DentaNote: dental clinical notes with local Gemma, no audio leaves the operatory
说明与用途
DentaNote 通过本地转录音频并提取结构化数据,将牙科记录创建时间缩短到不到一分钟,确保所有患者数据留在设备上,并允许临床医生进行审核。
问题
Clinicians lose time building structured dental notes after dictating audio, and existing solutions risk patient data leaving the machine.
结果
DentaNote reduces note creation time from ~10 min to under 1 min per appointment, keeps all data local, and allows model swapping and validation to mitigate hallucinations.
工作流
- Record patient visit audio
- Run
dentanote run visit.wavto transcribe with Whisper and extract structured data with Gemma via Ollama - Validate JSON with Pydantic
- Render note with deterministic template
- Review
uncertain_itemsflagged for clinician verification - Export or edit note in Streamlit UI
证据
audio in, structured clinical note out, running 100% locally, with not a single byte leaving my machine.
The full pipeline — transcription with Whisper, extraction with Gemma via Ollama, schema validation, and rendering — took 11.2 seconds to turn a 30-second audio clip into a complete note (transcription: 7.7 s; extraction: 2.1 s; rendering is a deterministic template and doesn't register in the timing).
Both produced valid JSON on 100% of first attempts. Both failed on the same case (urgencia_dor predicted tooth 37 instead of 47 — the model "picked" a neighbor on the arch).
The small Whisper model on CPU transcribes ~3.8× faster than real time. So a 3-minute dictation becomes text in about 45 s, plus ~2 s of extraction — under a minute for a note I would have dictated entirely.
- 记录日期: 2026-10-21T00:41:07.143Z