Using machine learning to predict success in weaning patients off mechanical ventilation
Prediction of the Spontaneous Breathing Test Success Using Biosignal and Biomarker in Critical Care Unit by a Machine Learning Approach
This study is testing a new way to use machine learning to see if it can help doctors predict which patients in critical care will successfully breathe on their own after being on a ventilator.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 500 (estimated) |
| Sex | All |
| Sponsor | Centre Hospitalier Universitaire de Nice Academic / other |
| Locations | 1 site (Nice) |
| Trial ID | NCT05886803 on ClinicalTrials.gov |
What this trial studies
This observational study aims to develop a predictive algorithm using machine learning techniques to assess the likelihood of success in spontaneous breathing tests for patients in critical care units. By analyzing biosignals such as cardiac rate and ventilatory parameters, the study seeks to improve decision-making during the weaning process from mechanical ventilation. The goal is to enhance patient outcomes by reducing morbidity and mortality associated with difficult weaning attempts. The study will include patients who have undergone spontaneous breathing tests and have relevant biosignal data recorded in their health reports.
Who should consider this trial
Good fit: Ideal candidates for this study are patients in critical care units who have undergone a spontaneous breathing test and have corresponding biosignal data available.
Not a fit: Patients who have not undergone a spontaneous breathing test or whose biosignal data is not recorded will not benefit from this study.
Why it matters
Potential benefit: If successful, this approach could significantly improve the management of patients undergoing mechanical ventilation by accurately predicting weaning success.
How similar studies have performed: While few studies have explored machine learning in this context, the approach of using biosignals for prediction is relatively novel and has not been extensively tested.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Computerized health report (CHR) * Spontaneous breathing test should have been performed Exclusion Criteria: * Spontaneous breathing test has not been performed, * Biosignal (cardiac, respiratory) are not registered in the CHR * Patient died before the spontaneous breathing test * Opposition to the study has been expressed.
Where this trial is running
Nice
- University Hospital of Nice — Nice, France (Recruiting)
Study contacts
- Study coordinator: Romain LOMBARDI
- Email: lombardi.r@chu-nice.fr
- Phone: 0669032616
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.