ABSTRACT
Corona Virus Disease 2019 (COVID-19) and influenza are both caused by viruses, seriously affect human health, and are highly infectious. However, because the clinical manifestations of these two groups of diseases have almost identical symptoms, separate Polymerase Chain Reaction (PCR) tests must be used for patients in each disease group. This study proposes an automatic data-processing model based on artificial intelligence and gradient boosting to identifying COVID-19 and influenza. The model can learn directly from raw data without the need for human input to delete empty data. Methodology and techniques operate in two stages: first, it evaluates and processes data to reduce the dataset's complexity using the light gradient boosting machine (LightGBM);then, in the second stage, it builds a classification model for each disease group based on the extreme gradient boosting (XGBoost) method. The research tools showed that combining two gradient-boosting models both LightGBM and XGBoost to generate automatic COVID-19 and influenza classifiers from clinical data produced strong results and a superior performance versus one model alone, with an overall accuracy of over 99.96%. In the future, the developed model will enable patients to be diagnosed simply and accurately and thereby reduce countries' testing costs for COVID-19 and similar pandemics that may arise. © 2023 The Author(s). This open access article is distributed under a Creative Commons Attribution (CC-BY) 4.0 license.
ABSTRACT
Introduction: Undertaking effective drug safety monitoring can be particularly challenging in low-resource settings due to a lack of infrastructure, weak regulatory systems and poor access to training and education [1]. Given the continued impact the COVID-19 pandemic is having upon health systems globally, it is essential to ensure that pharmacovigilance systems in these vulnerable settings have the capacity to address both the exacerbated pre-existing and novel challenges that they now face [2]. This project seeks to harness the membership of an online pharmacovigilance platform, globalpharmacovigilance. org (GPV) to work together in a 'community of practice' (CoP) on specific challenges facing pharmacovigilance during the pandemic [3, 4]. Objective(s): To gather consensus on pharmacovigilance priorities in low-resource settings during the COVID-19 pandemic and provide resources to address them using a CoP model. Method(s): This project has built on a consensus-gathering methodology developed by The Global Health Network that has been implemented successfully during the pandemic to address wider COVID-19 research priorities. An online survey of GPV members was used to identify highly-ranked areas for pharmacovigilance improvement in low-resource settings during the pandemic. A virtual workshop was then hosted to invite further discussion on the survey results and reach consensus on the highest priorities. Members of the CoP were next invited to form virtual working groups, each focussing on one of the top 3 priorities identified. These groups are being supported by GPV to work together and facilitate the development (or provision, if pre-existing) of pharmacovigilance resources to address the priorities identified. Result(s): Of the 43 pharmacovigilance 'themes' that were presented to the CoP membership in the initial survey, 3 topics were identified as the highest priorities at that point in the COVID-19 pandemic, where support, training and guidance are needed;'The safety of COVID-19 vaccination in pregnancy', 'The safety of COVID-19 vaccination in children/adolescents' and 'Analysis of COVID-19 vaccine safety data'. As of May 2022, the number of GPV members interested in involvement in working groups addressing these themes are 207, 206, and 284 respectively. Initial group meetings took place in April 2022 and discussions are ongoing as to how to take group activities forward and address the priorities identified. Conclusion(s): A CoP model represents an effective method of consensus gathering amongst pharmacovigilance stakeholders at a global level, and allows rapid identification of healthcare priorities during public health emergencies. It is anticipated that working groups outputs will include the provision of resources designed to address the priorities identified.
ABSTRACT
Introduction: Undertaking effective drug safety monitoring can be particularly challenging in low-resource settings due to a lack of infrastructure, weak regulatory systems and poor access to training and education [1]. Given the continued impact the COVID-19 pandemic is having upon health systems globally, it is essential to ensure that pharmacovigilance systems in these vulnerable settings have the capacity to address both the exacerbated pre-existing and novel challenges that they now face [2]. This project seeks to harness the membership of an online pharmacovigilance platform, globalpharmacovigilance.org (GPV) to work together in a 'community of practice' (CoP) on specific challenges facing pharmacovigilance during the pandemic [3, 4]. Objective: To gather consensus on pharmacovigilance priorities in low-resource settings during the COVID-19 pandemic and provide resources to address them using a CoP model. Methods: This project has built on a consensus-gathering methodology developed by The Global Health Network that has been implemented successfully during the pandemic to address wider COVID-19 research priorities. An online survey of GPV members was used to identify highly-ranked areas for pharmacovigilance improvement in low-resource settings during the pandemic. A virtual workshop was then hosted to invite further discussion on the survey results and reach consensus on the highest priorities. Members of the CoP were next invited to form virtual working groups, each focussing on one of the top 3 priorities identified. These groups are being supported by GPV to work together and facilitate the development (or provision, if pre-existing) of pharmacovigilance resources to address the priorities identified. Results: Of the 43 pharmacovigilance 'themes' that were presented to the CoP membership in the initial survey, 3 topics were identified as the highest priorities at that point in the COVID-19 pandemic, where support, training and guidance are needed;'The safety of COVID-19 vaccination in pregnancy', 'The safety of COVID-19 vaccination in children/adolescents' and 'Analysis of COVID-19 vaccine safety data'. As of May 2022, the number of GPV members interested in involvement in working groups addressing these themes are 207, 206, and 284 respectively. Initial group meetings took place in April 2022 and discussions are ongoing as to how to take group activities forward and address the priorities identified. Conclusion: A CoP model represents an effective method of consensus gathering amongst pharmacovigilance stakeholders at a global level, and allows rapid identification of healthcare priorities during public health emergencies. It is anticipated that working groups outputs will include the provision of resources designed to address the priorities identified.
