Addressing racial and ethnic disparities in access to the liver transplant waiting list: a data science-focused and team-based approach

解决肝移植等候名单中的种族和民族差异：以数据科学为中心、基于团队的方法

• 批准号: 10506394
• 负责人: Alexandra Teresa Strauss
• 金额: $ 17.39万
• 依托单位: JOHNS HOPKINS UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-08-15 至 2027-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10506394
• 关键词: Address; Adherence; Adult; Affect; Award; Awareness; Bioethics; Bioethics Consultants; Cessation of life; Characteristics; Charge; Cirrhosis; Clinical; Complex; Data; Data Display; Data Science; Data Scientist; Decision Making; Decision Support Systems; Delphi Technique; Documentation; Dropout; Engineering; Epidemiologist; Ethnic Origin; Evaluation; Evidence based intervention; Feedback; Focus Groups; Funding; Future; Goals; Health Disparities Research; Healthcare; Hepatology; Hispanic; Informatics; Institutes; Institutional Racism; Intervention; Learning; Life; Liver; Liver diseases; Machine Learning; Measures; Medical; Medical center; Mentors; Methods; Modeling; Molds; Organ; Outcome; Pathway interactions; Patients; Physicians; Predictive Analytics; Process; Process Measure; Promoting Action on Research Implementation in Health Services framework; Protocols documentation; Provider; Psychosocial Assessment and Care; Public Health Schools; Qualitative Methods; Qualitative Research; Race; Research; Savings; Scientist; Severity of illness; Socioeconomic Status; Supervision; System; Techniques; Testing; Time; Training; Transplant Recipients; Transplant Surgeon; Transplantation; Vulnerable Populations; Waiting Lists; Work; base; black patient; clinical decision support; cohort; comorbidity; curative treatments; demographics; design; experience; health disparity; health equity; implementation science; implementation trial; improved; insight; interdisciplinary approach; liver transplantation; machine learning method; machine learning model; mathematical model; mortality; multilevel analysis; patient-level barriers; predictive modeling; primary outcome; psychosocial; racial and ethnic disparities; racism; research clinical testing; satisfaction; secondary outcome; skills; social; social health determinants; supervised learning; support tools; tool development; transplant centers

Project Summary In the US, 4.5 million adults have liver disease, and liver transplantation (LT) is the only curative treatment for those with cirrhosis; transplant centers are charged with determining recipients for a life-saving organ. Disparities exist for patients listed for LT: Black patients are under-represented on 81% of US transplant center waitlists, and 62% under-represent Hispanic patients. LT centers assess each patient’s appropriateness for transplant, culminating in a decision to list for transplant or decline. If listed, patients are prioritized based on disease severity and will either receive a liver or be de-listed for a variety of reasons, such as death. While prior disparities research has targeted factors affecting post-listing outcomes (e.g., waitlist dropout, post-LT survival), an upstream focus on pre-listing patient-level barriers, structural/institutional racism, and interpersonal racism has not been well studied despite having high impact on equity for LT patients. LT listing decision-making is variable. Objective clinical measures are utilized, but social determinants of health (SDOH, e.g., racism, socioeconomic position) and subjectivity permeate data gathering, clinical observations, and psychosocial assessments. A data-driven approach to LT listing has yet to be described. Predictive analytics (supervised machine learning) can be harnessed to strengthen objectivity and minimize bias of complex decision-making. Preliminary data from my qualitative work are the first to comprehensively outline potential pathways resulting in the listing disparities and reveal that transplant center providers are cautiously optimistic for machine learning-based clinical decision support tools in LT evaluation. The hypothesis is that timely access to summarized, objective data can improve provider decision-making and listing disparities. Using a multi-disciplinary approach to apply data science techniques from an equity perspective, Dr. Strauss will leverage her strong relationships with experts from Johns Hopkins Medical Center: experienced transplant team, transplant research lab, Malone Center for Engineering in Healthcare, School of Public Health social epidemiologists, and the Berman Institute of Bioethics. The overarching project goal is to improve equity in LT decision-making using a data-driven and team-based intervention; the overarching training goal is to gain skills in machine learning, health equity interventions, and implementation science. AIM 1: Develop and internally validate a machine learning-based model to assist LT listing decision-making. AIM 2: Create a data-driven, equity-focused intervention for team decision-making in LT evaluation. AIM 3: Design a multicenter pilot implementation trial of a data-driven, equity-focused intervention for LT evaluation. Impact: Through this project, Dr. Strauss will develop a data-driven and equity-focused intervention that will address disparities in LT listing. This mentored award will develop Dr. Strauss into an R01-funded, independent physician-scientist with advanced skills in machine learning, health equity research, and implementation science.

项目摘要 在美国，有450万成人患有肝病，肝移植（LT）是唯一的治疗方法 患有肝硬化的人；移植中心负责确定挽救生命器官的受体。 列出的LT的患者存在差异：黑人患者在81％的美国移植中心中的差异不足 候补名单和62％的代表性西班牙裔患者。 LT中心评估每个患者的适当性 移植，最终决定列出移植或衰落的决定。如果列出，请根据 疾病的严重程度，由于多种原因（例如死亡）将接受肝脏或被列入肝脏。尽管 先前的差异研究针对影响后列表结果的因素（例如，候补名单辍学，lt 生存），上游的重点是预列前患者级别的障碍，结构/机构种族主义和 人际种族主义并不是对LT患者股权产生巨大影响的研究目的地。 LT上市 决策是可变的。利用了客观的临床措施，但是健康的社会决定者（SDOH， 例如，种族主义，社会经济地位）和主观性渗透到数据收集，临床观察和 社会心理评估。数据驱动的LT清单方法尚未描述。预测分析 （监督机器学习）可以利用以增强客观性并最大程度地减少复杂的偏见 决策。我定性工作的初步数据是第一个全面概述潜在潜力的数据 导致清单分布的途径，并揭示了移植中心提供商谨慎乐观 用于基于机器学习的临床决策支持工具LT评估。假设是及时 访问摘要，客观数据可以改善提供商的决策和上市差异。使用 从公平的角度使用数据科学技术的多学科方法，Strauss博士将 利用她与约翰·霍普金斯医学中心的专家的牢固关系：经验丰富的移植 团队，移植研究实验室，马龙医疗保健工程中心，公共卫生学院社会学院 流行病学家和伯曼生物伦理研究所。总体项目目标是提高LT的股权 使用基于数据驱动和团队的干预措施决策；总体培训目标是获得技能 在机器学习，健康公平干预和实施科学中。目标1：开发和内部 验证基于机器学习的模型，以帮助LT上市决策。目标2：创建一个数据驱动， 以股权为重点的干预措施，用于LT评估中的团队决策。目标3：设计多中心飞行员 以数据驱动的股权干预措施进行LT评估的实施试验。影响：通过此 项目，Strauss博士将开发以数据驱动和股权为中心的干预措施，该干预将解决LT中的分布 清单。这个重要的奖项将使施特劳斯博士成为由R01资助的独立身体科学家， 机器学习，健康公平研究和实施科学方面的高级技能。