Prediction of the Spontaneous Breathing Test Success Using Biosignal and Biomarker in Critical Care Unit by a Machine Learning Approach

Launched by CENTRE HOSPITALIER UNIVERSITAIRE DE NICE · May 24, 2023

Keywords

ClinConnect Summary

This clinical trial is studying how to predict whether patients can successfully stop using mechanical ventilation, which is a machine that helps them breathe. When patients are in critical care, the process of weaning them off this support can be challenging, and about 20% of first attempts are unsuccessful. Researchers are using advanced computer techniques called machine learning to analyze data from patients' past health records, including heart rate and breathing patterns, to help doctors make better decisions about when a patient is ready to breathe on their own.

To be eligible for this study, participants need to have their breathing ability tested, and their health data must be available in electronic records. Patients who have not had this test, who have not had their vital signs recorded, or who have passed away before the test cannot participate. If enrolled, patients will not need to do anything extra; the study will use their existing health information to help improve future care for others in similar situations. This research aims to enhance patient safety and reduce the time spent in intensive care.

Gender

ALL

Eligibility 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.