Working read · 10 Aug 2026
What the files are — and what to build
Combined take from the WhatsApp ask and three Max discharge summaries.
What’s in the folder
| File | What it really is |
|---|---|
document.txt | WhatsApp group: product ask |
3 .rtf files | Max CLBS discharge summaries (sample data), not chats |
One family case:
- Nasibakhon — DCLD HCV → dual-lobe LDLT recipient
- Mukhriddin — son, left-lobe donor
- Tuichivai — brother, left-lobe donor
Matches Selva’s ask: give Manu discharge summaries and build an AI follow-up model.
What they want
One liver-clinic product in three layers:
- At registration — quick screening for all patients (past disease, surgery, meds, hospitalisations, similar illness, smoking/alcohol/drugs, marital, sleep/diet/bowel/urine).
- After diagnosis / discharge — pathways by type: liver/DCLD medical care; post-transplant; living donor.
- Behind it — registry + later AI from ~100 discharge summaries for reminders and summaries.
HEAL Group / ET AI article = inspiration only, not the product.
What to build
Max CLBS patient intake + follow-up assistant — not a general hospital AI, not auto-prescribing ChatGPT.
v1
- Screening questionnaire at registration
- Structured patient record + patient type
- Doctor-approved advice templates (confirm before patient sees)
- Basic registry row from screening + discharge fields
v2
- Ingest more discharge summaries
- Extract meds / advice / review dates
- WhatsApp/SMS reminders
- Light AI: summarise DS, flag missed follow-up — not invent treatment
Do not start with full autonomous AI prescribing. Chat says “AI”; documents show structured intake + pathway follow-up first.
Mismatch to resolve with Selva
Chat DCLD pack ≠ post-LT recipient pack. Donors and recipients already differ. Need pathway templates, not one medicine list for everyone.
Next build: screening form → patient type → advice template → registry row, using these 3 summaries as seed cases.