ABSTRACT
The current study considers the development of a 5-layer pipeline for identifying and classifying COVID-19-induced lung lesions. Such system is multilayer, built upon convolutional and fully connected neural networks and logistic self-organised forest built using the group method of data handling (GMDH) principles. This pipeline includes a mechanism for finding lesions regions in lungs computer tomography images and for calculating related lung damage volume. The layer for finding images with lesions reached a Matthews Correlation Coefficient of 0.98. The layer for lesions segmentation reached a Dice similarity coefficient of 0.74, while the layer for lesions classification reached Fl-scores of 1, 0.95, 0.93 respectively for the ground-glass, opacity, crazy-paving and consolidation lesion type. Results demonstrate the effectiveness of the implemented multi-layer system in solving tasks of lesions identification and classification while being composed into a single pipeline. © 2022 IEEE.
ABSTRACT
Introduction: COVID-19 pandemic has dramatically affected healthcare systems, as well as everyday life worldwide [1,2]. Pharmacovigilance has definitely had a central role in this context of emergency, for both new and old molecules being investigated as potential treatments for COVID-19, but above all for the monitoring of COVID-19 vaccines [3]. Objective(s): The aim of this study was to investigate how COVID-19 pandemic has changed the adverse drug reactions (ADRs) reporting at the University Hospital of Catania. Method(s): We performed a descriptive analysis of individual case safety reports (ICSRs) collected in the Italian National Pharmacovigilance Network by the University Hospital of Catania from January 2019 to December 2021. Data were compared in terms of number of reports per year, patient characteristics, treatments, severity of reactions, and type of reporter. Result(s): Overall, the number of ICSRs collected was 1,664, 463 in 2019, 590 in 2020 and 611 in 2021 (Figure 1). In the majority of cases, ADRs have involved female subjects in the 18-65 years age group (mean age 49 years). Most cases were classified as not serious (81%);nevertheless, reports of serious ADRs progressively raised from 13.2% in 2019 to 16.6% in 2020 and 25% in 2021. In 2019 and 2020 almost all ICSRs were spontaneously sent by physicians, while in 2021 a greater reporting by citizens (13.9%), pharmacists (11.1%) and other health care professionals (3.8%) has been observed. Adalimumab represented the most frequently reported suspected drug in 2019 and 2020, with the highest number of ICSRs concerning lack of therapeutic response (77% and 92.5%, respectively). In 2021 the number of ADRs caused by vaccines has dramatically risen, from zero in 2019-2020 to 251 in 2021, as a consequence of COVID-19 vaccination campaign (tozinameran 32.6%). Most of ICSRs concerned general and administration site conditions (68.8%), with fever being the most frequently reported ADR (29.1%). Tozinameran was also associated with the highest number of serious ADRs (n = 34) in 2021. Conclusion(s): This study showed that COVID-19 outbreak did not have a significant impact on ADRs reporting until the introduction of COVID-19 vaccines. It is noteworthy that treatments for COVID-19 were not listed among the suspected drugs, although the high number of patients treated in our institution during 2020 and 2021. It will be useful to investigate the possible underlying reasons (lack of ADR? difficulty in distinguishing ADR from the disease? lack of time in an emergency situation?) with healthcare professionals directly involved in the treatment of COVID-19.
ABSTRACT
Introduction: COVID-19 pandemic has dramatically affected healthcare systems, as well as everyday life worldwide [1,2]. Pharmacovigilance has definitely had a central role in this context of emergency, for both new and old molecules being investigated as potential treatments for COVID-19, but above all for the monitoring of COVID-19 vaccines [3]. Objective: The aim of this study was to investigate how COVID-19 pandemic has changed the adverse drug reactions (ADRs) reporting at the University Hospital of Catania. Methods: We performed a descriptive analysis of individual case safety reports (ICSRs) collected in the Italian National Pharmacovigilance Network by the University Hospital of Catania from January 2019 to December 2021. Data were compared in terms of number of reports per year, patient characteristics, treatments, severity of reactions, and type of reporter. Results: Overall, the number of ICSRs collected was 1,664, 463 in 2019, 590 in 2020 and 611 in 2021 (Figure 1). In the majority of cases, ADRs have involved female subjects in the 18-65 years age group (mean age 49 years). Most cases were classified as not serious (81%);nevertheless, reports of serious ADRs progressively raised from 13.2% in 2019 to 16.6% in 2020 and 25% in 2021. In 2019 and 2020 almost all ICSRs were spontaneously sent by physicians, while in 2021 a greater reporting by citizens (13.9%), pharmacists (11.1%) and other health care professionals (3.8%) has been observed. Adalimumab represented the most frequently reported suspected drug in 2019 and 2020, with the highest number of ICSRs concerning lack of therapeutic response (77% and 92.5%, respectively). In 2021 the number of ADRs caused by vaccines has dramatically risen, from zero in 2019-2020 to 251 in 2021, as a consequence of COVID-19 vaccination campaign (tozinameran 32.6%). Most of ICSRs concerned general and administration site conditions (68.8%), with fever being the most frequently reported ADR (29.1%). Tozinameran was also associated with the highest number of serious ADRs (n = 34) in 2021.