Predictive Modeling of Vaccination Uptake in U.S. Counties: A Machine Learning-based Approach (Preprint)

2021 ◽  
Author(s):  
Queena Cheong ◽  
Martin Au-yeung ◽  
Stephanie Quon ◽  
Katsy Concepcion ◽  
Jude Dzevela Kong
Keyword(s):  
Public Health ◽  
Machine Learning ◽  
Predictive Modelling ◽  
Sociodemographic Factors ◽  
Vaccine Uptake ◽  
Vaccination Rates ◽  
Vaccination Uptake ◽  
Sociodemographic Data ◽  
Public Health Officials ◽  
The U.S

BACKGROUND While the COVID-19 pandemic has left an unprecedented impact globally, countries such as the United States of America have reported the most significant incidence of COVID-19 cases worldwide. Within the U.S., various sociodemographic factors have played an essential role in the creation of regional disparities. Regional disparities have resulted in the unequal spread of disease between U.S. counties, underscoring the need for efficient and accurate predictive modelling strategies to inform public health officials and reduce the burden on healthcare systems. Furthermore, despite the widespread accessibility of COVID-19 vaccines across the U.S., vaccination rates have become stagnant, necessitating predictive modelling to identify important factors impacting vaccination uptake. OBJECTIVE To determine the association between sociodemographic factors and vaccine uptake across counties in the U.S. METHODS Sociodemographic data on fully vaccinated and unvaccinated individuals were sourced from several online databases, such as the U.S. Centre for Disease Control and U.S. Census Bureau COVID-19 Site. Machine learning analysis was performed using XGBoost and sociodemographic data. RESULTS Our model predicted COVID-19 vaccination uptake across U.S. countries with 59% accuracy. In addition, it identified location, education, ethnicity, and income as the most critical sociodemographic features in predicting vaccination uptake in U.S. counties. Lastly, the model produced a choropleth demonstrating areas of low and high vaccination rates, which can be used by healthcare authorities in future pandemics to visualize and prioritize areas of low vaccination and design targeted vaccination campaigns. CONCLUSIONS Our study reveals that sociodemographic characteristics are predictors of vaccine uptake rate across counties in the U.S. and if leveraged appropriately can assist policy makers and public health officials to understand vaccine uptake rates and craft policies to improve them.

scholarly journals Determinants of COVID-19 Vaccine Acceptance in the U.S.

2020 ◽  
Author(s):  
Amyn A. Malik ◽  
SarahAnn M. McFadden ◽  
Jad Elharake ◽  
Saad B. Omer
Keyword(s):  
Public Health ◽  
New York ◽  
Influenza Vaccine ◽  
Risk Perceptions ◽  
Adult Population ◽  
Vaccine Uptake ◽  
Sources Of Information ◽  
Vaccine Acceptance ◽  
Public Health Officials ◽  
The U.S

Background:The COVID-19 pandemic continues to adversely affect the U.S., which leads globally in total cases and deaths. As COVID-19 vaccines are under development, public health officials and policymakers need to create strategic vaccine-acceptance messaging to effectively control the pandemic and prevent thousands of additional deaths. Methods: Using an online platform, we surveyed the U.S. adult population in May 2020 to understand risk perceptions about the COVID-19 pandemic, acceptance of a COVID-19 vaccine, and trust in sources of information. These factors were compared across basic demographics. Findings: Of the 672 participants surveyed, 450 (67%) said they would accept a COVID-19 vaccine if it is recommended for them. Males (72%), older adults (≥55 years; 78%), Asians (81%), and college and/or graduate degree holders (75%) were more likely to accept the vaccine. When comparing reported influenza vaccine uptake to reported acceptance of the COVID-19 vaccine: 1) participants who did not complete high school had a very low influenza vaccine uptake (10%), while 60% of the same group said they would accept the COVID-19 vaccine; 2) unemployed participants reported lower influenza uptake and lower COVID-19 vaccine acceptance when compared to those employed or retired; and, 3) black Americans reported lower influenza vaccine uptake and lower COVID-19 vaccine acceptance than nearly all other racial groups. Lastly, we identified geographic differences with Department of Health and Human Services regions 2 (New York) and 5 (Chicago) reporting less than 50 percent COVID-19 vaccine acceptance. Interpretation: Although our study found a 67% acceptance of a COVID-19 vaccine, there were noticeable demographic and geographical disparities in vaccine acceptance. Before a COVID-19 vaccine is introduced to the U.S., public health officials and policymakers must prioritize effective COVID-19 vaccine-acceptance messaging for all Americans, especially those who are most vulnerable.

