Ensuring the Quality of Surgical Instruments with Artificial Intelligence: A Focus on Sternum Wire

Abstract

Aim: This study aimed to investigate the Effectiveness of integrating artificial intelligence (AI) into quality assurance processes for surgical instruments, specifically focusing on sternum wire used in cardiac and thoracic surgeries. Methods: A total of 200 samples of sterile stainless-steel suture wire were evaluated according to established regulatory standards, including GG-N-211b and ISO 9001. Key quality parameters analyzed included needle strength, sharpness, configuration, penetration force, and labeling. Quality assessments were performed using traditional manual methods as well as automated machine vision systems, which were comprised of vision processing hardware, monochrome cameras, LED lighting, and communication protocols for precise control. Results: The study revealed that the automated machine vision systems markedly reduced inspection time while achieving an overall accuracy of 96% in detecting needle quality, compared to 80% accuracy with manual inspections. The new AI-driven visual inspection approach significantly outperformed traditional methods, particularly in identifying nuanced and objective defects. Conclusion: The results of our study highlight the potential of AI-powered quality assurance systems to enhance the efficiency and effectiveness of inspections for high-risk medical devices, ultimately promoting patient safety during surgical procedures.