Consultation Summarizer
Turning a live doctor and patient conversation into an accurate transcript and a structured SOAP-format summary, without the clinician typing anything.
- Before
- Clinicians wrote their notes after the fact, from memory, at the end of a shift. The record was thin, late, and occasionally wrong in ways nobody could audit.
- What we built
- A speech pipeline that handles overlapping speakers and clinical vocabulary, feeding a language model constrained to the SOAP structure so the output lands in the fields the record system expects rather than as free prose. Handling was built to HIPAA and GDPR requirements from the first commit, not retro-fitted before launch.
- The hard part
- Clinical language is exactly where general transcription falls over, and a summary that invents a symptom is worse than no summary at all. Most of the engineering went into the checks around the model, not the model itself.