Prediction of Duration of Mechanical Ventilation in Acute Hypoxemic Respiratoty Failure

NCT06815523 | Active Not Recruiting

• 1 other identifier: PIFIISC24
• Study Type: observational
• Target: 1,241
• Locations: 1 country
• Sites: 2

Brief Summary

Acute hypoxemic respiratory failure (AHRF) is a common cause of admission in intensive care units (ICUs) worldwide. We will assess machine learning (ML) techniques for prediction of prolonged duration (\> or = to 7 days) of mechanical ventilation (MV) in 1,241 patients enrolled in the PANDORA study in Spain. The study was registered with ClinalTrials.gov (NCT03145974). Our aim is to identify a model with the minimum number of variables that predict duration of prolonged ventilation in AHRF patients using data as early as from the first 48 hours with machine learning algorithms.

Conditions

Acute Hypoxemic Respiratory Failure

Keywords

mechanical ventilation; machine learning; prediction of prolonged mechanical ventilation; outcome

Outcome Measures

Primary Outcomes (1)

• MV duration

  duration of mechanical ventilation

  up to 100 weeks

Study Arms (2)

Derivation/testing cohort

The investigators will use a chort of 75% of patients, randomly selected, with data at T0, T24 and T48 after diagnosis of acute hypoxemic respiratory failure (AHRF). We will apply machine learning approaches.

Other: Machine learning and logistic regression for the training/testing cohort and validation cohort

Validation hohort

we will use 25% of unseen patients, randomly selected, with data at T0, T24 and T48 after diagnosis of AHRF.

Other: Machine learning and logistic regression for the training/testing cohort and validation cohort

Interventions

Machine learning and logistic regression for the training/testing cohort and validation cohort OTHER

Machine learning and logistic regression for the validation cohort

Derivation/testing cohort; Validation hohort

Eligibility Criteria

• Age: 18 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 1241 ventilated patients with AHRF admitted in a network of Spainisg ICUs.

You may qualify if:

• enotracheal intubation puls mechanical ventilation
• PaO2/FiO2 ratio \<or = 300 mmHg under MV with PEEP \>or =5 and FiO2 \>or = 0.3

You may not qualify if:

• Brain death patients

Sponsors & Collaborators

• Jesus Villar: lead
• Hospital Universitario Dr. Negrín (Las Palmas de Gran Canaria): collaborator
• Iinstituto de Salud Carlos III: collaborator

Study Sites (2)

Hospital Dr. Negrin

Las Palmas de Gran Canaria, Las Palmas, 35019, Spain

Location

Hospital Universitario La Paz

Madrid, Spain

Location

Related Publications (1)

• Villar J, Gonzalez-Martin JM, Fernandez C, Soler JA, Rey-Abalo M, Mora-Ordonez JM, Ortiz-Diaz-Miguel R, Fernandez L, Murcia I, Robaglia D, Anon JM, Ferrando C, Parrilla D, Dominguez-Berrot AM, Cobeta P, Martinez D, Amaro-Harpigny A, Andaluz-Ojeda D, Fernandez MM, Gomez-Bentolila E, Steyerberg EW, Camporota L, Szakmany T. Predicting Outcome and Duration of Mechanical Ventilation in Acute Hypoxemic Respiratory Failure: The PREMIER Study. J Clin Med. 2025 Nov 7;14(22):7903. doi: 10.3390/jcm14227903.

  PMID: 41302939 DERIVED

MeSH Terms

Conditions

Respiratory Insufficiency

Interventions

Machine Learning; Logistic Models

Condition Hierarchy (Ancestors)

Respiration Disorders; Respiratory Tract Diseases

Intervention Hierarchy (Ancestors)

Artificial Intelligence; Algorithms; Mathematical Concepts; 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

  Fundacion Canaria Instituto de Investigación Sanitaria de Canarias

  STUDY DIRECTOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Scientific Advisor

Study Record Dates

• First Submitted: February 3, 2025
• First Posted: February 7, 2025
• Study Start: February 2, 2025
• Primary Completion: May 1, 2026
• Study Completion (Estimated): June 1, 2026
• Last Updated: March 11, 2025

Record last verified: 2025-03

Data Sharing

• IPD Sharing: Will not share

Locations

ES (2)