Improved Adverse Drug Event Prediction Through Information Component Guided Pharmacological Network Model (IC-PNM)

Ji, Xiangmin; Wang, Lei; Hua, Liyan; Zhang, Pengyue; Shendre, Aditi; Feng, Weixing; Li, Jin; Li, Lang

doi:10.1109/tcbb.2019.2928305

Cited by 6 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, while the drug-ADE pairs with small sample sizes had more negative data than the drug-ADE pairs with large sample sizes, they also contained positive data. As stated in our previous research, in training a PNM model, the training model should include both large and small sample size drug-ADE pairs when selecting the training data ( Ji, et al, 2021 ). Therefore, the probabilities calculated by PNM were not influenced by any confounders.…”

Section: Discussionmentioning

confidence: 99%

“…Furthermore, the small sample size drug-ADE pairs contain more negative and positive data than large sample size drug-ADE pairs. In training of the PNM model, the training model should include both positive and negative data when selecting the training data ( Ji, et al, 2021 ). Therefore, the PNM can control the influence of any confounding bias.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Combining a Pharmacological Network Model with a Bayesian Signal Detection Algorithm to Improve the Detection of Adverse Drug Events

Cui

et al. 2022

Front. Pharmacol.

Self Cite

View full text Add to dashboard Cite

Introduction: Improving adverse drug event (ADE) detection is important for post-marketing drug safety surveillance. Existing statistical approaches can be further optimized owing to their high efficiency and low cost.Objective: The objective of this study was to evaluate the proposed approach for use in pharmacovigilance, the early detection of potential ADEs, and the improvement of drug safety.Methods: We developed a novel integrated approach, the Bayesian signal detection algorithm, based on the pharmacological network model (ICPNM) using the FDA Adverse Event Reporting System (FAERS) data published from 2004 to 2009 and from 2014 to 2019Q2, PubChem, and DrugBank database. First, we used a pharmacological network model to generate the probabilities for drug-ADE associations, which comprised the proper prior information component (IC). We then defined the probability of the propensity score adjustment based on a logistic regression model to control for the confounding bias. Finally, we chose the Side Effect Resource (SIDER) and the Observational Medical Outcomes Partnership (OMOP) data to evaluate the detection performance and robustness of the ICPNM compared with the statistical approaches [disproportionality analysis (DPA)] by using the area under the receiver operator characteristics curve (AUC) and Youden’s index.Results: Of the statistical approaches implemented, the ICPNM showed the best performance (AUC, 0.8291; Youden’s index, 0.5836). Meanwhile, the AUCs of the IC, EBGM, ROR, and PRR were 0.7343, 0.7231, 0.6828, and 0.6721, respectively.Conclusion: The proposed ICPNM combined the strengths of the pharmacological network model and the Bayesian signal detection algorithm and performed better in detecting true drug-ADE associations. It also detected newer ADE signals than a DPA and may be complementary to the existing statistical approaches.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Combining a Pharmacological Network Model with a Bayesian Signal Detection Algorithm to Improve the Detection of Adverse Drug Events

Cui

et al. 2022

Front. Pharmacol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The method uses stacked autoencoders, weighted support vector machines, and an autoencoder-based semi-supervised learning algorithm to improve classification performance, outperforming other approaches. In [9], the authors enhanced the pharmacovigilance's ability to predict ADEs. They applied an information component-guided pharmacological network model (IC-PNM) as a novel approach to test the data from the FDA Adverse Event Reporting System (FAERS).…”

Section: Related Workmentioning

confidence: 99%

Layer-Weighted Attention and Ascending Feature Selection: An Approach for Seriousness Level Prediction Using the FDA Adverse Event Reporting System

