Artificial Intelligence-Based Motion Analysis for Early Detection of COPD

Официальное название

Development of an Artificial Intelligence-Based Motion Analysis System for the Detection of Chronic Obstructive Pulmonary Disease (COPD)

Обзор

This study aims to develop a non-invasive and contact-free diagnostic system that uses artificial intelligence (AI) to detect Chronic Obstructive Pulmonary Disease (COPD) by analyzing walking patterns. Participants in this study will include individuals with a diagnosis of COPD and healthy volunteers. All participants will undergo a 6-minute walk test (6MWT), during which their movements will be recorded using video. In addition, they will complete a breathing test (spirometry) and a short questionnaire about symptoms. The recorded videos will be analyzed using an AI model based on motion tracking software. This model will evaluate walking-related parameters such as step count, step length, walking time, and total walking distance. The goal is to determine whether walking patterns can be used to detect COPD with high accuracy, especially in situations where traditional lung function tests may not be available or feasible. This study is observational and does not involve any experimental drug or treatment. The results may help to create new diagnostic tools that are easy to use, safe, and accessible for early detection of COPD.

Вмешательства

• Другое Gait Video Recording and Analysis
  Participants undergo a 6-minute walk test (6MWT) while being recorded on video. The footage is later analyzed using artificial intelligence algorithms to assess gait parameters.

Первичные конечные точки

• Diagnostic Accuracy of AI-Based Gait Analysis for Detection of COPD [Срок оценки: At time of initial assessment (Day 0)]

Критерии участия

Критерии включения

• Aged between 40 and 80 years
• Ability to provide informed consent
• For COPD group: Previously diagnosed with COPD based on GOLD criteria (FEV1/FVC < 0.70)
• For control group: No history of pulmonary disease and normal spirometry results
• Physically able to perform the 6-minute walk test
• Willingness to participate in video recording during gait analysis

Критерии исключения

• Younger than 40 or older than 80 years
• Acute respiratory tract infection or other active infections
• Severe heart failure, advanced arrhythmias, or other serious cardiovascular conditions
• Physical disability preventing completion of the 6-minute walk test
• Neurological or orthopedic conditions causing major gait disturbance
• Inability to perform spirometry due to physical or cognitive limitations
• Pregnant or breastfeeding women Diagnosed with other serious pulmonary diseases (e.g., interstitial lung disease, active tuberculosis) Refusal to give informed consent or to be video recorded

Критерии приведены из реестра в оригинале (на английском). Окончательную оценку соответствия проводит исследовательский центр.

Здоровые добровольцы: Да

Дизайн исследования

Модель наблюдения

Когортное

Центры проведения

Список центров уточняется — проверьте первичный протокол.

Публикации

• Altan G, Kutlu Y, Allahverdi N. Deep Learning on Computerized Analysis of Chronic Obstructive Pulmonary Disease. IEEE J Biomed Health Inform. 2019 Jul 26. doi: 10.1109/JBHI.2019.2931395. Online ahead of print. PMID 31369388
• Agusti A, Celli BR, Criner GJ, Halpin D, Anzueto A, Barnes P, Bourbeau J, Han MK, Martinez FJ, Montes de Oca M, Mortimer K, Papi A, Pavord I, Roche N, Salvi S, Sin DD, Singh D, Stockley R, Lopez Varela MV, Wedzicha JA, Vogelmeier CF. Global Initiative for Chronic Obstructive Lung Disease 2023 Report: GOLD Executive Summary. Eur Respir J. 2023 Apr 1;61(4):2300239. doi: 10.1183/13993003.00239-2023. PMID 36858443

Идентификаторы

NCT: NCT07010211 · B.30.2.ODM.0.20.08/220

Первоисточники (государственные реестры)

• ClinicalTrials.gov (NIH, США)

Открыть это исследование на ClinicalTrials.gov ↗