Acute Lung Injury
Conditions
Keywords
artificial intelligence, biotrauma, electric impedance tomography, patient-ventilator asynchrony
Brief summary
Patient-ventilator asynchrony (PVA) has deleterious effects on the lungs. PVA can lead to acute lung injury and worsening hypoxemia through biotrauma. Little is known about how PVA affects lung aeration estimated by electric impedance tomography (EIT). Artificial intelligence can promote the detection of PVA and with its help, EIT measurements can be correlated to asynchrony.
Detailed description
Patient-ventilator asynchrony (PVA) is a common phenomenon with invasively- and non-invasively ventilated patients. PVA has deleterious effects on the lungs. It causes not just patient discomfort and distress but also leads to acute lung injury and worsening hypoxemia through biotrauma. The latter significantly impacts outcomes and increases the duration of mechanical ventilation and intensive care unit stay. However, PVA is a widely investigated incident related to mechanical ventilation, though little is known about how it affects lung aeration estimated by electric impedance tomography (EIT). EIT is a non-invasive, real-time monitoring technique suitable for detecting changes in lung volumes during ventilation. Artificial intelligence can promote the detection of PVA by flow versus time assessment. If continuous EIT recording is correlated with the latter, impedance tomography changes evoked by asynchrony can be estimated
Interventions
DEVICEEIT
continuous electric impedance tomography measurement
DEVICEpatient-ventilator asynchrony assessment
patient-ventilator asynchrony assessment by flow/time curve and machine learning
Sponsors
Hochschule Furtwangen University
Budapest University of Technology and Economics
Szeged University
Kiskunhalas Semmelweis Hospital the Teaching Hospital of the University of Szeged
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to 100 Years
Inclusion criteria
* any patient ventilated invasively * any patient ventilated non-invasively
Exclusion criteria
* age under 18
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| distribution | during mechanical ventilation | gas distribution in lungs assessed by electric impedance tomography |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| connecting asysnchrony cycles with electric impedance tomography measurements | during mechanical ventilation | connecting machine learning assessed patient-ventilator asynchrony respiratory cycles with the inherent respiratory cycle recorded by the electric impedance tomography |
| identifying unic electric impedance tomography signs of asynchrony | during mechanical ventilation | following connection described under outcome 2, identification if single patient-ventilator asynchrony types (delayed cycling, premature cycling, auto trigger, ineffective effort, double trigger) present specific electric impedance tomography changes |
Countries
Hungary
Contacts
Primary ContactAndrás Lovas, M.D. Ph.D.
Outcome results
None listed