Personalized Risk Stratification in Atrial Fibrillation using Portable, Explainable Artificial Intelligence

使用便携式、可解释的人工智能对心房颤动进行个性化风险分层

• 批准号: 10905154
• 负责人: BENJAMIN ADAM STEINBERG
• 金额: $ 77万
• 依托单位: UNIVERSITY OF UTAH
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-05 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10905154
• 关键词: Address; Anticoagulants; Artificial Intelligence; Atrial Fibrillation; Automobile Driving; Awareness; Benchmarking; Big Data; Caring; Clinical; Confounding Factors (Epidemiology); Data; Data Set; Disparity; Electronics; Environment; Equity; Failure; Goals; Health system; Healthcare; Healthcare Systems; Institution; Investigation; Left; Methodology; Methods; Mission; Modeling; Morbidity - disease rate; Online Systems; Oral; Outcome; Patients; Performance; Population; Population Heterogeneity; Prevention strategy; Prevention therapy; Process; Public Health; Research; Risk; Risk Estimate; Risk Factors; Risk Management; Risk Marker; Role; Site; Source; Stroke; Stroke prevention; Testing; Time; United States National Institutes of Health; Validation; Work; artificial intelligence method; auricular appendage; cohort; comorbidity; design; disparity reduction; health care disparity; health care settings; health difference; improved; innovation; large datasets; mortality; novel; outcome disparities; patient subsets; portability; precision medicine; predictive tools; prevent; prospective; public health relevance; risk prediction; risk prediction model; risk stratification; social; social consciousness; social health determinants; socioeconomics; standard of care; stroke risk; support tools; synergism; therapy adverse effect; tool

PROJECT SUMMARY/ABSTRACT Implementation of contemporary strategies to reduce stroke related to atrial fibrillation (AF) is limited by (1) rudimentary stroke risk stratification tools and (2) disparities in care and outcomes of AF. There remains a critical need for personalized, socially-aware, equitable stroke risk prediction among patients with AF, in order to optimally implement contemporary stroke-prevention therapies. A major long-term goal is to develop a portable, equitable risk-stratification tool to improve stroke-prevention among patients with AF. The objectives of this project are to (i) discover new risk-factor relationships for patients with AF that incorporate social determinants of health (SDoH), using an innovative comorbidity discovery framework (Poisson Binomial Comorbidity [PBC]); (ii) combine these with established risk factors using explainable, artificial-intelligence (AI) methods; and (iii) develop, deploy and test an augmented, personalized stroke risk stratification tool for AF patients across different health systems in a disparity-aware fashion. Our central hypothesis is that stroke prevention can be improved through methods that: leverage all available data, including SDoH; capture and quantify synergies among known and newly-discovered risk factors in socioeconomic context; and can be ported to other health systems, adapting to different populations. The rationale for this project is that current AF-related stroke risk management lacks the precision and awareness required to optimally implement treatments because it does not adequately account for (1) population diversity, (2) SDoH and disparities, (3) synergistic interactions among risk factors, and (4) novel, emerging risk factors. The central hypothesis will be tested by pursuing three specific aims: 1) Discover new clinical and socioeconomic relationships that determine stroke risk in patients with AF; 2) Develop a socially-conscious, AI-based machinery for calculating personalized stroke risk among patients with AF; and 3) Benchmark an AI-based, socially-aware stroke risk predictor across a diverse cohort of health systems using PCORnet and use it to discover biases and drivers of downstream care disparities. In the first aim, the PBC approach will be used to leverage large datasets that include SDoH, in order identify new risk markers. The second aim will focus on building novel, Probabilistic Graphical Models (PGMs) to understand the impact of SDoH on AF-related stroke risk. In the third aim, the models will be tested across a diverse set of healthcare systems to understand portability, diversity, and bias. The research proposed in this application is innovative because it (1) leverages uniquely-available data on SDoH, (2) employs a much more powerful and portable analytic approach to understand risk; and (3) is designed with an eye towards understanding and reducing disparities and bias in risk prediction models. The proposed research is significant because it will improve care across the spectrum of patients with AF, while at the same time addressing disparities and bias in the present standard of care. Ultimately, the results will yield a much more personalized and equitable approach to stroke prevention in the setting of AF.

项目摘要/摘要 实施减少与房颤相关的中风的当代策略（AF）受（1）的限制 基本的中风风险分层工具以及（2）AF的护理和结果差异。仍然有一个 对AF患者的个性化，社会意识，公平中风风险预测的批判性需求 最佳实施当代预防疗法。一个主要的长期目标是开发 便携式，公平的风险分层工具，可改善AF患者的中风预防。目标 这个项目的是（i）发现与社会社会的AF患者发现新的风险因素关系 使用创新的合并症发现框架（Poisson Binomial）健康决定因素（SDOH） 合并症[PBC]）; （ii）使用可解释的人工智能（AI）将这些与已建立的风险因素结合起来 方法; （iii）为AF开发，部署和测试一个增强的个性化中风风险分层工具 以差异感知方式，不同卫生系统的患者。我们的中心假设是中风 可以通过：利用所有可用数据（包括SDOH）的方法来改进预防；捕获和 在社会经济背景下量化已知和新发现的风险因素之间的协同作用；可以 移植到其他卫生系统，适应不同的人群。该项目的理由是当前 与AF相关的中风风险管理缺乏最佳实施所需的精度和意识 治疗是因为它不能充分说明（1）人口多样性，（2）SDOH和差异，（3） 风险因素之间的协同相互作用，以及（4）新颖的新兴危险因素。中心假设将是 通过追求三个具体目标测试：1）发现新的临床和社会经济关系 确定AF患者的中风风险； 2）开发一种具有社会意识的，基于AI的机械用于计算 AF患者的个性化中风风险； 3）基准基于AI的，具有社会意识的中风风险 使用PCORNET进行多种卫生系统的预测因子，并使用它来发现偏见和驱动因素 下游护理差异。在第一个目标中，PBC方法将用于利用大型数据集 包括SDOH，以确定新的风险标记。第二个目标将重点放在构建小说，概率 图形模型（PGM）了解SDOH对与AF相关的中风风险的影响。在第三个目标中 模型将在各种医疗系统中进行测试，以了解可移植性，多样性和偏见。 该应用程序中提出的研究具有创新性 SDOH，（2）采用更强大和便携式的分析方法来了解风险； （3）是 设计的是要理解和减少风险预测模型中的差异和偏见。这 拟议的研究很重要，因为它将改善各种AF患者的护理，而在 同时解决当前护理标准中的差异和偏见。最终，结果将产生 在AF的环境中，更个性化和公平的预防方法。