scholarly journals An economic and disease transmission model of human papillomavirus and oropharyngeal cancer in Texas

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Chengxue Zhong ◽  
Li Xu ◽  
Ho-Lan Peng ◽  
Samantha Tam ◽  
Li Xu ◽  
...  
Keyword(s):  
Public Health ◽  
Human Papillomavirus ◽  
Oropharyngeal Cancer ◽  
Hpv Vaccine ◽  
Health Benefits ◽  
Incidence Rates ◽  
Vaccine Uptake ◽  
Males And Females ◽  
Quality Adjusted Life ◽  
The U.S

AbstractIn 2017, 46,157 and 3,127 new oropharyngeal cancer (OPC) cases were reported in the U.S. and Texas, respectively. About 70% of OPC were attributed to human papillomavirus (HPV). However, only 51% of U.S. and 43.5% of Texas adolescents have completed the HPV vaccine series. Therefore, modeling the demographic dynamics and transmission of HPV and OPC progression is needed for accurate estimation of the economic and epidemiological impacts of HPV vaccine in a geographic area. An age-structured population dynamic model was developed for the U.S. state of Texas. With Texas-specific model parameters calibrated, this model described the dynamics of HPV-associated OPC in Texas. Parameters for the Year 2010 were used as the initial values, and the prediction for Year 2012 was compared with the real age-specific incidence rates in 23 age groups for model validation. The validated model was applied to predict 100-year age-adjusted incidence rates. The public health benefits of HPV vaccine uptake were evaluated by computer simulation. Compared with current vaccination program, increasing vaccine uptake rates by 50% would decrease the cumulative cases by 4403, within 100 years. The incremental cost-effectiveness ratio of this strategy was $94,518 per quality-adjusted life year (QALY) gained. Increasing the vaccine uptake rate by 50% can: (i) reduce the incidence rates of OPC among both males and females; (ii) improve the quality-adjusted life years for both males and females; (iii) be cost-effective and has the potential to provide tremendous public health benefits in Texas.

scholarly journals Influenza vaccine uptake among adults living with young children

2018 ◽  
Vol 4 (1) ◽  
pp. 41 ◽  
Author(s):  
Nirma Khatri Vadlamudi ◽  
Fawziah Marra
Keyword(s):  
Young Children ◽  
Influenza Vaccine ◽  
Influenza Vaccination ◽  
Perceived Health ◽  
Canadian Community Health Survey ◽  
Demographic Characteristics ◽  
Vaccine Uptake ◽  
Vaccination Programs ◽  
Vaccination Rates ◽  
Vaccination Uptake

Background: Many studies report vaccine uptake among young adults aged 18 to 49 years is low. In Canada, the National Advisory Committee on Immunization (NACI) recommends influenza vaccination for adults in contact with young children, however vaccination rates for this specific population are missing. An estimate is required to identify appropriate public health interventions. The objective of this study was to describe recent trends in influenza vaccination uptake among Canadian adults aged 18 to 49 years old living with or without young children.Methods: The Canadian Community Health Survey (2013-2014) dataset, available for public use was used after grouping individuals by influenza vaccination uptake within the past year in adults aged 18 to 49 years.  The relationship between living in a household with young children and influenza vaccination uptake was examined using a multivariable logistic regression model.Results: Among Canadian adults aged 18 to 49 years, the influenza vaccination uptake was 24.1% in adult household contacts with young children compared to 18.2% in those without young children (p<.0001). After adjusting for socio-demographic characteristics and self-perceived health, we determined that vaccine uptake was associated with living in a household with young children (adjusted OR: 1.30 [95%CI: 1.17-1.44]). While socio-demographic characteristics and self-perceived health greatly influenced influenza vaccination uptake, we also found marital status was a strong influencer of influenza vaccine uptake (adjusted OR:  1.31 [95%CI: 1.16-1.48]). Conclusion: Overall, influenza vaccination uptake among caregiving adults is low. Increased vaccine uptake was associated with living in a household with one or more young children. Targeted education and vaccination programs are required to improve uptake of the influenza vaccine in this age group.

scholarly journals Russian Twitter Accounts and the Partisan Polarization of Vaccine Discourse, 2015–2017

2020 ◽  
Vol 110 (5) ◽  
pp. 718-724 ◽  
Author(s):  
Dror Walter ◽  
Yotam Ophir ◽  
Kathleen Hall Jamieson
Keyword(s):  
Public Health ◽  
Machine Learning ◽  
Health Disparities ◽  
Network Analysis ◽  
Internet Research ◽  
Unsupervised Machine Learning ◽  
Health Implications ◽  
Vaccination Rates ◽  
Partisan Polarization ◽  
The Us

