Select the procedure. Dictate naturally — or type, or both.
Dictum structures the note in your template, with your vocabulary.
Then fights the denial for you.
The ask is simple: auto-select the right template before walking in — GAE, back pain, kypho, ESI, ablation, UFE, varicose veins — dictate your findings, and get a structured note out without fighting your EHR.
The voice-to-structure engine is built and tested. 101 tests passing. Medical-grade speech recognition with your IR vocabulary as keyterms — it knows kyphoplasty, basivertebral nerve, genicular artery, CEAP, Kellgren-Lawrence. Works on Android, Windows, and iPhone — no app install, runs in your browser.
Template auto-selection is the next build target. The architecture already supports it — sessions carry a config object and keyterm sets. What we're adding: a procedure template registry (11 IR templates mapped), pre-visit picker UI, structured output formatting, and an insurance defense layer that catches missing documentation before you submit — gap analysis, prior auth letter generation, and denial appeal prep.
Four steps between selecting the procedure and having a structured note.
Before you walk in, tap the procedure. Templates pre-load your IR vocabulary as Deepgram keyterms and set the output structure. One tap — SpineJack consult, GAE evaluation, UFE follow-up, whatever you're doing next.
After the visit, dictate what matters — on your phone, desktop, or wherever you document. Speak naturally using your own terminology. Dictum understands IR vocabulary out of the box and structures your dictation against the template fields. Type anything you prefer to type.
When the visit ends, the intelligence layer processes the raw transcript against your template. Free-form conversation becomes structured fields — HPI, relevant imaging, assessment, plan, procedure details. You didn't fill out a form. You had a conversation. This three-tier extraction pipeline is built and tested — real-time voice to structured clinical data.
Review the structured note. Tap to correct any misrecognitions — Dictum learns your corrections and adds them to future keyterm sets. Before you export, the insurance gap analysis checks your note against payer-specific criteria: is the KL grade documented? KOOS score? Compression therapy duration? Missing fields get flagged. One click generates a prior auth letter citing your documented criteria + guideline language. Export to clipboard, PDF, or FHIR.
Each template packs the right vocabulary, output structure, and procedure-specific fields. Select before you walk in.
What it looks like when you dictate a GAE consult. Your words, your vocabulary, automatically mapped to template fields with structured extraction.
No vapor. Here's the stack, what's running, and where templates slot in.
Each card is a template with its vocabulary, output fields, and the terminology Dictum needs to nail. These are the exact keyterm sets that get injected into Deepgram.
Green is built and tested. Yellow is the active build. Gray is planned.
FastAPI proxy, WebSocket relay with asyncio.TaskGroup, Deepgram Nova-3 + Flux adapters, 8-type event schema, JWT auth, session persistence, rate limiting, parameter validation.
Web-based companion works on Android Chrome, Windows Chrome/Edge, and iPhone Safari. getUserMedia + AudioContext, QR pairing for walk-around dictation. Zero app install required. Audited: zero iOS-specific code branches.
11 IR templates mapped (BVN, MILD, kypho, ESI/SNRB, facet/MBB/RFA, SIJ, GAE, UFE, renal ablation, cryo, varicose veins). Procedure picker UI, per-template keyterm presets, output schemas. Spine DDx routing tree (~60-80 rules). Your actual Wash U GAE template mapped field-by-field.
Three-tier extraction pipeline, built and tested. Tier 1: regex (<10ms) for vitals, scores, laterality. Tier 2: fast LLM (~300ms) for section routing. Tier 3: full LLM (~1.5s) for structured extraction. For IR, we extend with procedure-specific fields (KL grade, KOOS, Modic type, CEAP class) and correction feedback for vocabulary learning.
RAG-powered payer criteria matching (Medicare LCD, UHC, Aetna, Cigna, BCBS). Post-note gap analysis flags missing documentation. One-click prior auth letter generation citing SIR/ACR guidelines. Denial appeal letters with peer-to-peer talking points. Payer criteria as markdown knowledge base — policy updates are document edits, not code changes. GAE, VV, and spine (facet RFA dual-block) are priority targets.
PII/PHI redaction at the Deepgram level, audit logging, data retention controls, HIPAA documentation. Required before clinical deployment.
Structured notes in FHIR format. Integration patterns for Epic, Cerner. Copy-to-clipboard as the day-one bridge.
Not a generic transcription app hoping doctors will use it. A voice system designed around procedure-specific documentation — your procedures, your vocabulary, your templates. With an insurance defense layer that fights the denial before it happens. Purpose-built integration, not a feature checklist.
dictum — your voice, structured. your denial, defended.