Background: Existing studies on cardiovascular diseases (CVDs) often focus on individual‐level behavioral risk factors, but research examining social determinants is limited. This study applies a novel machine learning approach to identify the key predictors of county‐level care costs and prevalence of CVDs (including atrial fibrillation, acute myocardial infarction, congestive heart failure, and ischemic heart disease). Methods and Results: We applied the extreme gradient boosting machine learning approach to a total of 3137 counties. Data are from the Interactive Atlas of Heart Disease and Stroke and a variety of national data sets. We found that although demographic composition (eg, percentages of Black people and older adults) and risk factors (eg, smoking and physical inactivity) are among the most important predictors for inpatient care costs and CVD prevalence, contextual factors such as social vulnerability and racial and ethnic segregation are particularly important for the total and outpatient care costs. Poverty and income inequality are the major contributors to the total care costs for counties that are in nonmetro areas or have high segregation or social vulnerability levels. Racial and ethnic segregation is particularly important in shaping the total care costs for counties with low poverty rates or social vulnerability level. Demographic composition, education, and social vulnerability are consistently important across different scenarios. Conclusions: The findings highlight the differences in predictors for different types of CVD cost outcomes and the importance of social determinants. Interventions directed toward areas that have been economically and socially marginalized may aid in reducing the impact of CVDs.
8 March 2024 in British Journal of Sociology of Education
Benefiting from social support in online health communities requires maintaining textual communication. Investigating the process and identifying successful patterns can guide devising interventions to help online support seekers. We propose new methods to investigate the relationship between support-seeking requests and response messages in an online drug recovery forum. We use LIWC2015 text analysis software to quantify the support-seeking messages and apply machine learning algorithms to code the amount of informational and emotional support in the responses. Our work has several findings regarding the language in request messages that would increase or decrease the chances of receiving more informational or emotional support in response. For example, expressions of positive emotions and self-reference in request messages were associated with receiving more emotional support, and messages that used words indicating close relationships received more informational support. These findings contribute to the current understanding of computer-mediated communication of social support in online health communities, identifying strategies to mobilize maximal social resources. Moreover, our proposed methods can be used in other studies to investigate the exchange of social support or similar topics on online platforms.
As the state has shifted its priorities towards social harmony and poverty alleviation, this study finds rhetorical resonance, combined with strong lineage solidarity, as an emerging strategy for villages to compete for government resources and investments. By articulating grassroots needs as being in line with local cadres’ performance goals, villages have successfully converted their needs into development proposals and mobilized lineage solidarity to persuade local cadres of the feasibility of such proposals. Drawing on three villages’ school-saving efforts in Fujian province, our fieldwork illustrates how one village retained its school by mobilizing lineage solidarity and converting education into a “model” village project to boost cultural tourism. Others failed to do so and lost their schools. Under the target-based cadre management system, the bottom-up competition for government support is largely shaped by the villages’ pre-existing development and resource structures, which may maximize management efficiency but may also reinforce socioeconomic inequalities between villages. 摘要 随着中国政府对社会和谐和扶贫工作的日益重视,本研究发现,宗族团结如果能够与当下的政策话语相结合(话语共鸣),能够帮助村庄得到更多的政府资源和支持。一些村庄通过发掘基层需求与当地干部绩效目标的一致性,将村民的利益需求转化为符合上级政府意图的发展项目和策略,并依靠宗族的动员能力来向当地干部证明这些项目的可行性。本研究比较了福建省三个村庄在撤点并校政策下的不同保校策略:其中一个村庄依靠宗族的动员能力将教育转化为当地以文化旅游促发展的 “模范村”项目的一部分,村小得以保存并发展;而在另外两个村,保校策略未能与脱贫和发展导向的政策话语接轨,在学童流失的情况下难以证明自己的资源优势,村小被撤或降级。在绩效导向的干部管理体制下,村庄已有的发展水平和资源结构极大地影响了它们能否得到政府的支持,这可能会提高政府的管理效率,但也可能加剧村庄之间的社会经济不平等。