ABSTRACT
Introduction: The Istituto Superiore di Sanita and the Agenzia Italiana del Farmaco coordinate the project TheShinISS-Vax, Flu, a post-marketing "active" surveillance of influenza vaccines. We report the results of the investigation using the Self- Controlled Case Series (SCCS) design on influenza vaccine and Guillain-Barre syndrome in vaccinated population aged over than 6 months, during the influenza vaccine campaign 2020-2021 in Italy. Materials and methods: A SCCS multi-regional study was carried out using linked data from Regional Health Care Registries of Valle d'Aosta, Friuli Venezia Giulia, Emilia-Romagna, Toscana, Lazio, Campania, and Puglia. Relative incidence of Guillain-Barre syndrome was estimated, comparing the exposure risk periods (0-41 days from the vaccination day, subdivided in six intervals) with the unexposed period.
ABSTRACT
Objectives: The study aimed to design and develop a monitoring system to assess the possible implications of the COVID-19 infection and the measures taken to limit its spreading on adherence to chronic therapies. Methods: Within the HEALTH-DB project and in collaboration with a pool of Local Healthcare Entities, a monitoring system called "fail-to-refill" was designed to evaluate the lack of adherence to chronic therapies in Italian clinical practice settings. Based on the date and dosage coverage of last prescription, all patients that should have refilled in the last month a prescription for chronic therapies are identified, and it is verified if they had the refill. The analysis was centred on two classes of chronic treatments, belonging to different distribution systems: lipid-lowering agents (distributed in community pharmacy) and biological therapies for chronic autoimmune conditions (dispensed by National Health System hospitals for outpatients use, ie direct distribution). The monthly analysis covered the no-COVID-19 period (01/2017-02/2020) and the COVID-19 period (03/2020-12/2020). Results: During the COVID-19 period, in May 2020, an increase (42%) of the fail-to-refill rate for lipid-lowering agents distributed in community pharmacies was observed, compared to the rate during the no-COVID-19 period (34% -35% during 2017-2019), while negligible changes were observed in the following months. Regarding the direct distribution, the fail-to-refill rate of biologics was higher during the COVID-19 period, 34% (May), 35% (June), and 37% (July) versus 26-30% (May 2017-2019), 28-29% (June 2017-2021), and 24-28% (July 2017-2019) of the no-COVID-19 period. Conclusions: During the COVID-19 pandemic, an increasing trend of failed refill to chronic therapies has been observed, especially among biologics, probably due to their dispensing system and the difficulty of accessing hospitals. The "fail-to-refill" monitoring system could support the Health Authorities to identify patients who do not correctly refill their prescriptions, thus optimizing the medication adherence and reducing negative clinical outcomes related to it.
ABSTRACT
Objectives: To estimate the prognostic factors underlying severity of Sars-Cov-2 infection using a machine learning approach. Methods: The analysis is based on administrative databases of Italian Entities. Patients who were hospitalized with COVID-19 diagnosis (ICD-9 078.89) after 1st January 2020 were included into the dataset together with 13 relevant features representing age, sex and clinical history of each patient. Each record was labelled as 0 (hospitalized patients) or 1 (patients in intensive care or deceased). KerasTuner was used to define the architecture of the Neural Network achieving good accuracy score. To identify prognostic factors underlying severity of Sars Cov-2 infection, feature’s importance was evaluated starting from a Random Forest Classifier. Results: The preliminary dataset built contains 10.448 records from 9.346 hospitalized patients. The selected neural network is made of 13 input nodes, each one representing a feature, 1024 nodes in the hidden layer, processing information that comes from the input layer, and 2 nodes in the output layer, each one representing a label to define patient’s condition. The neural network obtained was able to achieve 64% of accuracy on the testing set. The condition of approximately 2 out of 3 patients was correctly predicted just by analysing their features. The feature’s importance computed from the Random Forest Classifier indicated that patient’s age is the primary prognostic factor underlying severity of Sars Cov-2 infection. The combination of the other features slightly improved model’s performance. Conclusions: The preliminary analysis shows that age is a prognostic factor of fundamental importance in defining the severity of Sars Cov-2 infection. The model obtained could be used to predict disease progression in patients most at risk by analysing their information in the databases. The model will be further improved through a process of feature selection to increase its accuracy and to allow the identification of other prognostic factors.