Background Machine learning can operationalize the rich and complex data in electronic patient records for exploratory pharmacovigilance endeavours. Objective The objective of this review is to identify applications of machine learning and big patient data in exploratory pharmacovigilance. Methods We searched PubMed and Embase and included original articles with an exploratory pharmacovigilance purpose, focusing on medicinal interventions and reporting the use of machine learning in electronic patient records with ≥1000 patients collected after market entry. Findings Of 2557 studies screened, seven were included. Those covered six countries and were published between 2015 and 2021. The most prominent machine learning methods were random forests, logistic regressions, and support vector machines. Two studies used artificial neural networks or naive Bayes classifiers. One study used formal concept analysis for association mining, and another used temporal difference learning. Five studies compared several methods against each other. The numbers of patients in most data sets were in the order of thousands; two studies used what can more reasonably be considered big data with >1 000 000 patients records. Conclusion Despite years of great aspirations for combining machine learning and clinical data for exploratory pharmacovigilance, only few studies still seem to deliver somewhat on these expectations.
Coronavirus-disease-2019 (COVID-19) mRNA vaccination effectively reduces mortality and morbidity in cirrhotic patients, but the immunogenicity and safety of vaccination have been partially characterized. The study aimed to evaluate humoral response, predictive factors, and safety of mRNA-COVID-19 vaccination in cirrhotic patients compared to healthy subjects. A prospective, single-center, observational study enrolled consecutive cirrhotic patients who underwent mRNA-COVID-19 vaccination from April to May 2021. Anti-spike-protein (anti-S) and nucleocapsid-protein (anti-N) antibodies were evaluated before the first (T0) and the second (T1) doses and 15 days after completing the vaccination. An age and sex-matched healthy reference group was included. The incidence of adverse events (AEs) was assessed. In total, 162 cirrhotic patients were enrolled, 13 were excluded due to previous SARS-CoV-2 infection; therefore, 149 patients and 149 Health Care Workers (HCWs) were included in the analysis. The seroconversion rate was similar in cirrhotic patients and HCWs at T1 (92.5% vs. 95.3%, p = 0.44) and T2 (100% in both groups). At T2, anti-S-titres were significantly higher in cirrhotic patients compared to HCWs (2776.6 vs. 1756 BAU/mL, p < 0.001]. Male sex (β = −0.32 [−0.64, −0.04], p = 0.027) and past-HCV-infection (β = −0.31 [−0.59, −0.04], p = 0.029) were independent predictors of lower anti-S-titres on multiple-gamma-regression-analysis. No severe AEs occurred. The COVID-19-mRNA vaccination induces a high immunization rate and anti-S-titres in cirrhotic patients. Male sex and past-HCV infection are associated with lower anti-S-titres. The COVID-19-mRNA vaccination is safe.
ObjectivesWe describe the preliminary results of bulevirtide compassionate use in patients with hepatitis B and delta virus (HBV/HDV)‐related cirrhosis and clinically significant portal hypertension, including those living with HIV.MethodsWe conducted a prospective observational study of consecutive patients. Clinical evaluation, liver function tests, bile acid levels, HDV‐RNA, HBV‐DNA, hepatitis B surface antigen, and liver and spleen stiffness were assessed at baseline and after treatment months 1, 2, 3, 4, 6, 9, and 12. HIV‐RNA and CD4+/CD8+ count were assessed in people living with HIV. The first drug injection was administered under nurse supervision, and counselling was provided and adherence reviewed at each visit.ResultsIn total, 13 patients (61.5% migrants) were enrolled. The median treatment duration was 11 months. At month 6, mean alanine aminotransferase (ALT) levels fell by 64.5% and mean liver and spleen stiffness decreased by 8.6 and 0.9 kPa, respectively. The mean baseline HDV‐RNA was 3.34 log IU/mL and 5.10 log IU/mL in people without and with HIV (n = 5) (p = 0.28), respectively. A similar mean decline was observed in both groups: −2.06 log IU/mL and −1.93 log IU/mL, respectively (p = 0.87). A combined response (undetectable HDV RNA or ≥ −2 log IU/mL decline vs. baseline, with ALT normalization) was achieved in 66% of subjects without and in 60% of patients with HIV. Patients with HIV showed persistently undetectable HIV‐RNA and a progressive increase in CD4+/CD8+ cells during treatment. No patient discontinued bulevirtide because of adverse effects.ConclusionsPreliminary results suggest that bulevirtide is feasible and well‐tolerated in populations with difficult‐to‐treat conditions, such as those with HIV/HBV/HDV co‐infection and migrants, when special attention is given to patient education. HDV‐RNA decline during treatment was similar in people living with and without HIV.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.