The tool

Forge a Breast Cancer diagnostic dataset

Choose how many workup 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 stage-at-diagnosis (I-IV) measure for malignant records — the four detection_mode/histologic_grade/receptor_status/stage_at_diagnosis columns only exist in this mode. Single-stage is the classic diagnostic-classification shape (the Wisconsin dataset's shape) — malignant-vs-benign 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 breast-cancer epidemiology literature, not derived from real clinical data.

Malignancy probability

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

Stage at diagnosis two-stage only

Only computed for malignant records when stage mode above is two-stage. stage_score_bands (the latent-score-to-I/II/III/IV bucketing) isn't editable here — only the score contributions feeding into it are.