Philippines version. Set to the Philippines: prompts write medicines by generic name as the Generics Act requires, frame claims for PhilHealth's CF4 or an HMO, and follow the Data Privacy Act on patient data. US version
AI Prompts for Doctors (Philippines)
Prompt templates for Philippine doctors: clinic notes, referral letters, PhilHealth clinical summaries and handouts with generic drug names and a privacy check.
The interactive tool loads here when JavaScript runs.
About this toolWhat is AI Prompts for Doctors?
This version sets the region to the Philippines, so every prompt adds four local rules. Drafts use US spelling, dates such as November 6, 2026, and pesos. Medicines are written by generic name, because the Generics Act (Republic Act No. 6675) requires all medical practitioners, private ones included, to write prescriptions using the generic name; a brand name may follow if it is in your notes. Lab values stay in exactly the units your source uses, and DOH, PhilHealth or specialty society guidance is named only if it is in the material, otherwise marked [CHECK PHILIPPINE GUIDELINE].
The US prior authorization template becomes Philippine paperwork. For a PhilHealth claim, the clinical summary goes on Claim Form 4 and the clinical record on Claim Form 3; for an HMO patient it is a request to the HMO. The template note tells the assistant to frame the draft for whichever your material names, tie each statement to the chart, and never state case rates or benefit amounts from memory.
Patient data is the main risk. Under the Data Privacy Act of 2012 (Republic Act No. 10173), information about a person's health is sensitive personal information, which may be processed only on the grounds the Act lists, such as specific consent or medical treatment. The privacy check masks names after a "Patient:" label or a title, dates, phone numbers and PhilHealth PINs written after "PhilHealth PIN", but read the result before you paste.
- 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
Updated
How to use AI Prompts for Doctors
- Type your specialty and setting, for example outpatient cardiology, and choose your region so the prompt uses local spelling and conventions.
- 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.
- Fill in the fields with de-identified notes, or press Try an example to see a finished prompt built from fictional data.
- Run the privacy check, mask any identifiers it finds, then copy the prompt and paste it into your approved assistant.
- Review the draft against the check-the-output list before anything goes into the chart or to a patient.
Worked examples
Masking a clinic note
Input
Patient: Maria Santos, 67F, PhilHealth PIN 12-345678901-2, seen 11/02/2026, 0917 123 4567, FBS 132 mg/dL
Output
Patient: [NAME-1], 67F, PhilHealth PIN [RECORD-ID-1], seen [DATE-1], [PHONE-1], FBS 132 mg/dL
The name, PhilHealth PIN, date and mobile number are masked; the age and the lab value stay because the draft needs them. A name written as "Pt. Maria Santos" has no label the check knows, so it would not be masked.
Clinical summary for a PhilHealth claim
Input
Prior authorization template, region Philippines, admission for community-acquired pneumonia, notes and lab results pasted
Output
Prompt with the template rules, the four Philippines rules and a note to frame the draft as a CF4 clinical summary (or a request to the patient's HMO), each statement tied to the chart
The assistant drafts from your notes only. You check the summary against the chart and enter codes and amounts from PhilHealth's current lists yourself.
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
- Write the generic name first in your notes; the prompts keep it and add a brand name only if you included one.
- Paste lab results with their units; the prompts are told not to convert them.
- Use the hospital's approved tool for anything that still identifies a patient.
- Check every ICD-10 or PhilHealth code the assistant suggests against the current list before filing.
Sources and further reading
- Downloads: claim forms (Claim Form 3 and Claim Form 4), PhilHealth
- Republic Act No. 6675: Generics Act of 1988, Lawphil (Arellano Law Foundation). Section 6(b): prescriptions written using the generic name; brand name optional.
- Republic Act No. 10173: Data Privacy Act of 2012, Lawphil (Arellano Law Foundation). Section 3(l) sensitive personal information; Section 13 processing of sensitive personal information.
Frequently asked questions
Do doctors in the Philippines have to prescribe by generic name?
Yes. Section 6 of the Generics Act (Republic Act No. 6675) requires medical, dental and veterinary practitioners, private ones included, to write prescriptions using the generic name; the brand name may be added. The prompts follow that rule.
Can AI help with a PhilHealth CF4?
It can draft the clinical summary from notes you paste, in the structure your hospital uses for Claim Form 4. You remain responsible for every entry, and codes and case rates must come from PhilHealth's current issuances, not the assistant.
Is it legal to paste patient data into ChatGPT in the Philippines?
Health information is sensitive personal information under the Data Privacy Act of 2012, and processing it is prohibited unless one of the Act's exceptions applies, such as specific consent or medical treatment. Remove identifiers or use a tool your institution has approved.
Does the privacy check catch PhilHealth numbers?
Yes, when the number follows "PhilHealth PIN", "PhilHealth ID" or "PhilHealth number". It also masks mobile numbers written without spaces, such as 09171234567. Unlabelled numbers are left alone, so check before pasting.
Will the prompts quote DOH guidelines?
Only if the guideline text is in your material. Otherwise the assistant writes [CHECK PHILIPPINE GUIDELINE: topic], so you can look it up rather than trust a summary from memory.
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.
Related Tools You May Like
Free, in-browser tools that pair well with this one.