Related Experiment Video
Updated: May 22, 2026
08:21
Utilizing a 3D Printed Laparoscopic Nissen Fundoplication Model to Shorten a Resident's Learning Curve
Published on: August 15, 2025
AI-driven qualitative skill assessment in laparoscopic training: a prospective observational study
Dimitrios Chatziisaak1,2,3, Moritz Sparn2, Pascal Burri4
1Department of Transplantation, Guy's & St Thomas's NHS Foundation Hospitals NHS Trust, London, UK.
NPJ Digital Medicine
|May 20, 2026
Summary
Artificial intelligence (AI) can reliably assess surgical skills using video analysis. This technology offers a scalable solution for evaluating qualitative aspects of performance in surgical training.
Area of Science:
- Surgical Education
- Medical Simulation
- Artificial Intelligence in Medicine
Background:
- Qualitative assessment of surgical skills is crucial for proficiency-based training but challenging to scale due to reliance on expert evaluators.
- Current simulator metrics provide objective data but often miss qualitative performance nuances.
- Artificial intelligence (AI)-based video analysis presents a potential solution for standardized and reproducible surgical skill assessment.
Purpose of the Study:
- To evaluate the reliability and agreement of an AI-based video analysis model for assessing qualitative surgical skills.
- To determine if AI can provide standardized and reproducible qualitative assessments comparable to expert raters.
Main Methods:
- Prospective observational study involving 50 junior surgical residents performing laparoscopic cholecystectomy on porcine models.
- Video recordings of procedures were anonymized, segmented, and assessed by expert raters and an AI model using the Global Operative Assessment of Laparoscopic Skills (GOALS).
- Statistical analysis included test-retest reliability (ICC) and agreement between AI and expert ratings.
Main Results:
- The AI model demonstrated excellent test-retest reliability for the overall GOALS score (ICC 0.91) and good reliability across most domains.
- Agreement between AI and expert ratings was excellent for the total score (ICC 0.92), with good to excellent concordance in individual domains and minimal bias.
- AI-based assessment showed high consistency and minimal deviation from expert evaluations.
Conclusions:
- AI-based video analysis offers a reliable and reproducible method for qualitative assessment of laparoscopic surgical skills.
- This technology has the potential to facilitate the scalable integration of qualitative evaluation into surgical training programs.
- AI video analysis may also be applicable to other video-based clinical assessment settings.
