# The $0-per-report feature: a patient-friendly radiology explainer that runs on the clinic's own laptop

> Source: <https://dev.to/utkarsh_singh-27/the-0-per-report-feature-a-patient-friendly-radiology-explainer-that-runs-on-the-clinics-own-4152>
> Published: 2026-10-18 11:10:50+00:00

*This is a submission for the [Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle](https://dev.to/challenges/hacktoberfest-week2-2026-10-12).*

**[PlainRay](https://github.com/4-thkind/plainray)** turns radiology reports into plain-language patient explainers — on the clinic's own machine, with an open-weight model, for zero rupees per report.

It reads a report and produces, in one pass:

Who would pay for this: the kind of clinic that runs two radiologists, one front desk, and a stack of reports whose first word is usually "IMPRESSION:". Behind that desk sits a person who answers "what does effusion mean?" eleven times a week. Every hosted "AI patient portal" wants a per-report meter and a copy of the report on someone else's server. PlainRay flips it: **flat license, zero usage cost, nothing ever leaves the machine.**

The side-hustle math that makes it a real product instead of a demo: the clinic already owns the laptop, and the model runs on an RTX 4060. So the unit economics are: model = free forever, electricity = what the lamp costs, product = one flat fee per workstation. There is no other version of this offer where the *cost driver of the whole business is $0* — that's only possible because the model is an open-weight one you can download.

Three synthetic reports are in the repo (`samples/sample_reports.json` — no real PHI is ever committed). Here is the actual flow, captured locally while the machine was offline for everything else:

The second frame is the mammography screening sample — the star of the show, because screening reports are the least readable of all ([see it here](https://raw.githubusercontent.com/4-thkind/plainray/main/demo/02-mammo-explained.png)).

No login, no cloud, no network. Unplug the ethernet cable and it keeps working — that is the demo. Run it yourself:

```
git clone https://github.com/4-thkind/plainray
ollama pull gemma3:4b          # one time, ~3 GB
python -m plainray serve       # http://127.0.0.1:7860
python -m plainray explain --file report.txt   # JSON on stdout
python -m plainray selftest    # prompts + validator + readability, no model needed
```

Everything lives in the [4-thkind/plainray](https://github.com/4-thkind/plainray) repo:

`plainray/llm.py` — a minimal local Ollama client in stdlib `urllib`, ~40 lines. No pip, no SDK.` plainray/prompts.py` — the patient-safety prompt, readable in plain text by whoever deploys it.`plainray/app.py` — CLI (`explain` / `serve` / `selftest`) and a validator that enforces the JSON shape: caps list lengths, dedupes glossary terms, refuses an empty summary.`plainray/readability.py` — a Flesch-Kincaid grader in stdlib. Numbers, not promises.`static/index.html` — the UI; the server binds to `127.0.0.1` on purpose.`_validate()` rebuilds the JSON from scratch. A 4B model | Sample report | Raw grade | PlainRay explainer | 
|---|---|---|
| Chest X-ray, consolidation | 10.4 | **7.6** | 
| Knee MRI, meniscus tear | 10.0 | **7.6** | 
| Mammography screening | 12.3 | **6.7** | 

`http.server`). Clinic IT never touches a package manager.` PLAINRAY_MODEL`): `gemma3:12b` on a bigger box, or the medical-tuned sibling `medgemma` — same code, same prompt.
This project was built in one working session with an AI coding agent — I set the problem, the constraints ("small, specific, useful, and it must actually run on this laptop") and reviewed everything it produced. The short form of that session — constraints discovered first, the decisions worth keeping, and what was hard — is checked into the repo as [`AGENT_NOTES.md`](https://github.com/4-thkind/plainray/blob/main/AGENT_NOTES.md). No DevRelay install for this build; the notes file is the session, honestly summarized.

Honest version: **my first real user test hasn't happened yet.** During this challenge window I built the product and ran it end-to-end on my own machine against three synthetic reports; nobody's real report went through it, because the right first user is a clinic that will trade one afternoon for a demo, and setting that up properly takes longer than the window. Rather than report a fake ten, here is the actual next step: one call to my cousin's ortho clinic, a printed example made from `samples/`, and two questions I'll log verbatim in the repo — *would you pay, and how much per year?*

If you're a radiologist or run a small clinic and want to be user #1: the demo runs from a fresh clone in under two minutes, and my contact is on my profile.

**Best Use of Gemma** — Gemma 3 4B runs entirely on-device through Ollama, powers the whole product, and the architecture keeps `gemma3:12b` / `medgemma` as one-variable drop-ins.

*(Solo build — no teammates.)*