PathWISE converts non-computable clinical flowchart artefacts into validated executable HL7 CQL libraries for five UK NHS cancer pathways using multi-agent LLMs and deterministic verification.
Medobvious: Exposing the medical moravec’s paradox in vlms via clinical triage.arXiv preprint arXiv:2603.23501, 2026
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
RAPTOR+ shows fine-tuned VLMs achieve higher reading accuracy and substantially better evidence grounding than zero-shot models on 223 colorectal cancer referral forms.
citing papers explorer
-
PathWISE: Multi-Agent Cancer Pathway Triaging Ontology Learning from Clinical Flowcharts
PathWISE converts non-computable clinical flowchart artefacts into validated executable HL7 CQL libraries for five UK NHS cancer pathways using multi-agent LLMs and deterministic verification.
-
RAPTOR+: A Visually Grounded Vision-Language Framework to Improve Clinical Trust and Auditability in Automated Cancer Referral Processing
RAPTOR+ shows fine-tuned VLMs achieve higher reading accuracy and substantially better evidence grounding than zero-shot models on 223 colorectal cancer referral forms.