Leveraging computer vision for predicting collision risks: a cross-sectional analysis of 2019-2021 fatal collisions in the USA.

OBJECTIVE: The USA has higher rates of fatal motor vehicle collisions than most high-income countries. Previous studies examining the role of the built environment were generally limited to small geographic areas or single cities. This study aims to quantify associations between built environment characteristics and traffic collisions in the USA. METHODS: Built environment characteristics were derived from Google Street View images and summarised at the census tract level. Fatal traffic collisions were obtained from the 2019-2021 Fatality Analysis Reporting System. Fatal and non-fatal traffic collisions in Washington DC were obtained from the District Department of Transportation. Adjusted Poisson regression models examined whether built environment characteristics are related to motor vehicle collisions in the USA, controlling for census tract sociodemographic characteristics. RESULTS: Census tracts in the highest tertile of sidewalks, single-lane roads, streetlights and street greenness had 70%, 50%, 30% and 26% fewer fatal vehicle collisions compared with those in the lowest tertile. Street greenness and single-lane roads were associated with 37% and 38% fewer pedestrian-involved and cyclist-involved fatal collisions. Analyses with fatal and non-fatal collisions in Washington DC found streetlights and stop signs were associated with fewer pedestrians and cyclists-involved vehicle collisions while road construction had an adverse association. CONCLUSION: This study demonstrates the utility of using data algorithms that can automatically analyse street segments to create indicators of the built environment to enhance understanding of large-scale patterns and inform interventions to decrease road traffic injuries and fatalities.

Neighborhood built environment, obesity, and diabetes: A Utah siblings study.

Background: This study utilizes innovative computer vision methods alongside Google Street View images to characterize neighborhood built environments across Utah. Methods: Convolutional Neural Networks were used to create indicators of street greenness, crosswalks, and building type on 1.4 million Google Street View images. The demographic and medical profiles of Utah residents came from the Utah Population Database (UPDB). We implemented hierarchical linear models with individuals nested within zip codes to estimate associations between neighborhood built environment features and individual-level obesity and diabetes, controlling for individual- and zip code-level characteristics (n = 1,899,175 adults living in Utah in 2015). Sibling random effects models were implemented to account for shared family attributes among siblings (n = 972,150) and twins (n = 14,122). Results: Consistent with prior neighborhood research, the variance partition coefficients (VPC) of our unadjusted models nesting individuals within zip codes were relatively small (0.5%-5.3%), except for HbA1c (VPC = 23%), suggesting a small percentage of the outcome variance is at the zip code-level. However, proportional change in variance (PCV) attributable to zip codes after the inclusion of neighborhood built environment variables and covariates ranged between 11% and 67%, suggesting that these characteristics account for a substantial portion of the zip code-level effects. Non-single-family homes (indicator of mixed land use), sidewalks (indicator of walkability), and green streets (indicator of neighborhood aesthetics) were associated with reduced diabetes and obesity. Zip codes in the third tertile for non-single-family homes were associated with a 15% reduction (PR: 0.85; 95% CI: 0.79, 0.91) in obesity and a 20% reduction (PR: 0.80; 95% CI: 0.70, 0.91) in diabetes. This tertile was also associated with a BMI reduction of -0.68 kg/m2 (95% CI: -0.95, -0.40). Conclusion: We observe associations between neighborhood characteristics and chronic diseases, accounting for biological, social, and cultural factors shared among siblings in this large population-based study.

Road Traffic Injuries and the Built Environment in Bogotá, Colombia, 2015-2019: A Cross-Sectional Analysis.

Nine in 10 road traffic deaths occur in low- and middle-income countries (LMICs). Despite this disproportionate burden, few studies have examined built environment correlates of road traffic injury in these settings, including in Latin America. We examined road traffic collisions in Bogotá, Colombia, occurring between 2015 and 2019, and assessed the association between neighborhood-level built environment features and pedestrian injury and death. We used descriptive statistics to characterize all police-reported road traffic collisions that occurred in Bogotá between 2015 and 2019. Cluster detection was used to identify spatial clustering of pedestrian collisions. Adjusted multivariate Poisson regression models were fit to examine associations between several neighborhood-built environment features and rate of pedestrian road traffic injury and death. A total of 173,443 police-reported traffic collisions occurred in Bogotá between 2015 and 2019. Pedestrians made up about 25% of road traffic injuries and 50% of road traffic deaths in Bogotá between 2015 and 2019. Pedestrian collisions were spatially clustered in the southwestern region of Bogotá. Neighborhoods with more street trees (RR, 0.90; 95% CI, 0.82-0.98), traffic signals (0.89, 0.81-0.99), and bus stops (0.89, 0.82-0.97) were associated with lower pedestrian road traffic deaths. Neighborhoods with greater density of large roads were associated with higher pedestrian injury. Our findings highlight the potential for pedestrian-friendly infrastructure to promote safer interactions between pedestrians and motorists in Bogotá and in similar urban contexts globally.

