AD-05 · Adherence Support
Adherence supportSynthetic demo dataTarget state: Adherence decline · onset 5 d · prior: symptom −2%, persistence +14%, tolerance +3%Simulate for P-01737
For P-01737
Eligible at 78% confidence. Among the 284 most similar trajectories: 3 accepted, 33% improved, mean effect −7%.
What it is
Adherence support for 14 days: dose-time anchoring, a reason-for-missing dialog, a weekly nurse text, and simplification of the daily plan to three items.
How it works
Restores dosing before anything else; when the dose is missed, no other protocol can work. Content is reduced, not added.
What the patient does, day by day
| Day 1 | ✓ | Anchor the dose Dose tied to a daily routine the patient picks. |
| Every day | ✓ | Three items only The daily plan is cut to the three highest-value to-dos. |
| On a miss | ✓ | Reason dialog Symptom, forgot, side effect, cost — routed accordingly. |
| Weekly | 🏥 | Nurse text Short check-in. |
Delivery
- Owner
- Companion
- Channel
- Companion + weekly nurse SMS
- Duration
- 14 days
- Touchpoints
- Dose-time reminder; "why did you miss it" dialog
- Cost
- ≈ €35 per patient
Monitoring
- · Dose timestamps
- · To-do completion
- · Reasons for missing
Stop rules
- · Adherence still < 60 % at day 14 → clinician review
Contraindications
- none recorded
Evidence in NBL-101
8 accepted · 38% improved · mean effect −9%By biology segment
| Low microbial diversity | n 7 | 43% |
| IL6 high-expression variant | n 5 | 40% |
| FUT2 non-secretor | n 4 | 25% |
By trajectory cluster
| EC-01 | n 6 | 33% |
Works best when
- · Adherence < 60 % and GI < 50 (behaviour-led)
Works poorly when
- · Adherence drop caused by GI ≥ 50 (treat the GI first)
- · Toxicity-led discontinuation
What the model has learned about it
No learned rule yet for AD-05. Run learning after campaign results.
Campaigns using it
None yet. 232 patients look eligible right now.