High Medical College of Professional Studies “Milutin Milanković" , Belgrade , Serbia
High Medical College of Professional Studies “Milutin Milanković" , Belgrade , Serbia
High Medical College of Professional Studies “Milutin Milanković" , Belgrade , Serbia
Department of Kinesiology, Faculty of Sport and Physical Education, University of Nis , Niš , Serbia
Computer vision technology is increasingly being utilized in modern surgery to enhance patient safety through real-time automatic detection of critical operative events. However, challenges related to video quality, lighting conditions, and camera angles can affect system performance. This study aims to develop and evaluate an artificial intelligence-based system to accurately recognize critical surgical moments and risky situations in operating rooms. The system was developed using deep neural network algorithms and was trained on standardized surgical video recordings. The evaluation was conducted in two phases: (1) simulation testing using 50 video recordings of standardized surgical procedures, and (2) clinical testing in 10 real operating rooms. Performance metrics included precision, recall, F1-score, and ROC analysis, along with user feedback from surgical teams. During simulation testing, the system achieved a precision of 93%, a recall of 90%, and an F1-score of 91.5%. The ROC analysis yielded an AUC of 0.95, indicating high accuracy in differentiating critical from non-critical events. In the clinical environment, the system detected 88% of critical events with an average response delay of 1.2 seconds. Feedback from the surgical team indicated that 85% found the system highly useful, especially during laparoscopic procedures. The developed computer vision system demonstrated robust performance in both simulated and clinical settings. Integrating the system into clinical workflows could improve surgical safety and enhance team coordination. Further optimization is needed to reduce response delays and minimize the impact of environmental factors such as lighting and camera angles. The study highlights the potential of AI-based systems to support surgical practice, improve patient outcomes, and enhance real-time decision-making.
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.