Experiences of racism in the U.S. - A perspective from Asian & Pacific Islander, Black, Latina, and Middle Eastern women.

Introduction: Racism is a critical social determinant of health because it can have a direct impact on health and well-being, as well as infiltrate systems, policies, and practices. Few studies have explored the similarities and differences of experiences with racism and health between different minoritized groups. The objective of this paper is to examine how racism influences life experiences from the perspectives of Asian & Pacific Islander, Black, Latina, and Middle Eastern women. Methods: Eleven online racially/ethnically homogeneous focus groups with a total of 52 participants were conducted in the U.S., with representation from the North, South, and West coast. The online focus groups were recorded, transcribed, and two were translated into English (from Vietnamese and Spanish). The data was coded through NVivo and analyzed through a series of team meetings to establish themes. Results: Participants reported experiences of racism and discrimination, including physical and verbal personal attacks. They shared the role of microaggressions in their daily life, along with the ubiquitous anti-Black sentiment discussed in every group. Our participants discussed the complexities of intersectionality in their experience of discrimination, specifically regarding immigration status, language spoken, and gender. Participants also reported the role of direct racism and vicarious racism (e.g., the experiences with racism of friends or family, awareness of racist incidents via the news) in affecting their mental health. Some effects were fear, stress, anxiety, depression, and self-censoring. For participants in the Black and Latina focus groups, mental health stressors often manifested into physical issues. Discussion: Understanding the nuances in experiences across racial/ethnic groups is beneficial in identifying potential interventions to prevent and address racism and its negative health impacts.

Exploring Psychosocial and Structural Syndemic Effects as Predictors of HIV Risk Behaviors Among Black Women (HPTN 064).

Background: Syndemic models have been used in previous studies exploring HIV-related outcomes; however, these models do not fully consider intersecting psychosocial (e.g., substance use, depressive symptoms) and structural factors (unstable housing, concentrated housing vacancy) that influence the lived experiences of women. Therefore, there is a need to explore the syndemic effects of psychosocial and structural factors on HIV risk behaviors to better explain the multilevel factors shaping HIV disparities among black women. Methods: This analysis uses baseline data (May 2009-August 2010) from non-Hispanic black women enrolled in the HIV Prevention Trials Network 064 Women's Seroincidence Study (HPTN 064) and the American Community Survey 5-year estimates from 2007 to 2011. Three parameterizations of syndemic factors were applied in this analysis a cumulative syndemic index, three syndemic groups reflecting the level of influence (psychosocial syndemic group, participant-level structural syndemic group, and a neighborhood-level structural syndemic group), and syndemic factor groups. Clustered mixed effects log-binomial analyses measured the relationship of each syndemic parameterization on HIV risk behaviors in 1,347 black women enrolled in HPTN 064. Results: A higher syndemic score was significantly associated with increased prevalence of unknown HIV status of the last male sex partner (adjusted prevalence ratio (aPR) = 1.07, 95% confidence interval or CI 1.04-1.10), involvement in exchange sex (aPR = 1.17, 95% CI: 1.14-1.20), and multiple sex partners (aPR = 1.07, 95% CI: 1.06-1.09) in the last 6 months. A dose-response relationship was observed between the number of syndemic groups and HIV risk behaviors, therefore, being in multiple syndemic groups was significantly associated with increased prevalence of reporting HIV risk behaviors compared with being in one syndemic group. In addition, being in all three syndemic groups was associated with increased prevalence of unknown HIV status of the last male sex partner (aPR = 1.67, 95% CI: 1.43-1.95) and multiple sex partners (aPR = 1.53, 95% CI: 1.36-1.72). Conclusions: Findings highlight syndemic factors influence the lived experiences of black women.

