Opportunistic Atherosclerotic Cardiovascular Disease Risk Estimation at Abdominal CTs with Robust and Unbiased Deep Learning

通过稳健且公正的深度学习进行腹部 CT 机会性动脉粥样硬化性心血管疾病风险评估

• 批准号: 10636536
• 负责人: Akshay Chaudhari
• 金额: $ 62.27万
• 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: 2023-09-01 至 2028-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10636536
• 关键词: 3-Dimensional; Abdomen; Accident and Emergency department; Address; Adipose tissue; Adult; Affect; Algorithms; American; Aorta; Atherosclerosis; Body Composition; Cardiology; Cardiovascular Diagnostic Techniques; Cardiovascular Diseases; Cardiovascular system; Cessation of life; Classification; Clinic; Clinical; Computed Tomography Scanners; Computerized Medical Record; Data; Data Set; Detection; Early Diagnosis; Eligibility Determination; Ensure; Equation; Equity; Ethnic Origin; Event; Exhibits; Future; Goals; Image; Insurance; Intervention; Label; Liver; Measures; Medical Imaging; Methods; Modeling; Morbidity - disease rate; Morphologic artifacts; Muscle; Myocardial Infarction; Myocardial Ischemia; Patient risk; Patients; Performance; Phenotype; Pilot Projects; Population; Population Heterogeneity; Primary Prevention; Protocols documentation; Quality Control; Race; Radiation; Radiology Specialty; Reader; Recommendation; Recording of previous events; Risk; Risk Estimate; Scanning; Site; Stroke; Subgroup; Techniques; Testing; Three-Dimensional Imaging; Tissues; Training; Uncertainty; Validation; Variant; Vascular calcification; Work; X-Ray Computed Tomography; abdominal CT; automated segmentation; bone; burden of illness; calcification; cardiometabolic risk; cardiometabolism; cardiovascular disorder prevention; cardiovascular disorder risk; cardiovascular health; cohort; comorbidity; contrast enhanced computed tomography; cost; deep learning; deep learning algorithm; deep learning model; digital twin; early screening; efficacious treatment; health equity; heart disease risk; high risk; imaging study; improved; innovation; learning strategy; lifestyle intervention; mortality; multimodal data; multimodality; patient stratification; patient subsets; pharmacologic; predictive modeling; prevent; quantitative imaging; radiologist; risk prediction; segmentation algorithm; socioeconomics; statistics; stroke event; success; supervised learning; tool

PROJECT SUMMARY Atherosclerotic cardiovascular disease (ASCVD) is the main cause of morbidity and mortality worldwide, and affects 18+ million adults nationally. However, 80% of ASCVD deaths may be prevented with prompt intervention following early screening for ASCVD risk – a powerful rationale for the unmet need of accurate subclinical ASCVD diagnoses. Thus, in this study we assess whether a deep learning (DL)-based analysis of pre-existing abdominal computed tomography (CT) scans paired with electronic medical records (EMR) improves prediction of cardiovascular death, myocardial infarction, and stroke in a large multi-site primary prevention population. We will conduct this study in a large, diverse, real-world population with an external validation to ascertain whether we can improve upon the clinically-utilized pooled cohort equations (PCE) that have numerous shortcomings. 20+ million abdominal CT scans performed annually in the US. While these scans answer specific clinical questions, quantitative information related to tissue phenotypes associated with cardiometabolic risk is simply not evaluated. DL algorithms can be used to quantify body composition metrics for adipose tissue, muscle, bone, liver, and vascular calcifications, which can all be used to improve upon the PCE for determining cardiovascular events. In aim 1 of our proposal, we will build automated segmentation algorithms with a built-in quality control mechanism to extract these body composition metrics in 125,000+ diverse subjects to ascertain population-level normative values of tissue size and radiodensity. In aim 2, we will augment the PCE covariates with these body composition values and additional EMR features for predicting ASCVD risk with advanced DL models. Moreover, we will devise new algorithmic approaches for improving health equity by ensuring similar model performance across patient sub-groups of PCE eligibility, race/ethnicity, insurance type, and CT scanner make/model. In aim 3, we will build a new ASCVD risk estimator that directly uses 3D imaging data. We will augment this end-to-end prediction approach by integrating multi-modal models that leverage both imaging data and EMR data. Realizing the need for improved explainability of DL solutions, we will build digital twins of each subject to describe why model predictions are being made and what changes a patient could make to lower ASCVD risk. We will train all models on data from Stanford (25k patients), test on data from Stanford (8k patients), and externally validate the models on data from three Mayo Clinic sites (20k+ patients) to assess the generalizability of our tools. We have assembled an inter-disciplinary MPI team of DL experts, cardiologists, and abdominal radiologists to build such ASCVD risk models. We develop innovative tools to improve accuracy, generalizability, bias, and explainability of DL-based ASCVD risk models. Our long-term goal is to enable early detection of silent atherosclerosis and trigger interventions that may ultimately prevent over 800,000 death, myocardial infarction, and stroke events in diverse Americans annually.

