scholarly journals Influence of social determinants of health and county vaccination rates on machine learning models to predict COVID-19 case growth in Tennessee

2021 ◽  
Author(s):  
Lukasz S Wylezinski ◽  
Coleman R Harris ◽  
Cody N Heiser ◽  
Jamieson D Gray ◽  
Charles F Spurlock
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Social Determinants Of Health ◽  
Social Determinants ◽  
The United States ◽  
Determinants Of Health ◽  
Learning Models ◽  
Vaccination Rates ◽  
The Impact ◽  
Machine Learning Models

The SARS-CoV-2 (COVID-19) pandemic has exposed health disparities throughout the United States, particularly among racial and ethnic minorities. As a result, there is a need for data-driven approaches to pinpoint the unique constellation of clinical and social determinants of health (SDOH) risk factors that give rise to poor patient outcomes following infection in US communities. We combined county-level COVID-19 testing data, COVID-19 vaccination rates, and SDOH information in Tennessee. Between February-May 2021, we trained machine learning models on a semi-monthly basis using these datasets to predict COVID-19 incidence in Tennessee counties. We then analyzed SDOH data features at each time point to rank the impact of each feature on model performance. Our results indicate that COVID-19 vaccination rates play a crucial role in determining future COVID-19 disease risk. Beginning in mid-March 2021, higher vaccination rates significantly correlated with lower COVID-19 case growth predictions. Further, as the relative importance of COVID-19 vaccination data features grew, demographic SDOH features such as age, race, and ethnicity decreased while the impact of socioeconomic and environmental factors, including access to healthcare and transportation, increased. Incorporating a data framework to track the evolving patterns of community-level SDOH risk factors could provide policymakers with additional data resources to improve health equity and resilience to future public health emergencies.

scholarly journals Influence of social determinants of health and county vaccination rates on machine learning models to predict COVID-19 case growth in Tennessee

2021 ◽  
Vol 28 (1) ◽  
pp. e100439
Author(s):  
Lukasz S Wylezinski ◽  
Coleman R Harris ◽  
Cody N Heiser ◽  
Jamieson D Gray ◽  
Charles F Spurlock
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Social Determinants Of Health ◽  
Social Determinants ◽  
Determinants Of Health ◽  
Learning Models ◽  
Vaccination Rates ◽  
Data Framework ◽  
The Impact ◽  
Machine Learning Models

IntroductionThe SARS-CoV-2 (COVID-19) pandemic has exposed health disparities throughout the USA, particularly among racial and ethnic minorities. As a result, there is a need for data-driven approaches to pinpoint the unique constellation of clinical and social determinants of health (SDOH) risk factors that give rise to poor patient outcomes following infection in US communities.MethodsWe combined county-level COVID-19 testing data, COVID-19 vaccination rates and SDOH information in Tennessee. Between February and May 2021, we trained machine learning models on a semimonthly basis using these datasets to predict COVID-19 incidence in Tennessee counties. We then analyzed SDOH data features at each time point to rank the impact of each feature on model performance.ResultsOur results indicate that COVID-19 vaccination rates play a crucial role in determining future COVID-19 disease risk. Beginning in mid-March 2021, higher vaccination rates significantly correlated with lower COVID-19 case growth predictions. Further, as the relative importance of COVID-19 vaccination data features grew, demographic SDOH features such as age, race and ethnicity decreased while the impact of socioeconomic and environmental factors, including access to healthcare and transportation, increased.ConclusionIncorporating a data framework to track the evolving patterns of community-level SDOH risk factors could provide policy-makers with additional data resources to improve health equity and resilience to future public health emergencies.

scholarly journals Designing and implementing equity-based pandemic preparedness and response learning modules: Lessons from a multi-country short-course

2021 ◽  
Author(s):  
Anatole Manzi ◽  
Phaedra Henley ◽  
Hannah Lieberman ◽  
Langley Topper ◽  
Bernice Wuethrich ◽  
...  
Keyword(s):  
Social Determinants Of Health ◽  
Social Determinants ◽  
The United States ◽  
Determinants Of Health ◽  
Average Score ◽  
Pandemic Preparedness ◽  
Short Course ◽  
The Social ◽  
Pandemic Response ◽  
The Impact