Objectives. To understand how Twitter accounts operated by the Russian Internet Research Agency (IRA) discussed vaccines to increase the credibility of their manufactured personas. Methods. We analyzed 2.82 million tweets published by 2689 IRA accounts between 2015 and 2017. Combining unsupervised machine learning and network analysis to identify “thematic personas” (i.e., accounts that consistently share the same topics), we analyzed the ways in which each discussed vaccines. Results. We found differences in volume and valence of vaccine-related tweets among 9 thematic personas. Pro-Trump personas were more likely to express antivaccine sentiment. Anti-Trump personas expressed support for vaccination. Others offered a balanced valence, talked about vaccines neutrally, or did not tweet about vaccines. Conclusions. IRA-operated accounts discussed vaccines in manners consistent with fabricated US identities. Public Health Implications. IRA accounts discussed vaccines online in ways that evoked political identities. This could exacerbate recently emerging partisan gaps relating to vaccine misinformation, as differently valenced messages were targeted at different segments of the US public. These sophisticated targeting efforts, if repeated and increased in reach, could reduce vaccination rates and magnify health disparities.

scholarly journals Influenza forecasting for the French regions by using EHR, web and climatic data sources with an ensemble approach ARGONet

2019 ◽  
Author(s):  
Canelle Poirier ◽  
Yulin Hswen ◽  
Guillaume Bouzillé ◽  
Marc Cuggia ◽  
Audrey Lavenu ◽  
...  
Keyword(s):  
Public Health ◽  
Machine Learning ◽  
Disease Activity ◽  
Real Time ◽  
Data Sources ◽  
Monitoring Systems ◽  
Surveillance Systems ◽  
Influenza Activity ◽  
Public Health Officials ◽  
The Right

AbstractEffective and timely disease surveillance systems have the potential to help public health officials design interventions to mitigate the effects of disease outbreaks. Currently, healthcare-based disease monitoring systems in France offer influenza activity information that lags real-time by 1 to 3 weeks. This temporal data gap introduces uncertainty that prevents public health officials from having a timely perspective on the population-level disease activity. Here, we present a machine-learning modeling approach that produces real-time estimates and short-term forecasts of influenza activity for the 12 continental regions of France by leveraging multiple disparate data sources that include, Google search activity, real-time and local weather information, flu-related Twitter micro-blogs, electronic health records data, and historical disease activity synchronicities across regions. Our results show that all data sources contribute to improving influenza surveillance and that machine-learning ensembles that combine all data sources lead to accurate and timely predictions.Author summaryThe role of public health is to protect the health of populations by providing the right intervention to the right population at the right time. In France and all around the world, Influenza is a major public health problem. Traditional surveillance systems produce estimates of influenza-like illness (ILI) incidence rates, but with one-to three-week delay. Accurate real-time monitoring systems of influenza outbreaks could be useful for public health decisions. By combining different data sources and different statistical models, we propose an accurate and timely forecasting platform to track the flu in France at a spatial resolution that, to our knowledge, has not been explored before.

scholarly journals Myths Surrounding Covid-19 Vaccine Candidates: A Guide to Fight Back

2021 ◽  
Author(s):  
John Zizzo
Keyword(s):  
Public Health ◽  
Herd Immunity ◽  
Vaccine Uptake ◽  
Protective Measure ◽  
Vaccine Hesitancy ◽  
Health Providers ◽  
Vaccine Candidates ◽  
The Public ◽  
News Organizations ◽  
Public Health Officials

The Covid-19 pandemic has propelled public health officials into the socio-political sphere due to the need for constantly updated information on behalf of the public. However, many individuals choose to acquire health information/guidance from indirect sources, including social media, news organizations, and general word of mouth. As a result, myths and false narratives about various essential health topics, including vaccine characteristics and protective measures, can circulate un-verified between millions of individuals with little recourse. These can further widen the “gap” between public knowledge and current research, resulting in lower vaccine uptake (vaccine hesitancy) and protective measure adherence. Such actions have profound implications as nations attempt to achieve herd immunity and end the pandemic once and for all. Thus, it is vital that public health officials, health providers, researchers, and the general public be able to differentiate common Covid-19 myths from facts and be prepared to approach such interactions via sound reasoning and research-based evidence. This chapter will serve as a guide to accomplish just that.

scholarly journals Mobility network reveals the impact of geographic vaccination heterogeneity on COVID-19

