Ignite Creation Date:
2025-12-24 @ 11:15 PM
Ignite Modification Date:
2026-01-01 @ 11:31 PM
Study NCT ID:
NCT07043556
Status:
RECRUITING
Last Update Posted:
2025-07-18
First Post:
2025-06-21
Is Gene Therapy:
True
Has Adverse Events:
False
Brief Title:
Assessment of Artificial Intelligence Algorithms for ROTEM
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2025-12-24'}, 'conditionBrowseModule': {'meshes': [{'id': 'D020141', 'term': 'Hemostatic Disorders'}], 'ancestors': [{'id': 'D014652', 'term': 'Vascular Diseases'}, {'id': 'D002318', 'term': 'Cardiovascular Diseases'}, {'id': 'D006474', 'term': 'Hemorrhagic Disorders'}, {'id': 'D006402', 'term': 'Hematologic Diseases'}, {'id': 'D006425', 'term': 'Hemic and Lymphatic Diseases'}]}}, 'protocolSection': {'designModule': {'studyType': 'OBSERVATIONAL', 'designInfo': {'timePerspective': 'PROSPECTIVE', 'observationalModel': 'OTHER'}, 'enrollmentInfo': {'type': 'ESTIMATED', 'count': 144}, 'targetDuration': '30 Days', 'patientRegistry': True}, 'statusModule': {'overallStatus': 'RECRUITING', 'startDateStruct': {'date': '2025-07-01', 'type': 'ACTUAL'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2025-07', 'completionDateStruct': {'date': '2025-12-15', 'type': 'ESTIMATED'}, 'lastUpdateSubmitDate': '2025-07-15', 'studyFirstSubmitDate': '2025-06-21', 'studyFirstSubmitQcDate': '2025-06-21', 'lastUpdatePostDateStruct': {'date': '2025-07-18', 'type': 'ACTUAL'}, 'studyFirstPostDateStruct': {'date': '2025-06-29', 'type': 'ACTUAL'}, 'primaryCompletionDateStruct': {'date': '2025-12-05', 'type': 'ESTIMATED'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'treatment', 'timeFrame': '1 hour', 'description': 'Agreement (yes/no) between AI model and expert panel on whether treatment is indicated.'}], 'secondaryOutcomes': [{'measure': 'Agreement on Type of Coagulopathy as Determined by ROTEM Analysis Between AI Model and Expert Panel', 'timeFrame': '1 Hour', 'description': 'Agreement on type of coagulopathy'}, {'measure': 'Concordance of ROTEM-Based Treatment Recommendations Between AI and Expert Panel', 'timeFrame': '1 Hour', 'description': 'Concordance of treatment recommendations (fibrinogen, PCC, plasma, protamine, etc.)'}]}, 'oversightModule': {'isUsExport': False, 'oversightHasDmc': False, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'conditions': ['Coagulopathy']}, 'descriptionModule': {'briefSummary': 'The goal of this observational validation study is to evaluate whether artificial intelligence (AI) models can accurately interpret ROTEM (Rotational Thromboelastometry) data and provide appropriate treatment recommendations in adult patients undergoing elective cardiac or liver transplantation surgery.\n\nThe main questions it aims to answer are:\n\nCan AI models (e.g., ChatGPT and Gemini ) accurately determine whether treatment is indicated based on ROTEM parameters? Can AI models correctly identify the type of coagulopathy (e.g., fibrinogen deficiency, platelet dysfunction)? Are the treatment recommendations from AI models concordant with expert clinical consensus? Researchers will compare the decisions made by AI models to a gold standard expert panel to see if AI models can match or approximate expert-level decision-making in interpreting ROTEM outputs.\n\nParticipants will:\n\nUndergo elective cardiac or liver transplant surgery. Have standard ROTEM tests performed intraoperatively.\n\nHave their anonymized ROTEM data reviewed independently by:\n\nA panel of 3 clinical experts. AI models (ChatGPT and Gemini) using standardized prompts and ROTEM interpretation guidelines.', 'detailedDescription': 'Rotational thromboelastometry (ROTEM) is a point-of-care viscoelastic testing method used to assess the coagulation status of patients undergoing high-risk surgical procedures, such as cardiac surgery and liver transplantation. While ROTEM-guided transfusion algorithms have improved clinical outcomes, the accurate interpretation of ROTEM results remains complex and heavily dependent on clinical experience.\n\nThis prospective observational validation study aims to assess the accuracy and clinical decision-making performance of artificial intelligence (AI)-based language models in interpreting ROTEM findings. The study will compare the AI-based evaluations to expert consensus in terms of both diagnostic accuracy and treatment recommendations.\n\nDe-identified ROTEM case data will be converted into structured clinical vignettes, which will be independently interpreted by at least three experienced clinicians (serving as the gold standard) and AI models. Each AI system will be prompted with ROTEM parameters in a standardized format and asked to assess coagulopathy type and suggest appropriate treatment options. ROTEM interpretation algorithms, such as Görlinger\'s protocol, will be provided as background context to ensure consistent guidance.\n\nThe study will include adult patients (≥18 years) undergoing elective cardiac surgery or liver transplantation, provided complete and technically valid ROTEM results are available. The main outcome of the study is the agreement between AI-based and expert decisions regarding the need for treatment. Secondary outcomes include diagnostic classification of coagulopathy, concordance in treatment recommendations, and standard accuracy metrics (sensitivity, specificity, PPV, NPV, overall accuracy, and Cohen\'s Kappa).\n\nThis study does not involve any direct patient interventions or changes in treatment based on AI output. All data will be anonymized before analysis, and informed consent will be obtained from all participants.