Advancing Telemedicine in Pulmonology: Acoustic-waveform Respiratory Evaluation (AWARE) Via Sensing and Machine Learning on Smartphones

Indiana University4 个研究点分布在 1 个国家目标入组 800 人开始时间: 2024年7月23日最近更新: 2025年10月24日

适应症

试验速览

阶段: 不适用
状态: 招募中
发起方: Indiana University
入组人数: 800
试验地点: 4
主要终点: Estimation of FEV1

研究概览研究设计入排标准结局指标研究者研究点记录与标识符相似试验

研究概览

简要总结

The study will evaluate the feasibility of using smartphone speakers and microphones to evaluate the caliber of the airways, detect airway obstruction, aid in airway disease diagnosis, and identify disease exacerbations.

详细描述

Asthma and COPD respectively affect millions of people in the US. Chronic lower respiratory diseases represented the fourth leading cause of death in the country before the pandemic. For these and other pulmonary diseases like cystic fibrosis (CF), monitoring disease remotely but objectively could lead to marked improvements in disease control, quality of life, and overall prognosis. However, current disease monitoring and management often rely on subjective symptom report, and objective pulmonary function tests (PFTs) are often only done a handful of times a year at subspecialty referral centers. The primary hypothesis for this study is that smartphone-based sensing and machine learning (ML) approaches can advance pulmonary telemedicine by enabling comprehensive pulmonary disease evaluation with high accuracy, reliability, and adaptability. The investigators further hypothesize that AWARE can accurately help identify different lung diseases, estimate lung function, and detect changes associated with exacerbations. In Aim 1, investigators will develop and improve a smartphone sensing approach as an accurate and reliable aide in airway disease diagnosis. Investigators will recruit a sample of healthy individuals and individuals with asthma, COPD, CF, and other airway diseases, to assess whether AWARE can accurately classify subjects in their disease groups. In Aim 2, investigators will improve the ML approach to estimate lung function accurately and adaptively, including traditional PFT indices from spirometry and impulse oscillometry. And in Aim 3, investigators will develop deep learning techniques to identify changes in airway conditions associated disease exacerbations, by performing AWARE during stable disease and acute exacerbations. For these aims, investigators will recruit a cohort of pediatric and adult subjects with a wide range of demographic and anthropometric characteristics, to have adequate representation of various airway diseases, a broad range of lung function, and the ability to obtain measurements during acute disease exacerbations. The study protocol will include study questionnaires, anthropometry, body composition, and three sets of PFTs: spirometry, oscillometry, and AWARE. A subgroup of subjects will additionally perform AWARE at home for up to two weeks, allowing investigators to evaluate supervised vs unsupervised and in-clinic vs. at-home measurements. Similarly, a subgroup of subjects will perform AWARE dual testing (i.e., with both study smartphones and their own smartphone) to evaluate repeatability using diverse equipment and software platforms.

研究设计

研究类型: Interventional
分配方式: Non Randomized
干预模型: Parallel
主要目的: Diagnostic
盲法: None

入排标准

年龄范围: 8 Years 至 70 Years（Child, Adult, Older Adult）
性别: All
接受健康志愿者: 是

入选标准

•Age 8-70 years
•Ability to perform spirometry and oscillometry
•Signed informed consent (and assent for children as appropriate)
•No respiratory or other major disease (for healthy controls), or physician-diagnosed asthma, COPD, CF, or other airway diseases

排除标准

•Inability or unwillingness to perform AWARE, spirometry, or oscillometry
•Acute or chronic illness that, at the judgement of investigators, may affect lung function and alter the results of AWARE or the reference PFTs (spirometry and AOS)