Artificial intelligence in colorectal surgery: an AI-powered systematic review.

Area of Science:

• Surgical Innovation
• Medical Informatics
• Computational Medicine

Background:

• Artificial intelligence (AI) presents transformative potential for surgical procedures.
• Understanding current applications and future expectations of AI in colorectal surgery is crucial.
• This review focuses on the perioperative roles of AI in this surgical specialty.

Purpose of the Study:

• To systematically review and define the perioperative applications of artificial intelligence (AI) in colorectal surgery.
• To assess the current state and future potential of AI technologies in this field.
• To identify key areas where AI is being utilized or explored.

Main Methods:

• A systematic literature search adhering to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines was performed.
• Databases searched included PubMed, Embase, Scopus, and Cochrane Library, along with gray literature.
• Natural language processing (NLP) and machine learning (ML) software aided in identifying potentially eligible studies from January 1997 to March 2021.

Main Results:

• Out of 1238 identified articles, 115 were included in the final analysis.
• Preoperative applications include treatment algorithm tailoring, decision support, complication risk assessment, and outcome prediction.
• Intraoperative uses involve AI-enhanced surgery and robotic integration, while postoperative applications focus on Enhanced Recovery after Surgery (ERAS) pathways.

Conclusions:

• AI in colorectal surgery is currently in its early stages, with limited available data.
• Potential applications span preoperative, intraoperative, and postoperative phases, including pathology assessment and research.
• The rapid advancement of AI suggests its increasing integration into routine surgical practice is probable.