Related Experiment Video
Updated: May 21, 2026

Non-Intubated Video-Assisted Thoracoscopic Surgery
Published on: May 26, 2023
Automatic detection of AutoPEEP during controlled mechanical ventilation.
Quang-Thang Nguyen1, Dominique Pastor, Erwan L'her
1Department of Signal and Communications, Institut Télécom; Télécom Bretagne, Brest, France. quang.nguyen@telecom-bretagne.eu
Automatic detection of auto-positive end expiratory pressure (AutoPEEP) in mechanical ventilation is now possible. This new platform accurately identifies AutoPEEP, aiding clinicians in optimizing patient care.
Area of Science:
- Biomedical Engineering
- Respiratory Physiology
- Critical Care Medicine
Background:
- Dynamic hyperinflation, termed auto-positive end expiratory pressure (AutoPEEP), is a common issue in mechanically ventilated patients.
- AutoPEEP is often recognized by observing the expiratory flow waveform, where flow fails to return to zero before the next breath.
- Current detection relies on expert clinical observation, highlighting the need for automated solutions.
Purpose of the Study:
- To introduce a platform for the automatic detection of AutoPEEP using the flow signal from mechanical ventilators.
- To develop and validate algorithms for reliable AutoPEEP identification.
Main Methods:
- Utilized robust non-parametric hypothesis testing for algorithm development, requiring no prior signal distribution information.
- Proposed two detectors: Signal Norm Testing (SNT) and a sequential extension of SNT.
- Assessed performance using a respiratory system analog and retrospective patient data.
Main Results:
- The developed algorithm demonstrated effective AutoPEEP detection on both simulated and real-world data.
- Clinical data analysis showed the detectors achieved 93% accuracy and 90% recall (sensitivity) for AutoPEEP detection.
Conclusions:
- The proposed platform enables automatic and early detection of AutoPEEP.
- Integration into mechanical ventilators can provide continuous monitoring, assisting clinicians and improving patient-ventilator interface management.
Related Concept Videos
Mechanical Ventilation I: Indication and Settings
Ventilatory Modes
There are three ventilatory modes: full support, partial support, and spontaneous. These are described below.
Full Support Modes
Full support modes include controlled mechanical ventilation, continuous mandatory...
Mechanical Ventilation III: Noninvasive Ventilation
Noninvasive Positive-Pressure Ventilation (NIPPV)
Cardiopulmonary Resuscitation II: ACLS Airway Management
Mechanical Ventilation II: Invasive Ventilation
Negative-Pressure Ventilators
Negative-pressure ventilators create a vacuum around the chest or body to draw air into the lungs, simulating breathing. This method does not require an...
Assessment of Ventilation I: Respiratory Rate
A Ventilation assessment is critical for monitoring a patient's health status. Respiration, one of the most accessible vital signs, provides insights into the function of numerous body systems and can indicate serious health issues, such as brainstem injuries from head trauma.
Critical Guidelines for Assessing Ventilation:
