Prediction of Duration of Mechanical Ventilation in ARDS (PIONEER)

Predicting Length of Mechanical Ventilation in Moderate-to-severe Acute Respiratory Distress Syndrome Using Machine Learning

The investigators are planning to perform a secondary analysis of an academic dataset of 1,303 patients with moderate-to-severe acute respiratory distress syndrome (ARDS) included in several published cohorts (NCT00736892, NCT022288949, NCT02836444, NCT03145974), aimed to characterize the best early scenario during the first three days of diagnosis to predict duration of mechanical ventilation in the intensive care unit (ICU) using supervised machine learning (ML) approaches.

Study Overview

• Status: Completed
• Conditions: Acute Respiratory Distress Syndrome
• Intervention / Treatment: Other: Logistic regression Cross validation Area under the RIC curves Machine learning analysis. .

Detailed Description

The acute respiratory distress syndrome (ARDS) is an important cause of morbidity, mortality, and costs in intensive care units (ICUs) worldwide. Most ARDS patients require mechanical ventilation (MV). Few studies have investigated the prediction of MV duration of ARDS.

For model description and testing, the investigators will extract data from he first three ICU days after diagnosis of moderate-to-severe ARDS from patients included in the de-identified database, which includes 1,000 mechanically ventilated patients enrolled in several observational cohorts in Spain, coordinated by the principal investigator (JV), and funded by the Instituto de Salud Carlos III (ISCIII). The investigators will follow the TRIPOD guidelines and machine learning techniques will be implemented [Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Logistic regression analysis) for the development and accuracy of prediction models. Disease progression will be tracked along those 3 ICU days to assess lung severity according to Berlin criteria. For external validation, the investigators will use 303 patients enrolled in a contemporary observational study (NCT03145974). The investigators will evaluate the accuracy of prediction models by calculation several statistics, such as sensitivity, specificity, positive predictive value, negative value for each model. The investigators will select the best early prediction model with data captured on the 1st, 2nd, or 3rd day.

• Study Type: Observational
• Enrollment (Actual): 1303

Contacts and Locations

Study Locations

• Spain
  • Albacete, Spain
    • Complejo Hospitalario de Albacete
  • Albacete, Spain, 02006
    • Complejo Hospitalario Universitario de Albacete (ICU)
  • Barcelona, Spain, 08036
    • Department of Anesthesia, Hospital Clinic
  • Ciudad Real, Spain, 13005
    • Hospital General de Ciudad Real (ICU)
  • Cuenca, Spain
    • Hospital Virgen De La Luz
  • La Coruña, Spain, 15006
    • Hospital Universitario de A Coruña (ICU)
  • León, Spain
    • Complejo Hospitalario Universitario de León
  • Madrid, Spain
    • Hospital Fundación Jiménez Díaz
  • Madrid, Spain, 28046
    • Hospital Universitario La Paz (ICU)
  • Madrid, Spain, 28034
    • Hospital Universitario Ramón y Cajal (Anesthesia)
  • Murcia, Spain, 30120
    • Hospital Universitario Virgen de Arrixaca (ICU)
  • Málaga, Spain
    • Hospital Universitario Carlos Haya
  • Málaga, Spain, 29010
    • Hospital Universitario Regional de Malaga Carlos Haya (ICU)
  • Valladolid, Spain, 47012
    • Hospital Universitario Río Hortega (ICU)
  • Zamora, Spain, 49022
    • Hospital Virgen de la Concha (ICU)
  • Las Palmas
    • Las Palmas De Gran Canaria, Las Palmas, Spain, 35019
      • Hospital Universitario Dr. Negrin
  • Madrid
    • Majadahonda, Madrid, Spain, 28222
      • Hospital Universitario Puerta de Hierro (ICU)
  • Tenerife
    • Santa Cruz de Tenerife, Tenerife, Spain
      • Hospital Universitario NS de Candelaria
  • Toledo
    • Talavera de la Reina, Toledo, Spain
      • Hospital NS del Prado
• United Kingdom
  • Cardiff, United Kingdom
    • Cardiff University

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: N/A

• Sampling Method: Non-Probability Sample

Study Population

De-identified dataset including 1,303 patients with moderate/severe ARDS admitted consecutively in a network of Spanish ICUs.

Description

Inclusion Criteria:

• Berlin criteria for moderate to severe acute respiratory distress syndrome

Exclusion Criteria:

• Postoperative patients ventilated <24h
• brain death patients

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Confirmatory cohort; It will contain 303 patients (for external validation)	Other: Logistic regression Cross validation Area under the RIC curves Machine learning analysis. .; we will use robust machine learning approaches, such as Random Forest and XGBoost.
Derivation and testing cohort; It will contain 1000 ARDS patients	Other: Logistic regression Cross validation Area under the RIC curves Machine learning analysis. .; we will use robust machine learning approaches, such as Random Forest and XGBoost.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Days on mechanical ventilation	Duration of mechanical ventilation	from diagnosis to extubation

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
ICU mortality	mortality in the intensive care unit	up to 24 weeks

Collaborators and Investigators

• Sponsor: Dr. Negrin University Hospital
• Collaborators: Cardiff University; Unity Health Toronto; Leiden University Medical Center
• Investigators: Principal Investigator: Jesús Villar, Hospital Universitario D. Negrin

Publications and helpful links

General Publications

• Villar J, Ambros A, Mosteiro F, Martinez D, Fernandez L, Ferrando C, Carriedo D, Soler JA, Parrilla D, Hernandez M, Andaluz-Ojeda D, Anon JM, Vidal A, Gonzalez-Higueras E, Martin-Rodriguez C, Diaz-Lamas AM, Blanco J, Belda J, Diaz-Dominguez FJ, Rico-Feijoo J, Martin-Delgado C, Romera MA, Gonzalez-Martin JM, Fernandez RL, Kacmarek RM; Spanish Initiative for Epidemiology, Stratification and Therapies of ARDS (SIESTA) Network. A Prognostic Enrichment Strategy for Selection of Patients With Acute Respiratory Distress Syndrome in Clinical Trials. Crit Care Med. 2019 Mar;47(3):377-385. doi: 10.1097/CCM.0000000000003624.
• Figueroa-Casas JB, Dwivedi AK, Connery SM, Quansah R, Ellerbrook L, Galvis J. Predictive models of prolonged mechanical ventilation yield moderate accuracy. J Crit Care. 2015 Jun;30(3):502-5. doi: 10.1016/j.jcrc.2015.01.020. Epub 2015 Jan 30.

Study record dates

Study Major Dates

• Study Start (Actual): August 14, 2023
• Primary Completion (Actual): February 2, 2024
• Study Completion (Actual): February 2, 2024

Study Registration Dates

• First Submitted: August 4, 2023
• First Submitted That Met QC Criteria: August 14, 2023
• First Posted (Actual): August 15, 2023

Study Record Updates

• Last Update Posted (Actual): March 20, 2024
• Last Update Submitted That Met QC Criteria: March 19, 2024
• Last Verified: February 1, 2024

More Information

Terms related to this study

• Keywords: intensive care unit; mechanical ventilation; duration of ventilation; machine learning.
• Additional Relevant MeSH Terms: Pathologic Processes; Respiratory Tract Diseases; Respiration Disorders; Lung Diseases; Disease; Infant, Newborn, Diseases; Lung Injury; Infant, Premature, Diseases; Syndrome; Respiratory Distress Syndrome; Respiratory Distress Syndrome, Newborn; Acute Lung Injury
• Other Study ID Numbers: PIFIISC21-36

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No