AI Use Cases for Doctors

← Browse workflows

Talking to patients

Write a fuller, kinder answer to a patient question

My replies to patient questions come out short and clipped because I'm tired.

Blinded preference evaluation De-identified text only Individual access available

Source check: 2026-11-11 · Physician review: not yet recorded

The workflow

  1. For a first test, use fictional or appropriately de-identified content. For identifiable clinical records, use a workspace covered by your organization’s patient-data agreement; removing names alone is insufficient.
  2. Paste the patient's question with every identifier removed.
  3. Ask for a warm, plain-language reply under 200 words.
  4. Correct any medical content and cut anything you wouldn't say yourself.
  5. Send it from your own portal or email under your name.

Tools and cost

USD unless stated otherwise. Billing periods and eligibility matter. A tool listed here was not necessarily tested in the cited study.

Claude (Free plan)
$0 · Free plan · Price source
General AI assistant (free plan): chat, files, code, on web, desktop and mobile.

Individual self-service
Consumer plan has no BAA; eligible commercial products are separate.

Doximity Ask (formerly Doximity GPT)
$0 · verified US physicians, NPs and PAs · Price source
Doximity's clinical question tool (formerly Doximity GPT), with links to journals and guidelines.

Verified Doximity account
Doximity describes suite coverage under its BAA.

What the evidence supports

For 195 public online health questions, evaluators preferred chatbot answers in 78.6% of 585 ratings. Chatbot responses were much longer.

Primary study · Read the source ↗

Where it goes wrong

This measured reviewer preference for responses to online questions, not clinical accuracy, patient outcomes or conversations with an established physician.

← All use cases