Related Experiment Video
Updated: Jun 27, 2025
07:46
Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
Published on: August 9, 2024
711
Implementation of artificial intelligence-based computer vision model in laparoscopic appendectomy: validation,
Danit Dayan1, Nadav Dvir2, Haneen Agbariya2
1Division of General Surgery, Affiliated to Sackler Faculty of Medicine, Tel Aviv Medical Center, Tel Aviv University, 6, Weizman St., 6423906, Tel Aviv-Yafo, Israel. danitd.75@gmail.com.
Surgical Endoscopy
|April 25, 2024
Summary
An AI model accurately grades laparoscopic appendectomy complexity and safety adherence, predicting operative time but not postoperative outcomes. This technology enhances surgical assessment and efficiency in general surgery.
Area of Science:
- Artificial Intelligence in Surgery
- Computer Vision Applications
- Surgical Workflow Analysis
Background:
- The application of artificial intelligence (AI) in general surgery is rapidly advancing.
- This study presents the real-world implementation of an AI-based computer-vision model for laparoscopic appendectomy (LA).
Purpose of the Study:
- To evaluate the accuracy of an AI model in grading surgical complexity and adherence to safety protocols during LA.
- To assess the clinical correlation between AI-driven assessments and patient outcomes.
Main Methods:
- A retrospective analysis of 499 laparoscopic appendectomy videos using the 'Surgical Intelligence Platform'.
- Comparison of AI-generated annotations with manual assessments by two expert surgeons.
- Correlation of complexity grades with intraoperative and postoperative outcomes using patient data from 365 cases.
Main Results:
- The AI model demonstrated high agreement with expert surgeons for complexity grading (kappa 0.86) and full safety adherence (kappa 0.88).
- Higher complexity grades correlated with longer operative times, increased intraoperative events, and longer hospital stays.
- No significant correlation was found between complexity grade and postoperative complications, mortality, or readmissions.
Conclusions:
- The AI model accurately assesses complexity and safety in laparoscopic appendectomy.
- The AI system can predict intraoperative duration and course but shows no correlation with postoperative outcomes.
- Further research is warranted to explore the full clinical utility of AI in surgical procedures.
