Toward Accurate Cardiovascular Disease Prediction in Hispanics/Latinos: Modeling Risk and Resilience Factors

实现西班牙裔/拉丁裔的准确心血管疾病预测：风险和弹性因素建模

基本信息

批准号：
10852318
负责人：
Melissa Ann Flores
金额：
$ 24.9万
依托单位：
UNIVERSITY OF ARIZONA
依托单位国家：
美国
项目类别：
财政年份：
2023
资助国家：
美国
起止时间：
2023-09-01 至 2026-08-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10852318
关键词：
Address Adopted Adult Algorithms Arizona Atherosclerosis Behavior Therapy Cardiovascular Diseases Complement Country Data Dimensions Disease Disease Outcome Economics Ethnic Population Etiology Exhibits Family Foundations Functional disorder Future Goals Heart Diseases High Density Lipoproteins Hispanic Community Health Study/Study of Latinos Hispanic Populations Household Incidence Intervention Knowledge Latino Population Latinx Literature Machine Learning Measurement Measures Medical Mentors Methods Mexican Modeling Modification Neighborhoods Population Public Health Research Research Proposals Resources Risk Risk Estimate Risk Factors Role Sampling Social Environment Social Network Solid Spouses Stroke Testing Training Universities Validation Work cardiovascular disorder epidemiology cardiovascular disorder risk cardiovascular health cardiovascular risk factor career cultural values data reduction disease disparity experience improved machine learning algorithm model development mortality predictive modeling resilience resilience factor risk prediction risk prediction model risk selection social social capital socioeconomics stem theories

项目摘要

PROJECT SUMMARY/ABSTRACT Existing heart disease and stroke prediction models (e.g., Framingham) tend to overestimate risk for Hispanics/Latinxs (H/L)s. This inaccuracy has significant economic and public health impacts associated with inaccurate surveillance, intervention targeting, and medical management. Model inaccuracies likely stem from pervasive underrepresentation of H/Ls in model development and validation efforts. Consequently, traditional risk factors for cardiovascular disease (CVD) may be specific to the populations upon whom they were derived, and not generalizable to H/Ls. In addition, there may be unique disease determinants for H/Ls that remain untested or unincorporated leading to error in prediction. Importantly, resilience factors such as culturally- moderated social capital may be critical to understanding risk in this population. Addressing these gaps will lead to better understanding of CVD risk with corresponding implications for targeted intervention strategies. This K99/R00 MOSAIC proposal will use secondary data to inform current 10-year CVD risk models using theory and data-driven methods to increase CVD prediction model accuracy in H/Ls. The proposed training plan establishes a solid foundation for a career investigating H/L CVD risk and resilience factors. The training plan leverages substantial resources at The University of Arizona and a mentoring team of senior content experts. The candidate will gain the following, 1) expertise in H/L CVD disparities, 2) advanced knowledge in CVD epidemiology, risk, and etiology and pathophysiology of atherosclerotic disease, 3) applied machine learning, cross-validation, and selection of risk prediction models, and 4) cultural factors and social capital influencing H/L CVD. The research proposal has three aims focused on evaluating and informing existing 10- year CVD prediction in H/Ls. Using secondary data from the Hispanic Community Health Study/Study of Latinos (HCHS/SOL), the candidate will (Aim 1 – K99) evaluate the prediction accuracy of current 10-year CVD risk models using a large H/L sample with significant representation of diverse H/Ls (HCHS/SOL). (Aim 2 – R00) the candidate will use available data to identify a group of target risk factors that improve risk prediction in H/Ls. (Aim 3 – R00) the candidate will test whether adding a social resilience component to CVD risk models will improve their prediction accuracy for this group. Machine learning will be used to identify valid predictors of 10-year CVD in Latinos. The social resilience component will capture the multi-dimensionality of social environments (e.g. spouse, family, neighborhood) using data reduction methods. The proposed research proposal adopts a holistic view of cardiovascular health to elucidate both risk and resilience factors in this growing ethnic group.

项目概要/摘要现有的心脏病和中风预测模型（例如 Framingham）往往会高估风险这种不准确的情况会对经济和公共健康产生重大影响。不准确的监测、干预目标和医疗管理可能源于模型的不准确。在传统的模型开发和验证工作中，H/L 的代表性普遍不足。心血管疾病（CVD）的危险因素可能特定于其来源人群，并且不能推广到 H/L 此外，H/L 可能还存在独特的疾病决定因素。重要的是，诸如文化等弹性因素会导致预测错误。适度的社会资本对于了解这一人群的风险可能至关重要。有助于更好地了解 CVD 风险，并对有针对性的干预策略产生相应的影响。该 K99/R00 MOSAIC 提案将使用二手数据为当前 10 年 CVD 风险模型提供信息理论和数据驱动的方法，以提高 H/L 中 CVD 预测模型的准确性。计划为调查 H/L CVD 风险和恢复因素的职业生涯奠定了坚实的基础。计划利用亚利桑那大学的大量资源和高级内容指导团队候选人将获得以下知识：1) H/L CVD 差异方面的专业知识，2) 先进的知识。 CVD流行病学、风险以及动脉粥样硬化性疾病的病因学和病理生理学，3）应用机器风险预测模型的学习、交叉验证和选择，4) 文化因素和社会资本 H/L CVD。影响研究提案有三个目标，重点是评估和告知现有的 10- 使用来自西班牙社区健康研究/研究的二手数据对 H/L 进行年度 CVD 预测。拉丁裔 (HCHS/SOL)，候选人将（目标 1 – K99）评估当前 10 年的预测准确性使用具有显着代表性的不同 H/L (HCHS/SOL) 的大型 H/L 样本进行 CVD 风险模型（目标 2）。 – R00）候选人将使用可用数据来识别一组改善风险预测的目标风险因素在 H/L（目标 3 – R00）中，考生将测试是否在 CVD 风险中添加社会复原力成分。模型将提高该组的预测准确性，机器学习将用于识别有效的内容。拉丁美洲人 10 年 CVD 的预测因子将体现社会复原力的多维性。使用数据缩减方法的社会环境（例如配偶、家庭、邻居）。该提案采用心血管健康的整体观点来阐明这一领域的风险和复原力因素不断增长的族裔群体。