Adverse Drug Event (ADE) extraction is one of the core tasks in digital pharmacovigilance, especially when applied to informal texts. This task has been addressed by the Natural Language Processing ...community using large pre-trained language models, such as BERT. Despite the great number of Transformer-based architectures used in the literature, it is unclear which of them has better performances and why. Therefore, in this paper we perform an extensive evaluation and analysis of 19 Transformer-based models for ADE extraction on informal texts. We compare the performance of all the considered models on two datasets with increasing levels of informality (forums posts and tweets). We also combine the purely Transformer-based models with two commonly-used additional processing layers (CRF and LSTM), and analyze their effect on the models performance. Furthermore, we use a well-established feature importance technique (SHAP) to correlate the performance of the models with a set of features that describe them: model category (AutoEncoding, AutoRegressive, Text-to-Text), pre-training domain, training from scratch, and model size in number of parameters. At the end of our analyses, we identify a list of take-home messages that can be derived from the experimental data.
Background The increasing prevalence of fungal infections necessitates broader use of antifungal medications. However, the prevalence of adverse drug events (ADEs) restricts their clinical ...application. This study aimed to develop a reliable ADEs trigger for antifungals to enable proactive ADEs monitoring, serving as a reference for ADEs prevention and control. Methods This investigation comprises two phases. Initially, the trigger was established via a literature review, extraction of relevant items, and refinement through Delphi expert consultation. Subsequently, the validity of the trigger was assessed by analyzing hospital records of antifungal drug users from 1 January 2019 to 31 December 2020. The correlation between each trigger signal and ADEs occurrence was examined, and the sensitivity and specificity of the trigger were evaluated through the spontaneous reporting system (SRS) and Global Trigger Tool (GTT). Additionally, risk factors contributing to adverse drug events (ADEs) resulting from antifungal use were analyzed. Results: Twenty-one preliminary triggers were refined into 21 final triggers after one expert round. In the retrospective analysis, the positive trigger rate was 65.83%, with a positive predictive value (PPV) of 28.75%. The incidence of ADEs in inpatients was 28.75%, equating to 44.58 ADEs per 100 admissions and 33.04 ADEs per 1,000 patient days. Predominant ADEs categories included metabolic disturbances, gastrointestinal damage, and skin rashes. ADEs severity was classified into 36 cases at grade 1, 160 at grade 2, and 18 at grade 3. The likelihood of ADEs increased with longer stays, more positive triggers, and greater comorbidity counts. Conclusion This study underscores the effectiveness of the GTT in enhancing ADEs detection during antifungal medication use, thereby confirming its value as a monitoring tool.
Ipilimumab 3 mg/kg was the first agent to demonstrate improved survival in previously treated patients with metastatic melanoma in a phase 3 trial (MDX010-20). Ipilimumab produced a characteristic ...spectrum of immune-related adverse events (irAEs) of special interest, consistent with its immune-based mechanism of action.
In MDX010-20, 676 previously treated patients were randomized 3:1:1 to receive ipilimumab 3 mg/kg plus the glycoprotein 100 melanoma antigen vaccine (gp100), ipilimumab 3 mg/kg + placebo, or gp100 vaccine + placebo. For the current report, the authors conducted a detailed analysis of the time to onset and resolution of irAEs associated with ipilimumab therapy.
Grade 2 through 5 irAEs generally developed during the induction phase of treatment (0-12 weeks). Most, including grade 3/4 irAEs, were reversible when managed with treatment guidelines using vigilant monitoring and corticosteroids. The median time to resolution (to grade 1 or 0 or to the grade at baseline) of irAEs that had an onset during the induction phase was approximately 6 weeks for grade 2 through 4 irAEs and 8 weeks for grade 3 and 4 irAEs. Across the entire study duration, most grade 2 through 4 irAEs resolved within 12 weeks.
Most ipilimumab-associated irAEs, including grade 3/4 symptoms, developed within 12 weeks of initial dosing and resolved within 12 weeks of onset. IrAEs were well characterized in their evolution and could be managed using published algorithms.
Aims
We aimed to investigate the efficacy and effectiveness of pharmacist‐led interventions to reduce adverse drug events (ADEs) in older people living in residential aged care facilities (RACFs).
...Methods
We systematically searched MEDLINE via PubMed, Embase, Cochrane Central Register of Controlled Trials and PsycINFO from their inceptions to July 2020. We investigated experimental study designs that employed a control group, or quasi‐experimental studies conducted in RACFs.
Results
We screened 3826 records and included 23 studies. We found seven single‐component and 16 multicomponent pharmacist‐led interventions to reduce ADEs in older people living in RACFs. The most frequent single‐component pharmacist‐led intervention was medication review. Medication review and education provision to healthcare professionals were the most common components in many pharmacist‐led multicomponent interventions. Thirteen studies (56%) showed no effect, whereas ten studies (43%) reported significant reductions in ADEs following pharmacist‐led interventions either as a sole intervention or as a part of a multi‐component intervention. Many interventions focused on reducing the incidence of falls (39%).
