Machine Learning Model to Predict Outcome and Duration of Mechanical Ventilation in Acute Hypoxemic Respiratory Failure

Acute Hypoxemic Respiratory Failure Clinical Trial

— MEMORIAL  

Official title:

Developing an Optimal Machine Learning Model to Predict ICU Outcome and Duration of Mechanical Ventilation in Patients With Acute Hypoxemic Respiratory Failure

Clinical Trial Details — Status: Active, not recruiting

Administrative data

• NCT number: NCT06333002
• Other study ID #: PI24/00325
• Status: Active, not recruiting
• Start date: March 19, 2024
• Est. completion date: May 30, 2026

Study information

• Verified date: March 2024
• Source: Dr. Negrin University Hospital
• Contact: n/a
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

Acute hypoxemic respiratory failure (AHRF) is the most common cause of admission in the intensive care units (UCIs) worldwide. We will assess the value of machine learning (ML) techniques for early prediction of ICU death and prolonged duration (>7 days) of mechanical ventilation (MV) in 1,241 patients enrolled in the PANDORA (Prevalence AND Outcome of acute Respiratory fAilure) Study in Spain. The study was registered with ClinicalTrials.gov (NCT03145974). Our aim is to evaluate the minimum number of variables models using logistic regression and four supervised ML algorithms: Random Forest, Extreme Gradient Boosting, Support Vector Machine and Multilayer Perceptron.

Description:

Acute hypoxemic respiratory failure (AHRF) is the most common cause of admission in the intensive care units (UCIs) worldwide. We will assess the value of machine learning (ML) techniques for early prediction of ICU death and prolonged duration (>7 days) of mechanical ventilation (MV) in AHRF patients on MV. Few studies have investigated the prediction of mortality and duration of MV in patients with AHRF. For model development, the investigators will extract data for the first 3 days after diagnosis of AHRF from patients included in the de-identified database of the PANDORA cohort. We had a database with 2,000,000 anonymized and dissociated demographics and clinical, data from 1,241 patients with AHRF enrolled in our PANDORA cohort (Prevalence AND Outcome of acute Respiratory fAilure) from 22 Spanish hospitals and coordinated by the principal investigator (JV). The investigators will follow the Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) guidelines for model prediction. We will screen collected variables employing a genetic algorithm variable selection method to achieve parsimony. We evaluated the minimum number of variables models using logistic regression and 4 supervised ML algorithms: Random Forest, Extreme Gradient Boosting, Support Vector Machine and Multilayer Perceptron. We will use a 5-fold cross-validation in the dataset of 1,000 patients selected randomly in training data (80%) and testing data (20%). For external validation, we will use the remaining 241 patients.

Recruitment information / eligibility

• Status: Active, not recruiting
• Enrollment: 1241
• Est. completion date: May 30, 2026
• Est. primary completion date: May 30, 2026
• Accepts healthy volunteers: No
• Gender: All
• Age group: 18 Years to 100 Years

Eligibility

Inclusion Criteria:

• endotracheal intubation plus mechanical ventilation (MV)
• PaO2/FiO2 ratio =300 mmHg under MV with positive end-expiratory pressure (PEEP) =5 cmH2O and FiO2 =0.3.

Exclusion Criteria:

• Post-operative patients ventilated <24 h
• Brain death patients.

Related Conditions & MeSH terms

• Acute Hypoxemic Respiratory Failure
• Respiratory Insufficiency

Intervention

Other:
• machine learning analysis
We will use robust machine learning approaches, such as Random Forest, Extreme Gradient Boosting, Support Vector Machine and Multilayer Perceptron.

Locations

Country	Name	City	State
Spain	Hospital General Universitario de Ciudad Real	Ciudad Real
Spain	Hospital Virgen de La Luz	Cuenca
Spain	Hospital Universitario La Paz	Madrid
Spain	Hospital Universitario Puerta de Hierro	Madrid
Spain	Hospital Universitario Virgen de Arrixaca	Murcia
Spain	Hospital Universitario NS de Candelaria	Santa Cruz De Tenerife
Spain	Hospital Cinico de Valencia	Valencia
Spain	Hospital Universitario Rio Hortega	Valladolid

Sponsors (1)

Lead Sponsor	Collaborator
Dr. Negrin University Hospital

Country where clinical trial is conducted

Spain, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	ICU mortality	death in the intensive care unit	up to 100 weeks (from inclusion to death or diascharge from intensive care unit
Secondary	MV duration	duration of mechanical ventilation	up to 100 weeks (from inclusion to extubation)