**Data source**
The herbal database (`assets/therapy/herbal_database.json`) is derived from a 5,722-page CNRI knowledge base. It is structured as: condition name → list of herbs, each with a reference count.
The reference count reflects how many source documents cited that herb for that condition. Higher counts indicate broader cross-reference support.
**How it works**
1. The engine takes the organ keywords associated with the triggered iris zone.
2. It runs a case-insensitive prefix search across all condition names in the database.
3. Up to **4 matching conditions** per zone are returned, each with up to **6 herbs** ranked by reference count.
4. Zones are sorted so the highest-severity zone appears first.
**What the panel shows**
Each recommendation card displays:
– **Eye badge** (OD/OS) and **finding badge** (FLAT/PROT/ANW)
– **Zone name** and associated organ system
– **Severity percentage** from the iris analysis
– **Matched conditions** — up to 4 condition names relevant to that organ
– **Herb list** per condition — herb name + reference count shown as a chip; tapping a chip opens the source reference list
– **Evidence note** — total number of references for the top herb
**Disclaimer strip**
A disclaimer is shown at the bottom of every herbal card and is also printed in the PDF. It reminds practitioners that herb–drug interactions exist and that professional supervision is required.
List of book references used in software:
