The tool

Forge a Chronic Kidney Disease diagnostic dataset

Choose how many risk-assessment records you want and a seed. The same two numbers will always produce the same dataset — write the seed down and cite it in your methodology chapter.

Capped at 20,000 — the API generates synchronously (see ROADMAP.md Phase 1 for the planned async path beyond that).

Two-stage additionally computes a KDIGO GFR category (G1-G5), an albuminuria category (A1-A3), and a primary cause for CKD-positive records — the four screening_status/gfr_category/albuminuria_category/primary_cause columns only exist in this mode. Single-stage is the classic diagnostic-classification shape — CKD-positive-vs-negative only.

Advanced: customize the model

Same directional relationships described in the methodology — strengthen, weaken, or rebalance them here without touching any code. Defaults are illustrative, anchored against general CKD epidemiology literature specific to Ghana and sub-Saharan Africa, not derived from real clinical data.

CKD-diagnosis probability

Patient age is table-rated off the age-band base-CKD-prevalence anchor (not adjustable here); these loadings multiply on top of it. Active in both stage modes.

KDIGO staging two-stage only

Only computed for CKD-positive records when stage mode above is two-stage. stage_score_bands (the latent-score-to-G1..G5 bucketing) isn't editable here — only the score contributions feeding into it are.