2021 ◽  
Author(s):  
Yuan Yuan ◽  
Eaman Jahani ◽  
Shengjia Zhao ◽  
Yong-Yeol Ahn ◽  
Alex Pentland
Keyword(s):  
Computational Models ◽  
Negative Impact ◽  
Vaccination Campaign ◽  
Vaccination Rate ◽  
Control Measures ◽  
Vaccine Uptake ◽  
Vaccination Rates ◽  
The Impact ◽  
Hub Effect ◽  
The U.S

ABSTRACTMassive vaccination is one of the most effective epidemic control measures. Because one’s vaccination decision is shaped by social processes (e.g., socioeconomic sorting and social contagion), the pattern of vaccine uptake tends to show strong social and geographical heterogeneity, such as urban-rural divide and clustering. Yet, little is known to what extent and how the vaccination heterogeneity affects the course of outbreaks. Here, leveraging the unprecedented availability of data and computational models produced during the COVID-19 pandemic, we investigate two network effects—the “hub effect” (hubs in the mobility network usually have higher vaccination rates) and the “homophily effect” (neighboring places tend to have similar vaccination rates). Applying Bayesian deep learning and fine-grained simulations for the U.S., we show that stronger homophily leads to more infections while a stronger hub effect results in fewer cases. Our simulation estimates that these effects have a combined net negative impact on the outcome, increasing the total cases by approximately 10% in the U.S. Inspired by these results, we propose a vaccination campaign strategy that targets a small number of regions to further improve the vaccination rate, which can reduce the number of cases by 20% by only vaccinating an additional 1% of the population according to our simulations. Our results suggest that we must examine the interplay between vaccination patterns and mobility networks beyond the overall vaccination rate, and that the government may need to shift policy focus from overall vaccination rates to geographical vaccination heterogeneity.

scholarly journals Determinants of COVID-19 vaccine hesitancy and vaccine uptake in a national cohort of U.S. adults

2021 ◽  
Author(s):  
Madhura S Rane ◽  
Shivani Kochhar ◽  
Emily Poehlein ◽  
William You ◽  
McKaylee Robertson ◽  
...  
Keyword(s):  
Public Health ◽  
Healthcare Workers ◽  
Vaccine Uptake ◽  
Vaccine Hesitancy ◽  
Lower Odds ◽  
The Public ◽  
National Longitudinal Study ◽  
Public Health Threat ◽  
National Cohort ◽  
The U.S

Background Vaccine hesitancy in the U.S. may limit the potential to alleviate the public health threat caused by the COVID-19 pandemic. Methods We estimated trends in and correlates of vaccine hesitancy, and its association with subsequent vaccine uptake among 5,085 United States adults from the CHASING COVID Cohort study, a national longitudinal study. Trends in willingness to vaccinate were examined longitudinally in three rounds of interviews from September to December 2020. We assessed correlates of willingness to vaccinate in December 2020. We also estimated the association between willingness to vaccinate in December 2020 and subsequent vaccine uptake in February 2021. Results Vaccine hesitancy and resistance decreased from 51% and 8% in September 2020 to 35% and 5% in December 2020, respectively. Compared to Non-Hispanic (NH) White participants, NH Black and Hispanic participants had higher adjusted odds ratios (aOR) for both vaccine hesitancy (aOR: 3.3 [95% CI: 2.6, 4.2] for NH Black and 1.8 [95% CI: 1.5, 2.2] for Hispanic) and vaccine resistance (aOR: 6.4 [95% CI: 4.3, 9.4] for NH Black and 1.9 [95% CI: 1.3, 2.7] for Hispanic). Willingness to vaccinate was associated with lower odds of vaccine uptake among 65+ year olds (aOR: 0.4, 95% CI: 0.3, 0.6 for hesitancy; aOR: 0.1, 95% CI: 0.01, 0.6 for resistance) and healthcare workers (aOR: 0.2, 95% CI: 0.1, 0.3 for hesitancy; aOR: 0.04, 95% CI: 0.006, 0.2 for resistance). Conclusions Awareness and distribution efforts should focus on vaccine hesitant vulnerable populations.

scholarly journals Influenza vaccination uptake and factors influencing vaccination decision among patients with chronic kidney or liver disease

PLoS ONE ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. e0249785
Author(s):  
Michael Eder ◽  
Haris Omic ◽  
Jana Gorges ◽  
Florian Badt ◽  
Zeljko Kikic ◽  
...  
Keyword(s):  
Health Care ◽  
Liver Disease ◽  
Influenza Vaccination ◽  
Tertiary Care ◽  
Winter Season ◽  
Sociodemographic Factors ◽  
Cross Sectional ◽  
Perceived Risks ◽  
Vaccination Rates ◽  
Vaccination Uptake

