[R21] Integrated computer-aided, point-of-care ultrasound for tuberculosis screening

[R21] 用于结核病筛查的集成计算机辅助床旁超声

• 批准号: 10511853
• 负责人: Yingda Linda Xie
• 金额: $ 22.31万
• 依托单位: RBHS-NEW JERSEY MEDICAL SCHOOL
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-06-16 至 2023-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10511853
• 关键词: Address; Adult; Algorithms; Artificial Intelligence; Artificial Intelligence platform; Biological Assay; COVID-19 screening; Cessation of life; Characteristics; Clinical; Clinics and Hospitals; Communicable Diseases; Communities; Computer Assisted; Computer-Assisted Diagnosis; Computers; Data; Data Set; Decision Support Systems; Detection; Development; Devices; Diagnosis; Diagnostic tests; Early Intervention; Early treatment; Epidemiology; Equipment; Evaluation; Future; Goals; Health Services Accessibility; Health care facility; Household; Image; Image Analysis; Improve Access; Individual; Infection; Laboratories; Lung; Methodology; Methods; Microbiology; Morbidity - disease rate; Mycobacterium tuberculosis; Outcome; Parents; Performance; Phenotype; Pneumonia; Population; Prevalence; Protocols documentation; Pulmonary Tuberculosis; Radiation exposure; Radiology Specialty; Rapid diagnostics; Reporting; Reproducibility; Research; Resource-limited setting; Resources; Respiratory Tract Infections; Risk; Specificity; Sputum; Staging; Standardization; Supervision; Support System; Symptoms; System; Technology; Testing; Thoracic Radiography; Training; Triage; Tuberculosis; Tuberculosis diagnosis; Ultrasonography; base; case finding; cohort; computer aided detection; cost; deep learning algorithm; deep learning model; detection platform; digital; disability; evidence base; health care service; high risk; improved; indexing; machine learning model; mortality; point of care; point of care testing; portability; protocol development; scale up; screening; tool; transmission process; ultrasound

PROJECT ABSTRACT Mycobacterium tuberculosis (TB, Mtb) is one of the leading causes of infectious disease mortality worldwide, with a persistent gap in global case detection. In 2020, only 5.8 million of the estimated 9.9 million individuals who became ill with TB were diagnosed and reported. Active case finding efforts to find these undetected cases by screening individuals in the community for TB is not feasible in most resource-limited settings due to the large number needed to screen with sputum microbiologic tests to detect one case. A rapid, highly sensitive point-of-care test that can be performed in the field to screen for high-risk individuals can improve access to active case finding by substantially reducing the number needed to test. Despite progress in the field, there remains a lack of such tests that achieve both the point-of-care characteristics accessible for large-scale screening and the target accuracy profiles for a triage or rapid diagnostic test. Point-of-care ultrasound (POCUS) devices are low-cost, portable, avoid radiation exposure, and do not require trained radiologic staff, making them amenable to wide scale with minimal resource needs. Lung ultrasound has been found to diagnose adult pneumonia at a comparable to improved performance level than chest-X-ray and holds promise as a TB triage test. Further application of artificial intelligence-based computer aided diagnosis algorithms can further improve reproducibility by automating and standardizing image interpretation, and potentially improve performance as evolving AI platforms train on growing datasets. To explore the utility of POCUS CAD for TB screening, we will conduct a systematic evaluation of POCUS for TB screening among TB household contacts across a spectrum of early to advanced infection phenotypes. We will additionally pilot an integrated computer-aided detection algorithm for POCUS-based detection of pulmonary TB with the integration of clinical, exposure, and prevalence data to explore whether these variables can increase specificity for TB. We will then evaluate performance profiles using both deconstructed feature-based analysis and deep-learning algorithms to inform the potential utility of POCUS as a TB triage test to enable widespread active case finding for the millions of undiagnosed TB cases.

项目摘要 结核分枝杆菌 (TB, Mtb) 是传染病死亡的主要原因之一 全球病例发现方面持续存在差距。到 2020 年，预计只有 580 万 990 万名结核病患者得到诊断和报告。积极寻找病例 通过对社区中的个人进行结核病筛查来发现这些未被发现的病例的努力并不可行 由于需要大量痰液筛查，因此在大多数资源有限的环境中都是可行的 微生物学测试以发现一例。一种快速、高度灵敏的现场检测，可以 在现场筛查高危人群可以提高主动发现病例的机会 大幅减少测试所需的数量。尽管该领域取得了进展，但仍然存在 缺乏此类测试来实现大规模可实现的即时护理特征 用于分类或快速诊断测试的筛选和目标准确度曲线。现场护理 超声 (POCUS) 设备成本低、便携、避免辐射暴露，并且不需要 训练有素的放射工作人员，使他们能够以最少的资源需求进行大规模的工作。肺 已发现超声诊断成人肺炎的速度与改良后的速度相当 性能水平高于胸部 X 光检查，有望作为结核病分类测试。进一步应用 基于人工智能的计算机辅助诊断算法可以进一步提高 通过自动化和标准化图像解释来提高可重复性，并有可能提高 随着不断发展的人工智能平台在不断增长的数据集上进行训练，性能不断提高。探索 POCUS 的实用性 CAD用于结核病筛查，我们将对POCUS用于结核病筛查进行系统评估 结核病家庭接触者涵盖各种早期到晚期感染表型。我们将 另外还试验了一种用于基于 POCUS 的检测的集成计算机辅助检测算法 结合临床、暴露和患病率数据来探讨肺结核是否 这些变量可以提高结核病的特异性。然后，我们将使用以下方法评估性能概况 解构基于特征的分析和深度学习算法来告知潜力 POCUS 作为结核病分类测试的实用性，可以为数百万患者广泛发现活跃病例 未确诊的结核病病例。