Artificial Intelligence and Digital Tools Across the Hepato-Pancreato-Biliary Surgical Pathway: A Systematic Review

Area of Science:

• Surgical Innovation
• Medical Imaging
• Artificial Intelligence in Medicine

Background:

• Hepato-pancreato-biliary (HPB) surgery demands high precision in imaging, planning, and decision-making.
• Artificial intelligence (AI) and digital technologies are emerging as valuable tools in HPB surgical care.
• These technologies offer potential advancements in various aspects of HPB surgical procedures.

Purpose of the Study:

• To systematically review the application of AI and digital technologies in HPB surgical care.
• To evaluate the impact of these technologies on imaging interpretation, preoperative planning, intraoperative guidance, and outcome prediction.
• To synthesize current evidence on the efficacy and feasibility of AI in HPB surgery.

Main Methods:

• A PRISMA-guided systematic review was conducted, including studies published up to June 2025.
• Searched for AI/digital technologies like machine learning, deep learning, radiomics, augmented/mixed reality, and computer vision in HPB surgery.
• Focused on studies addressing imaging interpretation, preoperative planning, intraoperative guidance, or outcome prediction.

Main Results:

• 38 studies met inclusion criteria, demonstrating AI's high diagnostic performance in lesion detection/classification (AUC ~0.80-0.98).
• Machine learning models showed superior prediction of postoperative complications compared to traditional scores.
• AI-assisted 3D reconstructions, AR/MR systems, and computer vision enhanced preoperative planning and intraoperative navigation/safety.

Conclusions:

• AI and digital tools demonstrate promising results across the HPB surgical pathway, from diagnostics to intraoperative guidance.
• Current evidence supports technical feasibility and suggests potential clinical benefits.
• Prospective, multicenter validation, consistent reporting, and attention to implementation factors are crucial for routine adoption and realizing full clinical impact.