A multi-modal approach for efficient, point-of-care screening of hypertrophic cardiomyopathy

一种高效、即时筛查肥厚型心肌病的多模式方法

基本信息

批准号：
10749588
负责人：
Evangelos Oikonomou
金额：
$ 7.63万
依托单位：
YALE UNIVERSITY
依托单位国家：
美国
项目类别：
财政年份：
2023
资助国家：
美国
起止时间：
2023-09-01 至 2026-08-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10749588
关键词：
Address Affect Algorithms Amyloid Anatomy Artificial Intelligence Awareness Board Certification Cardiac Cardiovascular system Case/Control Studies Clinical Clinical Informatics Communities Computer Models Computer Vision Systems Computing Methodologies Consumption Data Data Set Detection Development Devices Diagnosis Diagnostic tests Disease Early Diagnosis Echocardiography Electrocardiogram Electronic Health Record Eligibility Determination Emergency department visit Ensure Event Fellowship General Population Generations Goals Health Health system Hypertrophic Cardiomyopathy Image Individual Label Lead Learning Left Ventricular Hypertrophy Libraries Machine Learning Magnetic Resonance Magnetic Resonance Imaging Maps Medical Informatics Mentors Mentorship Methods Modality Modeling Morbidity - disease rate Morphologic artifacts Noise Outcome Pathway interactions Patients Performance Phenotype Population Population Heterogeneity Postdoctoral Fellow Prevalence Process Provider Randomized, Controlled Trials Research Resource-limited setting Retrospective cohort Risk Screening procedure Signal Transduction Specialized Center Structure Technology Testing Time Training Two-Dimensional Echocardiography Ultrasonography advanced analytics autoencoder biobank cardiac magnetic resonance imaging career clinical heterogeneity computer science computing resources cost deep learning model denoising design diagnostic algorithm empowerment experience feasibility testing genetic testing heart dimension/size hypertensive heart disease implementation science improved improved outcome inherited cardiomyopathy machine learning algorithm medical schools mortality multimodality novel novel therapeutics point of care portability prevent primary care clinic prospective recruit screening screening program simulation skills spectrograph sudden cardiac death supervised learning tool two-dimensional ultrasound underserved community user-friendly vision science wearable device

项目摘要

PROJECT SUMMARY Hypertrophic cardiomyopathy (HCM) is the most common inherited cardiomyopathy, affecting up to 0.5% of the general population. HCM confers an increased risk of morbidity and mortality but remains clinically underrecognized. Traditionally, the diagnosis of HCM has relied on comprehensive assessment by echocardiography or magnetic resonance imaging, modalities which are not available for screening of the general population. As novel disease-modifying therapies emerge, there is a need for efficient strategies to improve HCM screening outside specialized centers. The research proposed in this post-doctoral fellowship will leverage advanced computational methods and the expanding availability of wearable and portable technologies to adapt machine learning algorithms for the efficient, point-of-care screening of HCM. In Aim 1, the applicant proposes to use a large electrocardiographic (ECG) library to adapt ECG signals for use with wearable devices and fine-tune those signals for the detection of HCM. Noising-denoising algorithms and cross-modal pre-training with corresponding echocardiographic and cardiac magnetic resonance videos will ensure that the models are robust to noise and learn key representations of the HCM phenotype, respectively. In Aim 2, single-view, two- dimensional echocardiographic videos will be extracted, pre-processed, and augmented to simulate point-of- care image acquisition. Through a self-supervised, contrastive pre-training approach, the applicant will build data-efficient computational models to screen for HCM based on echocardiographic videos reflecting the quality and unique challenges seen with point-of-care use. In Aim 3, the applicant proposes a prospective case-control study of patients with and without HCM, who will undergo point-of-care electrocardiography and echocardiography, to test the feasibility and real-world performance of a two-stage HCM screening protocol based on Aims 1 and 2. The proposal is supported by strong mentorship from experts in biomedical machine learning, computer vision, and implementation science. The Yale School of Medicine offers the facilities and computational resources necessary to accomplish the research goals, whereas the Yale-New Haven Health electronic health record and well-phenotyped echocardiographic and ECG libraries ensure access to a diverse and representative population. The proposed period of mentored research will support the applicant’s training in computer vision, advanced analytics, and medical informatics. The experience, data, and skillset acquired during this period will further support the applicant in preparing for a successful career in the implementation science of cardiovascular artificial intelligence technologies.

项目概要肥厚型心肌病 (HCM) 是最常见的遗传性心肌病，影响高达 0.5% 的患者 HCM 会增加普通人群的发病率和死亡率，但在临床上仍然存在。传统上，HCM 的诊断依赖于综合评估。超声心动图或磁共振成像，这些方法无法用于筛查随着新的疾病缓解疗法的出现，需要有效的策略来治疗。该博士后奖学金提出的研究将改善专业中心外的 HCM 筛查。利用先进的计算方法和可穿戴和便携式技术的不断扩展的可用性在目标 1 中，申请人采用机器学习算法来进行高效的 HCM 护理点筛查。建议使用大型心电图 (ECG) 库来调整心电图信号以用于可穿戴设备并对这些信号进行微调以检测 HCM 的噪声-去噪算法和跨模式预训练。具有相应的超声心动图和心脏磁共振视频将确保模型分别在目标 2、单视图、双视图中对噪声具有鲁棒性并学习 HCM 表型的关键表示。三维超声心动图视频将被提取、预处理和增强以模拟点通过自我监督的对比预训练方法，申请人将建立护理图像采集。基于反映质量的超声心动图视频的数据高效计算模型来筛查 HCM 在目标 3 中，申请人提出了前瞻性病例对照。对患有和不患有 HCM 的患者进行的研究，这些患者将接受护理点心电图检查和超声心动图，测试两阶段 HCM 筛查方案的可行性和实际性能基于目标 1 和 2。该提案得到生物医学机器专家的大力支持耶鲁大学医学院提供学习、计算机视觉和科学实施的设施和服务。完成研究目标所需的计算资源，而耶鲁-纽黑文健康中心电子健康记录和表型良好的超声心动图和心电图库确保获得多样化的信息拟议的指导研究期将支持申请人的培训。计算机视觉、高级分析和医学信息学。这段时期将进一步支持申请人为在实施科学领域取得成功的职业生涯做好准备心血管人工智能技术。