Aldughayfiq,

Allahem,

Mostafa

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

In this study, we introduce a novel combination of layer-static-weighted attention and ascending feature selection techniques to predict the seriousness level of adverse drug events using the Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS). We utilized natural language processing (NLP) to analyze the terms in the active substance field, in addition to considering demographic and event information such as patient sex, healthcare provider qualification, and drug characterization. Our ascending feature selection method, which progressively incorporates additional features based on their importance, demonstrated continuous enhancements in prediction performance. Simultaneously, we employed a layer-static-weighted attention technique, which dynamically adjusts the model’s focus between natural language processing (NLP) and demographic features. This technique achieved its best performance at a balanced weight of 50%, yielding an average test accuracy of 74.56% and CV ROC score of 0.83 when 4000 features were included, indicating a compelling advantage to include a larger volume of meaningful features. By integrating these methodologies, we constructed a robust model capable of effectively predicting seriousness levels, offering significant potential for improving pharmacovigilance and enhancing drug safety monitoring. The results underscore the value of NLP and demographic data in predicting drug event seriousness and demonstrate the effectiveness of our combined techniques. We encourage further research to refine these methods and evaluate their application to other clinical datasets.

show abstract

“…Disproportionality analysis is a common method used to detect signals in drug vigilance databases and is employed to identify unknown AEs ( Noguchi et al, 2021 ; Javed and Kumar, 2024 ). The reporting odds ratio (ROR) is a method of frequency disproportionality analysis, while the information component (IC) is a component of Bayesian disproportionality analysis ( Ji et al, 2021 ). ROR is a classic method and also an algorithm frequently used by the Pharmaceuticals and Medical Devices Agency of Japan (PMDA) and the Netherlands Pharmacovigilance Centre (Lareb) ( Noguchi et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

Examining the safety of mirabegron: an analysis of real-world pharmacovigilance data from the US FDA adverse event reporting system (FAERS) database

Wang,

Zhang,

et al. 2024

Front. Pharmacol.

View full text Add to dashboard Cite

Background: Mirabegron, the first β-3 adrenergic receptor agonist, received approval from the Food and Drug Administration (FDA) in 2012 for the treatment of overactive bladder (OAB). This pharmacovigilance study investigated the safety profile of mirabegron treatment using the US FDA Adverse Event Reporting System (FAERS) database.Methods: This study employed disproportionality analyses, including the reporting odds ratio (ROR) and Bayesian Confidence Propagation Neural Network (BCPNN) algorithm, to quantify signals of adverse events associated with mirabegron.Results: From the first quarter of 2012 to the third quarter of 2023, a comprehensive total of 14,356,234 adverse event (AE) reports were submitted to the FDA Adverse Event Reporting System database. Within this dataset, encompassing 18,763 reports specifically associated with mirabegron, healthcare professionals notably contributed 2,902 of these reports. A total of 80 preferred terms (PTs) of interest were identified using both the ROR and information component algorithms. The most common AEs included blood pressure increased, urinary retention, atrial fibrillation, dry mouth, and tachycardia, which were consistent with the product instructions. Unexpected significant AEs, such as arrhythmia, palpitations, dementia, transient ischemic attack, Parkinson’s disease, anti-neutrophil cytoplasmic antibody positive vasculitis, lip swelling, and swollen tongue, were also identified. The study findings indicated that the majority of onset time occurred within 30 days (n = 358, 55.68%). However, AEs were still possible after 1 year of mirabegron treatment.Conclusion: This study provided valuable evidence for the real-world safety of mirabegron, helping clinical professionals enhance their understanding of mirabegron’s safety in clinical practice. It also contributed valuable evidence for further safety studies on mirabegron.

show abstract

Improved Adverse Drug Event Prediction Through Information Component Guided Pharmacological Network Model (IC-PNM)

Cited by 6 publications

References 26 publications

Combining a Pharmacological Network Model with a Bayesian Signal Detection Algorithm to Improve the Detection of Adverse Drug Events

Combining a Pharmacological Network Model with a Bayesian Signal Detection Algorithm to Improve the Detection of Adverse Drug Events

Layer-Weighted Attention and Ascending Feature Selection: An Approach for Seriousness Level Prediction Using the FDA Adverse Event Reporting System

Examining the safety of mirabegron: an analysis of real-world pharmacovigilance data from the US FDA adverse event reporting system (FAERS) database

Contact Info

Product

Resources

About