Addressing racial disparities in lung cancer screening

解决肺癌筛查中的种族差异

• 批准号: 10383711
• 负责人: Melinda Aldrich
• 金额: $ 57.8万
• 依托单位: VANDERBILT UNIVERSITY MEDICAL CENTER
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-04-05 至 2025-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10383711
• 关键词: Accounting; Address; Advisory Committees; African American; African American population; Age; Algorithms; Biometry; Calibration; Cessation of life; Clinical; Clinical Data; Cohort Studies; Communities; Data; Decision Aid; Development; Diagnostic; Eligibility Determination; Etiology; Failure; Focus Groups; Gold; Guidelines; Individual; Knowledge; Lead; Life; Lung; Machine Learning; Malignant Neoplasms; Malignant neoplasm of lung; Measures; Mission; Modeling; National Cancer Institute; National Health Interview Survey; Natural History; Online Systems; Patients; Population; Precision Health; Preventive service; Property; Prospective cohort; Provider; Public Health Informatics; Publishing; Race; Research; Risk; Risk Factors; Rural; Screening for cancer; Smoking; Smoking Behavior; Smoking History; Statistical Methods; Statistical Models; Surveys; Techniques; Testing; Translating; United States; Validation; Variant; Visit; Woman; Women' s Health; Work; age group; base; black women; cancer epidemiology; cancer risk; clinical implementation; cohort; community engagement; comorbidity; data harmonization; design; experience; health disparity; high risk; improved; innovation; low socioeconomic status; lung cancer screening; machine learning algorithm; mortality; multi-ethnic; multidisciplinary; novel; patient oriented; personalized predictions; personalized risk prediction; population based; predictive modeling; prospective; racial difference; racial disparity; racial diversity; real world application; risk prediction model; rural area; screening; screening guidelines; screening program; shared decision making; simulation; statistical and machine learning; study population; tool; urban area; web-based tool

PROJECT SUMMARY/ABSTRACT Screening promotes early detection of cancer to decrease mortality. Unfortunately, significant racial disparities exist in lung cancer screening. Recently published findings by our team show that under current national screening guidelines African Americans have reduced eligibility for lung cancer screening compared to whites. These screening guidelines are based on a combination of age and smoking pack-year criteria derived from a national lung screening trial that was primarily (91%) white. Importantly, smoking behaviors and baseline risks for lung cancer differ greatly between African Americans and whites. Because of this, a risk-based screening strategy may provide a more equitable assessment of eligibility than current screening guidelines. However, the development of personalized risk prediction models for lung cancer in African Americans has been limited. To address this gap and to improve equity in screening eligibility, we propose building a personalized prediction tool using the combined data from three large-scale population-based prospective cohorts with substantial African American representation. The combined cohorts have over 336,000 individuals (44% African American) and 9,132 incident lung cancer cases from across the United States. We propose the following three aims: 1) construct a well-calibrated natural-history model of lung cancer risk for screening in African Americans, 2) evaluate lung cancer screening strategies by simulation and identify sub-populations who would benefit from screening, accounting for comorbidities and false-positives, and 3) develop a web-based decision aid for screening that is culturally appropriate. We will employ innovative machine learning techniques and state-of-the- art statistical methods to build a well-calibrated lung cancer prediction model for African Americans. Careful examination will identify sub-populations (such as women, low socioeconomic status, rural, age groups, etc.) that will benefit from screening. A key innovative aspect of this proposal is its community-engaged approach and partnership with a Community Advisory Board, both of which will help translate our empirical findings into the design of a patient-oriented decision aid. This project is relevant to the mission of the National Cancer Institute since it focuses on establishing equity in lung cancer screening eligibility. Our findings will have sustained impact on precision health and motivate improved clinical strategies for the early detection of lung cancer for African Americans.

项目总结/摘要 筛查促进癌症的早期发现，以降低死亡率。不幸的是， 存在于肺癌筛查中。我们团队最近发表的研究结果显示，在目前的国家 与白人相比，非裔美国人接受肺癌筛查的资格有所减少。 这些筛查指南是基于年龄和吸烟包-年标准的组合，这些标准来自一个 国家肺筛查试验，主要是（91%）白色。重要的是，吸烟行为和基线风险 非裔美国人和白人之间的肺癌发病率差异很大。因此，基于风险的筛查 与目前的筛选指南相比，该战略可能提供更公平的资格评估。但 非裔美国人肺癌的个体化风险预测模型的开发受到限制。到 为了解决这一差距，提高筛查资格的公平性，我们建议建立一个个性化的预测工具， 使用来自三个大规模基于人群的前瞻性队列的合并数据， 美国代表。合并后的队列有超过336，000人（44%为非洲裔美国人）， 来自美国各地的9，132例肺癌病例。我们提出以下三个目标：1） 构建一个良好校准的肺癌风险自然史模型，用于非裔美国人的筛查，2） 通过模拟评估肺癌筛查策略，并确定将受益于 筛查，解释合并症和假阳性，以及3）开发基于网络的决策辅助工具， 文化上合适的筛选。我们将采用创新的机器学习技术和最先进的 艺术的统计方法，建立一个良好的校准肺癌预测模型，为非洲裔美国人。小心 检查将确定亚群体（如妇女、社会经济地位低的群体、农村群体、年龄组等）。 能从筛查中获益该提案的一个关键创新方面是其社区参与的方法， 与社区咨询委员会建立伙伴关系，这两者都将有助于将我们的经验发现转化为 设计一个以病人为导向的决策辅助工具。这个项目与国家癌症研究所的使命有关 因为它的重点是建立肺癌筛查资格的公平性。我们的发现将产生持续影响 关于精准健康，并推动改善非洲肺癌早期检测的临床策略 美国人