Population-level Pulmonary Embolism Outcome Prediction with Imaging and Clinical Data: A Multi-Center Study

利用影像学和临床数据预测人群水平的肺栓塞结果：一项多中心研究

• 批准号: 10687126
• 负责人: CURTIS P LANGLOTZ
• 金额: $ 41.44万
• 依托单位: STANFORD UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-08-01 至 2025-07-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10687126
• 关键词: Acute; Algorithms; Angiography; Anticoagulant therapy; Architecture; Biological Markers; Blood Vessels; Cardiogenic Shock; Caring; Cause of Death; Chest imaging; Clinical; Clinical Data; Code; Collaborations; Computational Technique; Computerized Medical Record; Computers; Computing Methodologies; Data; Data Analytics; Data Set; Diagnosis; Diagnostic; Diagnostic Imaging; Engineering; Environment; Evaluation; Exhibits; Fostering; Funding; Goals; Health Care Costs; Health Insurance Portability and Accountability Act; Healthcare; Heart Arrest; Hemorrhage; Hospitals; Image; Individual; Information Systems; Institution; Intelligence; Laboratories; Learning; Lung; Medical Imaging; Medicine; Methods; Modeling; Morbidity - disease rate; Multicenter Studies; National Heart, Lung, and Blood Institute; Outcome; Outcome Measure; Outpatients; Pathology Report; Patient-Focused Outcomes; Patients; Pharmaceutical Preparations; Population; Pulmonary Embolism; Pulmonary Hypertension; Radiology Specialty; Recurrence; Research; Resuscitation; Risk; Risk Assessment; Scanning; Sensitivity and Specificity; Severities; Site; Source; Statistical Models; Structure; Syndrome; System; Testing; Therapeutic; Time; Training; United States; United States National Library of Medicine; X-Ray Computed Tomography; breast imaging; care delivery; chronic thromboembolic pulmonary hypertension; clinical care; clinical predictors; data de-identification; data repository; deep learning; deep learning model; demographics; design; digital medicine; electronic structure; experience; health care quality; health data; health record; heterogenous data; high risk; hospital readmission; imaging biomarker; imaging study; improved; improved outcome; indexing; learning strategy; mortality; mortality risk; neuroimaging; outcome prediction; patient safety; patient stratification; point of care; precision medicine; predictive modeling; primary outcome; prognostic model; prospective; radiological imaging; risk stratification; secondary outcome; stem

Project Summary Pulmonary embolism (PE) is a leading cause of death in the United States. Risk stratification for acute PE treatment can reduce mortality. Risk scoring systems use clinical and laboratory electronic medical record (EMR) data. In addition, biomarkers on computed tomography imaging can identify which patients with PE are at high risk of death, independent of clinical data. Despite advances in clinical and image-driven scoring systems, improving outcomes in acute PE depends on implementation of patient-specific EMR and imaging data analytic prognostic models at the point of care. The promise of digital medicine stems in part from the hope that by digitizing health data, we can leverage computer information systems to understand and improve care. A method that can make use of these data to predict patient-specific outcomes could not only provide major benefits for patient safety and healthcare quality but also reduce healthcare costs. Unfortunately, most of this information is not yet included in predictive statistical models that clinicians use to improve care delivery. This is because traditional computational methods and techniques are insufficient at accurately analyzing such high volumes of heterogeneous data. The goal of this proposal is to develop an automated precision medicine approach to achieve point-of-care risk stratification for PE patient outcomes using a fusion deep learning strategy that can simultaneously analyze health records and imaging data. An ideal PE risk-scoring system would not only predict mortality, but also assess the risk for the many debilitating long-term consequences of acute PE. Such a system would, therefore, facilitate optimal management and would likely require intelligent use of clinical, laboratory, and imaging data together in order to provide accurate patient -specific risk scoring for multiple PE outcome measures. In order to build a robust model, we propose to apply distributed training of deep learning models across four large US healthcare institutions. By distributing the algorithm rather than the data, we avoid sharing individually identifiable patient information. If successful, this project will be the first endeavor to leverage diagnostic imaging (pixel) data in combination with structured and unstructured EMR data to predict outcomes. We have the ideal research team, experience, and methods to develop an automated risk-scoring system for acute PE patients. Using a powerful combination of clinical, laboratory, and imaging data, this system will provide patient-specific risk scoring for multiple PE outcome measures. Further, this project will foster multi- center collaborations, which will afford us the opportunity to investigate the generalizability of our approach to different populations of PE patients and to train, test, and ultimately deploy our automated predictive model in a variety of clinical environments.

