1344. Predicting Measles Outbreaks in the United States: Application of Different Modeling Approaches

Abstract Background Although measles is still rare in the United States (U.S.), there have been recent resurgent outbreaks in the U.S. To improve the accuracy of prediction given the rarity of measles events, we used machine learning (ML) algorithms to model measles case predictions at the U.S. county level. Methods The main outcome was occurrence of ≥1 measles case at the U.S. county level. Two ML prediction models were developed (HDBSCAN, a clustering algorithm, and XGBoost, a gradient boosting algorithm) and compared with traditional logistic regression. We included 28 predictors in the following categories: sociodemographics, population statistics, measles vaccination coverage, healthcare access, and exposure to measles via international air travel. The models were trained on 2014 case data and validated on 2018 case data. Models were compared using area under the receiver operating curve (AUC), sensitivity, specificity, positive predictive value (PPV), and F2 score (combined measure of sensitivity and PPV). Results There were 667 measles cases in 2014 and 375 in 2018 in the U.S. We identified U.S. counties for 635 (95.2%) cases in 2014 and 366 (97.6%) cases in 2018 through published sources, corresponding to 81/3143 (2.6%) counties in 2014 and 64/3143 (2.0%) counties in 2018 with ≥1 measles case. HDBSCAN had the highest sensitivity (0.92), but lowest AUC (0.68) and PPV (0.04) (Table). XGBoost had the highest F2 score (0.49), best balance of sensitivity (0.72) and specificity (0.94), and AUC = 0.92. Logistic regression had high AUC (0.91) and specificity (1.00) but the lowest sensitivity (0.16). Conclusion Machine learning approaches outperformed logistic regression by maximizing sensitivity to predict counties with measles cases, an important criterion to consider to prevent or prepare for future outbreaks. XGBoost or logistic regression could be considered to maximize specificity. Prioritizing sensitivity versus specificity may depend on county resources, priorities, and measles risk. Different modeling approaches could be considered to optimize surveillance efforts and develop effective interventions for timely response. Disclosures Stephanie Kujawski, PhD MPH, Merck & Co., Inc. (Employee, Shareholder) Boshu Ru, Ph.D., Merck & Co. Kenilworth, NJ (NYSE: MRK) (Employee, Shareholder) Amar K. Das, MD, PhD, Merck (Employee) richard baumgartner, PhD, Merck (Employee) Shuang Lu, MBA, MS, Merck (Employee) Matthew Pillsbury, PhD, Merck & CO. (Employee, Shareholder) Joseph Lewnard, PhD, Merck (Consultant, Grant/Research Support) James H. Conway, MD, FAAP, GSK (Advisor or Review Panel member)Merck (Advisor or Review Panel member)Moderna (Advisor or Review Panel member)Pfizer (Advisor or Review Panel member)Sanofi Pasteur (Research Grant or Support) Manjiri D. Pawaskar, PhD, Merck & Co., Inc. (Employee, Shareholder)

Download Full-text

Disproportionately Overrepresented: Women in Local Elected Offices

State and Local Government Review ◽

10.1177/0160323x18813641 ◽

2018 ◽

Vol 50 (3) ◽

pp. 165-176 ◽

Cited By ~ 1

Author(s):

Ethan M. Bernick ◽

Brianne Heidbreder

Keyword(s):

United States ◽

Maximum Likelihood ◽

Gender Norms ◽

The United States ◽

Census Bureau ◽

National Association ◽

County Level ◽

Political Factors ◽

Using Data ◽

The U.S

This research examines the position of county clerk, where women are numerically disproportionately over-represented. Using data collected from the National Association of Counties and the U.S. Census Bureau, the models estimate the correlation between the county clerk’s sex and county-level demographic, social, and political factors with maximum likelihood logit estimates. This research suggests that while women are better represented in the office of county clerk across the United States, when compared to other elective offices, this representation may be because this office is not seen as attractive to men and its responsibilities fit within the construct of traditional gender norms.

