Machine Learning Model to Predict Outcome in Acute Hypoxemic Respiratory Failure

NCT06333002 | Active Not Recruiting

• 1 other identifier: PI24/00325
• Study Type: observational
• Target: 1,241
• Locations: 1 country
• Sites: 8

Brief 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 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.

Conditions

Acute Hypoxemic Respiratory Failure

Keywords

outcome; mechanical ventilation; machine learning

Outcome Measures

Primary Outcomes (1)

• ICU mortality

  death in the intensive care unit

  up to 100 weeks (from inclusion to death or diascharge from intensive care unit

Secondary Outcomes (1)

• MV duration

  up to 100 weeks (from inclusion to extubation)

Study Arms (3)

Derivation cohort

It will contain 800 patients randomly selected (1,000 patients with AHRF)

Other: machine learning analysis

Validation cohort

It will contain 200 patients randomly selected (20% of 1000 patients with AHRF

Other: machine learning analysis

Confirmatory cohort

It will contain the remaining 241 patients randomply selected (por external validation)

Other: machine learning analysis

Interventions

machine learning analysis OTHER

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

Also known as: Logistic regression, cross validation, and area under the ROC curves

Confirmatory cohort; Derivation cohort; Validation cohort

Eligibility Criteria

• Age: 18 Years - 100 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

De-identified dataset inclusing 1,241 mechanically ventilated patients with acute hypoxemic respiratory failure admitted consecutively in a network of Spanish ICUs.

You may qualify if:

• 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.

You may not qualify if:

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

Sponsors & Collaborators

• Dr. Negrin University Hospital: lead

Study Sites (8)

Hospital General Universitario de Ciudad Real

Ciudad Real, 13005, Spain

Location

Hospital Virgen de La Luz

Cuenca, 16002, Spain

Location

Hospital Universitario La Paz

Madrid, 28046, Spain

Location

Hospital Universitario Puerta de Hierro

Madrid, 28222, Spain

Location

Hospital Universitario Virgen de Arrixaca

Murcia, 3012, Spain

Location

Hospital Universitario NS de Candelaria

Santa Cruz de Tenerife, 38010, Spain

Location

Hospital Cinico de Valencia

Valencia, 46010, Spain

Location

Hospital Universitario Rio Hortega

Valladolid, 47012, Spain

Location

MeSH Terms

Conditions

Respiratory Insufficiency

Interventions

Logistic Models

Condition Hierarchy (Ancestors)

Respiration Disorders; Respiratory Tract Diseases

Intervention Hierarchy (Ancestors)

Models, Statistical; Statistics as Topic; Epidemiologic Methods; Investigative Techniques; Risk; Probability; Regression Analysis; Models, Theoretical; Health Care Evaluation Mechanisms; Quality of Health Care; Health Care Quality, Access, and Evaluation; Public Health; Environment and Public Health

Study Officials

• Jesus Villar, MD, PhD

  Fundación Canaria Instituto de Investigación Sanitaria de Canarias

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: principal investigator

Study Record Dates

• First Submitted: March 19, 2024
• First Posted: March 27, 2024
• Study Start: March 19, 2024
• Primary Completion (Estimated): May 30, 2026
• Study Completion (Estimated): May 30, 2026
• Last Updated: February 11, 2025

Record last verified: 2025-02

Data Sharing

• IPD Sharing: Will not share

Locations

ES (8)