ABSTRACT
Background: Patients with haemato-oncological malignancies are one of the high-risk groups for a severe course in case of Covid-19 infections. Furthermore, vaccination results in signifcantly lower response rates in haematological malignancies and lower antibody levels in patients with solid cancer. We investigated efcacy and safety of a heterologous booster vaccination with Ad26.COV2.S DNA vector vaccine in haemato-oncological patients without antibody response after doubledose BNT162b2 mRNA Covid-19 vaccine. Methods: A total of 32 haemato-oncological non-respond-ers to double-dose BNT162b2 received a heterologous booster vaccination with Ad26.COV2.S. Blood samples were assessed directly before the vaccination (T0) and 4 weeks after (T1). Safety assessment was performed using a standardised questionnaire. Results: The overall response rate was 31 %, with a mean (SD) antibody titre of 693.79 (1096.99) BAU/ml. Patients with chronic lymphocytic leukaemia or lymphoma showed a sig-nifcantly lower response rate (P = 0.048). Adverse events were reported in 29.6 % of patients, whereby 7.1 % were graded as severe, which includes grade III and IV events following CTCAE. Conclusions: The heterologous booster vaccination with Ad26.COV2.S led to a serological response in 9 out of 29 patients without response after double-dose BNT162b2. Furthermore, the vaccination was safe in our cohort, leading to mainly mild local and systemic reactions. Overall, this vaccination regimen should be further evaluated to increase the response rate in the highly vulnerable population of haemato-oncological patients.
ABSTRACT
Background/Introduction: Undertaking effective drug safety monitoring is particularly challenging in low-resource settings due to a lack of infrastructure, weak regulatory systems and poor access to training and education [1]. Given the impact that the COVID-19 pandemic is having upon health systems globally, it is essential to ensure that pharmacovigilance systems in these vulnerable settings have the capacity to address both the exacerbated pre-existing and novel challenges that they now face [2]. This project will harness the membership of an online pharmacovigilance platform, globalpharmacovigilance.org (GPV) to create a community of practice (CoP) to address the challenges facing pharmacovigilance during the pandemic[3, 4]. This community can use proven approaches to reach strong and highly democratic consensus on pharmacovigilance priorities, and then provide relevant resources (whether existing or new training, guidance, tools, mentoring) to address the gaps. The online platform will be used by the CoP to share best practices, engage more widely and disseminate outputs and guidance. Objective/Aim: To identify priorities for pharmacovigilance in low-resource settings during the COVID-19 pandemic and provide resources to address these within a CoP model. Methods: This project will build on a consensus-gathering methodology developed by The Global Health Network that has been implemented successfully during the pandemic to address wider COVID-19 research priorities. An online survey, distributed via social media, mailing lists and directly on GPV, will be used to identify priority areas for pharmacovigilance improvement in low-resource settings. Participants will then be invited to attend an online open workshop, in which the survey results will be presented and consensus gathered on an area for focus. Attendees will be invited to form a working group(s). Membership will be self-selective to encourage involvement from all experience levels. This working group(s) will then be supported to work together to facilitate the development of (or provision of, if already available elsewhere) pharmacovigilance resources to address the priorities identified. Results: Results will be presented in the form of a knowledge gap analysis for pharmacovigilance in low-resource settings during the COVID-19 pandemic, consisting of qualitative/quantitative results from the survey and qualitative data from the workshop. Qualitative/ quantitative data on the uptake and use of the GPV platform will also be presented. Conclusion: It is anticipated that findings will help to understand whether and how a CoP may be built and engaged with using an online platform during a pandemic, and then contribute to a priority area for improvement or development within pharmacovigilance at that time.