IEEE transactions on bio-medical engineering · 2026
Model-Based Analysis of Pulse Transit Time-Derived Features for the Classification of Obstructive and Central Apneas.
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.
Ben-Tolila Arthur, Le Rolle Virginie, Duprez Joan, Pepin Jean-Louis, Hernandez Alfredo I
Аннотация
OBJECTIVE: Pulse transit time (PTT) is a promising tool for the non-invasive identification and characterization of obstructive and central apneas in sleep apnea syndrome (SAS). However, a lack of standardized and physiologically explainable features extracted from PTT limits its interpretability and the possibility to perform this classification automatically.
METHODS: Features were extracted from PTT and its oscillations ($\Delta$PTT) to characterize their variation during obstructive and central apneas, on a database of 26 patients from the HYPNOS clinical study. They were used to train a random forest classifier and obtain a ranking of feature importance. The most significant features were studied using a Morris sensitivity analysis of a novel integrated model of cardio-respiratory interactions simulating the PTT, to understand the main physiological mechanisms modulating them.
RESULTS: An AUC of 0.83$\pm$0.12 was obtained for the classification. The most significant features were related to $\Delta$PTT and its changes during the apnea compared to the baseline. They were sensitive to model parameters affecting its sensitivity to blood CO$_{2}$.
CONCLUSION AND SIGNIFICANCE: A new integrated model of PTT in sleep apnea was proposed, and allowed for the physiological interpretation of novel informative PTT features for the classification of obstructive and central apneas.
METHODS: Features were extracted from PTT and its oscillations ($\Delta$PTT) to characterize their variation during obstructive and central apneas, on a database of 26 patients from the HYPNOS clinical study. They were used to train a random forest classifier and obtain a ranking of feature importance. The most significant features were studied using a Morris sensitivity analysis of a novel integrated model of cardio-respiratory interactions simulating the PTT, to understand the main physiological mechanisms modulating them.
RESULTS: An AUC of 0.83$\pm$0.12 was obtained for the classification. The most significant features were related to $\Delta$PTT and its changes during the apnea compared to the baseline. They were sensitive to model parameters affecting its sensitivity to blood CO$_{2}$.
CONCLUSION AND SIGNIFICANCE: A new integrated model of PTT in sleep apnea was proposed, and allowed for the physiological interpretation of novel informative PTT features for the classification of obstructive and central apneas.