项目概要 动脉粥样硬化性心血管疾病（ASCVD）是全世界发病和死亡的主要原因， 然而，通过及时干预，80% 的 ASCVD 死亡是可以预防的。 早期筛查 ASCVD 风险——准确的亚临床需求未得到满足的有力理由 因此，在本研究中，我们评估是否对已有的情况进行基于深度学习 (DL) 的分析。 腹部计算机断层扫描 (CT) 扫描与电子病历 (EMR) 相结合可改善预测 大型多站点一级预防人群中心血管死亡、心肌梗塞和中风的发生率。 将在大量、多样化的现实世界人群中进行这项研究，并进行外部验证以确定是否 我们可以改进临床使用的合并队列方程（PCE），但它有很多缺点。 美国每年进行超过 2000 万次腹部 CT 扫描，而这些扫描可回答特定的临床问题。 问题，与心脏代谢风险相关的组织表型相关的定量信息很简单 未评估的 DL 算法可用于量化脂肪组织、肌肉、骨骼的身体成分指标。 肝脏和血管钙化，这些都可以用来改善心血管测定的 PCE 在我们提案的目标 1 中，我们将构建具有内置质量控制的自动分割算法。 提取超过 125,000 名不同受试者的身体成分指标以确定人群水平的机制 在目标 2 中，我们将增强组织大小和放射密度的标准值与这些物体的 PCE 协变量。 成分值和附加 EMR 功能，用于使用先进的 DL 模型预测 ASCVD 风险。 我们将设计新的算法方法，通过确保类似的模型性能来改善健康公平 涵盖 PCE 资格、种族/民族、保险类型和 CT 扫描仪品牌/型号的患者亚组。 3、我们将构建一个直接使用 3D 成像数据的新 ASCVD 风险估计器，我们将增强这种端到端的能力。 通过集成利用成像数据和 EMR 数据的多模态模型进行预测。 由于需要提高深度学习解决方案的可解释性，我们将为每个主题构建数字孪生来描述原因 模型预测正在进行中，以及患者可以做出哪些改变来降低 ASCVD 风险。 我们将根据斯坦福大学（25,000 名患者）的数据训练所有模型，对斯坦福大学（8,000 名患者）的数据进行测试，并 根据来自三个 Mayo Clinic 站点（超过 20,000 名患者）的数据对模型进行外部验证，以评估普遍性 我们组建了一支由 DL 专家、心脏病专家和腹部专家组成的跨学科 MPI 团队。 我们开发创新工具来提高准确性、普遍性、 基于深度学习的 ASCVD 风险模型的偏差和可解释性我们的长期目标是实现沉默的早期检测。 动脉粥样硬化并引发干预措施，最终可能预防超过 80 万人死亡、心肌梗死、 每年都有不同美国人发生中风事件。