Machine Learning for Ventricular Arrhythmias

室性心律失常的机器学习

• 批准号: 10658931
• 负责人: Sanjiv M Narayan
• 金额: $ 65.76万
• 依托单位: STANFORD UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-07-01 至 2027-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10658931
• 关键词: Ablation; Affect; Age; Anti-Arrhythmia Agents; Area Under Curve; Basic Science; Big Data; Biological; Biomedical Engineering; Caring; Classification; Clinical; Clinical Data; Clinical Sciences; Clinical Trials; Combined Modality Therapy; Computer Models; Computers; Data; Data Science; Data Set; Databases; Diabetes Mellitus; Diagnostic; Diffusion; Disease; Dizziness; Electrophysiology (science); FAIR principles; Fiber; Fibrosis; Gadolinium; Genetic; Genomics; Heart; Heart Arrest; Hospitalization; Image; Individual; Institution; Intelligence; Interruption; Label; Laboratories; Learning; Lesion; Life; Machine Learning; Magnetic Resonance; Magnetic Resonance Imaging; Methods; Modeling; Natural Language Processing; Patients; Pharmaceutical Preparations; Physicians; Physics; Population; Population Sciences; Predisposition; Recurrence; Registries; Risk; Strategic Planning; Syncope; Testing; Training; Translational Research; United States; United States National Institutes of Health; Ventricular Arrhythmia; Ventricular Fibrillation; Ventricular Tachycardia; clinical imaging; clinical phenotype; clinical predictors; comorbidity; complex data; computational pipelines; data visualization; diverse data; heart rhythm; improved; improved outcome; individual patient; machine learning prediction; mortality; non-invasive imaging; novel; personalized medicine; predicting response; predictive modeling; prevent; response; statistics; structural determinants; success; tool

Project Summary Ventricular tachycardia (VT) and fibrillation are leading causes of cardiac arrest, dizziness, syncope and hospitalization in the United States and worldwide. However, the management of patients at risk for VT remains suboptimal despite scientific discoveries from basic to population science. In particular, there is no framework to estimate which patients with VT are likely to respond to anti- arrhythmic medications or ablation. Therapy is thus empirical. There is great excitement to use analysis of “big data” to personalize VT therapy, but this has not yet improved outcomes. This project develops a novel computational approach to personalize VT therapy that combines machine learning in large registries with computational models. Machine learning will be applied to data across biological scales that span bedside, laboratory and non-invasive imaging, to predict which patients are likely to respond to therapy. Computer models will be used to estimate if a given patient's heart is likely to support VT before versus after therapy. We will validate results in large external registries from different Institutions. We have 3 specific aims: (1) To develop a computational pipeline to predict response to VT ablation using bedside, laboratory and non-invasive imaging; (2) To use machine learning of clinical data and non-invasive imaging to identify which patients with VT will respond to anti- arrhythmic medications in a large database; (3) To combine computational approaches to estimate the relative likelihood that a given patient will respond to various forms of therapy. Results from each Aim will be tested in independent external registries. We will probe computational models to identify clinical phenotypes that could be applied at the bedside. This project will provide immediate clinical impact for patients with VT. We will combine machine learning with physics-based computer models in large registries at Stanford and External centers. We will reduce computational bias using FAIR methods (Findable, Accessible, Interoperable, and Reusable), and make tools freely available per the 2018 NIH Strategic Plan for Data Science. Our team comprises experts in clinical and basic electrophysiology, imaging, machine learning, bioengineering and statistics. The project is very feasible.

项目摘要 室性心动过速（VT）和纤维性颤动是心脏骤停、头晕、 在美国和世界范围内发生晕厥和住院。然而，患者的管理 尽管从基础科学到人口科学都有科学发现，但室性心动过速的风险仍然不理想。在 特别是，没有框架来估计哪些VT患者可能对抗- 药物治疗或消融。因此，治疗是经验性的。使用分析令人非常兴奋 “大数据”来个性化VT治疗，但这尚未改善结果。 该项目开发了一种新颖的计算方法来个性化VT治疗， 在大型注册中心使用计算模型进行机器学习。机器学习将应用于数据 跨越床边，实验室和非侵入性成像的生物尺度，以预测 患者可能对治疗有反应。计算机模型将用于估计给定患者的 心脏在治疗前后可能支持VT。我们将在大型外部 不同机构的注册。我们有3个具体目标：（1）开发一个计算管道， 使用床旁、实验室和非侵入性成像预测VT消融的反应;（2）使用机器 学习临床数据和非侵入性成像，以确定哪些VT患者对抗- （3）结合联合收割机的计算方法， 给定患者将对各种形式的治疗作出反应的相对可能性。每个目标的结果将 在独立的外部注册中心进行测试。我们将探索计算模型来识别临床 可以应用于临床的表型。 该项目将为室性心动过速患者提供即时的临床影响。我们将联合收割机 在斯坦福大学和外部中心的大型注册中心学习基于物理的计算机模型。我们将 使用FAIR方法（可查找、可解释、可互操作和可重用）减少计算偏差， 并根据2018年NIH数据科学战略计划免费提供工具。我们的团队包括 临床和基础电生理学、成像、机器学习、生物工程和统计学专家。 这个项目是非常可行的。