Conclusions
This systematic review suggests that pharmacist‐led interventions have the potential to reduce the incidence of ADEs in older people living in RACFs. Medication review and educational programmes, particularly academic detailing, either as a single component or as part of multicomponent interventions were the most common approaches to reducing drug‐related harm in older people living in RACFs. The lack of a positive association between interventions and ADE in many studies suggests that targeted and tailored pharmacist‐led interventions are required to reduce ADEs in older people in RACFs.
Background
While the pharmacokinetic (PK) mechanisms for many drug interactions (DDIs) have been established, pharmacovigilance studies related to these PK DDIs are limited. Using a large ...surveillance database, a translational informatics approach can systematically screen adverse drug events (ADEs) for many DDIs with known PK mechanisms.
Methods
We collected a set of substrates and inhibitors related to the cytochrome P450 (CYP) isoforms, as recommended by the United States Food and Drug Administration (FDA) and Drug Interactions Flockhart table™. The FDA's Adverse Events Reporting System (FAERS) was used to obtain ADE reports from 2004 to 2018. The substrate and inhibitor information were used to form PK DDI pairs for each of the CYP isoforms and Medical Dictionary for Regulatory Activities (MedDRA) preferred terms used for ADEs in FAERS. A shrinkage observed‐to‐expected ratio (Ω) analysis was performed to screen for potential PK DDI and ADE associations.
Results
We identified 149 CYP substrates and 62 CYP inhibitors from the FDA and Flockhart tables. Using FAERS data, only those DDI‐ADE associations were considered that met the disproportionality threshold of Ω > 0 for a CYP substrate when paired with at least two inhibitors. In total, 590 ADEs were associated with 2085 PK DDI pairs and 38 individual substrates, with ADEs overlapping across different CYP substrates. More importantly, we were able to find clinical and experimental evidence for the paclitaxel‐clopidogrel interaction associated with peripheral neuropathy in our study.
Conclusion
In this study, we utilized a translational informatics approach to discover potentially novel CYP‐related substrate‐inhibitor and ADE associations using FAERS. Future clinical, population‐based and experimental studies are needed to confirm our findings.
Abstract
Objective
This article presents our approaches to extraction of medications and associated adverse drug events (ADEs) from clinical documents, which is the second track of the 2018 National ...NLP Clinical Challenges (n2c2) shared task.
Materials and Methods
The clinical corpus used in this study was from the MIMIC-III database and the organizers annotated 303 documents for training and 202 for testing. Our system consists of 2 components: a named entity recognition (NER) and a relation classification (RC) component. For each component, we implemented deep learning-based approaches (eg, BI-LSTM-CRF) and compared them with traditional machine learning approaches, namely, conditional random fields for NER and support vector machines for RC, respectively. In addition, we developed a deep learning-based joint model that recognizes ADEs and their relations to medications in 1 step using a sequence labeling approach. To further improve the performance, we also investigated different ensemble approaches to generating optimal performance by combining outputs from multiple approaches.
Results
Our best-performing systems achieved F1 scores of 93.45% for NER, 96.30% for RC, and 89.05% for end-to-end evaluation, which ranked #2, #1, and #1 among all participants, respectively. Additional evaluations show that the deep learning-based approaches did outperform traditional machine learning algorithms in both NER and RC. The joint model that simultaneously recognizes ADEs and their relations to medications also achieved the best performance on RC, indicating its promise for relation extraction.
Conclusion
In this study, we developed deep learning approaches for extracting medications and their attributes such as ADEs, and demonstrated its superior performance compared with traditional machine learning algorithms, indicating its uses in broader NER and RC tasks in the medical domain.
Published literature documents increased risk for psychiatric adverse events (P-AEs) following dopamine agonist (DA) initiation for treatment of primary restless legs syndrome (RLS). We examined the ...association between DA initiation and subsequent new-onset P-AEs among patients with a new diagnosis of RLS who had no history of psychiatric disorder or DA use.
Selected were adults (age 18 years or older) enrolled through United States employer-sponsored plans and Medicare Advantage from 7/1/2008-12/31/2014, with ≥ 2 years of claims data preceding their first RLS diagnosis ("preindex period"). Excluded were those with psychiatric diagnoses (International Classification of Diseases, Ninth Revision ICD-9 290-319) or DA use during the preindex period, and those with possible secondary RLS. Patients who initiated (DA+) versus did not initiate (DA-) DAs were matched 1:1 on age at index RLS diagnosis, sex, geographic region, and employment status, and preindex period comorbid illness burden and number of non-DA drug fills. Using a validated ICD-9-based severity-of-illness psychiatric disorder classification system, we compared likelihoods of new-onset P-AEs between matched pairs during parallel follow-up periods.
