AI Use Cases for Doctors

← Browse workflows

Teaching & learning

Make practice board questions, then vet them

I want fresh board-style questions on my weak topics, not the same question bank again.

Small education evaluation No patient data Individual access available

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

Try the prompt

An editorial starting template. Use invented examples for a first try; check the result before using it.

Create five practice questions from the supplied study material. Ask one question at a time, wait for my answer, then explain the reasoning using the supplied source. Separate source facts from interpretation. If the source does not support an answer, flag it instead of guessing. These are practice questions, not official exam items. Material: [study material]

The workflow

  1. Paste a short section of a trusted review article into Claude or ChatGPT.
  2. Ask for five board-style questions with explanations drawn only from that text.
  3. Check each answer key against the source.
  4. Throw out any question with two defensible answers.

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.

ChatGPT for Clinicians
$0 · verified US physicians, NPs, PAs and pharmacists · Price source
A version of ChatGPT for verified US clinicians, aimed at documentation, writing and research.

Individual clinician verification
Eligible clinician workspace: sign in Settings → Agreements; authority to sign required.

What the evidence supports

In a neurosurgery question-review study, consensus ratings found 25% of evaluated AI questions suitable for the exam versus 72% of human questions. The 89,587-question generation pipeline was not all reviewed.

Primary study · Read the source ↗

Where it goes wrong

The evaluation used selected questions and specialty reviewers. It did not measure learning outcomes; check stems, answers, explanations and references before studying from them.

← All use cases