Deep learning Based Phenotyping and Treatment Optimization for Heart Failure with Preserved Ejection Fraction

基于深度学习的射血分数保留的心力衰竭表型分析和治疗优化

基本信息

批准号：
10592341
负责人：
Quanzheng Li
金额：
$ 58.35万
依托单位：
MASSACHUSETTS GENERAL HOSPITAL
依托单位国家：
美国
项目类别：
财政年份：
2022
资助国家：
美国
起止时间：
2022-03-15 至 2026-02-28
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10592341
关键词：
3-Dimensional Aortic Valve Stenosis Big Data Biological Markers Cardiac Chronic Obstructive Pulmonary Disease Clinical Clinical Data Clinical Trials Code Communities Complex Computer software Data Development Diabetes Mellitus Diagnosis Diagnostic Dimensions Disease Disparate EFRAC Economic Burden Electronic Health Record Environmental Risk Factor Failure Goals Heart Heart failure Hospitalization Hypertension Image Image Analysis Knowledge Laboratories Learning Life Style Machine Learning Magnetic Resonance Malignant Neoplasms Measurement Methods Modeling Morbidity - disease rate Morphology Nature Obesity Epidemic Organ Outcome Patient imaging Patients Performance Pharmaceutical Preparations Phenotype Physicians Pilot Projects Population Prevalence Procedures Prognosis Psychological reinforcement Public Health Publishing Quality of life Radiology Specialty Recommendation Recording of previous events Reporting Research Resources Sepsis Series Source Code Surface Symptoms Syndrome Techniques Therapeutic Treatment Efficacy Validation Work aging population automated analysis biomarker identification cardiac magnetic resonance imaging clinical decision support clinical efficacy clinical investigation clinically significant comorbidity computerized data processing deep learning deep reinforcement learning effective therapy electronic health information feature extraction heart imaging image processing imaging biomarker improved individualized medicine lifestyle factors longitudinal analysis magnetic resonance imaging biomarker mortality multimodality novel novel therapeutics open data optimal treatments personalized medicine preservation reconstruction recurrent neural network risk stratification shape analysis symposium targeted treatment treatment optimization treatment planning treatment strategy trend

项目摘要

Heart failure with preserved ejection fraction (HFpEF) is a major public health problem that is rising in prevalence with the aging population and the epidemics of obesity, diabetes, and hypertension. HFpEF accounts for around 50% of all heart failure (HF) cases with a prevalence of at least 3 million in the U.S. HFpEF is associated with high morbidity and mortality. After HF hospitalization, the 5-year survival of HFpEF is a dismal 35%, which is worse than most cancers. In addition, quality of life in HFpEF is as poor or worse than HF with reduced ejection fraction (HFrEF). A series of large-scale clinical trials has been conducted, but most of them only provided neutral result and failed to prove the efficacy of treatments. The alarming trend of HFpEF with lack of effective therapies for patients constitutes a major public health problem. Recent studies have attributed this failure to distinct systemic nature of HFpEF syndrome and proposing sub-phenotypes within the heterogeneous HFpEF syndrome, which highlighted the increasing need for better-targeted therapies to specific HFpEF subtypes. The seemingly disparate but complex interrelated phenotypes, along with comorbidities, lifestyle and environmental factors, make the multi-organ syndrome best beneficial from a big data approach. However, conventional studies usually only included limited cross-sectional clinical symptoms, lab results and/or gross measurements on cardiac imaging to investigate HFpEF, overlooking the rich temporal information from electronic health record (EHR) and detailed spatial information reserved in imaging. In this proposal, we will introduce advance shape analysis method to extract novel image features and biomarker from CMR images and validate at population level (Aim 1). We will then combine image information with multi-dimensional temporal EHR data to jointly identify clinically significant HFpEF subclasses (i.e. phenotyping) using state-of-art machine learning technique (Aim 2). Towards therapeutic goals based on phenotyping, we will further investigate optimal treatment strategies with current available agents using deep reinforcement learning (RL) based on massive EHR data to meet the pressing need before ongoing trials provide sufficient evidence on new drugs with proved clinical efficacy (Aim 3). Furthermore, we will develop an online, open- access platform to facilitating the sharing of code, data and knowledge of this study (Aim 4). We believe this research can improve our understanding, phenotyping and management of HFpEF, which might positively ease the clinical and economic burdens in turn both in U.S. and worldwide.

射血分数保留的心力衰竭（HFpEF）是一个主要的公共卫生问题随着人口老龄化以及肥胖、糖尿病和糖尿病的流行，这种疾病的患病率正在上升高血压。 HFpEF 约占所有心力衰竭 (HF) 病例的 50%，且患病率较高在美国，至少有 300 万 HFpEF 与高发病率和死亡率相关。高频后住院后，HFpEF 的 5 年生存率仅为 35%，比大多数癌症还要糟糕。此外，HFpEF 的生活质量与射血分数降低的 HF 一样差甚至更差（HFrEF）。已经进行了一系列大规模的临床试验，但大多数仅提供结果为中性，未能证明治疗的有效性。 HFpEF 的惊人趋势患者缺乏有效的治疗方法构成了一个重大的公共卫生问题。最近的研究将这种失败归因于 HFpEF 综合征的独特系统性质并提出了异质性 HFpEF 综合征的亚表型，其中强调了对特定 HFpEF 亚型的更好靶向治疗的需求日益增长。看似不同但复杂的相互关联的表型，以及合并症、生活方式和环境因素使多器官综合症从大数据方法中获益最多。然而，传统研究通常只包括有限的横断面临床症状，实验室结果和/或心脏成像的粗略测量来研究 HFpEF，忽略了来自电子健康记录 (EHR) 的丰富时间信息和详细空间信息保留在成像中。在本提案中，我们将引入先进的形状分析方法来提取新颖的图像来自 CMR 图像的特征和生物标志物并在人群水平上进行验证（目标 1）。我们随后将将图像信息与多维时态EHR数据相结合，共同进行临床识别使用最先进的机器学习技术确定重要的 HFpEF 子类（即表型）（目标 2）。为了实现基于表型分析的治疗目标，我们将进一步研究最佳治疗方案使用基于深度强化学习 (RL) 的当前可用药物的治疗策略在正在进行的试验提供足够的证据之前，利用大量的电子病历数据来满足迫切的需求开发具有临床疗效的新药（目标 3）。此外，我们将开发一个在线、开放的访问平台，以促进本研究的代码、数据和知识共享（目标 4）。我们相信这项研究可以提高我们对 HFpEF 的理解、表型分析和管理，这可能会反过来积极减轻美国和全世界的临床和经济负担。