Download Full-text

Gulf of Mexico Coastal County Resilience to Natural Hazards

Gulf and Caribbean Research ◽

10.18785/gcr.3201.10 ◽

2021 ◽

Vol 32 ◽

pp. 67-78

Author(s):

Kevin Summers ◽

Linda Harwell ◽

Andrea Lamper ◽

Courtney McMillon ◽

Kyle Buck ◽

...

Keyword(s):

United States ◽

Gulf Of Mexico ◽

Natural Hazards ◽

Social Economic ◽

Multiple Scales ◽

The United States ◽

County Level ◽

Coastal County ◽

County Scale ◽

The U.S

Using a Cumulative Resilience Screening Index (CRSI) that was developed to represent resilience to natural hazards at multiple scales for the United States, the U.S. coastal counties of the Gulf of Mexico (GOM) region of the United States are compared for resilience for these types of natural hazards. The assessment compares the domains, indicators and metrics of CRSI, addressing environmental, economic and societal aspects of resilience to natural hazards at county scales. The index was applied at the county scale and aggregated to represent states and two regions of the U.S. GOM coastline. Assessments showed county—level resilience in all GOM counties was low, generally below the U.S. average. Comparisons showed higher levels of resilience in the western GOM region while select counties in Louisiana, Mississippi and Alabama exhibited the lowest resilience (<2.0) to natural hazards. Some coastal counties in Florida and Texas represented the highest levels of resilience seen along the GOM coast. Much of this increased resilience appears to be due to higher levels of governance and broader levels of social, economic and ecological services.

Download Full-text

Spatial Clustering of County-Level COVID-19 Rates in the U.S

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph182212170 ◽

2021 ◽

Vol 18 (22) ◽

pp. 12170

Author(s):

Marcus R. Andrews ◽

Kosuke Tamura ◽

Janae N. Best ◽

Joniqua N. Ceasar ◽

Kaylin G. Battey ◽

...

Keyword(s):

United States ◽

Health Disparities ◽

Rural Areas ◽

Metropolitan Areas ◽

Spatial Clustering ◽

The United States ◽

County Level ◽

Communities Of Color ◽

States Data ◽

The U.S

Despite the widespread prevalence of cases associated with the coronavirus disease 2019 (COVID-19) pandemic, little is known about the spatial clustering of COVID-19 in the United States. Data on COVID-19 cases were used to identify U.S. counties that have both high and low COVID-19 incident proportions and clusters. Our results suggest that there are a variety of sociodemographic variables that are associated with the severity of COVID-19 county-level incident proportions. As the pandemic evolved, communities of color were disproportionately impacted. Subsequently, it shifted from communities of color and metropolitan areas to rural areas in the U.S. Our final period showed limited differences in county characteristics, suggesting that COVID-19 infections were more widespread. The findings might address the systemic barriers and health disparities that may result in high incident proportions of COVID-19 clusters.

Download Full-text

Impact of COVID-19 Second Wave on Healthcare Networks in the United States

10.1101/2020.07.11.20151217 ◽

2020 ◽

Author(s):

Emad M. Hassan ◽

Hussam Mahmoud

Keyword(s):

United States ◽

Healthcare System ◽

The United States ◽

Healthcare Systems ◽

Mitigation Strategies ◽

County Level ◽

Protective Measures ◽

The Impact ◽

Second Wave ◽

The U.S

The risk of overwhelming healthcare systems from a second wave of COVID-19 is yet to be quantified. Here, we investigate the impact of different reopening scenarios of states around the U.S. on COVID-19 hospitalized cases and the risk of overwhelming the healthcare system while considering resources at the county level. We show that the second wave might involve an unprecedented impact on the healthcare system if an increasing number of the population becomes susceptible and/or if the various protective measures are discontinued. Furthermore, we explore the ability of different mitigation strategies in providing considerable relief to the healthcare system. The results can aid healthcare planners, policymakers, and state officials in making decisions on additional resources required and on when to return to normalcy.