Abstract BackgroundThe COVID-19 pandemic has had disproportionate impacts across race, social class, and geography. Insufficient attention has been paid to addressing the massive inequities worsened by COVID-19. In July 2020, Partners In Health (PIH) and the University of Global Health Equity (UGHE) designed a four-module short course, “An Equity Approach to Pandemic Preparedness and Response: Emerging Insights from COVID-19 Global Response Leaders.” We describe the design and use of a case-based, short-course education model to transfer knowledge and skills in equity approaches to pandemic preparedness and response.MethodsThis course used case studies of Massachusetts and Navajo Nation in the U.S, and Rwanda to highlight examples of equity-centered pandemic response. A post-session assessment survey was completed by course participants after each of the four modules. A mixed-method analysis was conducted to understand knowledge acquisition on key topics and assess participants’ experience and satisfaction with the course. Additionally, a landscape analysis was conducted to identify other equity-centered courses for pandemic response offered previously and to compare the content, audience, and intended outcomes.Results Forty-four percent of participants identified, “Immediate need for skills and information to address COVID-19” as their primary reason for attending the course. Participants reported that they are very likely (4.75 out of 5) to use the information, tools, or skills from the course in their work. The average score for content related questions answered correctly was 82-88% for each session. Participants (~70-90%) said their understanding was Excellent or Very Good for each session. Participants expressed a deepened understanding of the importance of prioritizing vulnerable communities and built global solidarity.ConclusionParticipants viewed the training as highly relevant, well-presented, actionable, shareable, and contributed to a new level of understanding of the social determinants of health and equity issues surrounding pandemic preparedness, crisis response, and long-term population recovery. This course offered a clear analysis of the impact of racism on the pandemic in the United States, the intersection of racism and wealth inequality; the role of the social determinants of health in pandemic preparedness, outcomes and response; and the impacts of neocolonialism on pandemic response in low- and middle-income countries.

scholarly journals Comparing Decision Tree-Based Ensemble Machine Learning Models for COVID-19 Death Probability Profiling

2020 ◽  
Author(s):  
Carlos Pedro Gonçalves ◽  
José Rouco
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Decision Tree ◽  
Age Group ◽  
Learning Models ◽  
Ensemble Machine Learning ◽  
Death Probability ◽  
Group Sex ◽  
The Impact ◽  
Machine Learning Models

AbstractWe compare the performance of major decision tree-based ensemble machine learning models on the task of COVID-19 death probability prediction, conditional on three risk factors: age group, sex and underlying comorbidity or disease, using the US Centers for Disease Control and Prevention (CDC)’s COVID-19 case surveillance dataset. To evaluate the impact of the three risk factors on COVID-19 death probability, we extract and analyze the conditional probability profile produced by the best performer. The results show the presence of an exponential rise in death probability from COVID-19 with the age group, with males exhibiting a higher exponential growth rate than females, an effect that is stronger when an underlying comorbidity or disease is present, which also acts as an accelerator of COVID-19 death probability rise for both male and female subjects. The results are discussed in connection to healthcare and epidemiological concerns and in the degree to which they reinforce findings coming from other studies on COVID-19.

scholarly journals Child Poverty, Toxic Stress, and Social Determinants of Health: Screening and Care Coordination

2018 ◽  
Vol 23 (3) ◽  
Author(s):  
Lucine Francis ◽  
Kelli DePriest ◽  
Marcella Wilson ◽  
Deborah Gross
Keyword(s):  
Child Health ◽  
Social Determinants Of Health ◽  
Social Determinants ◽  
Child Poverty ◽  
Well Being ◽  
The United States ◽  
Determinants Of Health ◽  
Practice Research ◽  
The Impact ◽  
Health And Well Being

Social determinants of health (SDOH) refer to the social, economic, and physical conditions in which people live that may affect their health. Poverty, which affects nearly 15 million children in the United States, has far-reaching effects on children’s physical and mental health. Although it is difficult to change a family’s economic circumstances, nurses can play a critical role to address SDOH through screening and effective coordination of care. As nurses, our role is to minimize the effects of SDOH, including poverty, on child health and well-being through our practice, research, and professional education. We present three exemplars of child poverty to demonstrate the impact on child health and well-being and propose a model of care for nurses to assess and address SDOH in the pediatric clinical setting.

