Small decisions. Interesting possibilities.Submit contentSubmit

Live clinical-transcript classification prototype

During a live clinical consultation (with an ambient scribe), the transcript is periodically supplied to Jev, which traverses a medical ontology to classify symptoms, update the differential diagnosis, suggest treatments and identify red flags in real time.

Added to Jevfast

How it uses Jev

During a live consultation, the ambient-scribe transcript is periodically supplied to Jev, which traverses a medical ontology to classify symptoms, update a differential diagnosis, suggest treatments, and identify red flags.

App workflow

  1. Capture consultation text

    An ambient scribe produces the transcript during the consultation.

  2. Refresh the analysis

    The transcript is periodically supplied to Jev.

  3. Traverse the ontology

    Jev classifies symptoms, updates the differential, suggests treatments, and checks for red flags.

Why it is interesting

It applies repeated bounded decisions to a changing transcript and ontology during a live interaction. The post describes a prototype, not clinical validation.