Trajectories in county-level Low Birthweight Rates and Associated Contextual Factors in the United States, 2016-2021.

Introduction: Infants with low birthweight (less than 2500 grams) have greater risk of mortality, long-term neurologic disability and chronic diseases such as diabetes and cardiovascular disease as compared to infants with normal birthweight. This study examined the trajectories of low birthweight rate in the U.S. across the metropolitan and non-metropolitan counties over the time period of 2016-2021 and the associated contextual factors. Methods: This longitudinal study utilized data on 21,759,834 singleton births across 3,108 counties. Data on birthweight and maternal sociodemographic and behavioral characteristics was obtained from the National Center for Health Statistics. A generalized estimating equations model was used to examine the association of county-level contextual variables with low birthweight rates. Results: A significant increase in low birthweight rates was observed across the counties over the duration of the study. Large metro and small metro counties had significantly higher low birthweight rates as compared to non-metro counties. High percentage of Black women, underweight women, age more than 35 years, lack of prenatal care, uninsured population, and high violent crime rate was associated with an increase in low-birth-weight rates. Other contextual characteristics (percentage of married women, American Indian/Alaskan Native women, and unemployed population) differed in their associations with low birthweight rates depending on county metropolitan status. Conclusions: Our study findings emphasize the importance of developing interventions to address geographical heterogeneity in low birthweight burden, particularly for metropolitan areas and communities with vulnerable racial/ethnic and socioeconomic groups.

Rosie, a Health Education Question-and-Answer Chatbot for New Mothers: Randomized Pilot Study.

BACKGROUND: Stark disparities exist in maternal and child outcomes and there is a need to provide timely and accurate health information. OBJECTIVE: In this pilot study, we assessed the feasibility and acceptability of a health chatbot for new mothers of color. METHODS: Rosie, a question-and-answer chatbot, was developed as a mobile app and is available to answer questions about pregnancy, parenting, and child development. From January 9, 2023, to February 9, 2023, participants were recruited using social media posts and through engagement with community organizations. Inclusion criteria included being aged ≥14 years, being a woman of color, and either being currently pregnant or having given birth within the past 6 months. Participants were randomly assigned to the Rosie treatment group (15/29, 52% received the Rosie app) or control group (14/29, 48% received a children's book each month) for 3 months. Those assigned to the treatment group could ask Rosie questions and receive an immediate response generated from Rosie's knowledgebase. Upon detection of a possible health emergency, Rosie sends emergency resources and relevant hotline information. In addition, a study staff member, who is a clinical social worker, reaches out to the participant within 24 hours to follow up. Preintervention and postintervention tests were completed to qualitatively and quantitatively evaluate Rosie and describe changes across key health outcomes, including postpartum depression and the frequency of emergency room visits. These measurements were used to inform the clinical trial's sample size calculations. RESULTS: Of 41 individuals who were screened and eligible, 31 (76%) enrolled and 29 (71%) were retained in the study. More than 87% (13/15) of Rosie treatment group members reported using Rosie daily (5/15, 33%) or weekly (8/15, 53%) across the 3-month study period. Most users reported that Rosie was easy to use (14/15, 93%) and provided responses quickly (13/15, 87%). The remaining issues identified included crashing of the app (8/15, 53%), and users were not satisfied with some of Rosie's answers (12/15, 80%). Mothers in both the Rosie treatment group and control group experienced a decline in depression scores from pretest to posttest periods, but the decline was statistically significant only among treatment group mothers (P=.008). In addition, a low proportion of treatment group infants had emergency room visits (1/11, 9%) compared with control group members (3/13, 23%). Nonetheless, no between-group differences reached statistical significance at P<.05. CONCLUSIONS: Rosie was found to be an acceptable, feasible, and appropriate intervention for ethnic and racial minority pregnant women and mothers of infants owing to the chatbot's ability to provide a personalized, flexible tool to increase the timeliness and accessibility of high-quality health information to individuals during a period of elevated health risks for the mother and child. TRIAL REGISTRATION: ClinicalTrials.gov NCT06053515; https://clinicaltrials.gov/study/NCT06053515.