Wealth and the health of older Black women in the United States

2018 ◽  
Vol 34 (5) ◽  
pp. 1055-1068
Author(s):  
Andy Sharma
Keyword(s):  
United States ◽  
Health Care ◽  
Black Women ◽  
Social Determinants Of Health ◽  
Social Determinants ◽  
Panel Study ◽  
Well Being ◽  
The United States ◽  
Determinants Of Health ◽  
The Impact

Summary Public health scholars and policy-makers are concerned that the United States continues to experience unmanageable health care costs while struggling with issues surrounding access and equity. To addresses these and other key issues, the National Academy of Medicine held a public symposium, Vital Directions for Health and Health Care: A National Conversation during September 2016, with the goal of identifying clear priorities for high-value health care and improved well-being. One important area was addressing social determinants of health. This article contributes to this objective by investigating the impact of wealth on older Black women’s health. Employing the 2008/2010 waves of the RAND Health and Retirement Study on a sample of 906 older Black women, this panel study examined self-assessed health ratings of very good/good/fair/poor within a relaxed random effects framework, thereby controlling for both (i) observed and (ii) unobserved individual-level heterogeneity. This analysis did not find a statistically significant association with wealth despite a difference of approximately $75 000 in its valuation from very good to poor health. This also occurred after wealth was (i) readjusted for outliers and (ii) reformulated as negative, no change or positive change from 2008. This finding suggests that wealth may not play as integral a role. However, the outcome was significant for earnings and education, particularly higher levels of education. Scholars should further this inquiry to better understand how earnings/education/wealth operate as social determinants of health for minority populations.

Abstract 16126: Cumulative Impact of Social Determinants of Health Risk Score on Obesity Among Young Adults in the United States

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Muhammad Haisum Maqsood ◽  
Javier Valero-Elizondo ◽  
Rahul Singh ◽  
Karan Shah ◽  
Maryam Hyder ◽  
...  
Keyword(s):  
Young Adults ◽  
Social Determinants Of Health ◽  
Social Determinants ◽  
The United States ◽  
Determinants Of Health ◽  
P Value ◽  
Cumulative Impact ◽  
Cumulative Score ◽  
Prevalence Of Obesity ◽  
The Impact

Introduction: The growing prevalence of obesity has created a major burden on the health care system. To date, studies examining social determinants of obesity in adults have mostly focused on individual social determinants of health (SDOH) components. In this study, we explore the influence of cumulative SDOH on obesity among young adults (< 45) as compared with middle- aged (45-64) and elderly (≥ 65) populations in the US. Methods: We examined cross-sectional data on 164,696 adult participants from the National Health Interview Survey (2013-17). For each individual, the unfavorable SDOH risk factor was identified from 39 sub-components, stemming from 6 general domains (economic stability, neighborhood and physical environment, community and social context, food, education, and healthcare system access). Risk factors were then aggregated to develop a cumulative score, wherein individuals were divided into quartiles. Obesity was calculated from self-reported height and weight and defined as BMI ≥ 30 kg/m 2 . Adults with a BMI <18.5 kg/m 2 were excluded from the analysis. Results: The age-adjusted prevalence of obesity was 32.5%, which translates to 78 million US adults annually. A linear increase in the prevalence of age-adjusted obesity was noted with increasing unfavorable SDOH prevalence across all age groups. In the overall population, those with the worst (4 th quartile) vs best (1 st quartile) SDOH profile had 1.47 higher odds of being obese in adjusted models. There was evidence, however, of effect modification by age (p-value for interaction < 0.001), with a stronger association of unfavorable SDOH risk with obesity in the young (<45 years) as compared with middle age and elderly (Table). Conclusions: A higher burden of SDOH is more strongly associated with obesity in young adults. Estimating and understanding the impact of SDOH may have practical implications for informing effective interventions to combat early adulthood obesity and its ensuing complications.

Sign in / Sign up

Export Citation Format

Share Document