From Bench to Bedside: A Machine Learning Tool for the Detection of Inspiratory Leak

NCT07428694 — Recruiting, 20 participants, University of Oslo

ClinicalTrials Daily · Areas · Conditions · Drugs · Sponsors ·

Registry	NCT07428694
Status	Recruiting
Study type	Observational
Enrollment	20 (Estimated)
Sponsor	University of Oslo (Other); collaborators: Oslo University Hospital
Conditions	Chronic Respiratory Failure
Dates	start 2025-10-01, primary completion 2026-10-01 (estimated), completion 2026-10-01 (estimated), first posted 2026-02-24, last updated 2026-02-24
Locations	1 site in Norway

-Summary

Study of the applicability of machine learning tools in detecting inspiratory leakage in longterm non-invasive ventilation. The study was conducted in two stages. Firstly the ML model was trained on both bench model created scenarios and then ten patients. And secondly the success of the model was assessed in a proof of concept pilot study of ten patients.

Expand all sections · Collapse all

+Outcome measures

Primary outcomes

Correct interpretation of inspiratory leak by machine learning tool [one year]: Measured in comparison with god standard method of polygraphy

+Eligibility

Sex: All, ages: 18 Years to any

Inclusion Criteria:

* elective hospitalisation for control of non-invasive ventilation
* use of ResMedLumis 100/150 ventilator
* treatment for >3 months

Exclusion Criteria:

* current exacerbation

+Locations (1)

Facility	City	Country	Status
Oslo University Hospital	Oslo	Norway	Recruiting

My Notes

Public

To Read Reading Read