Executable change control for clinical AI: every model update, by an engineer, a pipeline or an AI agent, is checked against its approved change plan (FDA PCCP, EU AI Act Art. 43(4)).
-
Updated
Oct 20, 2026 - Python
Executable change control for clinical AI: every model update, by an engineer, a pipeline or an AI agent, is checked against its approved change plan (FDA PCCP, EU AI Act Art. 43(4)).
VIGILANT: Measurements for Adaptive AI
FDA GMLP + PCCP validation evidence for ML-based Software as a Medical Device: drift detection, subgroup fairness, PCCP change evaluation with three-band confidence routing. FastAPI + React.
FDA-Compliant Machine Learning Operations Pipeline — GMLP checklist automation, PCCP-ready model versioning, demographic bias monitoring, and drift detection
Hash-chained, append-only record schema + reference verifier for an AI/ML medical device's FDA SaMD classification lifecycle, pre-submission through 510(k)/De Novo/PMA, PCCP per FDA Dec 2024 final, post-market modifications, 21 CFR §820 QMS evidence refs. Healthcare-readiness scaffolding, not certification.
To associate your repository with the pccp topic, visit your repo's landing page and select "manage topics."