Automated lung sound analysis to improve the clinical diagnosis of pulmonary tuberculosis in children

自动肺音分析提高儿童肺结核的临床诊断

• 批准号: 10717389
• 负责人: Devan Jaganath
• 金额: $ 62.02万
• 依托单位: UNIVERSITY OF CALIFORNIA, SAN FRANCISCO
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-15 至 2028-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10717389
• 关键词: 10 year old; 5 year old; Address; Adult; Airway Disease; Algorithms; Artificial Intelligence; Cessation of life; Chest; Child; Childhood; Classification; Clinical; Clinical Data; Consensus; Data; Detection; Diagnosis; Diagnostics Research; Disease; Early Diagnosis; Early treatment; Enrollment; Evaluation; Funding; Gambia; HIV; Health Status; Health care facility; Infrastructure; Lower respiratory tract structure; Modeling; Performance; Physicians; Pilot Projects; Pneumonia; Pulmonary Tuberculosis; Radiology Specialty; Reader; Resource-limited setting; Respiratory Disease; Respiratory Sounds; Respiratory Tract Diseases; Risk Factors; Role; Sensitivity and Specificity; Services; Signs and Symptoms; Site; South Africa; Specificity; Specimen; Sputum; Standardization; Stethoscopes; Subgroup; Symptoms; Testing; Thoracic Radiography; Time; Training; Triage; Tuberculosis; Tuberculosis diagnosis; Uganda; Underweight; United States National Institutes of Health; Work; World Health Organization; artificial intelligence algorithm; clinical care; clinical diagnosis; cohort; deep learning model; digital; digital health; early childhood; experience; girls; improved; laboratory facility; lung development; machine learning model; mortality; novel; point of care; prevent; prospective; radiological imaging; radiologist; respiratory; tool; tuberculosis diagnostics; tuberculosis treatment; wireless

PROJECT SUMMARY The majority of deaths from childhood tuberculosis (TB) are in children not initiated on treatment, highlighting the urgent need to prevent delays in diagnosis. However, the diagnosis of childhood TB is challenging, as sputum-based testing is invasive and has low yield in children, and chest X-ray (CXR) is not routinely available in high burden settings and requires trained readers. The World Health Organization (WHO) has therefore endorsed TB treatment decision algorithms to reduce delays in timely TB treatment initiation among children presenting to lower-level health facilities. However, TB treatment decision algorithms have uncertain accuracy and available data suggest they are likely to have poor specificity in the absence of CXR. Artificial-intelligence algorithms applied to lung sounds collected using a digital stethoscope (Lung AI) have the potential to enhance detection of lower respiratory tract disease in children being evaluated for TB. The overall objective of the proposed project is to evaluate whether Lung AI can improve the accuracy of TB treatment decision algorithms for childhood TB. We hypothesize that Lung AI can improve specificity while maintaining the high sensitivity of TB treatment decision algorithms. To assess this hypothesis, we will leverage 1) existing well-characterized cohorts to evaluate novel pediatric TB diagnostics; 2) expertise in digital stethoscopes and the development of Lung AI algorithms for TB; and 3) experience in assessing digital health tools in high TB burden settings. In Aim 1, we will examine the accuracy of new and current TB treatment decision algorithms using existing data collected from three ongoing childhood TB diagnostic cohorts in Uganda, South Africa, and the Gambia. At the same time, we will prospectively enroll children with TB symptoms in Uganda, perform a complete TB evaluation to classify TB status per NIH consensus definitions, and record lung sounds using a wireless digital stethoscope. In Aim 2, we will use these lung sounds to train Lung AI algorithms using deep learning models to identify lower airway abnormalities in children in reference to standardized lung sound definitions and radiology CXR reads. We will evaluate these models in an independent test set of children with TB symptoms and healthy children. In Aim 3, we will create a Lung AI model to detect microbiologically-confirmed or clinically-diagnosed TB in children, and compare its accuracy to 1) the best-performing TB treatment decision algorithm, and 2) a machine learning model that combines Lung AI and clinical variables, in the independent test set. Completion of these aims will determine the utility of TB treatment decision algorithms, while demonstrating the potential of a simple, affordable, digital health solution at the point-of-care to support the early diagnosis and treatment of TB and other respiratory diseases in children at lower-level health facilities.

项目摘要 儿童结核病（TB）的大多数死亡都没有在治疗中开始 迫切需要防止诊断延迟。但是，儿童结核病的诊断是具有挑战性的，因为 基于痰液的测试是侵入性的，儿童的产量较低，胸部X射线（CXR）通常不可用 在高负担设置中，需要训练有素的读者。因此，世界卫生组织（谁） 认可结核病治疗决策算法，以减少儿童及时的结核病治疗启动的延迟 向低级医疗机构展示。但是，结核病治疗决策算法的精度不确定 并且可用的数据表明，在没有CXR的情况下它们的特异性可能很差。人工智能 使用数字听诊器（肺AI）收集到肺部声音的算法有可能增强 在评估结核病的儿童中检测下呼吸道疾病。总体目标 拟议的项目是评估肺AI是否可以提高结核病治疗决策算法的准确性 对于儿童结核病。我们假设肺AI可以提高特异性，同时保持高灵敏度 结核病治疗决策算法。为了评估这一假设，我们将利用1）现有的特征良好 评估新的小儿结核病诊断的同类； 2）数字听诊器的专业知识及其发展 TB的肺AI算法； 3）在高结核病负担设置中评估数字健康工具的经验。目标 1，我们将使用现有数据检查新的和当前的结核病治疗决策算法的准确性 从乌干达，南非和冈比亚的三个正在进行的儿童结核病诊断队列中收集。在 同时，我们将前瞻性地招募儿童在乌干达出现结核病症状，进行完整的结核病评估 根据NIH共识定义对结核病状态进行分类，并使用无线数字听觉仪记录肺部声音。 在AIM 2中，我们将使用这些肺部声音使用深度学习模型来训练肺AI算法 儿童的气道异常参考标准化的肺声定义和放射学CXR读取。 我们将在具有结核病症状和健康儿童的独立儿童测试中评估这些模型。在 AIM 3，我们将创建一个肺AI模型，以检测儿童的微生物确认或临床诊断的结核 并将其精度与1）表现最佳的结核病治疗决策算法进行比较，2）机器学习 在独立的测试集中结合了肺AI和临床变量的模型。这些目标的完成将 确定结核病治疗决策算法的效用，同时证明了简单的， 负担得起的数字健康解决方案在护理点，以支持结核病和其他的早期诊断和治疗 低级医疗机构儿童的呼吸道疾病。