CompletedNCT06815523

Prediction of Duration of Mechanical Venylation in Patients Wit Acute Hypoxemic Respiratory Failure Usinf Machine Learning Approaches

Sponsor: Jesus Villar

Trial Details

Condition	Acute Hypoxemic Respiratory Failure
Intervention	Machine learning and logistic regression for the training/testing cohort and validation cohort
Status	Completed
Participants	1,241
Est. Completion	1 May 2026
Last Updated	8 July 2026

Primary Outcome

MV duration

Eligibility Criteria

Inclusion Criteria

Inclusion Criteria: * enotracheal intubation puls mechanical ventilation * PaO2/FiO2 ratio \<or = 300 mmHg under MV with PEEP \>or =5 and FiO2 \>or = 0.3 Exclusion Criteria: * Brain death patients

Trial Sites

Countries

Spain

View Registry Entry

Related Analysis

Machine Learning vs Logistic Regression for Predicting Prolonged Mechanical Ventilation in Acute Hypoxemic Respiratory Failure: Findings from 1,241-Patient PANDORA Cohort

A completed Spanish study of 1,241 ICU patients has applied machine learning algorithms to predict prolonged mechanical ventilation (≥7 days) in acute hypoxemic respiratory failure using only 48-hour clinical data. The PANDORA cohort analysis compares ML approaches against logistic regression to identify the minimum variable set needed for accurate early prediction — with significant implications for ICU resource planning and weaning protocol initiation.

Read full article →

This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service