Automated detection of patient-ventilator asynchrony using pressure signals

Automated Detection of Patient Ventilator Asynchrony Using Pes Signal A Feasibility Study Towards a Detection Algorithm

This study is testing a new computer program that uses pressure signals to see if it can better detect when a patient and their ventilator aren't working well together during breathing support.

Quick facts

• Study type: Observational
• Enrollment: 50 (estimated)
• Ages: 18 Years to 100 Years
• Sex: All
• Sponsor: Leiden University Medical Center (Academic / other)
• Locations: 1 site (Leiden, Zuid - Holland)
• Trial ID: NCT06186557 on ClinicalTrials.gov

What this trial studies

This study aims to develop an automated algorithm for detecting patient-ventilator asynchrony (PVA) during mechanical ventilation by utilizing esophageal pressure signals and machine learning techniques. The researchers will create two algorithms: one that incorporates pressure, flow, and Pes signals, and another that uses only pressure and flow signals. The performance of these algorithms will be compared against expert evaluations to determine their effectiveness in identifying asynchronies. The goal is to improve the quantification and detection of PVA, which is often challenging for clinicians.

Who should consider this trial

Good fit: Ideal candidates for this study are adults aged 18 years or older who are intubated and receiving mechanical ventilation in the ICU for acute respiratory failure.

Not a fit: Patients who have undergone recent pneumectomy or lobectomy, or those unable to provide informed consent, may not benefit from this study.

Why it matters

Potential benefit: If successful, this study could lead to improved detection of patient-ventilator asynchrony, potentially reducing ICU stays and improving patient outcomes.

How similar studies have performed: While various automated algorithms for detecting PVA have been developed, their performance has been variable, indicating that this approach may offer novel insights into improving detection methods.

Eligibility criteria

Inclusion Criteria:

* admission to the ICU of the LUMC;
* age of 18 years or older;
* intubated and receiving mechanical ventilation because of acute respiratory failure or with a ventilation duration of at least 24 hours; and
* equipped with an esophageal balloon catheter

Exclusion Criteria:

* after recent pneumectomy or lobectomy;
* no informed consent

Where this trial is running

Leiden, Zuid - Holland

• Leiden University Medical Centre — Leiden, Zuid - Holland, Netherlands (Recruiting)

Study contacts

• Principal investigator: Abraham Schoe, MD, PhD — Leiden University Medical Centre
• Study coordinator: Abraham Schoe, MD, PhD

Conditions Mechanical Ventilation Complication; detection algorithm; mechanical ventilation; patient-ventilator interaction; convolutional neural network