Synthetic-data demo · PDPA consent & IRB approval are required before any real-data use.details
More soon

Pipeline · β-Thalassemia

v1.0.0-rc3 · model-lockedResearch preview
A
Illustrative reference pipeline. The real model pipeline runs off-platform (arm64) via make -C ml/bthal all — see the "From cohort to prediction" steps and /provenance for the real lineage + run record.
reference DAG
M0 … M16a
illustrative modules
modules shown
7 / 17
quality gates
10 passed · 0 failed · 14 pending
fitted model
XGBoost · per endpoint
ml/bthal
Pipeline DAG · 20 M-prefixed modules · local-mac
run_0061 · live
completerunningqueuedblockedhelper (not counted)
M0 · helperEnv validationM1OrchestratorM2AcquireM3c · helperChecksum + provenanceM11Cohort ingestM11s · helperSynthetic generatorM3SubsetM4QCM5AncestryM7lLD + tag SNPM6AnnotationM7Model trainM9pPGx layerM10pPRS transferabilityM12aRecalibraterecalM12Model lockM13Reports + figuresM14fFrontend static exportM15Lock + auditM16aAcceptance package
Runtime components · served alongside the build pipeline
excluded from build-DAG count and quality-gate KPI
runtime · 1
M13rruntime
Predict service
fastapi mock · batch
SLO · p95 latency < 200 ms (batch=32, 1k requests)
Fitted model
one calibrated XGBoost per endpoint
arm64 · synthetic-labeled cohort · no PHI
Contract
validation · figures · predictions
committed under public/data/bthal/
Reproduce (off-platform)
make -C ml/bthal all
cohort → train → evaluate → serve
From cohort to prediction
  1. 01generate_cohort → synthetic-labeled cohort (base rates → published anchors)
  2. 02train → one XGBoost classifier per endpoint + XGBoost regressors
  3. 03calibrate → isotonic / Platt by ECE
  4. 04evaluate → AUROC/AUPRC/Brier + calibration + DCA + TreeSHAP
  5. 05export → public/data/<id>/* contract (validation, figures, predictions)
  6. 06serve → FastAPI /predict (heuristic fallback if the server is down)
Research preview · not for clinical use · synthetic data · model v1.0.0-rc3
criteria versions