Clinical Decision Support for Assessing Pulmonary Embolism using Machine Learning

使用机器学习评估肺栓塞的临床决策支持

• 批准号: 10381875
• 负责人: Kevin M. Kramer
• 金额: $ 101.86万
• 依托单位: MINNESOTA HEALTHSOLUTIONS CORPORATION
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-02-17 至 2024-01-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10381875
• 关键词: 3-Dimensional; Accident and Emergency department; Accounting; Acute; Agreement; Angiography; Area; Artificial Intelligence; Automated Clinical Decision Support; Caliber; Cause of Death; Cessation of life; Chest; Chronic; Clinical; Complication; Computer software; Detection; Diagnosis; Embolism; Epidemiology; Europe; Hospitals; Image Analysis; Incidence; Intervention; Lead; Left ventricular structure; Location; Lung; Machine Learning; Manuals; Measurement; Measures; Medical Imaging; Minnesota; North America; Obstruction; Patient Care; Patients; Phase; Physicians; Pulmonary Embolism; Pulmonary Hypertension; Pulmonary vessels; Radiology Specialty; Right ventricular strain; Right ventricular structure; Risk; Software Tools; Speed; Staging; System; Thrombus; Time; Training; Trees; Universities; Visualization; X-Ray Computed Tomography; chronic thromboembolic pulmonary hypertension; clinical biomarkers; clinical decision support; convolutional neural network; improved; machine learning method; mortality; radiologist; research and development; software systems; support tools; tool

Project Summary/Abstract Minnesota HealthSolutions (MHS) proposes a Phase II project to develop and validate a software product capable of automatically detecting and staging pulmonary embolisms (PEs) using clinically routine pulmonary CT angiograms (CTAs). The proposed system will combine state-of-the-art machine learning methods and the clinical expertise at Duke University into a system that integrates seamlessly into the Radiology workflow and standard patient care path to improve the treatment decisions of physicians in the emergency department. Pulmonary embolism is the third most common cause of death in hospital patients with an estimated incidence of 1 per 1,000 patients. CTAs are routinely used to detect PE today; however, there is significant variability in the detection rate among radiologists using CTA. Furthermore, despite the strong evidence that the RV/LV ratio is an important clinical biomarker it is rarely measured quantitatively in practice. A successful completion of this project would provide a workflow-integrated tool capable of faster PE detection and more accurate staging of right heart strain to guide the physician’s treatment decision.

项目摘要/摘要 明尼苏达州HealthSolutions（MHS）提出了II期项目，以开发和验证软件产品 能够使用临床常规肺部自动检测和分期肺栓子（PE） CT血管造影（CTA）。提出的系统将结合最新的机器学习方法和 杜克大学的临床专业知识成为一个系统，该系统将无缝集成到放射学工作流中 改善急诊科医师治疗决策的标准患者护理路径。 肺栓塞是医院患者中第三大常见的死亡原因 每1000名患者的发病率为1。 CTA通常用于今天检测PE；但是，有重要的 使用CTA的放射学家检测率的可变性。此外，dospite的有力证据表明 RV/LV比是重要的临床生物标志物，在实践中很少进行定量测量。成功 该项目的完成将提供一个能够更快检测的工作流量集成工具 准确的右心脏应变阶段，以指导身体的治疗决策。