Vigilance and Protection: How Asian and Pacific Islander, Black, Latina, and Middle Eastern Women Cope with Racism.

BACKGROUND: Research is needed to fully investigate the differential mechanisms racial and ethnic groups use to deal with ongoing intersectional racism in women's lives. The aim of this paper was to understand how Asian American and Pacific Islander, Black, Latina, and Middle Eastern women experience racism-from personal perceptions and interactions to coping mechanisms and methods of protection. METHODS: A purposive sample of 52 participants participated in 11 online racially/ethnically homogeneous focus groups conducted throughout the USA. A team consensus approach was utilized with codebook development and thematic analysis. RESULTS: The findings relate to personal perceptions and interactions related to race and ethnicity, methods of protection against racism, vigilant behavior based on safety concerns, and unity across people of color. A few unique concerns by group included experiences of racism including physical violence among Asian American Pacific Islander groups, police brutality among Black groups, immigration discrimination in Latina groups, and religious discrimination in Middle Eastern groups. Changes in behavior for safety and protection include altering methods of transportation, teaching their children safety measures, and defending their immigration status. They shared strategies to help racial and ethnic minorities against racism including mental health resources and greater political representation. All racial and ethnic groups discussed the need for unity, solidarity, and allyship across various communities of color but for it to be authentic and long-lasting. CONCLUSION: Greater understanding of the types of racism specific groups experience can inform policies and cultural change to reduce those factors.

A Decade of Tweets: Visualizing Racial Sentiments Towards Minoritized Groups in the United States Between 2011 and 2021.

BACKGROUND: Research has demonstrated the negative impact of racism on health, yet the measurement of racial sentiment remains challenging. This article provides practical guidance on using social media data for measuring public sentiment. METHODS: We describe the main steps of such research, including data collection, data cleaning, binary sentiment analysis, and visualization of findings. We randomly sampled 55,844,310 publicly available tweets from 1 January 2011 to 31 December 2021 using Twitter's Application Programming Interface. We restricted analyses to US tweets in English using one or more 90 race-related keywords. We used a Support Vector Machine, a supervised machine learning model, for sentiment analysis. RESULTS: The proportion of tweets referencing racially minoritized groups that were negative increased at the county, state, and national levels, with a 16.5% increase at the national level from 2011 to 2021. Tweets referencing Black and Middle Eastern people consistently had the highest proportion of negative sentiment compared with all other groups. Stratifying temporal trends by racial and ethnic groups revealed unique patterns reflecting historical events specific to each group, such as the killing of George Floyd regarding sentiment of posts referencing Black people, discussions of the border crisis near the 2018 midterm elections and anti-Latinx sentiment, and the emergence of COVID-19 and anti-Asian sentiment. CONCLUSIONS: This study demonstrates the utility of social media data as a quantitative means to measure racial sentiment over time and place. This approach can be extended to a range of public health topics to investigate how changes in social and cultural norms impact behaviors and policy.A supplemental digital video is available at http://links.lww.com/EDE/C91.

Practical Guidance for the Development of Rosie, a Health Education Question-and-Answer Chatbot for New Mothers.

Communities of color experience higher maternal and infant mortality, as well as a host of other adverse outcomes, during pregnancy and postpartum. To address this, our team is developing a free, user-friendly, question-answering chatbot called Rosie. Chatbots have gained significant popularity due to their scalability and success in individualizing resources. In recent years, scientific communities and researchers have started recognizing this technology's potential to inform communities, promote health outcomes, and address health disparities. The development of Rosie is an interdisciplinary project, with teams focused on the technical build of the application (app), the development of machine learning models, and community outreach, making Rosie a chatbot built with the input from the communities it aims to serve. From June to October 2022, more than 20 demonstration sessions were conducted in Washington, District of Columbia, Maryland, and Virginia, where a total of 109 pregnant women and new mothers of color could interact with Rosie. Results from the live demonstrations showed that 75% of mothers searched for maternity and baby-related information at least once a week and more than 90% of participants expressed the likelihood to use the app. Most of the participants inquired about their baby's development, nutrition for babies, and identifying and addressing the causes of certain symptoms and conditions, accounting for about 80% of the total questions asked. Mother-related questions in the community demonstrations were mainly about pregnancy. The high level of interest in the chatbot is a clear indication of the need for more resources. Rosie aims to help close the racial gap in maternal and infant health disparities by providing new mothers with easy access to reliable health information.

