Automatic detection of breathlessness in adults on mechanical ventilation
Automatic Detection of Dyspnea in Mechanically Ventilated, Critically Ill Patients
This project will try to use ventilator pressure and flow signals to detect breathlessness in non-communicative adults recently intubated and receiving mechanical ventilation in the ICU.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 60 (estimated) |
| Sex | All |
| Sponsor | Hospital de Clinicas José de San Martín Academic / other |
| Locations | 1 site (Buenos Aires, Buenos Aires) |
| Trial ID | NCT07205952 on ClinicalTrials.gov |
What this trial studies
This observational study will enroll about 60 adult ICU patients who were endotracheally intubated within the previous 24 hours and are expected to need at least 24 hours of mechanical ventilation. Ventilator airway pressure and flow will be streamed into 131.1-second epochs for up to five days and a recursive algorithm will estimate inspiratory muscle pressure (Pmus) and calculate inspiratory effort time-pressure product (PmusPTP). Trained staff will collect MV-RDOS scores at least twice daily and time-match these subjective dyspnea ratings to the ventilator signal epochs to measure correlation and derive an ROC AUC threshold for PmusPTP equivalent to MV-RDOS > 2.6. Six supervised classifiers and a unanimity ensemble will be used to label discordant pairs, and ensemble-conflicting labels will be excluded from a secondary analysis.
Who should consider this trial
Good fit: Adults (≥18 years) who were endotracheally intubated within the past 24 hours, are non-communicative, and are expected to require at least 24 hours of mechanical ventilation.
Not a fit: Patients receiving continuous neuromuscular blockade, those ventilated on Airway Pressure Release Ventilation (APRV) mode, or patients who can reliably report symptoms are unlikely to benefit from this automated detection approach.
Why it matters
Potential benefit: If successful, this work could provide a continuous, objective way to detect dyspnea at the bedside so clinicians can identify and treat breathlessness sooner.
How similar studies have performed: Prior physiologic and pilot studies using ventilator waveforms and machine learning have shown promise at estimating inspiratory effort, but continuous automated dyspnea detection in mechanically ventilated patients remains relatively novel and not yet widely validated.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion criteria: * Adults of either sex (≥18 years) * Endotracheally intubated in the past 24 hours. * Expected to require ≥24 hours of mechanical ventilation. Exclusion criteria: * Continuous neuromuscular blockade. * Ventilated on Airway Pressure Release Ventilation mode.
Where this trial is running
Buenos Aires, Buenos Aires
- Hospital de Clínicas de la Universidad de Buenos Aires — Buenos Aires, Buenos Aires, Argentina (Recruiting)
Study contacts
- Principal investigator: Guillermo Gutierrez — The George Washington University School of Medicine and Health Sciences
- Study coordinator: Guillermo Gutierrez, MD, PhD
- Email: gutier@gwu.edu
- Phone: 17035595843
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.