Identified were 889 matched pairs. Compared with their DA- counterparts, DA+ patients were nearly two times more likely to experience development of any P-AE (odds ratio OR 1.71, 95% confidence interval CI 1.31-2.24, P < .0001); and similarly more likely to experience the development of a severe (OR 1.68, 95% CI 1.03-2.86, P = .04), moderately severe (OR 1.63, 95% CI 1.17-2.29, P = .004), or mild (OR 1.72, 95% CI 1.12-2.65, P = .01) P-AE.
Compared to DA- matched control patients, patients in whom RLS was newly diagnosed and who initiated de novo DAs demonstrated significantly increased risk for subsequent development of P-AEs of any severity.
To overcome the coronavirus disease 2019 (COVID-19) pandemic, large-scale vaccination is proceeding worldwide. As of December 23, 2021, 10 novel vaccines against COVID-19 had been validated for use ...by the World Health Organization (WHO), including BNT162b2 (Pfizer/BioNTech), mRNA-1273 (Moderna), AZD1222 (AstraZeneca), and Ad26.COV2.S (Janssen). These novel vaccines against COVID-19 showed acceptable safety profiles in randomized clinical trials. Most adverse events following immunization (AEFIs) associated with these novel vaccines ranged from mild to moderate and improved within a few days after administration. However, serious adverse events associated with vaccines that were not observed in the clinical trials were reported in real-world data. Adverse events of special interest include not only anaphylaxis or neurologic disorders (such as Guillain-Barré syndrome, transverse myelitis, or seizure) but also myocarditis or pericarditis associated with the messenger RNA (mRNA) vaccines and thrombosis with thrombocytopenia syndrome associated with the adenovirus-vector vaccines. Although several fatal cases of serious AEFIs that may have been related to vaccination have been reported, it is recommended to continue vaccination because the benefits of vaccines’ preventive effects against COVID-19 outweigh the risks of rare serious adverse events. Long-term monitoring of various AEFIs and sharing of clinical experiences are necessary for safe and efficient large-scale vaccination.
Abstract
Background
Trends in prescribing for nursing home (NH) residents, which may have been influenced by the coronavirus disease 2019 (COVID-19) pandemic, have not been characterized.
Methods
...Long-term care pharmacy data from 1944 US NHs were used to evaluate trends in prescribing of antibiotics and drugs that were investigated for COVID-19 treatment, including hydroxychloroquine, famotidine, and dexamethasone. To account for seasonal variability in antibiotic prescribing and decreased NH occupancy during the pandemic, monthly prevalence of residents with a prescription dispensed per 1000 residents serviced was calculated from January to October and compared as relative percent change from 2019 to 2020.
Results
In April 2020, prescribing was significantly higher in NHs for drugs investigated for COVID-19 treatment than 2019; including hydroxychloroquine (+563%, 95% confidence interval CI: 5.87, 7.48) and azithromycin (+150%, 95% CI: 2.37, 2.63). Ceftriaxone prescribing also increased (+43%, 95% CI: 1.34, 1.54). Prescribing of dexamethasone was 36% lower in April (95% CI: .55, .73) and 303% higher in July (95% CI: 3.66, 4.45). Although azithromycin and ceftriaxone prescribing increased, total antibiotic prescribing among residents was lower from May (−5%, 95% CI: .94, .97) through October (−4%, 95% CI: .94, .97) in 2020 compared to 2019.
Conclusions
During the pandemic, large numbers of residents were prescribed drugs investigated for COVID-19 treatment, and an increase in prescribing of antibiotics commonly used for respiratory infections was observed. Prescribing of these drugs may increase the risk of adverse events, without providing clear benefits. Surveillance of NH prescribing practices is critical to evaluate concordance with guideline-recommended therapy and improve resident safety.
During the coronavirus disease 2019 (COVID-19) pandemic, there was a higher prevalence of nursing home residents with a prescription dispensed for drugs that were investigated for COVID-19 treatment and antibiotics commonly used for respiratory infections than in the previous year.
Objectives
To summarize the evidence on the prevalence and preventability of drug‐related hospital readmissions.
Design
A systematic review was performed of studies that examined drug‐related ...hospital readmissions. PubMed, EMBASE, and the Cochrane Library were searched from inception through August 2016. Reference lists and a citation analysis on Web of Science and Scopus were also consulted. Two reviewers extracted study data with dual assessment of risk of bias. Prevalence and preventability of readmission due to drugs were calculated. Data were qualitatively summarized according to outcome.
Results
Nineteen studies met the eligibility criteria. Nine measured readmissions due to drug‐related problems, seven due to adverse drug reactions, two due to adverse drug events, and one due to drug‐drug interactions. Rates of readmissions due to drugs varied from 3% to 64% (median 21%, interquartile range (IQR) 14–23%). Readmissions were deemed preventable in 5% to 87% of cases (median 69%, IQR 19–84%). Evidence regarding the risk factors for drug‐related readmissions and drugs causing these readmissions was inconsistent.
Conclusion
Although studies show high variability in prevalence and preventability of drug‐related hospital readmissions, readmissions due to drugs seem to occur often, especially in older adults. Further research is needed to specify the causes of preventable readmissions and implement effective interventions to reduce medication‐related hospital admissions.