ARWAR: A network approach for predicting Adverse Drug Reactions

Background: To highlight the importance of spontaneous reporting programs in post marketing surveillance of medicines. Authors also aimed at providing various dimensions of spontaneous programs, including the strengths and weakness, and providing an insight on the future prospects of pharmacovigilance systems. Methods: Various literature related to post marketing surveillance and spontaneous reporting programs were reviewed and the relevant ones highlighting the strengths and weaknesses are summarized. A balance of information on strengths and weaknesses is listed. The health professionals’ awareness regarding existing spontaneous reporting programs is highlighted. Future prospects of pharmacovigilance are discussed. Results: Though beneficial, spontaneous reporting programs encounter several limitations and difficulties in diagnosing adverse drug reaction. Under-reporting and bias are major challenges. Online signal detection tools and innovative methods are needed to strengthen the spontaneous reporting programs. We provide the various issues to be considered while depending on spontaneous reporting programs as a method of post marketing surveillance. Conclusion: To strengthen the spontaneous reporting programs as an effective post marketing surveillance method, more awareness among health professionals and innovative strategies is needed. Integrating pharmacogenetic data can be a potential aspect of future pharmacovigilance. Plain language summary Monitoring adverse effects of marketed medicines through reporting by healthcare professionals and its challenges and way forward Introduction: This article highlights the importance of safety monitoring of medicines after they are launched in the market, mainly through reporting by healthcare professionals. We also highlight the strengths and weaknesses, and provide an insight on the future prospects of pharmacovigilance systems. Methods: Various literature related to the topic were reviewed and the relevant ones highlighting the strengths and weaknesses are summarized. A balance of information on strengths and weaknesses is listed. Health professionals’ awareness regarding existing programs on reporting safety of medicines is highlighted. Results: Though beneficial, reporting of adverse effects by healthcare professionals who deal with patient lacks clarity in diagnosing the adverse effects. Under-reporting and bias are the major challenges. Online software is needed to strengthen reporting by healthcare professionals. We list the various issues to be considered while depending on healthcare professionals’ reporting of adverse effects as a method of post marketing surveillance. Conclusion: To strengthen medicine safety monitoring and reporting by healthcare professionals, more awareness among health professionals and innovative strategies are needed. Integrating the genetic data of patients can be beneficial in predicting adverse effects, therefore avoiding them and enhancing safe prescribing and dispensing by healthcare professionals.

show abstract

“…Afterwards, an algorithm for link predictions, Random-Walk with Restarts, is applied, and will lead to predicting novel ADRs. 61 …”

Section: Post Marketing Surveillance Of Suspected Adrsmentioning

confidence: 99%

Post marketing surveillance of suspected adverse drug reactions through spontaneous reporting: current status, challenges and the future

Alomar

Tawfiq

Hassan

et al. 2020

Therapeutic Advances in Drug Safety

135

View full text Add to dashboard Cite

show abstract

“…Rahmani et al . 12 predicted unknown ADRs by applying a random walk algorithm to a network with drug and ADR nodes, where drug-ADR edges represent known ADRs and drug-drug edges indicate drug target similarity, but did not validate new ADRs in any real-world clinical data. Bresso et al .…”

Section: Predicting Unknown Adrsmentioning

confidence: 99%

Knowledge graph prediction of unknown adverse drug reactions and validation in electronic health records

Bean

Iqbal

et al. 2017

Sci Rep

View full text Add to dashboard Cite

Unknown adverse reactions to drugs available on the market present a significant health risk and limit accurate judgement of the cost/benefit trade-off for medications. Machine learning has the potential to predict unknown adverse reactions from current knowledge. We constructed a knowledge graph containing four types of node: drugs, protein targets, indications and adverse reactions. Using this graph, we developed a machine learning algorithm based on a simple enrichment test and first demonstrated this method performs extremely well at classifying known causes of adverse reactions (AUC 0.92). A cross validation scheme in which 10% of drug-adverse reaction edges were systematically deleted per fold showed that the method correctly predicts 68% of the deleted edges on average. Next, a subset of adverse reactions that could be reliably detected in anonymised electronic health records from South London and Maudsley NHS Foundation Trust were used to validate predictions from the model that are not currently known in public databases. High-confidence predictions were validated in electronic records significantly more frequently than random models, and outperformed standard methods (logistic regression, decision trees and support vector machines). This approach has the potential to improve patient safety by predicting adverse reactions that were not observed during randomised trials.

show abstract

“…For the purpose of predicting drug toxicity, in most cases we require a collection of experimental data reflecting molecular changes in the context of quantifiable cellular changes across different biological scales that are linked to toxicity at the body level [35]. So in addition to all the above-mentioned data, systems toxicology depends strongly on the quality and scope of databases annotating side effects (SIDER) and drug-induced differential gene expression, or a combination thereof [94][95][96][97].…”

Section: Huang Et Al Developed a New Metric To Measure The Strength O...mentioning

confidence: 99%

Predictive Systems Toxicology

Kiani

Shang

Zenil

et al. 2018

Methods in Molecular Biology

View full text Add to dashboard Cite

In this review we address to what extent computational techniques can augment our ability to predict toxicity. The first section provides a brief history of empirical observations on toxicity dating back to the dawn of Sumerian civilization. Interestingly, the concept of dose emerged very early on, leading up to the modern emphasis on kinetic properties, which in turn encodes the insight that toxicity is not solely a property of a compound but instead depends on the interaction with the host organism. The next logical step is the current conception of evaluating drugs from a personalized medicine point of view. We review recent work on integrating what could be referred to as classical pharmacokinetic analysis with emerging systems biology approaches incorporating multiple omics data. These systems approaches employ advanced statistical analytical data processing complemented with machine learning techniques and use both pharmacokinetic and omics data. We find that such integrated approaches not only provide improved predictions of toxicity but also enable mechanistic interpretations of the molecular mechanisms underpinning toxicity and drug resistance. We conclude the chapter by discussing some of the main challenges, such as how to balance the inherent tension between the predicitive capacity of models, which in practice amounts to constraining the number of features in the models versus allowing for rich mechanistic interpretability, i.e., equipping models with numerous molecular features. This challenge also requires patient-specific predictions on toxicity, which in turn requires proper stratification of patients as regards how they respond, with or without adverse toxic effects. In summary, the transformation of the ancient concept of dose is currently successfully operationalized using rich integrative data encoded in patient-specific models.

show abstract

ARWAR: A network approach for predicting Adverse Drug Reactions

Cited by 18 publications

References 49 publications

Post marketing surveillance of suspected adverse drug reactions through spontaneous reporting: current status, challenges and the future

Post marketing surveillance of suspected adverse drug reactions through spontaneous reporting: current status, challenges and the future

Knowledge graph prediction of unknown adverse drug reactions and validation in electronic health records

Predictive Systems Toxicology

Contact Info

Product

Resources

About