Canada version. Set to Canada: prompts use Canadian spelling, mmol/L, family doctor and 811 wording, frame drug coverage requests for provincial programs, and mask health card numbers and postal codes. US version

AI Prompts for Doctors (Canada)

Prompt templates for Canadian physicians: chart notes, referrals, drug program requests and patient letters in mmol/L, with health card masking first.

The interactive tool loads here when JavaScript runs.

About this tool

What is AI Prompts for Doctors?

This version starts with the region set to Canada. Each prompt tells the assistant to write Canadian English, keep glucose in mmol/L and HbA1c as written in your source, point patients to their family doctor, the provincial health line (811 in many provinces) or 911, and leave a [CHECK CANADIAN GUIDELINE] marker instead of quoting Diabetes Canada, Hypertension Canada or a provincial program from memory.

Coverage paperwork is Canadian too. When a drug is not a general benefit, the request usually goes to a provincial program, such as Ontario's Exceptional Access Program or BC PharmaCare Special Authority, or to a private drug plan as a prior authorization form. The template quotes the program's criteria you paste and points to chart evidence for each one, with gaps listed as "Not yet documented".

Privacy rules are provincial. Personal health information falls under laws such as PHIPA in Ontario or the Health Information Act in Alberta, and colleges set expectations on AI. The CPSO, for example, expects physicians to review everything an AI tool drafts, tell patients how AI is used and get consent before recording a visit with an AI scribe. The privacy check masks names, health card numbers, dates of birth and postal codes before you copy.

  • Ten templates covering notes, letters, payer appeals, evidence searches and patient education
  • Structured prompts with role, context, task, constraints and output format
  • PHI scan and one-click masking of names after titles, MRNs, dates, phone numbers, emails and ages over 89
  • Reading-level and language options for patient-facing text
  • Favourites, search and a Markdown export of the whole kit for your team
  • Runs locally in the browser with no account and no upload
Read the guide: AI for Doctors and Nurses: Safe Prompts for Notes, Letters and Teaching

Updated

How to use AI Prompts for Doctors

  1. Type your specialty and setting, for example outpatient cardiology, and choose your region so the prompt uses local spelling and conventions.
  2. Search or browse the templates and pick one, such as SOAP note from dictation or Prior authorization or appeal letter. Star the ones you use daily.
  3. Fill in the fields with de-identified notes, or press Try an example to see a finished prompt built from fictional data.
  4. Run the privacy check, mask any identifiers it finds, then copy the prompt and paste it into your approved assistant.
  5. Review the draft against the check-the-output list before anything goes into the chart or to a patient.

Worked examples

Masking an Ontario clinic note

Input

Patient: Claire Tremblay, OHIP 1234-567-890, DOB 1961-05-09, lives near M5V 3L9, A1C 7.4%.

Output

Patient: [NAME-1], OHIP [RECORD-ID-1], DOB [DATE-1], lives near [POSTCODE-1], A1C 7.4%.

The health card number, the ISO-format birth date and the postal code are all found; the A1C value is not an identifier and stays. Postal codes with a space in the middle are recognized even without a "postal code" label.

Exceptional Access Program request

Input

Prior authorization template, region Canada, a biologic after methotrexate was stopped for raised ALT, Ontario

Output

Prompt with the template's rules, three Canada rules and a note to frame the letter for a provincial program or private plan and its criteria

Paste the EAP criteria for the drug and the record facts. The draft maps each criterion to evidence, and anything the chart does not show yet goes in the "Not yet documented" list for you to fix before faxing or submitting.

Background and insight

Large language models write fluent clinical prose and also produce confident errors: a plausible lab value that was never measured, a guideline that does not say what the model claims, a dose with the wrong unit. The templates are built to make those errors visible. Each prompt asks for a list of gaps or unverified claims next to the draft, separates the physician's assessment from anything the model suggests, and forbids citations that are not in your material.

Privacy rules shape what you can paste. Under HIPAA a covered entity may share protected health information with a vendor only under a business associate agreement (45 CFR 164.502(e) and 164.504(e)), and HHS guidance from 2016 treats a cloud service that stores ePHI as a business associate even if it cannot read the data. Most consumer chat apps do not sign one. The Safe Harbor method in 45 CFR 164.514(b)(2) lists 18 identifiers to remove; the alternative is an expert determination. In the UK and EU, health data is special category data under GDPR Article 9.

The masking helper is pattern based. It catches common formats such as "Mr. Alvarez", "MRN: 4471203", 03/14/1957, phone numbers, emails and ages over 89, which are Safe Harbor identifiers, but it cannot recognise a name written without a title or a rare diagnosis that identifies someone in a small town. Read the masked text before you copy it.

Common use cases

  • Clinic documentation

    Turn dictated bullet points into a SOAP note in your preferred style, with gaps such as missing allergies flagged for you to fill.

  • Payer paperwork

    Draft prior authorization requests, appeals and peer-to-peer talking points that quote each policy criterion and point to the evidence.

  • Patient communication

    Explain results, reply to portal messages and write condition handouts at a reading level patients can act on.

  • Evidence questions

    Frame a bedside question as PICO with MeSH terms and a Boolean search string, then read the studies yourself.

Tips and limitations

  • Use the AI scribe or assistant your clinic, health authority or provincial program has approved for anything that cannot be fully de-identified.
  • Ask the model to list every number it used, then compare with the chart before you sign.
  • Check fee codes and diagnostic codes in your billing system; the Canada rules tell the model they must be verified.
  • For patients in Quebec, check whether a French version of patient-facing text is needed.

Sources and further reading

  1. New advice document supports expanded use of AI in clinical practice, College of Physicians and Surgeons of Ontario
  2. Personal Health Information Protection Act, 2004, Government of Ontario
  3. Summary of privacy laws in Canada, Office of the Privacy Commissioner of Canada

Frequently asked questions

Can Canadian physicians use ChatGPT for chart notes?

Only within your province's health privacy law and your college's expectations. Consumer chat apps are rarely approved custodial agents for personal health information. Remove identifiers, paste only what the task needs, or use a tool your clinic or health authority has approved.

What does the CPSO expect from doctors using AI?

Its advice on AI in clinical practice says physicians remain accountable for the record, must review what an AI tool produces for accuracy and completeness, should tell patients how AI is used and should get consent before recording a visit with an AI scribe. Other colleges have similar guidance.

Does the privacy check catch provincial health card numbers?

Numbers after labels such as "OHIP", "health card" or "PHN" are masked, as are postal codes written as A1A 1A1. A bare health card number with no label can be missed, so read the text before copying.

Can it write an Exceptional Access Program or Special Authority request?

It drafts the letter from the criteria and chart facts you paste. Submission still goes through the program's own form or portal, and you check that each criterion is really met.

Which units will the prompts use?

mmol/L for glucose and cholesterol, and HbA1c exactly as written in your source. Canadian labs report in SI units, so the model is told not to convert to US units.

Is there an in-depth guide to AI Prompts for Doctors?

Yes. “AI for Doctors and Nurses: Safe Prompts for Notes, Letters and Teaching” covers the background, how it works, common pitfalls and worked examples. Read the full guide.