Ignite Creation Date:
2025-12-25 @ 3:03 AM
Ignite Modification Date:
2026-01-01 @ 4:52 AM
Study NCT ID:
NCT06726733
Status:
NOT_YET_RECRUITING
Last Update Posted:
2024-12-10
First Post:
2024-12-06
Is NOT Gene Therapy:
True
Has Adverse Events:
False
Brief Title:
Assessing Intensive Care Unit (ICU) Indications: Human vs. ChatGPT-4o Predictions
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2025-12-24'}}, 'protocolSection': {'designModule': {'studyType': 'OBSERVATIONAL', 'designInfo': {'timePerspective': 'RETROSPECTIVE', 'observationalModel': 'CASE_CONTROL'}, 'enrollmentInfo': {'type': 'ESTIMATED', 'count': 500}, 'patientRegistry': False}, 'statusModule': {'overallStatus': 'NOT_YET_RECRUITING', 'startDateStruct': {'date': '2024-12-28', 'type': 'ESTIMATED'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2024-12', 'completionDateStruct': {'date': '2025-02', 'type': 'ESTIMATED'}, 'lastUpdateSubmitDate': '2024-12-06', 'studyFirstSubmitDate': '2024-12-06', 'studyFirstSubmitQcDate': '2024-12-06', 'lastUpdatePostDateStruct': {'date': '2024-12-10', 'type': 'ACTUAL'}, 'studyFirstPostDateStruct': {'date': '2024-12-10', 'type': 'ACTUAL'}, 'primaryCompletionDateStruct': {'date': '2025-02', 'type': 'ESTIMATED'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'Accuracy rate of ChatGPT-4 in predicting ICU indications', 'timeFrame': '3 month'}, {'measure': 'False positive rate', 'timeFrame': '3 month'}, {'measure': 'False negative rate', 'timeFrame': '3 month'}], 'secondaryOutcomes': [{'measure': 'Kappa statistic', 'timeFrame': '3 month'}]}, 'oversightModule': {'oversightHasDmc': False, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'keywords': ['AI', 'Intensive Care Unit', 'Clinical decision-making', 'Artificial Intelligenc'], 'conditions': ['Intensive Care Unit (ICU) Admission', 'Emergency Department Patient', 'Artificial Intelligence (AI)', 'Clinical Decision-making']}, 'descriptionModule': {'briefSummary': 'This retrospective study evaluates the accuracy of ICU admission indications by comparing clinical decisions with predictions from ChatGPT-4. Patient data, including demographics, vital signs, laboratory results, imaging findings, and clinical decisions, will be retrospectively collected and documented systematically using Case Report Forms. The model will be trained using ICU admission guidelines and tasked to predict ICU needs based on collected patient data. This study aims to systematically assess the alignment between AI-based predictions and clinical decisions for ICU admissions.', 'detailedDescription': 'This study has a retrospective design. The medical data of patients admitted to the emergency department and consulted to the anesthesiology and reanimation clinic for ICU indications will be collected retrospectively. Demographic information, vital signs, laboratory results, imaging findings, and clinical decisions of the patients will be recorded. These data will be systematically collected for each patient using an individual Case Report Form.\n\nInclusion Criteria for the Study:\n\nPatients aged 18 years and older who were consulted to the anesthesiology and reanimation clinic for ICU indications from the emergency department will be included in the study.\n\nExclusion Criteria for the Study:\n\nPatients consulted to the anesthesiology and reanimation clinic for ICU indications from inpatient services.\n\nPatients consulted to the anesthesiology and reanimation clinic from the emergency department for reasons other than ICU indications.\n\nPatients consulted to the anesthesiology and reanimation clinic for ICU indications from the emergency department but with insufficient recorded data (patients with data loss).