EVALLM
The ESMO framework for the evaluation of clinician-facing large language models in oncology.
Interactive checklist
28 questions for clinical evidence, institutional readiness, vendor assurance and post-deployment review.
Printable checklist
The clinical checklist with blank assessment and decision fields.
For AI agents
The agent skill and all 84 consensus statements in machine-readable form.
Evaluation domains
- 1Clinical accuracy
- 2Safety and harm
- 3Bias and equity
- 4Transparency, explainability and reproducibility
- 5Robustness, reliability and post-deployment monitoring
- 6Usability, workflow integration and clinical utility
- 7Governance, legal and ethical considerations
- 8Validation study design