Skip to main content
Search

Centre Hospitalier Universitaire Vaudois

2 related articles

Subscribe to updates
  1. medRxiv

    Variant interpretation moves into the hospital server room: a 9B local model writes ACMG reports and recovers 93% of causal variants in 327 singleton cases

    A 9B small language model running on one local GPU performs case-level and trio-based variant interpretation, recovering 93% of expert-reported causal variants across 327 solved singleton visual-impairment cases and classifying 82% of them as pathogenic or likely pathogenic.

  2. 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.

You’re all caught up