Ignite Creation Date:
2025-12-24 @ 4:06 PM
Ignite Modification Date:
2026-01-04 @ 4:47 PM
Study NCT ID:
NCT06456866
Status:
COMPLETED
Last Update Posted:
2025-01-22
First Post:
2024-06-08
Is Gene Therapy:
True
Has Adverse Events:
False
Brief Title:
Assessing the Accuracy of ChatGPT-4 in Interpreting Arterial Blood Gas Results
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2025-12-24'}}, 'protocolSection': {'designModule': {'studyType': 'OBSERVATIONAL', 'designInfo': {'timePerspective': 'PROSPECTIVE', 'observationalModel': 'CASE_ONLY'}, 'enrollmentInfo': {'type': 'ACTUAL', 'count': 398}, 'patientRegistry': False}, 'statusModule': {'overallStatus': 'COMPLETED', 'startDateStruct': {'date': '2024-06-14', 'type': 'ACTUAL'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2025-01', 'completionDateStruct': {'date': '2024-12-02', 'type': 'ACTUAL'}, 'lastUpdateSubmitDate': '2025-01-18', 'studyFirstSubmitDate': '2024-06-08', 'studyFirstSubmitQcDate': '2024-06-08', 'lastUpdatePostDateStruct': {'date': '2025-01-22', 'type': 'ACTUAL'}, 'studyFirstPostDateStruct': {'date': '2024-06-13', 'type': 'ACTUAL'}, 'primaryCompletionDateStruct': {'date': '2024-12-01', 'type': 'ACTUAL'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'blood gases sample interpretation', 'timeFrame': '10 minutes'}]}, 'oversightModule': {'oversightHasDmc': False, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'keywords': ['artificial intelligence'], 'conditions': ['Blood Gases']}, 'descriptionModule': {'briefSummary': 'Assessment of Acidosis and Alkalosis, Evaluation of Hypoxemia and Hyperoxemia, Evaluation of Hemoglobin Parameters, Assessment of Electrolytes, Evaluation of Metabolic Parameters (Glucose, Lactate, Bilirubin)', 'detailedDescription': "Model Training:\n\nThe collected data will be used to train the artificial intelligence model. Utilizing the deep learning infrastructure provided by ChatGPT Plus, our model will be optimized to produce highly accurate results in interpreting blood gases.\n\nDuring the training process, our model will be taught to interpret various blood gas samples, including assessments of acidosis-alkalosis, hypoxemia-hyperoxemia, hemoglobin, electrolytes, and metabolic parameters.\n\nModel Testing and Validation:\n\nThe trained model will be tested on previously unseen test datasets to evaluate its performance. This step is crucial for understanding how the model will perform in real-world scenarios.\n\nThe accuracy of the model will be assessed by comparing its interpretations with feedback provided by expert anesthesiologists.\n\nFurthermore, to comprehensively evaluate ChatGPT's effectiveness in this domain, the daily arterial blood gas results obtained in the intensive care unit will be submitted to ChatGPT for interpretation. The same questions will be posed, and the responses will be evaluated by an anesthesiology and reanimation specialist. These questions will be asked to the model:\n\nAssessment of Acidosis and Alkalosis, Evaluation of Hypoxemia and Hyperoxemia, Evaluation of Hemoglobin Parameters, Assessment of Electrolytes, Evaluation of Metabolic Parameters (Glucose, Lactate, Bilirubin)"}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['ADULT', 'OLDER_ADULT'], 'minimumAge': '18 Years', 'samplingMethod': 'PROBABILITY_SAMPLE', 'studyPopulation': 'A minimum of 398 arterial blood gas samples from patients in the intensive care unit will be included in the study', 'healthyVolunteers': False, 'eligibilityCriteria': 'Inclusion Criteria:\n\n* Patients aged 18 and above will be included in the study.\n* The study will evaluate arterial blood gas results.\n\nExclusion Criteria:\n\n* Venous blood gas results,\n* Blood gas results with calibration errors,\n* Blood gas results with incomplete data'}, 'identificationModule': {'nctId': 'NCT06456866', 'briefTitle': 'Assessing the Accuracy of ChatGPT-4 in Interpreting Arterial Blood Gas Results', 'organization': {'class': 'OTHER', 'fullName': 'Kanuni Sultan Suleyman Training and Research Hospital'}, 'officialTitle': 'Assessing the Accuracy of ChatGPT-4 in Interpreting Arterial Blood Gas Results', 'orgStudyIdInfo': {'id': 'Blood gases'}}, 'armsInterventionsModule': {'armGroups': [{'label': 'ChatGPT', 'interventionNames': ['Other: interpretation']}, {'label': 'Anesthesiology expert', 'interventionNames': ['Other: interpretation']}], 'interventions': [{'name': 'interpretation', 'type': 'OTHER', 'description': 'interpretation of blood gases samples', 'armGroupLabels': ['Anesthesiology expert', 'ChatGPT']}]}, 'contactsLocationsModule': {'locations': [{'zip': '34303', 'city': 'Istanbul', 'country': 'Turkey (Türkiye)', 'facility': 'Health Science University İstanbul Kanuni Sultan Süleyman Education and Training Hospital', 'geoPoint': {'lat': 41.01384, 'lon': 28.94966}}]}, 'ipdSharingStatementModule': {'ipdSharing': 'NO', 'description': 'there will be no IPD in this research. The investigators will only use blood gases samples and delete all the IPD.'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'Kanuni Sultan Suleyman Training and Research Hospital', 'class': 'OTHER'}, 'responsibleParty': {'type': 'PRINCIPAL_INVESTIGATOR', 'investigatorTitle': 'anesthesiology and reanimation specialist', 'investigatorFullName': 'Engin Ihsan Turan', 'investigatorAffiliation': 'Kanuni Sultan Suleyman Training and Research Hospital'}}}}