项目摘要 在美国，肺栓塞(PE)是导致死亡的主要原因。急性PE的危险分层 治疗可以降低死亡率。风险评分系统使用临床和实验室电子病历 (EMR)数据。此外，计算机断层成像上的生物标志物可以识别哪些PE患者是 有很高的死亡风险，与临床数据无关。尽管在临床和图像驱动评分方面取得了进展 系统，改善急性PE的预后取决于实施针对患者的EMR和成像 护理点的数据分析预后模型。 数字医疗的前景部分源于这样一种希望，即通过将健康数据数字化，我们可以利用 了解计算机信息系统，提高护理水平。一种可以利用这些数据的方法 预测特定于患者的结果不仅可以为患者的安全和医疗质量提供重大好处 而且还能降低医疗成本。不幸的是，这些信息中的大多数还没有包括在预测性信息中 临床医生用来改善护理服务的统计模型。这是因为传统的计算 在准确分析如此大量的异质数据方面，方法和技术是不够的。 这项提议的目标是开发一种自动化的精确医疗方法，以实现护理点风险 使用融合深度学习策略对PE患者的预后进行分层，该策略可以同时分析 健康记录和成像数据。一个理想的PE风险评分系统不仅可以预测死亡率，还可以 评估急性PE的许多衰弱的长期后果的风险。这样的系统将， 因此，促进最佳管理，可能需要智能地使用临床、实验室和 将成像数据放在一起，以便为多个PE结果提供准确的特定于患者的风险评分 措施。为了建立一个健壮的模型，我们提出应用深度学习模型的分布式训练 横跨美国四家大型医疗机构。通过分发算法而不是数据，我们避免了 共享可单独识别的患者信息。如果成功，这个项目将是第一个努力 利用诊断成像(像素)数据与结构化和非结构化EMR数据相结合来预测 结果。 我们拥有理想的研究团队、经验和方法来开发自动风险评分系统 急性PE患者。利用临床、实验室和成像数据的强大组合，该系统将 为多个PE结果测量提供特定于患者的风险评分。此外，该项目将促进多个 中心协作，这将使我们有机会调查我们的方法的普适性 对不同人群的PE患者进行培训、测试并最终部署我们的自动化预测模型 不同的临床环境。

项目成果

MedShift: Automated Identification of Shift Data for Medical Image Dataset Curation

MedShift：自动识别医学图像数据集管理的移位数据

• DOI: 10.1109/jbhi.2023.3275104
• 发表时间: 2023
• 期刊: IEEE Journal of Biomedical and Health Informatics
• 影响因子: 7.7
• 作者: Guo, Xiaoyuan;Gichoya, Judy Wawira;Trivedi, Hari;Purkayastha, Saptarshi;Banerjee, Imon
• 通讯作者: Banerjee, Imon

Developing medical imaging AI for emerging infectious diseases.

• DOI: 10.1038/s41467-022-34234-4
• 发表时间: 2022-11-18
• 期刊: Nature communications
• 影响因子: 16.6

President Biden's Executive Order on Artificial Intelligence-Implications for Health Care Organizations.

拜登总统关于人工智能的行政命令——对医疗保健组织的影响。

• DOI: 10.1001/jama.2023.25051
• 发表时间: 2024
• 期刊: JAMA
• 作者: Mello,MichelleM;Shah,NigamH;Char,DantonS
• 通讯作者: Char,DantonS

Efficient adversarial debiasing with concept activation vector - Medical image case-studies.

使用概念激活向量进行有效的对抗性去偏 - 医学图像案例研究。

• DOI: 10.1016/j.jbi.2023.104548
• 发表时间: 2024
• 期刊: Journal of biomedical informatics
• 影响因子: 4.5
• 作者: Correa,Ramon;Pahwa,Khushbu;Patel,Bhavik;Vachon,CelineM;Gichoya,JudyW;Banerjee,Imon
• 通讯作者: Banerjee,Imon