Machine learning to detect inspiratory leak in long-term non-invasive ventilation
From Bench to Bedside: A Machine Learning Tool for the Detection of Inspiratory Leak
This project tries to use a machine-learning program to detect inspiratory leaks in people with chronic respiratory failure who use long-term non-invasive ventilation.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 20 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | University of Oslo Academic / other |
| Locations | 1 site (Oslo) |
| Trial ID | NCT07428694 on ClinicalTrials.gov |
What this trial studies
This observational project developed a machine-learning model to spot inspiratory leaks during long-term non-invasive ventilation. The model was first trained using a bench model with created leak scenarios plus data from ten patients. The trained model was then tested in a proof-of-concept pilot involving ten additional patients during elective hospital visits. Participants used ResMed Lumis 100/150 ventilators and were on treatment for more than three months.
Who should consider this trial
Good fit: Ideal candidates are people with chronic respiratory failure who have been on long-term non-invasive ventilation for over three months, use a ResMed Lumis 100/150 ventilator, and can attend elective hospitalization for NIV control without a current exacerbation.
Not a fit: People experiencing an acute exacerbation, those who use other ventilator models, or those unable to attend hospitalization are unlikely to benefit from this specific project.
Why it matters
Potential benefit: If successful, the tool could help clinicians identify and reduce inspiratory leaks more quickly, improving ventilation effectiveness and patient comfort.
How similar studies have performed: Similar machine-learning approaches have shown limited, preliminary success in bench and small pilot studies, but broad clinical validation is still limited.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * elective hospitalisation for control of non-invasive ventilation * use of ResMedLumis 100/150 ventilator * treatment for \>3 months Exclusion Criteria: * current exacerbation
Where this trial is running
Oslo
- Oslo University Hospital — Oslo, Norway (Recruiting)
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.