Frontiers in medicine · 2026
Early hypoxia prediction in diseased patients via wheezing sounds in respiration: a prospective cohort study.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Huang Chun-Hsiang, Fan Cheng-Yi, Chen Chi-Hsin, Sung Chih-Wei, Chen Ching-Yu, Lin Shao-Yung, Tzeng Jing-Tong, Lee Chi-Chun, Sheed Andrew, Chou Eric H, Huang Edward Pei-Chuan
Аннотация
BACKGROUND: Early detection of hypoxia in the emergency room may reduce complications. Breath sounds can be evaluated immediately. Our research endeavors to investigate the relationship between breath sounds and oxygen demand.
METHODS: We recruited patients from the emergency department. Respiratory sounds in four locations were recorded with an electronic stethoscope and classified into normal, wheezing, or crackles. The primary outcome was increased oxygen demand (IOD) in the emergency room, and the secondary outcome was intensive care unit (ICU) admission. The prediction model was evaluated by logistic regression model.
RESULTS: Overall, 2,216 patients were recruited, and 171 (7.7%) had IOD. Through multivariable logistic regression, independent predictive factors for IOD were age (odds ratio [OR]: 1.02, 95% confidence interval [CI]: 1.01-1.03), lung cancer (OR: 3.56, 95% CI: 1.99-6.36), triage respiratory rate (OR: 1.02, 95% CI: 1.00-1.04), triage oxygen saturation (OR: 0.95, 95% CI: 0.92-0.98), and wheezing (OR: 2.87, 95% CI: 1.31-6.29). The area under receiver operating characteristic curve (AUROC) for IOD was 0.791 (95% CI 0.756-0.8273. Age (OR: 1.02, 95% CI: 1.00-1.03), coronary artery disease (OR: 3.00, 95% CI: 1.82-4.95), chronic obstructive pulmonary disease (aOR = 2.53, 95% CI = 1.32-4.84) and triage oxygen saturation (aOR = 0.96, 95% CI = 0.93-0.99) were significantly associated with increased ICU admission.
CONCLUSION: Wheezing, together with other bedside-available predictors, was independently associated with increased oxygen demand. This finding may facilitate early risk stratification and optimize oxygen resource allocation at the initial encounter, before laboratory or imaging examinations are available. Through voice-print analysis and artificial intelligence, future studies are warranted to further explore the predictive potential of breath sounds.
METHODS: We recruited patients from the emergency department. Respiratory sounds in four locations were recorded with an electronic stethoscope and classified into normal, wheezing, or crackles. The primary outcome was increased oxygen demand (IOD) in the emergency room, and the secondary outcome was intensive care unit (ICU) admission. The prediction model was evaluated by logistic regression model.
RESULTS: Overall, 2,216 patients were recruited, and 171 (7.7%) had IOD. Through multivariable logistic regression, independent predictive factors for IOD were age (odds ratio [OR]: 1.02, 95% confidence interval [CI]: 1.01-1.03), lung cancer (OR: 3.56, 95% CI: 1.99-6.36), triage respiratory rate (OR: 1.02, 95% CI: 1.00-1.04), triage oxygen saturation (OR: 0.95, 95% CI: 0.92-0.98), and wheezing (OR: 2.87, 95% CI: 1.31-6.29). The area under receiver operating characteristic curve (AUROC) for IOD was 0.791 (95% CI 0.756-0.8273. Age (OR: 1.02, 95% CI: 1.00-1.03), coronary artery disease (OR: 3.00, 95% CI: 1.82-4.95), chronic obstructive pulmonary disease (aOR = 2.53, 95% CI = 1.32-4.84) and triage oxygen saturation (aOR = 0.96, 95% CI = 0.93-0.99) were significantly associated with increased ICU admission.
CONCLUSION: Wheezing, together with other bedside-available predictors, was independently associated with increased oxygen demand. This finding may facilitate early risk stratification and optimize oxygen resource allocation at the initial encounter, before laboratory or imaging examinations are available. Through voice-print analysis and artificial intelligence, future studies are warranted to further explore the predictive potential of breath sounds.