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

项目概要/摘要 减少房颤（AF）相关卒中的当代策略的实施受到以下限制：（1） 基本的卒中风险分层工具和（2）AF的护理和结局的差异。 迫切需要在AF患者中进行个性化、社会意识、公平的卒中风险预测， 以最佳方式实施当代中风预防疗法。一个主要的长期目标是开发一个 便携式，公平的风险分层工具，以改善房颤患者的卒中预防。 该项目的目的是（i）发现AF患者的新风险因素关系， 健康的决定因素（SDoH），使用创新的共病发现框架（泊松二项式 科摩罗[PBC]）;（ii）使用可解释的人工智能（AI）将这些与已确定的风险因素相结合 方法;以及（iii）开发、部署和测试增强的个性化房颤卒中风险分层工具 不同卫生系统的患者之间进行沟通。我们的中心假设是中风 可以通过以下方法改进预防：利用所有可用数据，包括SDoH;捕获和 量化社会经济背景下已知和新发现的风险因素之间的协同作用; 移植到其他卫生系统，适应不同的人群。该项目的基本原理是， AF相关卒中风险管理缺乏最佳实施所需的精确度和意识 治疗，因为它没有充分考虑（1）人口多样性，（2）SDoH和差异，（3） 风险因素之间的协同作用，以及（4）新的、新出现的风险因素。核心假设是 通过追求三个具体目标进行测试：1）发现新的临床和社会经济关系， 确定房颤患者的中风风险; 2）开发一种具有社会意识的、基于人工智能的机器， AF患者中的个性化卒中风险;以及3）基准基于AI的社会意识卒中风险 使用PCORnet在不同的卫生系统队列中进行预测，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，以确定新风险标志。第二个目标将侧重于建立小说， 图形模型（PGM），以了解SDoH对AF相关卒中风险的影响。在第三个目标中， 模型将在不同的医疗保健系统中进行测试，以了解可移植性，多样性和偏见。 本申请中提出的研究具有创新性，因为它（1）利用了以下方面的大量可用数据： SDoH，（2）采用更强大且更便携的分析方法来了解风险;以及（3）是 其设计着眼于理解和减少风险预测模型中的差异和偏差。的 拟议的研究是重要的，因为它将改善整个房颤患者的护理，而在 同时解决目前护理标准中的差异和偏见。最终，结果将产生一个 更个性化和公平的方法来预防AF患者的卒中。

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.