Ignite Creation Date:
2025-12-25 @ 3:37 AM
Ignite Modification Date:
2025-12-26 @ 2:21 AM
Study NCT ID:
NCT06333002
Status:
ACTIVE_NOT_RECRUITING
Last Update Posted:
2025-02-11
First Post:
2024-03-19
Is NOT Gene Therapy:
False
Has Adverse Events:
False
Brief Title:
Machine Learning Model to Predict Outcome in Acute Hypoxemic Respiratory Failure
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2025-12-24'}, 'conditionBrowseModule': {'meshes': [{'id': 'D012131', 'term': 'Respiratory Insufficiency'}], 'ancestors': [{'id': 'D012120', 'term': 'Respiration Disorders'}, {'id': 'D012140', 'term': 'Respiratory Tract Diseases'}]}, 'interventionBrowseModule': {'meshes': [{'id': 'D016015', 'term': 'Logistic Models'}], 'ancestors': [{'id': 'D015233', 'term': 'Models, Statistical'}, {'id': 'D013223', 'term': 'Statistics as Topic'}, {'id': 'D004812', 'term': 'Epidemiologic Methods'}, {'id': 'D008919', 'term': 'Investigative Techniques'}, {'id': 'D012306', 'term': 'Risk'}, {'id': 'D011336', 'term': 'Probability'}, {'id': 'D012044', 'term': 'Regression Analysis'}, {'id': 'D008962', 'term': 'Models, Theoretical'}, {'id': 'D017531', 'term': 'Health Care Evaluation Mechanisms'}, {'id': 'D011787', 'term': 'Quality of Health Care'}, {'id': 'D017530', 'term': 'Health Care Quality, Access, and Evaluation'}, {'id': 'D011634', 'term': 'Public Health'}, {'id': 'D004778', 'term': 'Environment and Public Health'}]}}, 'protocolSection': {'designModule': {'studyType': 'OBSERVATIONAL', 'designInfo': {'timePerspective': 'PROSPECTIVE', 'observationalModel': 'COHORT'}, 'enrollmentInfo': {'type': 'ESTIMATED', 'count': 1241}, 'patientRegistry': False}, 'statusModule': {'overallStatus': 'ACTIVE_NOT_RECRUITING', 'startDateStruct': {'date': '2024-03-19', 'type': 'ACTUAL'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2025-02', 'completionDateStruct': {'date': '2026-05-30', 'type': 'ESTIMATED'}, 'lastUpdateSubmitDate': '2025-02-07', 'studyFirstSubmitDate': '2024-03-19', 'studyFirstSubmitQcDate': '2024-03-26', 'lastUpdatePostDateStruct': {'date': '2025-02-11', 'type': 'ACTUAL'}, 'studyFirstPostDateStruct': {'date': '2024-03-27', 'type': 'ACTUAL'}, 'primaryCompletionDateStruct': {'date': '2026-05-30', 'type': 'ESTIMATED'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'ICU mortality', 'timeFrame': 'up to 100 weeks (from inclusion to death or diascharge from intensive care unit', 'description': 'death in the intensive care unit'}], 'secondaryOutcomes': [{'measure': 'MV duration', 'timeFrame': 'up to 100 weeks (from inclusion to extubation)', 'description': 'duration of mechanical ventilation'}]}, 'oversightModule': {'oversightHasDmc': False, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'keywords': ['outcome', 'mechanical ventilation', 'machine learning'], 'conditions': ['Acute Hypoxemic Respiratory Failure']}, 'descriptionModule': {'briefSummary': '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.', 'detailedDescription': '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 AHRF patients on mechanical ventilation (MV). Few studies have investigated the prediction of mortality in patients with AHRF.\n\nFor model development, the investigators will extract data for the first 2 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.'}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['ADULT', 'OLDER_ADULT'], 'maximumAge': '100 Years', 'minimumAge': '18 Years', 'samplingMethod': 'NON_PROBABILITY_SAMPLE', 'studyPopulation': 'De-identified dataset inclusing 1,241 mechanically ventilated patients with acute hypoxemic respiratory failure admitted consecutively in a network of Spanish ICUs.', 'healthyVolunteers': False, 'eligibilityCriteria': 'Inclusion Criteria:\n\n* endotracheal intubation plus mechanical ventilation (MV)\n* PaO2/FiO2 ratio ≤300 mmHg under MV with positive end-expiratory pressure (PEEP) ≥5 cmH2O and FiO2 ≥0.3.