Artificial Intelligence in Bariatric Surgery: Current Status and Future Perspectives

Area of Science:

• Medical Informatics
• Surgical Technology

Background:

• Machine learning (ML) applications are expanding in healthcare but are underutilized in bariatric surgery.
• This systematic review provides an overview of ML's current role in bariatric surgery.

Purpose of the Study:

• To systematically review and summarize the applications of machine learning in bariatric surgery.
• To assess the predictive capabilities of ML algorithms for bariatric surgery outcomes.

Main Methods:

• Searched major databases (PubMed, EMBASE, Cochrane, Web of Science) for relevant studies.
• Evaluated the quality of included studies using the Cochrane risk of bias and PROBAST tools.

Main Results:

• Machine learning algorithms demonstrated high predictive accuracy, reaching up to 98% for postoperative complications and weight loss.
• The majority of ML applications focused on predicting key surgical outcomes.

Conclusions:

• Machine learning algorithms show significant potential for predicting surgical outcomes in bariatric procedures.
• External validation of ML models is crucial for their successful clinical implementation in bariatric surgery.