Diffusion Run
seed: 9612
Denoising convergence curve
Observed control N: 120
Borrowed ESS: 65
Estimated control reduction: 29.8%
prototype · diffusion mock
Ophthalmology Digital Twin · Diffusion Synthetic Control (Mock)
Mock diffusion pipeline for synthetic control arm generation: latent noise -> denoising steps -> calibrated patient-level output.
Setup
Endpoint: BCVA change at Week 24 (ETDRS letters) · Historical pool: AMD-118, AMD-122, AMD-OBS-19 (680)
Observed vs Synthetic
BCVA change: observed 2.10 ± 7.40 | synthetic 2.36 ± 3.87 ·Δ +0.26
CST change: observed -32.0 ± 58.0 | synthetic -34.8 ± 32.4 ·Δ -2.8
Mock method note
This is a product mock: generated patients are simulated with a deterministic pseudo-random denoising loop, then calibrated to scenario-level control moments.
Synthetic Patient Samples
| ID | Age | Base BCVA | Base CST | Duration (y) | BCVA Δ | CST Δ | Weight |
|---|---|---|---|---|---|---|---|
| SYN-001 | 70.2 | 60.2 | 405 | 4.2 | -1.5 | -62 | 0.79 |
| SYN-002 | 82.1 | 64.6 | 371 | 3.7 | 12.2 | -25 | 0.87 |
| SYN-003 | 80.4 | 51.1 | 399 | 4.7 | 4.9 | -29 | 0.79 |
| SYN-004 | 74.4 | 52.3 | 384 | 3.7 | 6.5 | -50 | 0.79 |
| SYN-005 | 77.3 | 59.8 | 489 | 3.4 | 0.6 | -12 | 0.82 |
| SYN-006 | 72.9 | 59.6 | 404 | 5.1 | 6 | -84 | 0.82 |
| SYN-007 | 70.9 | 46.4 | 374 | 6.2 | -0.5 | -45 | 0.78 |
| SYN-008 | 72.7 | 53.9 | 292 | 3.1 | 4.1 | -51 | 0.79 |
| SYN-009 | 69.7 | 53.3 | 401 | 4.9 | 0.5 | -65 | 0.83 |
| SYN-010 | 71.8 | 54.6 | 389 | 3.4 | 5.5 | -87 | 0.84 |
| SYN-011 | 75.9 | 48.4 | 388 | 4.2 | -0.6 | 14 | 0.83 |
| SYN-012 | 69.7 | 60.9 | 399 | 3.9 | -1.8 | -8 | 0.84 |
update log
Prototype Change Log
2026-03-05 · v0.1.0
Ophthalmology Diffusion Twin (Mock) Launch
- - Added a one-page mock prototype for synthetic control arm generation with diffusion-style denoising loop.
- - Included ophthalmology scenarios (nAMD, DME, GA) with configurable cohort size, denoising steps, and calibration strength.
- - Added side-by-side observed-vs-synthetic metrics and patient-level synthetic sample table for review.