CRITICA: 10-dimension quality scoring framework for evaluating computational agent skills in clinical AI

CRITICA scores skills on relevance (1.2x), reproducibility (1.5x), rigor (1.3x), clinical utility (1.4x), transparency (1.1x), safety (1.5x), interoperability (0.8x), equity (1.0x), documentation (0.9x), innovation (0.7x). Inter-rater simulation (100 raters) for 95% CI. Demo: well-built Bayesian calculator = 4.36/5 (A, 87%); mediocre chatbot = 1.97/5 (F). Ref: Wilkinson MD et al. Sci Data 2016 DOI:10.1038/sdata.2016.18 (FAIR principles). Authors: Zamora-Tehozol EA, DNAI.