Examining Twitter-Derived Negative Racial Sentiment as Indicators of Cultural Racism: Observational Associations With Preterm Birth and Low Birth Weight Among a Multiracial Sample of Mothers, 2011-2021.

BACKGROUND: Large racial and ethnic disparities in adverse birth outcomes persist. Increasing evidence points to the potential role of racism in creating and perpetuating these disparities. Valid measures of area-level racial attitudes and bias remain elusive, but capture an important and underexplored form of racism that may help explain these disparities. Cultural values and attitudes expressed through social media reflect and shape public norms and subsequent behaviors. Few studies have quantified attitudes toward different racial groups using social media with the aim of examining associations with birth outcomes. OBJECTIVE: We used Twitter data to measure state-level racial sentiments and investigate associations with preterm birth (PTB) and low birth weight (LBW) in a multiracial or ethnic sample of mothers in the United States. METHODS: A random 1% sample of publicly available tweets from January 1, 2011, to December 31, 2021, was collected using Twitter's Academic Application Programming Interface (N=56,400,097). Analyses were on English-language tweets from the United States that used one or more race-related keywords. We assessed the sentiment of each tweet using support vector machine, a supervised machine learning model. We used 5-fold cross-validation to assess model performance and achieved high accuracy for negative sentiment classification (91%) and a high F1 score (84%). For each year, the state-level racial sentiment was merged with birth data during that year (~3 million births per year). We estimated incidence ratios for LBW and PTB using log binomial regression models, among all mothers, Black mothers, racially minoritized mothers (Asian, Black, or Latina mothers), and White mothers. Models were controlled for individual-level maternal characteristics and state-level demographics. RESULTS: Mothers living in states in the highest tertile of negative racial sentiment for tweets referencing racial and ethnic minoritized groups had an 8% higher (95% CI 3%-13%) incidence of LBW and 5% higher (95% CI 0%-11%) incidence of PTB compared to mothers living in the lowest tertile. Negative racial sentiment referencing racially minoritized groups was associated with adverse birth outcomes in the total population, among minoritized mothers, and White mothers. Black mothers living in states in the highest tertile of negative Black sentiment had 6% (95% CI 1%-11%) and 7% (95% CI 2%-13%) higher incidence of LBW and PTB, respectively, compared to mothers living in the lowest tertile. Negative Latinx sentiment was associated with a 6% (95% CI 1%-11%) and 3% (95% CI 0%-6%) higher incidence of LBW and PTB among Latina mothers, respectively. CONCLUSIONS: Twitter-derived negative state-level racial sentiment toward racially minoritized groups was associated with a higher risk of adverse birth outcomes among the total population and racially minoritized groups. Policies and supports establishing an inclusive environment accepting of all races and cultures may decrease the overall risk of adverse birth outcomes and reduce racial birth outcome disparities.

Solidarity and strife after the Atlanta spa shootings: A mixed methods study characterizing Twitter discussions by qualitative analysis and machine learning.

Background: On March 16, 2021, a white man shot and killed eight victims, six of whom were Asian women at Atlanta-area spa and massage parlors. The aims of the study were to: (1) qualitatively summarize themes of tweets related to race, ethnicity, and racism immediately following the Atlanta spa shootings, and (2) examine temporal trends in expressions hate speech and solidarity before and after the Atlanta spa shootings using a new methodology for hate speech analysis. Methods: A random 1% sample of publicly available tweets was collected from January to April 2021. The analytic sample included 708,933 tweets using race-related keywords. This sample was analyzed for hate speech using a newly developed method for combining faceted item response theory with deep learning to measure a continuum of hate speech, from solidarity race-related speech to use of violent, racist language. A qualitative content analysis was conducted on random samples of 1,000 tweets referencing Asians before the Atlanta spa shootings from January to March 15, 2021 and 2,000 tweets referencing Asians after the shooting from March 17 to 28 to capture the immediate reactions and discussions following the shootings. Results: Qualitative themes that emerged included solidarity (4% before the shootings vs. 17% after), condemnation of the shootings (9% after), racism (10% before vs. 18% after), role of racist language during the pandemic (2 vs. 6%), intersectional vulnerabilities (4 vs. 6%), relationship between Asian and Black struggles against racism (5 vs. 7%), and discussions not related (74 vs. 37%). The quantitative hate speech model showed a decrease in the proportion of tweets referencing Asians that expressed racism (from 1.4% 7 days prior to the event from to 1.0% in the 3 days after). The percent of tweets referencing Asians that expressed solidarity speech increased by 20% (from 22.7 to 27.2% during the same time period) (p < 0.001) and returned to its earlier rate within about 2 weeks. Discussion: Our analysis highlights some complexities of discrimination and the importance of nuanced evaluation of online speech. Findings suggest the importance of tracking hate and solidarity speech. By understanding the conversations emerging from social media, we may learn about possible ways to produce solidarity promoting messages and dampen hate messages.