\n\nExclusion Criteria:\n\n* Post-operative patients ventilated \\<24 h\n* Brain death patients.'}, 'identificationModule': {'nctId': 'NCT06333002', 'acronym': 'MEMORIAL', 'briefTitle': 'Machine Learning Model to Predict Outcome in Acute Hypoxemic Respiratory Failure', 'organization': {'class': 'OTHER', 'fullName': 'Dr. Negrin University Hospital'}, 'officialTitle': 'Developing an Optimal Machine Learning Model to Predict ICU Outcome in Patients With Acute Hypoxemic Respiratory Failure', 'orgStudyIdInfo': {'id': 'PI24/00325'}}, 'armsInterventionsModule': {'armGroups': [{'label': 'Derivation cohort', 'description': 'It will contain 800 patients randomly selected (1,000 patients with AHRF)', 'interventionNames': ['Other: machine learning analysis']}, {'label': 'Validation cohort', 'description': 'It will contain 200 patients randomly selected (20% of 1000 patients with AHRF', 'interventionNames': ['Other: machine learning analysis']}, {'label': 'Confirmatory cohort', 'description': 'It will contain the remaining 241 patients randomply selected (por external validation)', 'interventionNames': ['Other: machine learning analysis']}], 'interventions': [{'name': 'machine learning analysis', 'type': 'OTHER', 'otherNames': ['Logistic regression, cross validation, and area under the ROC curves'], 'description': 'We will use robust machine learning approaches, such as Random Forest, Extreme Gradient Boosting, Support Vector Machine and Multilayer Perceptron.', 'armGroupLabels': ['Confirmatory cohort', 'Derivation cohort', 'Validation cohort']}]}, 'contactsLocationsModule': {'locations': [{'zip': '13005', 'city': 'Ciudad Real', 'country': 'Spain', 'facility': 'Hospital General Universitario de Ciudad Real', 'geoPoint': {'lat': 38.98626, 'lon': -3.92907}}, {'zip': '16002', 'city': 'Cuenca', 'country': 'Spain', 'facility': 'Hospital Virgen de La Luz', 'geoPoint': {'lat': 40.06667, 'lon': -2.13333}}, {'zip': '28046', 'city': 'Madrid', 'country': 'Spain', 'facility': 'Hospital Universitario La Paz', 'geoPoint': {'lat': 40.4165, 'lon': -3.70256}}, {'zip': '28222', 'city': 'Madrid', 'country': 'Spain', 'facility': 'Hospital Universitario Puerta de Hierro', 'geoPoint': {'lat': 40.4165, 'lon': -3.70256}}, {'zip': '3012', 'city': 'Murcia', 'country': 'Spain', 'facility': 'Hospital Universitario Virgen de Arrixaca', 'geoPoint': {'lat': 37.98704, 'lon': -1.13004}}, {'zip': '38010', 'city': 'Santa Cruz de Tenerife', 'country': 'Spain', 'facility': 'Hospital Universitario NS de Candelaria', 'geoPoint': {'lat': 28.46824, 'lon': -16.25462}}, {'zip': '46010', 'city': 'Valencia', 'country': 'Spain', 'facility': 'Hospital Cinico de Valencia', 'geoPoint': {'lat': 39.47391, 'lon': -0.37966}}, {'zip': '47012', 'city': 'Valladolid', 'country': 'Spain', 'facility': 'Hospital Universitario Rio Hortega', 'geoPoint': {'lat': 41.65541, 'lon': -4.72353}}], 'overallOfficials': [{'name': 'Jesus Villar, MD, PhD', 'role': 'PRINCIPAL_INVESTIGATOR', 'affiliation': 'Fundación Canaria Instituto de Investigación Sanitaria de Canarias'}]}, 'ipdSharingStatementModule': {'ipdSharing': 'NO'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'Dr. Negrin University Hospital', 'class': 'OTHER'}, 'responsibleParty': {'type': 'PRINCIPAL_INVESTIGATOR', 'investigatorTitle': 'principal investigator', 'investigatorFullName': 'Jesus Villar', 'investigatorAffiliation': 'Dr. Negrin University Hospital'}}}}