| 1. |
- Dong, Guojun, et al.
(författare)
-
Optimizing Signal Management in a Vaccine Adverse Event Reporting System : A Proof-of-Concept with COVID-19 Vaccines Using Signs, Symptoms, and Natural Language Processing
- 2024
-
Ingår i: Drug Safety. - : Adis. - 0114-5916 .- 1179-1942. ; 47:2, s. 173-
-
Tidskriftsartikel (refereegranskat)abstract
- Introduction: The Vaccine Adverse Event Reporting System (VAERS) has already been challenged by an extreme increase in the number of individual case safety reports (ICSRs) after the market introduction of coronavirus disease 2019 (COVID-19) vaccines. Evidence from scientific literature suggests that when there is an extreme increase in the number of ICSRs recorded in spontaneous reporting databases (such as the VAERS), an accompanying increase in the number of disproportionality signals (sometimes referred to as ‘statistical alerts’) generated is expected. Objectives: The objective of this study was to develop a natural language processing (NLP)-based approach to optimize signal management by excluding disproportionality signals related to listed adverse events following immunization (AEFIs). COVID-19 vaccines were used as a proof-of-concept. Methods: The VAERS was used as a data source, and the Finding Associated Concepts with Text Analysis (FACTA+) was used to extract signs and symptoms of listed AEFIs from MEDLINE for COVID-19 vaccines. Disproportionality analyses were conducted according to guidelines and recommendations provided by the US Centers for Disease Control and Prevention. By using signs and symptoms of listed AEFIs, we computed the proportion of disproportionality signals dismissed for COVID-19 vaccines using this approach. Nine NLP techniques, including Generative Pre-Trained Transformer 3.5 (GPT-3.5), were used to automatically retrieve Medical Dictionary for Regulatory Activities Preferred Terms (MedDRA PTs) from signs and symptoms extracted from FACTA+. Results: Overall, 17% of disproportionality signals for COVID-19 vaccines were dismissed as they reported signs and symptoms of listed AEFIs. Eight of nine NLP techniques used to automatically retrieve MedDRA PTs from signs and symptoms extracted from FACTA+ showed suboptimal performance. GPT-3.5 achieved an accuracy of 78% in correctly assigning MedDRA PTs. Conclusion: Our approach reduced the need for manual exclusion of disproportionality signals related to listed AEFIs and may lead to better optimization of time and resources in signal management. © 2023, The Author(s).
|
|
| 2. |
- Lorant, Camilla, et al.
(författare)
-
The risk factors associated with post-transplantation BKPyV nephropathy and BKPyV DNAemia : a prospective study in kidney transplant recipients
- 2024
-
Ingår i: BMC Infectious Diseases. - : BioMed Central (BMC). - 1471-2334. ; 24
-
Tidskriftsartikel (refereegranskat)abstract
- Background: BK polyomavirus (BKPyV) infection after kidney transplantation can lead to serious complications such as BKPyV-associated nephropathy (BKPyVAN) and graft loss. The aim of this study was to investigate the incidence of BKPyVAN after implementing a BKPyV screening program, to map the distribution of BKPyV genotypes and subtypes in the Uppsala-orebro region and to identify host and viral risk factors for clinically significant events.Methods This single-center prospective cohort study included kidney transplant patients aged >= 18 years at the Uppsala University Hospital in Sweden between 2016 and 2018. BKPyV DNA was analyzed in plasma and urine every 3 months until 18 months after transplantation. Also genotype and subtype were determined. A logistic regression model was used to analyze selected risk factors including recipient sex and age, AB0 incompatibility and rejection treatment prior to BKPyVAN or high-level BKPyV DNAemia.Results: In total, 205 patients were included. Of these, 151 (73.7%) followed the screening protocol with 6 plasma samples, while184 (89.8%) were sampled at least 5 times. Ten (4.9%) patients developed biopsy confirmed BKPyVAN and 33 (16.1%) patients met criteria for high-level BKPyV DNAemia. Male sex (OR 2.85, p = 0.025) and age (OR 1.03 per year, p = 0.020) were identified as significant risk factors for developing BKPyVAN or high-level BKPyV DNAemia. BKPyVAN was associated with increased viral load at 3 months post transplantation (82,000 vs. < 400 copies/mL; p = 0.0029) and with transient, high-level DNAemia (n = 7 (27%); p < 0.0001). The most common genotypes were subtype Ib2 (n = 50 (65.8%)) and IVc2 (n = 20 (26.3%)).Conclusions: Male sex and increasing age are related to an increased risk of BKPyVAN or high-level BKPyV DNAemia. BKPyVAN is associated with transient, high-level DNAemia but no differences related to viral genotype were detected.
|
|
| 3. |
- Rystedt, Einar, et al.