\n\nAs part of the AI evaluation and expert comparison, each ROTEM clinical scenario will be assessed based on a standardized set of 14 structured clinical questions. These questions are designed to determine both the presence and type of coagulopathy, as well as the appropriate treatment recommendations. The specific questions are:\n\nIs there evidence of coagulopathy based on the ROTEM findings?\n\nDo the ROTEM results indicate hyperfibrinolysis?\n\nDo the findings suggest the presence of residual heparin effect?\n\nIs there evidence of fibrinogen deficiency?\n\nIs there evidence of thrombocytopenia or platelet dysfunction?\n\nDo the results indicate coagulation factor deficiency?\n\nDo the findings suggest protamine overdose?\n\nIs treatment not required at this time?\n\nIs antifibrinolytic therapy indicated?\n\nShould protamine be administered?\n\nShould fibrinogen or fibrinogen-containing products be administered?\n\nShould platelet transfusion be performed?\n\nShould prothrombin complex concentrate (PCC) or fresh frozen plasma (FFP) be administered?\n\nIf bleeding continues, should reassessment be done after 10-15 minutes?\n\nEach question will be answered as "Yes" or "No" by both the AI system and the expert panel, and the responses will be used to calculate diagnostic and treatment concordance metrics.'}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['ADULT', 'OLDER_ADULT'], 'minimumAge': '18 Years', 'samplingMethod': 'PROBABILITY_SAMPLE', 'studyPopulation': 'The study population consists of adult patients (aged 18 years and older) undergoing elective cardiac surgeries-including coronary artery bypass grafting (CABG), valve surgery, and aortic procedures-and elective liver transplantation procedures. All participants will have complete and analyzable intraoperative ROTEM (Rotational Thromboelastometry) data available. Only patients who are able to provide written informed consent will be enrolled. Emergency cases, pediatric patients, and those with technically invalid ROTEM results will be excluded.', 'eligibilityCriteria': 'Inclusion Criteria:\n\n* Adult patients undergoing elective cardiac surgery (CABG, valve surgery, aortic procedures)\n* Adult patients undergoing liver transplantation\n* Availability of complete ROTEM results (EXTEM, INTEM, FIBTEM, +/- HEPTEM, APTEM)\n* Informed written consent obtained\n\nExclusion Criteria:\n\n* Incomplete or technically invalid ROTEM data\n* Pediatric patients (\\<18 years)\n* Refusal to participate or lack of informed consent\n* Emergency and redo surgeries'}, 'identificationModule': {'nctId': 'NCT07043556', 'briefTitle': 'Assessment of Artificial Intelligence Algorithms for ROTEM', 'organization': {'class': 'OTHER', 'fullName': 'Ondokuz Mayıs University'}, 'officialTitle': 'Assessment of Artificial Intelligence Algorithms for ROTEM Analysis in Coagulation Management', 'orgStudyIdInfo': {'id': 'ROTEM-AI'}}, 'armsInterventionsModule': {'interventions': [{'name': 'Artificial Intelligence-Based ROTEM Interpretation', 'type': 'OTHER', 'description': 'A structured artificial intelligence-based evaluation system that analyzes ROTEM (Rotational Thromboelastometry) parameters and provides treatment recommendations. ROTEM case data are converted into standardized clinical scenarios and evaluated by AI models using a predefined template. The AI output is compared to the consensus of expert clinicians regarding the presence and type of coagulopathy and the need for therapeutic intervention (e.g., fibrinogen, protamine, platelets, PCC, plasma). This intervention does not involve any patient-facing activity and is performed on de-identified data only.'}]}, 'contactsLocationsModule': {'locations': [{'city': 'Istanbul', 'status': 'RECRUITING', 'country': 'Turkey (Türkiye)', 'contacts': [{'name': 'Hüseyin İlksen Toprak', 'role': 'CONTACT'}], 'facility': 'İstanbul Aydın Üniversitesi Sağlık Uygulama ve Araştırma Merkezi Medical Park Florya Hastanesi', 'geoPoint': {'lat': 41.01384, 'lon': 28.94966}}, {'city': 'Samsun', 'status': 'RECRUITING', 'country': 'Turkey (Türkiye)', 'contacts': [{'name': 'Burhan DOST', 'role': 'CONTACT', 'email': 'burhandost@hotmail.com', 'phone': '+905327042493'}], 'facility': 'Ondokuz Mayis University', 'geoPoint': {'lat': 41.27976, 'lon': 36.3361}}], 'centralContacts': [{'name': 'Burhan Dost, Assoc. Prof.', 'role': 'CONTACT', 'email': 'burhandost@hotmail.com', 'phone': '+90 532 704 24 93'}], 'overallOfficials': [{'name': 'Burhan Dost, Assoc. Prof.', 'role': 'PRINCIPAL_INVESTIGATOR', 'affiliation': 'Ondokuz Mayıs University'}]}, 'ipdSharingStatementModule': {'infoTypes': ['STUDY_PROTOCOL', 'SAP'], 'timeFrame': '2 years', 'ipdSharing': 'YES', 'description': 'De-identified individual participant data (IPD), including demographic characteristics, surgical category, and ROTEM parameter values, may be shared upon reasonable request and at the discretion of the corresponding author. Requests will be evaluated based on the scientific validity of the proposal and availability of resources. No personal identifiers will be included, and data will be provided only after the publication of study results.'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'Ondokuz Mayıs University', 'class': 'OTHER'}, 'responsibleParty': {'type': 'PRINCIPAL_INVESTIGATOR', 'investigatorTitle': 'Associated Proffessor', 'investigatorFullName': 'BURHAN DOST', 'investigatorAffiliation': 'Ondokuz Mayıs University'}}}}