Modern Machine Learning Practices in Colorectal Surgery: A Scoping Review.

Area of Science:

• Medical Informatics
• Surgical Technology
• Artificial Intelligence in Medicine

Background:

• Machine learning (ML) is transforming medical practices, including surgery.
• ML models offer high precision in disease detection and outcome prediction.
• ML-guided colorectal surgeries demonstrate increased efficiency compared to traditional methods.

Purpose of the Study:

• To provide a comprehensive overview of recent research on ML applications in colorectal surgery.
• To identify and discuss the viable applications of ML within this surgical domain.

Main Methods:

• A systematic literature search was conducted using PubMed, Google Scholar, Medline, and the Cochrane Library.
• Screening of 172 articles resulted in the inclusion of 27 relevant studies.
• Included articles exclusively focused on ML in colorectal surgery with validated applications.

Main Results:

• Identified current applications of ML in colorectal surgery.
• Detailed the benefits, risks, and safety considerations associated with ML implementation.
• Highlighted the need for justified and evidence-based applications of ML.

Conclusions:

• Enhanced ML integration in surgery requires collaborative efforts between clinicians and data scientists to overcome current limitations.
• Addressing patient perspectives and perceived unreliability is essential for widespread adoption.
• Further research with precise outcomes is necessary to build societal confidence in ML-driven surgical advancements.