unthinkable
Case study · TeleRare Health, US · virtual genetics department for rare disease care

Rare disease patients finish their intake from a link and a phone call, and the geneticist starts the visit with the whole history ready.

TeleRare Health wanted patients with rare diseases to reach a genetic counsellor sooner, without forms, portals and repeated phone calls before the first visit.

United StatesRecords & imaging (EHR, PHR, PACS)

What changed

95%of intakes handled by AI agents (as reported)
80%of pre-test encounters completed within 15 minutes (as reported)
95%of referred patients onboarded without support (as reported)
What stood in the way

What stood in the way.

What stood in the way
  • Medical assistants and clinicians spent around 60 minutes per patient gathering histories and records from several systems before each visit.
  • New patients waited 2 to 3 months for a first visit, and partner EHRs handle billing well but not genetics workflows.
What changed
  • 95%of intakes handled by AI agents (as reported)
  • 80%of pre-test encounters completed within 15 minutes (as reported)
  • 95%of referred patients onboarded without support (as reported)
What we built

What we built.

  • Onboarding from an SMS or email link with Azure Entra magic-link sign-in, e-consent and demographics stored as FHIR resources in Azure Health Data Services.
  • An AI voice agent on Retell AI for structured pre-visit interviews, with breaks allowed, a transcript and summary for each call, and Microsoft Teams alerts when a call fails after retries.
  • An automatic Metriport HIE pull of diagnoses and encounter history once the patient record exists.
  • A prompt pipeline on Azure OpenAI that drafts the clinical note, CPT codes and MDM reasoning, shown with the transcript so clinicians can check it before copying it into the partner EHR.
  • Role-based views for patients, medical assistants and geneticists, HIPAA compliant from day one.
  • Azure Entra External ID
  • Azure Health Data Services
  • FHIR
  • Retell AI
  • Azure OpenAI
  • Azure Functions
  • Azure Logic Apps
  • Metriport
What it shows

What this work shows about us.

AI that clinicians can check

Every drafted note comes with its transcript and the reasoning behind it, and the clinician decides what goes into the chart.

Value without replacing the EHR

The platform handles everything before the clinician opens the chart, so partner hospitals keep their billing and EHR as they are.

Want to build similar AI voice intake for patient care? Tell us what you want to change. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with the right team.

Start your plan ↗
If we built it today

If we built it today, with AI.

What we would add now, moment by moment.

Booking

An agent would offer a newly referred patient the first open counselling slot as soon as intake is complete, and confirm it by message. The genetics team still sets its schedule.

Tests and results

An agent would prepare the genetic test order and family pedigree from the intake for the geneticist to approve and send to the lab. The geneticist decides which test to order.

Ask Unthinkable

Want this for your business?

Tell us what you run or what you're building. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with a senior AI engineer.

Send us a note instead

Required

Thanks. A senior AI engineer will reply to you.
u
Ask UnthinkableClarity first, then the right team
Your conversation

An AI agent. This prototype uses prepared answers and sends nothing.