Examining Exposure to Messaging, Content, and Hate Speech from Partisan News Social Media Posts on Racial and Ethnic Health Disparities.

We investigated the content of liberal and conservative news media Facebook posts on race and ethnic health disparities. A total of 3,327,360 liberal and conservative news Facebook posts from the United States (US) from January 2015 to May 2022 were collected from the Crowd Tangle platform and filtered for race and health-related keywords. Qualitative content analysis was conducted on a random sample of 1750 liberal and 1750 conservative posts. Posts were analyzed for a continuum of hate speech using a newly developed method combining faceted Rasch item response theory with deep learning. Across posts referencing Asian, Black, Latinx, Middle Eastern, and immigrants/refugees, liberal news posts had lower hate scores compared to conservative posts. Liberal news posts were more likely to acknowledge and detail the existence of racial/ethnic health disparities, while conservative news posts were more likely to highlight the negative consequences of protests, immigration, and the disenfranchisement of Whites. Facebook posts from liberal and conservative news focus on different themes with fewer discussions of racial inequities in conservative news. Investigating the discourse on race and health in social media news posts may inform our understanding of the public's exposure to and knowledge of racial health disparities, and policy-level support for ameliorating these disparities.

Racism During Pregnancy and Birthing: Experiences from Asian and Pacific Islander, Black, Latina, and Middle Eastern Women.

BACKGROUND: Despite persistent racial disparities in maternal health in the USA, there is limited qualitative research on women's experiences of discrimination during pregnancy and childbirth that focuses on similarities and differences across multiple racial groups. METHODS: Eleven focus groups with Asian American and Pacific Islander (AAPI), Black, Latina, and Middle Eastern women (N = 52) in the USA were conducted to discuss the extent to which racism and discrimination impact pregnancy and birthing experiences. RESULTS: Participants across groups talked about the role of unequal power dynamics, discrimination, and vulnerability in patient-provider relationships. Black participants noted the influence of prior mistreatment by providers in their healthcare decisions. Latinas expressed fears of differential care because of immigration status. Middle Eastern women stated that the Muslim ban bolstered stereotypes. Vietnamese participants discussed how the effect of racism on mothers' mental health could impact their children, while Black and Latina participants expressed constant racism-related stress for themselves and their children. Participants recalled better treatment with White partners and suggested a gradient of treatment based on skin complexion. Participants across groups expressed the value of racial diversity in healthcare providers and pregnancy/birthing-related support but warned that racial concordance alone may not prevent racism and emphasized the need to go beyond "band-aid solutions." CONCLUSION: Women's discussions of pregnancy and birthing revealed common and distinct experiences that varied by race, skin complexion, language, immigration status, and political context. These findings highlight the importance of qualitative research for informing maternal healthcare practices that reduce racial inequities.

Multi-Task Classification for Improved Health Outcome Prediction Based on Environmental Indicators.