Download Full-text

Secondary organic aerosol association with cardiorespiratory disease mortality in the United States

Nature Communications ◽

10.1038/s41467-021-27484-1 ◽

2021 ◽

Vol 12 (1) ◽

Author(s):

Havala O. T. Pye ◽

Cavin K. Ward-Caviness ◽

Ben N. Murphy ◽

K. Wyat Appel ◽

Karl M. Seltzer

Keyword(s):

United States ◽

Secondary Organic Aerosol ◽

Carbon Sources ◽

Organic Aerosol ◽

The United States ◽

County Level ◽

Risk Of Death ◽

Predictive Algorithms ◽

Increased Risk ◽

The U.S

AbstractFine particle pollution, PM2.5, is associated with increased risk of death from cardiorespiratory diseases. A multidecadal shift in the United States (U.S.) PM2.5 composition towards organic aerosol as well as advances in predictive algorithms for secondary organic aerosol (SOA) allows for novel examinations of the role of PM2.5 components on mortality. Here we show SOA is strongly associated with county-level cardiorespiratory death rates in the U.S. independent of the total PM2.5 mass association with the largest associations located in the southeastern U.S. Compared to PM2.5, county-level variability in SOA across the U.S. is associated with 3.5× greater per capita county-level cardiorespiratory mortality. On a per mass basis, SOA is associated with a 6.5× higher rate of mortality than PM2.5, and biogenic and anthropogenic carbon sources both play a role in the overall SOA association with mortality. Our results suggest reducing the health impacts of PM2.5 requires consideration of SOA.

Download Full-text

Lifestyle Effects on the Risk of Transmission of COVID-19 in the United States: Evaluation of Market Segmentation Systems

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18094826 ◽

2021 ◽

Vol 18 (9) ◽

pp. 4826

Author(s):

Esra Ozdenerol ◽

Jacob Seboly

Keyword(s):

United States ◽

The United States ◽

Mortality Rates ◽

Incidence Rates ◽

Statistical Testing ◽

Average Risk ◽

County Level ◽

Household Level ◽

The Impact ◽

The U.S

The aim of this study was to associate lifestyle characteristics with COVID-19 infection and mortality rates at the U.S. county level and sequentially map the impact of COVID-19 on different lifestyle segments. We used analysis of variance (ANOVA) statistical testing to determine whether there is any correlation between COVID-19 infection and mortality rates and lifestyles. We used ESRI Tapestry LifeModes data that are collected at the U.S. household level through geodemographic segmentation typically used for marketing purposes to identify consumers’ lifestyles and preferences. According to the ANOVA analysis, a significant association between COVID-19 deaths and LifeModes emerged on 1 April 2020 and was sustained until 30 June 2020. Analysis of means (ANOM) was also performed to determine which LifeModes have incidence rates that are significantly above/below the overall mean incidence rate. We sequentially mapped and graphically illustrated when and where each LifeMode had above/below average risk for COVID-19 infection/death on specific dates. A strong northwest-to-south and northeast-to-south gradient of COVID-19 incidence was identified, facilitating an empirical classification of the United States into several epidemic subregions based on household lifestyle characteristics. Our approach correlating lifestyle characteristics to COVID-19 infection and mortality rate at the U.S. county level provided unique insights into where and when COVID-19 impacted different households. The results suggest that prevention and control policies can be implemented to those specific households exhibiting spatial and temporal pattern of high risk.

Download Full-text

ESTIMATING CORN YIELD IN THE UNITED STATES WITH MODIS EVI AND MACHINE LEARNING METHODS

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprsannals-iii-8-131-2016 ◽

2016 ◽

Vol III-8 ◽

pp. 131-136 ◽

Cited By ~ 8

Author(s):

K. Kuwata ◽

R. Shibasaki

Keyword(s):

