Comparison of large language models and expert multidisciplinary team decisions in colorectal cancer

Key Points

• Evaluate how large language models replicate expert multidisciplinary team recommendations in colorectal cancer management.
• Comparison of LLM outputs with expert MDT recommendations
• Assessment of the accuracy of LLM predictions
• Evaluation of potential integration into clinical settings
• LLMs can partially replicate expert MDT recommendations
• Integration of LLMs should complement human expertise rather than replace it
• Highlights the value of combining human and AI decision-making in healthcare