Brain-Machine Interface for Mechanical Ventilation Using Respiratory-Related Evoked Potential

Abstract : The correct ventilation for patients in intensive care units plays a critical role for the prognostic and the recovery during the stay in the hospital. Desynchronization between the ventilator and the patient is an important source of stress, emphasized by the lack of communication due to intubation or loss of consciousness. This contribution proposes a novel approach based on electroencephalographic (EEG) activity to detect breathing effort. Relying both on recent neuroscience finding on respiratory-related evoked potential and on latest development of information geometry, the proposed approach elaborates on Rieman-nian distances between EEG covariance matrices to differentiate among different respiratory loads. The results demonstrate that this approach outperform existing state-of-the-art methods quantitatively, in terms of mean accuracy, and qualitatively, being able to predict level of breathing discomfort.
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download

https://hal.uvsq.fr/hal-01911136
Contributor : Sylvain Chevallier <>
Submitted on : Friday, November 16, 2018 - 6:46:22 PM
Last modification on : Friday, August 23, 2019 - 4:46:00 PM
Long-term archiving on : Sunday, February 17, 2019 - 12:39:36 PM

File

chevallier_icann_18_published....
Explicit agreement for this submission

Identifiers

Collections

Citation

Sylvain Chevallier, Guillaume Bao, Mayssa Hammami, Fabienne Marlats, Louis Mayaud, et al.. Brain-Machine Interface for Mechanical Ventilation Using Respiratory-Related Evoked Potential. 27th International Conference on Artificial Neural Networks( ICANN 2018), Oct 2018, Rhodes, Greece. ⟨10.1007/978-3 -030-01424-7_65⟩. ⟨hal-01911136⟩

Share

Metrics

Record views

51

Files downloads

100