Neural Network ◽

United States ◽

Machine Learning ◽

Crop Yield ◽

The United States ◽

Machine Learning Algorithms ◽

Corn Yield ◽

County Level ◽

Entire Area ◽

Modis Evi

Satellite remote sensing is commonly used to monitor crop yield in wide areas. Because many parameters are necessary for crop yield estimation, modelling the relationships between parameters and crop yield is generally complicated. Several methodologies using machine learning have been proposed to solve this issue, but the accuracy of county-level estimation remains to be improved. In addition, estimating county-level crop yield across an entire country has not yet been achieved. In this study, we applied a deep neural network (DNN) to estimate corn yield. We evaluated the estimation accuracy of the DNN model by comparing it with other models trained by different machine learning algorithms. We also prepared two time-series datasets differing in duration and confirmed the feature extraction performance of models by inputting each dataset. As a result, the DNN estimated county-level corn yield for the entire area of the United States with a determination coefficient (R2) of 0.780 and a root mean square error (RMSE) of 18.2 bushels/acre. In addition, our results showed that estimation models that were trained by a neural network extracted features from the input data better than an existing machine learning algorithm.

Download Full-text

Privatized Democracy: The Role of Election Services Vendors in the United States

American Politics Research ◽

10.1177/1532673x20920264 ◽

2020 ◽

Vol 48 (6) ◽

pp. 705-708 ◽

Cited By ~ 1

Author(s):

Nadine Suzanne Gibson

Keyword(s):

United States ◽

Logistic Regression ◽

The United States ◽

Minority Population ◽

County Level ◽

Regression Analyses ◽

Purchasing Decisions ◽

Term Maintenance

Election equipment in the United States is exclusively purchased from private-sector vendors. When a jurisdiction purchases voting equipment, it is actually purchasing the hardware and software along with a variety of services for the initial implementation and long-term maintenance and support of the system. Election services constitute roughly one third of county-level election expenditures. The results of logistic regression analyses estimating the likelihoods of county purchases of different election services from election services vendors suggest a relationship between purchasing decisions and county demographics, namely the size of the minority population. Localities in states with centralized contracting systems were also substantially more likely to purchase all forms of vendor services.

Download Full-text

Impact of multiple waves of COVID-19 on healthcare networks in the United States

PLoS ONE ◽

10.1371/journal.pone.0247463 ◽

2021 ◽

Vol 16 (3) ◽

pp. e0247463

Author(s):

Emad M. Hassan ◽

Hussam N. Mahmoud

Keyword(s):

United States ◽

The United States ◽

Mitigation Strategies ◽

County Level ◽

Protective Measures ◽

The Impact ◽

The U.S

The risk of overwhelming hospitals from multiple waves of COVID-19 is yet to be quantified. Here, we investigate the impact of different scenarios of releasing strong measures implemented around the U.S. on COVID-19 hospitalized cases and the risk of overwhelming the hospitals while considering resources at the county level. We show that multiple waves might cause an unprecedented impact on the hospitals if an increasing number of the population becomes susceptible and/or if the various protective measures are discontinued. Furthermore, we explore the ability of different mitigation strategies in providing considerable relief to hospitals. The results can help planners, policymakers, and state officials decide on additional resources required and when to return to normalcy.

Download Full-text

U.S. county level analysis to determine If social distancing slowed the spread of COVID-19

Revista Panamericana de Salud Pública ◽

10.26633/rpsp.2020.90 ◽

2020 ◽

Vol 44 ◽

pp. 1

Author(s):

Tannista Banerjee ◽

Arnab Nayak

Keyword(s):

United States ◽

Cell Phone ◽

The United States ◽

County Level ◽

Difference In Difference ◽

Social Distancing ◽

The Public ◽

Risks And Benefits ◽

Level Analysis ◽

The U.S

Objective. To analyze the effectiveness of social distancing in the United States (U.S.). Methods. A novel cell-phone ping data was used to quantify the measures of social distancing by all U.S. counties. Results. Using a difference-in-difference approach results show that social distancing has been effective in slowing the spread of COVID-19. Conclusions. As policymakers face the very difficult question of the necessity and effectiveness of social distancing across the U.S., counties where the policies have been imposed have effectively increased social distancing and have seen slowing the spread of COVID-19. These results might help policymakers to make the public understand the risks and benefits of the lockdown.

Download Full-text