This prospective multicenter observational study aims to evaluate the agreement between artificial intelligence (AI)-based interpretation and expert interpretation of rotational thromboelastometry (ROTEM) findings in clinically relevant settings. ROTEM is widely used to guide hemostatic therapy in perioperative and critically ill patients, but its interpretation is complex and subject to interobserver variability. The primary objective is to determine whether AI-based interpretation achieves agreement comparable to variability between expert clinicians. Secondary objectives include comparison of interpretation time, assessment of consistency of AI outputs, and evaluation of potential differences in clinical decision-making. ROTEM datasets will be independently assessed by multiple expert anesthesiologists and by an AI-based model using standardized input. Agreement between methods and variability of interpretation will be analyzed. The study aims to determine whether AI-assisted interpretation could serve as a reliable decision-support tool and reduce variability in ROTEM-guided clinical practice.
This prospective multicenter observational study is designed to evaluate the agreement between artificial intelligence (AI)-based interpretation and expert interpretation of rotational thromboelastometry (ROTEM) findings, with a focus on clinical decision-making in critically ill patients. ROTEM is a point-of-care viscoelastic method providing real-time information on coagulation, including clot formation, strength, and fibrinolysis. It is widely used to guide targeted hemostatic therapy in trauma, major surgery, and critical care. However, interpretation of ROTEM findings is complex and requires clinical expertise. Interobserver variability among clinicians may lead to inconsistent therapeutic decisions. Although algorithm-based approaches have been introduced, their implementation remains variable. Artificial intelligence (AI) has the potential to standardize interpretation by integrating multiple ROTEM parameters and generating consistent recommendations. Previous studies have shown that machine learning models can predict clinical outcomes or transfusion requirements based on viscoelastic data. However, evidence on agreement between AI-based interpretation and expert interpretation, particularly in real-world clinical decision-making, remains limited. The primary objective of this study is to determine whether AI-based interpretation achieves a level of agreement comparable to inter-expert variability in ROTEM interpretation. This study does not assume a single gold standard; instead, it evaluates agreement between methods, reflecting real-world clinical practice. Secondary objectives include: * comparison of interpretation time between AI and expert clinicians, * assessment of consistency (intra-method variability) of AI compared to inter-expert variability, * evaluation of potential impact on clinical decision-making, including identification of coagulation abnormalities and proposed treatment strategies. ROTEM measurements will be collected and presented in a standardized format, including graphical and numerical outputs. Each dataset will be independently evaluated by multiple expert anesthesiologists. The same datasets will be interpreted repeatedly by an AI-based large language model using a predefined standardized prompt, with multiple independent runs to assess intra-model variability. For each ROTEM dataset, both experts and AI will assess: * presence of a coagulation disorder, * dominant underlying abnormality, * appropriate therapeutic intervention, * and recommended treatment dose. Agreement between experts and AI, as well as inter-expert agreement, will be analyzed using appropriate statistical methods for categorical and continuous variables (e.g., kappa statistics and intraclass correlation coefficients). Time required for interpretation will also be recorded and compared. This study is not designed to determine the absolute correctness of interpretation, but to quantify agreement and variability between human experts and AI. By identifying clinically relevant discrepancies, the study aims to evaluate whether AI-assisted interpretation may serve as a reliable decision-support tool and reduce variability in ROTEM-guided hemostatic management.
Study Type
OBSERVATIONAL
Enrollment
400
The thromboelastography record will be assessed by LLM based artificial intelligence.
Agreement between AI-based and expert interpretation of ROTEM findings
Agreement between artificial intelligence (AI)-based interpretation and expert interpretation of ROTEM findings will be assessed and compared to inter-expert agreement. Agreement will be evaluated for predefined clinical decision outputs, including: * presence of coagulation disorder (yes/no), * identification of dominant coagulation abnormality (categorical), * selection of therapeutic intervention (categorical), * and recommended treatment dose (continuous). Agreement will be quantified using appropriate statistical methods for categorical and continuous data (e.g., Cohen's/Fleiss' kappa and intraclass correlation coefficients).
Time frame: Up to 24 hours after ROTEM measurement (time required for interpretation and data recording).
Interpretation time
Time required for interpretation of ROTEM findings by expert clinicians compared to AI-based interpretation. For experts, time will be measured from presentation of the ROTEM result to completion of responses. For AI, time will be measured from submission of the standardized query to completion of output generation.
Time frame: Up to 24 hours after ROTEM measurement.
Consistency of interpretation (intra-method variability)
Variability of AI-based interpretation across repeated independent runs will be assessed and compared with inter-expert variability. Consistency will be evaluated for all predefined outputs (diagnosis, treatment, dosing).
Time frame: Up to 24 hours after ROTEM measurement
Proportion of clinically discordant decisions
Proportion of cases in which AI-based interpretation differs from expert interpretation in clinically relevant outputs, including: * disagreement in diagnosis of coagulation disorder, * disagreement in selected treatment strategy, * or clinically relevant difference in recommended dose.
Time frame: Up to 24 hours after ROTEM measurement
Inter-expert agreement
Agreement between individual expert clinicians in interpretation of ROTEM findings will be evaluated to define baseline interobserver variability and provide a reference for comparison with AI-based interpretation.
Time frame: Up to 24 hours after ROTEM measurement
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.