(författare)
-
Validation of a web-based self-administered test for cognitive assessment in a Swedish geriatric setting
- 2024
-
Ingår i: PLOS ONE. - : Public Library of Science (PLoS). - 1932-6203. ; 19:2
-
Tidskriftsartikel (refereegranskat)abstract
- Computerized cognitive tests have the potential to cost-effectively detect and monitor cognitive impairments and thereby facilitate treatment for these conditions. However, relatively few of these tests have been validated in a variety of populations. Brain on Track, a self-administered web-based test, has previously been shown to have a good ability to differentiate between healthy individuals and patients with cognitive impairment in Portuguese populations. The objective of this study was to validate the differential ability and evaluate the usability of Brain on Track in a Swedish memory clinic setting. Brain on Track was administered to 30 patients with mild cognitive impairment/mild dementia and 30 healthy controls, all scheduled to perform the test from home after one week and after three months. To evaluate the usability, the patient group was interviewed after completion of the testing phase. Patients scored lower than healthy controls at both the first (median score 42.4 vs 54.1, p<0.001) and the second test (median score 42.3 vs 55.0, p<0.001). The test-retest intra-class correlation was 0.87. A multiple logistic regression model accounting for effects of age, gender and education rendered an ability of Brain on Track to differentiate between the groups with an area under the receiver operation characteristics curve of 0.90 for the first and 0.88 for the second test. In the subjective evaluation, nine patients left positive comments, nine were negative whereas five left mixed comments regarding the test experience. Sixty percent of patients had received help from relatives to log on to the platform. In conclusion, Brain on Track performed well in differentiating healthy controls from patients with cognitive impairment and showed a high test-retest reliability, on par with results from previous studies. However, the substantial proportion of patients needing help to log in could to some extent limit an independent use of the platform.
|
|
| 4. |
- Verweij, Stefan, et al.
(författare)
-
A Natural Language Processing Approach towards Harmonized Communication of Uncertainties Identified during the European Medicine Authorization Process
- 2024
-
Ingår i: Clinical Pharmacology and Therapeutics. - : John Wiley & Sons. - 0009-9236 .- 1532-6535. ; 115:4, s. 871-880
-
Tidskriftsartikel (refereegranskat)abstract
- Within the European Union, the European Medicines Agency's (EMA's) European Public Assessment Report (EPAR) is an important source of information for healthcare professionals and patients that allows them to understand important risks and uncertainties associated with the use of a medicine. However, the EPAR sections describing such important uncertainties can differ substantially in wording, length, and detail, thereby potentially limiting understanding. In this study, we therefore present a natural language processing approach to cluster sentences extracted from the sections on uncertainties in EPARs of centrally authorized medicines, as a steppingstone to harmonization of text describing uncertainties. We used a BERT language model together with dimensionality reduction (Uniform Manifold Approximation and Projection (UMAP)) and clustering (Density-Based Spatial Clustering of Applications with Noise (DBSCAN)) to identify semantic similarities between sentences. Clusters were labeled according to an overarching topic by reviewing the semantically similar sentences. Each cluster was also characterized according to medicine-related characteristics, such as efficacy or side effects. In total, 1,648 medicines were included in this study. For 573 of these medicines (authorized July 27, 2010 to December 31, 2022), we identified an EPAR that described a complete regulatory dossier and contained sections on uncertainties. Of these, 553 EPARs could be attributed to unique active substance-indication combinations. In these 553 EPARs, we identified 13,105 sentences in sections on uncertainties, leading to 26 clusters of which 2 were labeled as noise. The clusters and associated topics provided in this article can be used by regulators and medicine developers as a steppingstone toward a unified way of communicating uncertainties identified during the EMA process to the broader public.
|
|
