Photo Credit: PhonlamaiPhoto
The following is a summary of “Artificial Intelligence Assisted Surgical Scene Recognition: A Comparative Study Amongst Healthcare Professionals,” published in the October 2024 issue of Surgery by Williams et al.
Modern microscopic surgery captures vast amounts of operative video data, while advances in artificial intelligence (AI) enable automated analysis that could benefit patients and healthcare systems.
Researchers conducted a prospective study comparing a deep-learning model’s and healthcare professionals’ abilities in detecting cerebral aneurysms.
They conducted a cross-sectional comparative study in which neurosurgeons, anesthetists, and operating room (OR) nurses at variable stages of training and experience reviewed still frames from aneurysm clipping operations and labeled them as “aneurysm not in frame” or “aneurysm in frame” (n=5,154). The frames were then analyzed by the AI platform. A second round of data collection involved the neurosurgical team with AI assistance. The accuracy of aneurysm detection was calculated for human-only, AI-only, and AI-assisted human groups.
The results showed that healthcare professionals accurately labeled 70% of frames without AI assistance compared to 78% with AI assistance (OR 1.77, P<0.001). Neurosurgical attending demonstrated the most significant improvement, increasing from 77% to 92% correct predictions with AI assistance (OR 4.24, P=0.003).
They concluded that AI-assisted detection improved accuracy across all healthcare professionals, highlighting the significant role of AI in enhancing surgical performance.
