Sources, diffusion and prediction in COVID-19 pandemic: lessons learned to face next health emergency

Coccia, Mario

doi:10.3934/publichealth.2023012

Cited by 65 publications

(59 citation statements)

References 110 publications

(118 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These limitations highlight the necessity for more sophisticated modeling techniques in complex forecasting scenarios, a point also emphasized by Coccia (2023) [28]. In contrast, our method demonstrates greater flexibility and applicability across different mutation types.…”

Section: Mean Absolute Error Mean Squared Errormentioning

confidence: 84%

Predicting the Trend of SARS-CoV-2 Mutation Frequencies Using Historical Data

Zhou,

Hu,

Pan

et al. 2023

Preprint

View full text Add to dashboard Cite

As the SARS-CoV-2 virus rapidly evolves, predicting the trajectory of viral variations has become a critical yet complex task. A deep understanding of future mutation patterns, in particular the mutations that will prevail in the near future, is vital in steering diagnostics, therapeutics, and vaccine strategies in the coming months. In this study, we developed a model to forecast future SARS-CoV-2 mutation surges in real-time, using historical mutation frequency data from the USA. To improve upon the accuracy of traditional time-series models, we transformed the prediction problem into a supervised learning framework using a sliding window approach. This involved breaking the time series of mutation frequencies into very short segments. Considering the time-dependent nature of the data, we focused on modeling the first-order derivative of the mutation frequency. We predicted the final derivative in each segment based on the preceding derivatives, employing various machine learning methods, including random forest, XGBoost, support vector machine, and neural network models, in this supervised learning setting. Empowered by the novel transformation strategy and the high capacity of machine learning models, we witnessed low prediction error that is confined within 0.1% and 1% when making predictions for future 30 and 80 days respectively. In addition, the method also led to a notable increase in prediction accuracy compared to traditional time-series models, as evidenced by lower MAE, and MSE for predictions made within different time horizons. To further assess the method's effectiveness and robustness in predicting mutation patterns for unforeseen mutations, we categorized all mutations into three major patterns. The model demonstrated its robustness by accurately predicting unseen mutation patterns when training on data from two pattern categories while testing on the third pattern category, showcasing its potential in forecasting a variety of mutation trajectories. To enhance accessibility and utility, we built our methodology into an R-shiny app (https://swdatpredicts.shinyapps.io/rshiny_predict/), a tool with potential applicability in studying other infectious diseases, thus extending its relevance beyond the current pandemic.

show abstract

Section: Mean Absolute Error Mean Squared Errormentioning

confidence: 84%

Predicting the Trend of SARS-CoV-2 Mutation Frequencies Using Historical Data

Zhou,

Hu,

Pan

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…49 Addressing these challenges and navigating future health crises demand a multifaceted approach that encompasses vaccine delivery, supply chain optimization, vaccine development, tailored guidelines, behavioral modifications, strategic lockdowns, improving vaccination acceptance and targeted vaccination campaigns, all underpinned by strong governance, adequate public investments, and supportive sociocultural factors. 30,[51][52][53][54][55] With regard to crisis management, adopting strategies and new technology that involve minimal strict containment restrictions are more efficient. 53 For instance, a…”

Section: Resultsmentioning

confidence: 99%

Vaccination and its impact on healthcare utilization in two groups of vaccinated and unvaccinated patients with COVID‐19: A cross‐sectional study in Iran between 2021 and 2022

Kharazmi,

Bayati,

Majidpour Azad Shirazi

2024

Health Science Reports

View full text Add to dashboard Cite

Background and AimsOne of the main responsibilities of health systems impacted by the global Coronavirus disease 2019 (COVID‐19) pandemic, where the first case was discovered in Wuhan, China, in December 2019, is the provision of medical services. The current study looked into the impact of vaccination on the utilization of services provided to COVID‐19 patients.MethodsThis study was conducted in Iran between 2021 and 2022, utilizing a cross‐sectional research design. The research team collected data on the utilization of provided services and the number of COVID‐19 vaccines administered to 1000 patients in Iran through a random sampling approach. The data were analyzed with statistical methods, including the mean difference test, and multiple linear regression.ResultsRegression estimates show that after controlling for confounding variables like age, type of admission, and comorbidities, vaccination reduces the utilization of healthcare services in the general majority of services. The study's results reveal a fall in COVID‐19 patients' utilization of services, specifically in patients administered two or three doses of the vaccine. However, the reduction is not statistically significant. Regression models are in contrast to univariate analysis findings that vaccination increases the mean utilization of healthcare services for COVID‐19 patients in general. Comorbidities are a crucial factor in determining the utilization of diagnostic and treatment services for COVID‐19 patients.ConclusionFull COVID‐19 vaccination and other implementations, including investing in public health, cooperating globally, and vaccinating high‐risk groups for future pandemics, are essential as a critical response to this pandemic as they reduce healthcare service utilization to alleviate the burden on healthcare systems and allocate resources more efficiently.

show abstract

“…The ever-looming threat of the emergence of a new viral agent or the evolution of a new variant of SARS-CoV-2 that can evade new vaccines and antivirals, is very real [ 66 ]. These facts suggest that SARS-CoV-2 and similar respiratory viruses will continue to play a major role in society for the foreseeable future [ 67 ].…”

Section: Resultsmentioning

confidence: 99%

“…In fact, large numbers of mechanical ventilators in healthcare sector can support an effective health policy that minimizes negative effects of pandemic disease in society in particular when alternative treatments are missing and drug discovery process to treat unknown viral agents needs years to generate effective innovations. Hence, these findings bring us to suggest that an appropriate strategy of crisis management should be technology-oriented and focused on high levels of R&D investments in healthcare sector, in skilled human resources and in a pervasive diffusion of high-tech mechanical ventilators that improve the preparedness in countries to cope with unforeseen pandemic crisis (cf., [ 67 ].…”

Section: Resultsmentioning

confidence: 99%

Sources, diffusion and prediction in COVID-19 pandemic: lessons learned to face next health emergency

Cited by 65 publications

References 110 publications

Predicting the Trend of SARS-CoV-2 Mutation Frequencies Using Historical Data

Predicting the Trend of SARS-CoV-2 Mutation Frequencies Using Historical Data

Vaccination and its impact on healthcare utilization in two groups of vaccinated and unvaccinated patients with COVID‐19: A cross‐sectional study in Iran between 2021 and 2022

High potential of technology to face new respiratory viruses: mechanical ventilation devices for effective healthcare to next pandemic emergencies

Contact Info

Product

Resources

About