Overview
Show clinicians short pointers for history taking and examination, drawn from the record before the visit and the conversation during it. Each pointer says why it was suggested, and the clinician decides what to use.
How it works
Before the consultation it reads the EHR (referral, previous notes, results, medications) and works out which problems are likely to come up. During the consultation it listens ambiently and updates that picture as the conversation goes on. Based on this it shows short pointers for history taking and clinical examination, for example questions that help tell possible causes apart or examinations that should not be left out. The pointers are suggestions only and the clinician decides what to use. Each pointer shows why it was suggested, with a link to the part of the record or the conversation it came from.
What Corti handles
- Reading the record before the visit
- Live medical speech recognition
- Updating likely problems as the conversation changes
- Writing short pointers with their reasons
What you build
- The connection to your patient record
- Where the pointers appear during the visit
- Consent and recording controls for the room
Make it yours
- Write the instructions the agent follows
- Choose the language people speak
- Start from a ready-made template, or write your own
- Pick the model the agent runs on
- Let punctuation be added automatically, or only when someone says it
- Decide the structure and writing style of each document
- Connect the tools and data sources it can use
- …and much more