From Conversation to Chart — SOAP, ICD-10, and CPT
How a spoken visit becomes a structured, coded note — and why the coding step matters as much as the narrative.
A clinical note has two jobs: tell the story of the visit, and capture the coding that lets the visit be billed correctly. AI documentation is only useful if it does both. Here is how the pieces fit together.
The SOAP note is the narrative
Most clinicians already think in SOAP:
- Subjective — what the patient reports
- Objective — exam findings, vitals, results
- Assessment — the clinical impression
- Plan — what happens next
Structuring the note this way is not just tradition; it makes the chart scannable for the next person who opens it. A drafting tool that respects that structure produces notes a colleague can actually read.
The codes are where revenue lives
The narrative tells the story, but ICD-10 (diagnoses) and CPT (procedures and services) are what the claim is built on. Two things go wrong in the real world:
- Under-coding. A visit is documented but coded to a lower level than the work supports — often because it is 8pm and the provider just wants to be done.
- Mismatch. The codes do not line up with what the note describes, which invites denials.
Surfacing the ICD-10 and CPT suggestions alongside the note — while the details are fresh — helps the visit get coded to the level the documentation actually supports.
The after-visit summary is for the patient
The same encounter should also produce something the patient can take home: plain-language instructions, medication changes, and follow-up steps. Writing that by hand is one more task at the end of a long day; generating it from the same conversation is nearly free.
Review is not optional
Generated codes are suggestions. The clinician confirms the diagnoses, adjusts the level, and signs off. The value of automation here is not removing the human — it is making sure that by the time the human reviews, the draft and the codes are already sitting there, together, waiting for a yes.
That is the workflow Scribe360 is built around: conversation in, structured and coded note out, clinician in control of the final word.