Introduction Seasonal influenza is a major global health problem causing substantial morbidity and health care costs. Yet, in many countries, the rates of influenza vaccination remain low. Chronic kidney or liver diseases (CKLD) predispose patients to severe influenza infections, but data on vaccination acceptance and status is limited in this risk population. We investigated the influenza vaccination awareness considering sociodemographic factors in CKLD patients. Patients and methods This cross-sectional, questionnaire-based study recruited CKLD patients managed at three Viennese tertiary care centers between July and October 2020. CKLD was defined as chronic kidney- (all stages) or compensated/decompensated liver disease, including kidney/liver transplant recipients. Questionnaires assessed sociodemographic and transplant- associated parameters, patients vaccination status and the individuals self-perceived risks of infection and associated complications. Results In total 516 patients (38.1% female, mean age 56.4 years) were included. 43.9% of patients declared their willingness to be vaccinated in the winter season 2020/2021, compared to 25.4% in 2019/2020 and 27.3% in 2016–2018. Vaccination uptake was associated with the self-perceived risks of infection (OR: 2.8 (95%CI: 1.8–4.5), p<0.001) and associated complications (OR: 3.8 (95%CI: 2.3–6.3), p<0.001) as well as with previously received influenza vaccination (2019/2020: OR 17.1 (95%CI: 9.5–30.7), p<0.001; season 2016–2018: OR 8.9 (95%CI: 5.5–14.5), p<0.001). Most frequent reasons for not planning vaccination were fear of a) graft injury (33.3%), b) complications after vaccination (32.4%) and c) vaccine inefficiency (15.0%). Conclusion While influenza vaccination willingness in patients with CKLD is increasing in the 2020/2021 season, vaccination rates may still remain <50%. Novel co-operations with primary health care, active vaccination surveillance and financial reimbursement may substantially improve vaccination rates in high-risk CKLD patients.

H1N1 Influenza Vaccine Compliance among Hospital- and Non-Hospital-Based Healthcare Personnel

2012 ◽  
Vol 33 (7) ◽  
pp. 737-744 ◽  
Author(s):  
Terri Rebmann ◽  
Ayesha Iqbal ◽  
John Anthony ◽  
Richard C. Knaup ◽  
Kathleen S. Wright ◽  
...  
Keyword(s):  
Public Health ◽  
Side Effects ◽  
Influenza Vaccine ◽  
H1n1 Influenza ◽  
Vaccine Uptake ◽  
Healthcare Personnel ◽  
H1n1 Vaccine ◽  
Targeted Interventions ◽  
Perceived Importance ◽  
Public Health Officials

Background.The 2009 pandemic H1N1 influenza vaccine had lower uptake compared to seasonal influenza vaccine, and most studies examining uptake of H1N1 vaccine focused on hospital-based healthcare personnel (HCP). Determinants of H1N1 vaccine uptake among HCP in all work settings need to be identified so that interventions can be developed for use in encouraging uptake of future pandemic or emerging infectious disease vaccines.Objective.To identify factors influencing nonhospital HCP H1N1 influenza vaccine compliance.Design and Setting.An H1N1 influenza vaccine compliance questionnaire was administered to HCP working in myriad healthcare settings in March-June 2011.Methods.Surveys were used to assess H1N1 influenza vaccine compliance and examine factors that predicted H1N1 influenza vaccine uptake.Results.In all, 3,188 HCP completed the survey. Hospital-based HCP had higher compliance than did non-hospital-based personnel (x2 = 142.2, P < .001). In logistic regression stratified by hospital setting versus nonhospital setting, determinants of H1N1 vaccination among non-hospital-based HCP included extent to which H1N1 vaccination was mandated or encouraged, perceived importance of vaccination, access to no-cost vaccine provided on-site, no fear of vaccine side effects, and trust in public health officials when they say that the influenza vaccine is safe. Determinants of hospital-based HCP H1N1 vaccine compliance included having a mandatory vaccination policy, perceived importance of vaccination, no fear of vaccine side effects, free vaccine, perceived seriousness of H1N1 influenza, and trust in public health officials.Conclusions.Non-hospital-based HCP versus hospital-based HCP reasons for H1N1 vaccine uptake differed. Targeted interventions are needed to increase compliance with pandemic-related vaccines.

Sign in / Sign up

Export Citation Format

Share Document