医学
可穿戴计算机
心肺适能
心力衰竭
可穿戴技术
运动不耐症
机器学习
物理医学与康复
计算机科学
物理疗法
心脏病学
嵌入式系统
作者
Yasbanoo Moayedi,Farid Foroutan,Yuan Gao,Ben Kim,E. De Luca,Margaret Brum,Darshan H. Brahmbhatt,Joe Duhamel,Anne Simard,Chris McIntosh,Heather J. Ross
标识
DOI:10.1161/circheartfailure.124.012204
摘要
BACKGROUND: Heart failure (HF) is a highly prevalent condition characterized by exercise intolerance, an important metric for ambulatory prognostication. However, current methods to assess exercise capacity are often limited to tertiary HF centers, lacking scalability or accessibility. Wearable devices have the potential to provide near-continuous dynamic biometrics including exercise tolerance. METHODS: Leveraging the capabilities of Apple Watch and a custom application, the TRUE-HF (Ted Rogers Understanding of Exacerbations in Heart Failure) Apple cardiopulmonary exercise testing study aims to investigate whether HealthKit data from Apple Watch can estimate cardiorespiratory fitness, as compared with the gold standard peak oxygen uptake from cardiopulmonary exercise testing. The TRUE-HF study will evaluate the potential impact of wearable technology in the functional assessment of ambulatory patients with HF. The primary end point is to use HealthKit variables to estimate a TRUE-HF peak oxygen uptake. We outline key features of this trial designed to reduce the burden of wearable technology. In addition, we highlight the benefits of various machine learning analyses, with a particular focus on transformer models for the wearable space. CONCLUSIONS: Using cutting-edge wearable technology and machine learning analytics, TRUE-HF may provide state-of-the-art assessment of functional capacity by measuring participant-generated free-world data. REGISTRATION: URL: https://www.clinicaltrials.gov ; Unique identifier: NCT05008692.
科研通智能强力驱动
Strongly Powered by AbleSci AI