This paper aims to address the challenges associated with evaluating the impact of neighborhood environments on health outcomes. Google street view (GSV) images provide a valuable tool for assessing neighborhood environments on a large scale. By annotating the GSV images with labels indicating the presence or absence of specific neighborhood features, we can develop classifiers capable of automatically analyzing and evaluating the environment. However, the process of labeling GSV images to analyze and evaluate the environment is a time-consuming and labor-intensive task. To overcome these challenges, we propose using a multi-task classifier to enhance the training of classifiers with limited supervised GSV data. Our multi-task classifier utilizes readily available, inexpensive online images collected from Flickr as a related classification task. The hypothesis is that a classifier trained on multiple related tasks is less likely to overfit to small amounts of training data and generalizes better to unseen data. We leverage the power of multiple related tasks to improve the classifier's overall performance and generalization capability. Here we show that, with the proposed learning paradigm, predicted labels for GSV test images are more accurate. Across different environment indicators, the accuracy, F1 score and balanced accuracy increase up to 6 % in the multi-task learning framework compared to its single-task learning counterpart. The enhanced accuracy of the predicted labels obtained through the multi-task classifier contributes to a more reliable and precise regression analysis determining the correlation between predicted built environment indicators and health outcomes. The R2 values calculated for different health outcomes improve by up to 4 % using multi-task learning detected indicators.

Examination of the Public's Reaction on Twitter to the Over-Turning of Roe v Wade and Abortion Bans.

The overturning of Roe v Wade reinvigorated the national debate on abortion. We used Twitter data to examine temporal, geographical and sentiment patterns in the public's reaction. Using the Twitter API for Academic Research, a random sample of publicly available tweets was collected from 1 May-15 July in 2021 and 2022. Tweets were filtered based on keywords relating to Roe v Wade and abortion (227,161 tweets in 2021 and 504,803 tweets in 2022). These tweets were tagged for sentiment, tracked by state, and indexed over time. Time plots reveal low levels of conversations on these topics until the leaked Supreme Court opinion in early May 2022. Unlike pro-choice tweets which declined, pro-life conversations continued with renewed interest throughout May and increased again following the official overturning of Roe v Wade. Conversations were less prevalent in some these states had abortion trigger laws (Wyoming, North Dakota, South Dakota, Texas, Louisiana, and Mississippi). Collapsing across topic categories, 2022 tweets were more negative and less neutral and positive compared to 2021 tweets. In network analysis, tweets mentioning woman/women, supreme court, and abortion spread faster and reached to more Twitter users than those mentioning Roe Wade and Scotus. Twitter data can provide real-time insights into the experiences and perceptions of people across the United States, which can be used to inform healthcare policies and decision-making.

Leveraging 13 million responses to the U.S. COVID-19 Trends and Impact Survey to examine vaccine hesitancy, vaccination, and mask wearing, January 2021-February 2022.

BACKGROUND: The urgency of the COVID-19 pandemic called upon the joint efforts from the scientific and private sectors to work together to track vaccine acceptance and prevention behaviors. METHODS: Our study utilized individual responses to the Delphi Group at Carnegie Mellon University U.S. COVID-19 Trends and Impact Survey, in partnership with Facebook. We retrieved survey data from January 2021 to February 2022 (n = 13,426,245) to examine contextual and individual-level predictors of COVID-19 vaccine hesitancy, vaccination, and mask wearing in the United States. Adjusted logistic regression models were developed to examine individual and ZIP code predictors of COVID-19 vaccine hesitancy and vaccination status. Given the COVID-19 vaccine was rolled out in phases in the U.S. we conducted analyses stratified by time, January 2021-May 2021 (Time 1) and June 2021-February 2022 (Time 2). RESULTS: In January 2021 only 9% of U.S. Facebook respondents reported receiving the COVID-19 vaccine, and 45% were vaccine hesitant. By February 2022, 80% of U.S. Facebook respondents were vaccinated and only 18% were vaccine hesitant. Individuals who were older, held higher educational degrees, worked in white collar jobs, wore a mask most or all the time, and identified as white and Asian had higher COVID-19 vaccination rates and lower vaccine hesitancy across Time 1 and Time 2. Essential workers and blue-collar occupations had lower COVID vaccinations and higher vaccine hesitancy. By Time 2, all adults were eligible for the COVID-19 vaccine, but blacks and multiracial individuals had lower vaccination and higher vaccine hesitancy compared to whites. Those 55 years and older and females had higher odds of wearing masks most or all the time. Protective service, construction, and installation and repair occupations had lower odds of wearing masks. ZIP Code level percentage of the population with a bachelors' which was associated with mask wearing, higher vaccination, and lower vaccine hesitancy. CONCLUSION: Associations found in earlier phases of the pandemic were generally found to also be present later in the pandemic, indicating stability in inequities. Additionally, inequities in these important outcomes suggests more work is needed to bridge gaps to ensure that the burden of COVID-19 risk does not disproportionately fall upon subgroups of the population.

