Counterfactual graphs over treatment, resection and progression.
Counterfactual graphs over treatment, resection and progression.
GLIO-CAUS is one of 11 subsystems that compose AURORA-GLIO. It is independently usable but shares the same patient representation, provenance log and governance layer as every other AURORA module.
AURORA-GLIO does not just predict. It tries to reason. GLIO-CAUS builds counterfactual graphs over treatments, resection extents and progression patterns, trial-aware enough to exclude confounded comparisons. The clinician sees the counterfactual band, not just the point estimate.
It is the most cautious subsystem in the module. Causal claims are easy to mis-state in medicine; the module will refuse to compare arms where the data does not support a causal contrast. That refusal is a feature, not a limitation.
GLIO-CAUS can be installed standalone, or pulled in as part of the full AURORA-GLIO stack. Both ship the same code and weights, signed end-to-end. Pilot partners have access today; public alpha opens Q4 2026.
pip install aurora-glio[caus] aurora glio.caus compare \ --arm-a "GTR + Stupp" \ --arm-b "STR + Stupp"
GLIO-CAUS moves faster when the right people are in the room. Whether you carry a service line, a registry, or a few quiet weekends — there is a way in.
Sponsor GLIO-CAUS for your unit. Co-design the surface, the audit log and the override semantics with the team that built it. Pilot sponsors keep a council seat for the duration.
Run a research question on GLIO-CAUS. Federation means you can train across populations you cannot see alone. Whitepapers carry co-authorship, not acknowledgements.
GLIO-CAUS ships starter tasks tagged 'good-first-issue' on the pilot repo. SDKs in Python, TypeScript and Rust at public alpha. MIT, no CLA.
AURORA is in private pilot today and opens to the world at public alpha in Q4 2026 under MIT. If you carry the weight of these diseases — as a clinician, scientist, builder, patient or advocate — there is a seat at the table.