Leveraging artificial intelligence to support surgical oncology multidisciplinary team decision-making: a systematic...

Area of Science:

• Oncology
• Medical Informatics
• Artificial Intelligence

Background:

• Artificial intelligence (AI)-based clinical decision support systems (CDSSs) are increasingly utilized to aid clinicians in providing evidence-based treatment recommendations for multidisciplinary team (MDT) meetings.
• This systematic review aims to map the current landscape of AI-based CDSSs in surgical oncology decision-making.

Purpose of the Study:

• To systematically review and synthesize evidence on the performance of AI-based CDSSs in surgical oncology decision-making.
• To identify factors influencing the effectiveness and implementation of these systems within MDT settings.

Main Methods:

• A systematic search of Cochrane, Ovid MEDLINE, and Embase databases was conducted on February 3, 2025.
• Studies evaluating AI-based CDSSs for therapeutic decision-making in surgical oncology were included.
• Methodological quality was assessed using the Critical Appraisal Skills Programme Diagnostic Study Checklist, and data were synthesized narratively.

Main Results:

• Fifty-nine studies involving 23,158 patients were included, categorizing CDSSs into five types: decision tree-based, knowledge representation-based, Watson for Oncology, large language models, and others.
• Concordance with MDT or guideline recommendations varied widely (23.2%–99%), with decision tree- and knowledge-based systems showing higher concordance.
• Implementation challenges included technical limitations, socioeconomic/healthcare system constraints, and patient/tumor-specific factors. Benefits included improved guideline adherence and clinical trial identification.

Conclusions:

• AI-based CDSSs demonstrate potential in supporting surgical oncology MDT decision-making, offering benefits like improved guideline adherence and clinical trial enrollment.
• Significant challenges persist, including system maintenance, protocol variability, therapeutic availability, and patient heterogeneity.
• Larger prospective studies are essential to evaluate the real-world integration, clinical impact, and patient outcomes of AI-based CDSSs in MDT workflows.