\n\nModel Training and Prediction Analysis:\n\nChatGPT-4 will be trained according to the guidelines in "Yoğun Bakım Hasta Kabul Kriterleri (Rehberleri)" by Çiftçi B, Erdoğan C, and Demiraran Y (5). The collected patient data will be presented to the ChatGPT-4 model to obtain predictions regarding whether the patients require ICU admission. The predictions made by ChatGPT will be compared with clinical decisions, and accuracy rate, false positive rate, and false negative rate will be analyzed.\n\nStatistical Analysis Methods to Be Used in the Study:\n\nAccuracy Rate: The rate at which ChatGPT correctly predicts ICU indications will be calculated.\n\nFalse Positive Rate: The rate at which ChatGPT predicts ICU need for patients who do not require ICU admission will be evaluated.\n\nFalse Negative Rate: The rate at which ChatGPT predicts no ICU need for patients who require ICU admission will be analyzed.\n\nKappa Statistics: The agreement between ChatGPT predictions and clinical decisions will be measured.\n\nROC Curve and AUC: The performance of ChatGPT will be evaluated using the ROC curve and AUC.\n\nThe Case Report Form used for each patient ensures detailed and systematic data collection of clinical information, aiming to meaningfully compare the alignment of ChatGPT\'s predictions with clinical decisions.'}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['ADULT', 'OLDER_ADULT'], 'minimumAge': '18 Years', 'samplingMethod': 'NON_PROBABILITY_SAMPLE', 'studyPopulation': '500', 'eligibilityCriteria': 'Inclusion Criteria:\n\n* Patients aged 18 years and older who are consulted to the anesthesiology and reanimation clinic for ICU indications from the emergency department will be included in the study.\n\nExclusion Criteria:\n\n* Patients consulted to the anesthesiology and reanimation clinic for ICU indications from inpatient services.\n* Patients consulted to the anesthesiology and reanimation clinic from the emergency department for reasons other than ICU indications.\n* Patients consulted to the anesthesiology and reanimation clinic for ICU indications from the emergency department but with insufficient recorded data (patients with data loss)'}, 'identificationModule': {'nctId': 'NCT06726733', 'acronym': 'ICU', 'briefTitle': 'Assessing Intensive Care Unit (ICU) Indications: Human vs. ChatGPT-4o Predictions', 'organization': {'class': 'OTHER_GOV', 'fullName': 'Bursa Yuksek Ihtisas Training and Research Hospital'}, 'officialTitle': 'Evaluation of the Accuracy of Intensive Care Unit (ICU) Admission Indications in Emergency Department Patients: A Comparison Between Clinical Decisions and ChatGPT-4o Prediction', 'orgStudyIdInfo': {'id': 'BYIEAH-INKA'}}, 'contactsLocationsModule': {'locations': [{'city': 'Bursa', 'country': 'Turkey (Türkiye)', 'facility': 'Bursa Yuksek Ihtisas Training and Research Hospital', 'geoPoint': {'lat': 40.19559, 'lon': 29.06013}}], 'centralContacts': [{'name': 'İlkay Ceylan', 'role': 'CONTACT', 'email': 'ceylanilkay@yahoo.com', 'phone': '+902243664434'}, {'name': 'Aycan Kurtarangil Doğan', 'role': 'CONTACT', 'email': 'akurtarangil@gmail.com', 'phone': '+902243664434'}], 'overallOfficials': [{'name': 'İlkay Ceylan', 'role': 'PRINCIPAL_INVESTIGATOR', 'affiliation': 'ceylanilkay@yahoo.com'}]}, 'ipdSharingStatementModule': {'ipdSharing': 'NO'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'Bursa Yuksek Ihtisas Training and Research Hospital', 'class': 'OTHER_GOV'}, 'responsibleParty': {'type': 'PRINCIPAL_INVESTIGATOR', 'investigatorTitle': 'Doctor of anesthesiology and reanimation', 'investigatorFullName': 'Aycan KURTARANGİL DOĞAN', 'investigatorAffiliation': 'Bursa Yuksek Ihtisas Training and Research Hospital'}}}}