investigation. Conclusions: Some antipsychotic drugs seem to be linked to cardiomyopathy and myocarditis. The study shows the potential of bayesian neural networks in analysing data on drug safety.

Withdrawal reactions with selective serotonin re-uptake inhibitors as reported to the WHO system

AbstractObjective: The present study was performed both to investigate whether there might be a difference between the selective serotonin re-uptake inhibitors, (SSRIs) with regard to the incidence of withdrawal reactions, and to describe the associated symptoms. From the WHO database, therefore, all case reports from the year of introduction for each of the SSRIs, fluoxetine, paroxetine and sertraline, were retrieved. Sales figures were obtained from Intercontinental Medical Statistics International. The reporting rates were calculated as the number of reports per million defined daily doses (DDDs) sold per year. Results: The reporting rate of withdrawal reactions for paroxetine was found to be higher than that for sertraline and fluoxetine in each of the countries selected for detailed analyses (US, UK and Australia), as well as for all 16 countries combined. Moreover, using the WHO system of organ classification, the ratio of central nervous system to psychiatric withdrawal symptoms was 1.9 and 2.1 for paroxetine and sertraline, respectively, whereas that for fluoxetine was 0.48, indicating a possible qualitative difference between the SSRIs with respect to the nature of the withdrawal syndrome.

Data-mining analyses of pharmacovigilance signals in relation to relevant comparison drugs

Abstract Objective. The aim of this paper is to demonstrate the usefulness of the Bayesian Confidence Propagation Neural Network (BCPNN) in the detection of drug-specific and drug-group effects in the database of adverse drug reactions of the World Health Organization Programme for International Drug Monitoring. Methods. Examples of drug–adverse reaction combinations highlighted by the BCPNN as quantitative associations were selected. The anatomical therapeutic chemical (ATC) group to which the drug belonged was then identified, and the information component (IC) was calculated for this ATC group and the adverse drug reaction (ADR). The IC of the ATC group with the ADR was then compared with the IC of the drug–ADR by plotting the change in IC and its 95% confidence limit over time for both. Results. The chosen examples show that the BCPNN data-mining approach can identify drug-specific as well as group effects. In the known examples that served as test cases, beta-blocking agents other than practolol are not associated with sclerosing peritonitis, but all angiotensin-converting enzyme inhibitors are associated with coughing, as are antihistamines with heart-rhythm disorders and antipsychotics with myocarditis. The recently identified association between antipsychotics and myocarditis remains even after consideration of concomitant medication. Conclusion. The BCPNN can be used to improve the ability of a signal detection system to highlight group and drug-specific effects.

The application of knowledge discovery in databases to post-marketing drug safety : example of the WHO database

After market launch, new information on adverse effects of medicinal products is almost exclusively first highlighted by spontaneous reporting. As data sets of spontaneous reports have become larger, and computational capability has increased, quantitative methods have been increasingly applied to such data sets. The screening of such data sets is an application of knowledge discovery in databases (KDD). Effective KDD is an iterative and interactive process made up of the following steps: developing an understanding of an application domain, creating a target data set, data cleaning and pre‐processing, data reduction and projection, choosing the data mining task, choosing the data mining algorithm, data mining, interpretation of results and consolidating and using acquired knowledge.

A New Erice Report Considering the Safety of Medicines in the 21st Century

Pharmacovogilance policy, methods and practice require transformation at all levels to create an integrated, comprehensive, continuously improving system, fulfilling the broader remit of overall healthcare vigilance. In pursuit of this vision, energetic measures, including active engagement with patients, are needed to reduce our ignorance about many aspects of patients’ experience of medical therapies and their outcomes, including the benefits, but especially the extensive harm known to be caused by medical interventions. More information and communication in this domain will help set more accurate and realistic public expectations about the benefits and harm of therapy. All aspects of medicines development, regulation and use must be characterized by openness, transparency, ethical practice and a primary focus on the benefit and self-determined choices of patients. Notwithstanding, progress has been made in medicines safety information and communication but significant gaps and deficiencies remain. Promotion of the most beneficial use of medicines and the prevention of harm have not advanced sufficiently. This paper is a report from a group of experts, following previous similar decade reviews: the Erice Declaration (1996) and the Erice Manifesto (2006).

Pharmacovigilance Indicators: Desiderata for the Future of Medicine Safety

The thalidomide tragedy highlighted an unacceptable harm and potential risks of taking medicines [1]. This resulted in a global resolve that such a tragedy should never occur again, and all machinery to achieve this was put in place in the more developed countries in a rather systematic manner. This initial and prompt response ultimately resulted in the establishment of the WHO Programme for International Drug Monitoring (PIDM) schemes [2]. The initial focus was on suspected adverse drug reactions however over time the scope broadened to include other medicine-related problem. The occurrences regarding issues on medicinal safety after the thalidomide experience underscore the need for continuous watchfulness. The nomenclature has become more embracing and issues bordering on medicines safety coined “pharmacovigilance.”