Using Convolutional Neural Networks to Derive Neighborhood Built Environments from Google Street View Images and Examine Their Associations with Health Outcomes.

Built environment neighborhood characteristics are difficult to measure and assess on a large scale. Consequently, there is a lack of sufficient data that can help us investigate neighborhood characteristics as structural determinants of health on a national level. The objective of this study is to utilize publicly available Google Street View images as a data source for characterizing built environments and to examine the influence of built environments on chronic diseases and health behaviors in the United States. Data were collected by processing 164 million Google Street View images from November 2019 across the United States. Convolutional Neural Networks, a class of multi-layer deep neural networks, were used to extract features of the built environment. Validation analyses found accuracies of 82% or higher across neighborhood characteristics. In regression analyses controlling for census tract sociodemographics, we find that single-lane roads (an indicator of lower urban development) were linked with chronic conditions and worse mental health. Walkability and urbanicity indicators such as crosswalks, sidewalks, and two or more cars were associated with better health, including reduction in depression, obesity, high blood pressure, and high cholesterol. Street signs and streetlights were also found to be associated with decreased chronic conditions. Chain link fence (physical disorder indicator) was generally associated with poorer mental health. Living in neighborhoods with a built environment that supports social interaction and physical activity can lead to positive health outcomes. Computer vision models using manually annotated Google Street View images as a training dataset were able to accurately identify neighborhood built environment characteristics. These methods increases the feasibility, scale, and efficiency of neighborhood studies on health.

Google Street View Images as Predictors of Patient Health Outcomes, 2017-2019.

Collecting neighborhood data can both be time- and resource-intensive, especially across broad geographies. In this study, we leveraged 1.4 million publicly available Google Street View (GSV) images from Utah to construct indicators of the neighborhood built environment and evaluate their associations with 2017-2019 health outcomes of approximately one-third of the population living in Utah. The use of electronic medical records allows for the assessment of associations between neighborhood characteristics and individual-level health outcomes while controlling for predisposing factors, which distinguishes this study from previous GSV studies that were ecological in nature. Among 938,085 adult patients, we found that individuals living in communities in the highest tertiles of green streets and non-single-family homes have 10-27% lower diabetes, uncontrolled diabetes, hypertension, and obesity, but higher substance use disorders-controlling for age, White race, Hispanic ethnicity, religion, marital status, health insurance, and area deprivation index. Conversely, the presence of visible utility wires overhead was associated with 5-10% more diabetes, uncontrolled diabetes, hypertension, obesity, and substance use disorders. Our study found that non-single-family and green streets were related to a lower prevalence of chronic conditions, while visible utility wires and single-lane roads were connected with a higher burden of chronic conditions. These contextual characteristics can better help healthcare organizations understand the drivers of their patients' health by further considering patients' residential environments, which present both risks and resources.

Social Network Analysis on the Mobility of Three Vulnerable Population Subgroups: Domestic Workers, Flight Crews, and Sailors during the COVID-19 Pandemic in Hong Kong.

BACKGROUND: Domestic workers, flight crews, and sailors are three vulnerable population subgroups who were required to travel due to occupational demand in Hong Kong during the COVID-19 pandemic. OBJECTIVE: The aim of this study was to explore the social networks among three vulnerable population subgroups and capture temporal changes in their probability of being exposed to SARS-CoV-2 via mobility. METHODS: We included 652 COVID-19 cases and utilized Exponential Random Graph Models to build six social networks: one for the cross-sectional cohort, and five for the temporal wave cohorts, respectively. Vertices were the three vulnerable population subgroups. Edges were shared scenarios where vertices were exposed to SARS-CoV-2. RESULTS: The probability of being exposed to a COVID-19 case in Hong Kong among the three vulnerable population subgroups increased from 3.38% in early 2020 to 5.78% in early 2022. While domestic workers were less mobile intercontinentally compared to flight crews and sailors, domestic workers were 1.81-times in general more likely to be exposed to SARS-CoV-2. CONCLUSIONS: Vulnerable populations with similar ages and occupations, especially younger domestic workers and flight crew members, were more likely to be exposed to SARS-CoV-2. Social network analysis can be used to provide critical information on the health risks of infectious diseases to vulnerable populations.