CNN在呼吸机触发与评估中的应用

樊 佳乐, 梁 晨, 涂 图, 刘 宏德
东南大学

摘要


减少患者与呼吸机之间的不同步是呼吸机研究领域中的一项关键技术。因此，开发一种能够高效且准确的
算法来量化患者与呼吸机之间的不同步至关重要。随着深度学习的出现，这些目标变得越来越容易实现，并且为该
领域的创新和精确性提供了新的视野。开发了多个CNN模型来检测患者信号是否存在不同步现象，从而评估呼吸机
的性能。这些方法包括六个三分类模型。以延迟触发的检测为例，该触发模型的输入是由患者的膈肌肌电图信号和
压力信号组成的2×200信号，输出将状态分类为（同步、延迟触发、其他不同步）。该延迟触发模型的准确率达到了
96%。总之，我们开发的CNN检测和识别模型提高了呼吸机不同步分析效率。

关键词


CNN；吸气；同步；呼吸机

全文:

PDF


参考


[1]M. J. Tobin,“Physiologic Basis of Mechanical

Ventilation,”Annals of the American Thoracic Society, vol.

15, no. Suppl 1, pp. S49-S52, 2018.

[2]D. Chong and G. Belteki,“Detection and quantitative

analysis of patient-ventilator interactions in ventilated infants by

deep learning networks,”Pediatric Research, pp. 1-9, 2024.

[3]C. Sinderby et al.,“An automated and standardized

neural index to quantify patient-ventilator interaction,”

Critical Care, vol. 17, pp. 1-9, 2013.

[4]S. I. Mirzadeh, M. Farajtabar, A. Li, N. Levine, A.

Matsukawa, and H. Ghasemzadeh,“Improved knowledge

distillation via teacher assistant,”in Proceedings of the AAAI

conference on artificial intelligence, 2020, vol. 34, no. 04, pp.

5191-5198.

[5]E. Calderini, M. Confalonieri, P. Puccio, N. Francavilla,

L. Stella, and C. Gregoretti,“Patient-ventilator asynchrony

during noninvasive ventilation: the role of expiratory trigger,”

Intensive care medicine, vol. 25, pp. 662-667, 1999.

[6]M. Kyo,“Patient-ventilator asynchrony, impact

on clinical outcomes and effectiveness of interventions: a

systematic review and meta-analysis,”Journal of intensive

care, vol. 9, no. 1, p. 50.

[7]D. Wihardini,“Long Short-Term Memory (LSTM):

Trends and Future Research Potential,”future, vol. 5, p. 6.

[8]A. Graves and A. Graves,“Long short-term

memory,”Supervised sequence labelling with recurrent neural

networks, pp. 37-45, 2012.

[9]J. Ham, H. J. Yoo, J. Kim, and B. Lee,“Vowel

speech recognition from rat electroencephalography using

long short-term memory neural network,”PLoS One, vol.

17, no. 6, p. e0270405, 2022.

[10]A. Dexter, N. Mcninch, D. Kaznoch, and T. A.

Volsko,“Validating Lung Models Using the ASL 5000

Breathing Simulator,”Simulation in Healthcare Journal of the

Society for Simulation in Healthcare, p. 117, 2018.


Refbacks

  • 当前没有refback。