AI Ethics, Safety & Responsible Prompting in Healthcare

** Prompt Engineering: Mastering AI Communication from Zero to Expert
Lesson Content
0% Complete

Learning Objectives

1. Identify and avoid HIPAA violations when building clinical AI prompts.

2. Recognize AI hallucinations and know how to verify clinical output.

3. Apply responsible prompting rules to all 5 principles.

4. Understand who is accountable when AI produces wrong clinical information.

 

Why This Lesson Is Non-Negotiable

Using AI in healthcare is powerful — but it carries serious patient safety and legal responsibilities. This lesson is not optional. Every principle learned in this course must be applied within these safety boundaries.

 

HIPAA Prompt Safety: What NEVER Goes in a Prompt

NEVER Include in a Prompt

Safe Alternative to Use Instead

Patient full name (e.g., Maria Gonzalez)

Use: ‘Patient A’ or ’62-year-old female patient’

Date of birth, Social Security Number, MRN

Use: approximate age and generic demographics

Specific hospital name tied to a real patient

Use: ‘regional hospital’ or ‘City General’ without patient ID

Real physician names linked to patient records

Use: ‘attending physician’ generically

Insurance plan details and claim numbers

Use: ‘standard insurance coverage’ generically

 

NOTE: In this course, ‘Maria Gonzalez’ is a fictional training case only — not a real patient. In real clinical practice, always use de-identified or fictional patient data when prompting public AI tools.

 

AI Hallucination — The Biggest Clinical Risk

What Is an AI Hallucination?

An AI hallucination occurs when the model produces confident, fluent, plausible-sounding information

that is factually wrong. In healthcare, this can mean:

 

  – Recommending a drug that is contraindicated for a patient’s condition

  – Citing a clinical guideline that does not exist or is outdated

  – Stating an incorrect medication dosage with the same confidence as a correct one

  – Generating a lab value that was not in the prompt and is clinically wrong

 

AI hallucinations do not look like errors — they look like correct, well-formatted clinical output.

This is what makes them dangerous. Always verify clinical AI output against authoritative sources.

 

5 Responsible Prompting Rules

  1. Always treat AI clinical output as a DRAFT — never as a final clinical decision.
  2. Always verify AI-generated diagnoses, medications, and dosages against current clinical guidelines.
  3. Never enter real patient PHI into a public AI tool (ChatGPT, Claude, Gemini, Copilot).
  4. Report AI output errors through your hospital’s quality assurance and incident reporting system.
  5. Know and follow your hospital’s AI use policy before deploying any AI prompt in a clinical workflow.

 

Real-Life Healthcare Example — Safety

Maria Gonzalez (Patient Thread — Lesson 3.5): Hallucination Risk Scenario

You ask AI to generate Maria’s discharge medication list.

The AI produces a clean, well-formatted table — it looks perfect.

 

BUT: On review, a clinical pharmacist notices the AI has listed Metformin at 2000mg twice daily.

Maria has CKD Stage 2. Metformin at this dose is contraindicated with her eGFR of 52.

Standard guidance: Metformin should be reduced or held at eGFR < 45; caution at eGFR 45–60.

 

The AI produced a plausible, correctly formatted medication entry — with a dangerous dosage.

It did not hallucinate the drug name. It hallucinated the dose for this patient’s renal status.

 

Lesson: Never use AI-generated medication lists without clinical pharmacist review.

Always specify patient renal function in the prompt: ‘Patient has CKD Stage 2, eGFR 52.

Recommend renally-adjusted dosing for all medications.’

 

Even with this addition — VERIFY before use. AI is a drafting tool, not a prescribing authority.

 

Course Outline