DentaNote: dental clinical notes with local Gemma, no audio leaves the operatory

Описание и применение

DentaNote сокращает время создания стоматологических записей до менее минуты, обрабатывая аудио локально и гарантируя, что данные не покидают машину, при этом поддерживая проверку и редактирование результатов.

Задача

Clinicians lose time building structured dental notes after dictating audio, and existing solutions risk patient data leaving the machine.

Результат

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.

Рабочий процесс

• Record patient visit audio
• Run dentanote run visit.wav to transcribe with Whisper and extract structured data with Gemma via Ollama
• Validate JSON with Pydantic
• Render note with deterministic template
• Review uncertain_items flagged for clinician verification
• Export or edit note in Streamlit UI

Доказательства

audio in, structured clinical note out, running 100% locally, with not a single byte leaving my machine.

Источник

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).

Источник

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).

Источник

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.

Источник