AI advice for colorectal liver metastases moves beyond prompting: encoding the surgeon's reasoning lifted overall concordance from 0.444 to 0.626
Decisions in colorectal liver metastases weigh tumor biology, resectability and future liver remnant, and large language models previously produced recommendations from prompting alone with limited agreement with expert multidisciplinary practice. The METATRON study formalized the evaluation sequence hepatobiliary surgeons follow at tumor boards into a structured workflow and combined it with guideline retrieval, testing 110 synthetic vignettes scored by three independent LLM judges across five dimensions. The workflow-plus-retrieval strategy reached the highest composite score (0.626 versus 0.444 for baseline), yet sensitivity for anatomical resectability remained 40%, insufficient for autonomous clinical use.