Adverse Drug Event Prevention and Detection in Older Emergency Department Patients

Koehl, Jennifer L.

doi:10.1016/j.cger.2023.04.008

Cited by 2 publications

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clinicians can utilize this information to create more successful preventative plans and gain a better understanding of how ADEs occur. Furthermore, the authors of [15] highlighted the importance of using interactive support tools to reduce the number of ADEs and prevent unnecessary prescribing cascades in older adults. Instead of just predicting whether ADEs will occur in cancer patients, the authors of [16] attempted to develop a new method for timing ADEs.…”

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

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

show abstract

Pharmacogenomic Drug-Gene Interactions in Geriatric Emergency Department Patients That Have Fallen

Shih,

Engstrom,

Pandya

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: Pharmacogenomic assisted prescribing of medications utilizes individual genetic information to identify drug-gene interactions. We aimed to assess potential pharmacogenomic drug-gene interactions in geriatric emergency department (ED) patients that have sustained a fall. Methods: This was a prospective study involving 25 older adult ED patients with fall related injury. Data collected included current medications, demographics and mechanism of injury. All patients provided a DNA sample for pharmacogenomic testing, MatchMyMeds (DNA Labs, Boca Raton, FL) which assessed genetic data for 23 enzyme systems and reports on potential drug-gene interactions for 134 medications. Each patients medications were reviewed against their pharmacogenomic report and categorized as Green (go), Yellow (caution) or Red (stop) based on their genetic information and published interactions by the Clinical Pharmacogenetics Implementation Consortium (CPIC), Dutch Pharmacogenetics Working Group (DPWG) and Food and Drug Administration-approved drug label information. The main study outcome was pharmacogenomic drug-gene interactions. Results: Of the 25 patients enrolled (median age, 81 years, IQR: 76-85), 68% were female. Patients were taking a median of 8 medications (IQR: 5-11). The most common types were antihypertensives, statins, anticoagulants, and anti-platelet medications. Significant drug-gene interactions (Yellow or Red) were identified in 14/25 (56%) patients. Further, 6/25 (24%) had one or more potentially serious (Red) interactions identified. Conclusions: In geriatric ED patients with a fall-related injury, a majority have a significant pharmacogenomic drug-gene interactions. DNA testing identifies these interactions and can assist with pharmacogenomic-guided medication prescribing which may decrease ADEs and improve clinical outcomes.

show abstract

Adverse Drug Event Prevention and Detection in Older Emergency Department Patients

Cited by 2 publications

References 38 publications

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

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

Pharmacogenomic Drug-Gene Interactions in Geriatric Emergency Department Patients That Have Fallen

Contact Info

Product

Resources

About