Increased availability of epidemiological data, novel digital data streams, and the rise of powerful machine learning approaches have generated a surge of research activity on real-time epidemic forecast systems. In this paper, we propose the use of a novel data source, namely retail market data to improve seasonal influenza forecasting. Specifically, we consider supermarket retail data as a proxy signal for influenza, through the identification of sentinel baskets, i.e., products bought together by a population of selected customers. We develop a nowcasting and forecasting framework that provides estimates for influenza incidence in Italy up to 4 weeks ahead. We make use of the Support Vector Regression (SVR) model to produce the predictions of seasonal flu incidence. Our predictions outperform both a baseline autoregressive model and a second baseline based on product purchases. The results show quantitatively the value of incorporating retail market data in forecasting models, acting as a proxy that can be used for the real-time analysis of epidemics.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8297944 | PMC |
| http://dx.doi.org/10.1371/journal.pcbi.1009087 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Comprehensive molecular epidemiology of influenza viruses in Brazil: insights from a nationwide analysis.
Virus Evol
November 2024
Center for Viral Surveillance and Serological Assessment (CeVIVAS), Instituto Butantan, Avenida Vital Brasil, 1500, Butantã, São Paulo, São Paulo 05503-900, Brazil.
Influenza A and B viruses represent significant global health threats, contributing substantially to morbidity and mortality rates. However, a comprehensive understanding of the molecular epidemiology of these viruses in Brazil, a continental-size country and a crucial hub for the entry, circulation, and dissemination of influenza viruses within South America, still needs to be improved. This study addresses this gap by consolidating data and samples across all Brazilian macroregions, as part of the Center for Viral Surveillance and Serological Assessment project, together with an extensive number of other Brazilian sequences provided by a public database during the epidemic seasons spanning 2021-23.
View Article and Find Full Text PDFHybrid neural network models for time series disease prediction confronted by spatiotemporal dependencies.
MethodsX
June 2025
Department of Statistics, Shahjalal University of Science and Technology, Sylhet, Bangladesh.
In infectious disease outbreak modeling, there remains a gap in addressing spatiotemporal challenges present in established models. This study addresses this gap by evaluating four established hybrid neural network models for predicting influenza outbreaks. These models were analyzed by employing time series data from eight different countries to challenge the models with imposed spatial difficulties, in a month-on-month structure.
View Article and Find Full Text PDFBurden of RSV infections among young children in primary care: a prospective cohort study in five European countries (2021-23).
Lancet Respir Med
January 2025
Netherlands Institute for Health Services Research, Utrecht, Netherlands. Electronic address:
Background: The majority of respiratory syncytial virus (RSV) infections in young children are managed in primary care, however, the disease burden in this setting remains poorly defined.
Methods: We did a prospective cohort study in primary care settings in Belgium, Italy, Spain, the Netherlands, and the UK during the RSV seasons of 2020-21 (UK only; from Jan 1, 2021), 2021-22, and 2022-23. Children aged younger than 5 years presenting to their general practitioner or primary care paediatrician with symptoms of an acute respiratory tract infection were eligible for RSV testing.
Safety and immunogenicity of ascending doses of influenza A(H7N9) inactivated vaccine with or without MF59®.
Vaccine
January 2025
Division of Microbiology and Infectious Diseases, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Bethesda, MD, USA.
Introduction: While it remains impossible to predict the timing of the next influenza pandemic, novel avian influenza A viruses continue to be considered a significant threat.
Methods: A Phase II study was conducted in healthy adults aged 18-64 years to assess the safety and immunogenicity of two intramuscular doses of pre-pandemic 2017 influenza A(H7N9) inactivated vaccine administered 21 days apart. Participants were randomized (n = 105 in each of Arms 1-3) to receive 3.
Immunogenicity in mice and non-human primates of an Advax-CpG55.2-adjuvanted recombinant hemagglutinin seasonal quadrivalent influenza vaccine.
Vaccine
January 2025
Vaxine Pty Ltd, Warradale, Adelaide, SA 5046, Australia; Australian Respiratory and Sleep Medicine Institute Ltd, Adelaide, SA 5042, Australia. Electronic address:
Article Synopsis
- There's an urgent need to boost the effectiveness of seasonal influenza vaccines, with recombinant hemagglutinin showing potential benefits over traditional methods.
- In a study, two adjuvants (Advax-CpG55.2 and alum-CpG55.2) were tested to see if they could improve the immune response of a quadrivalent influenza vaccine (QIV) in mice.
- Results showed that the adjuvanted vaccines led to much higher levels of protective antibodies and significantly reduced illness in mice infected with the H1N1 strain, suggesting that this approach could be a better alternative for seasonal flu vaccinations.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!