Back to Columns
AI & DX8 min read

A Physician's Guide to ChatGPT: Real Examples for Referral Letters, Summaries, and Patient Materials

July 18, 2026

A Physician's Guide to ChatGPT: Real Examples for Referral Letters, Summaries, and Patient Materials
Share this article

Generative AI, including ChatGPT, is becoming a familiar presence even in clinical settings. That said, many physicians remain unsure how to use it: "How exactly should I use ChatGPT in medicine?" and "Is it okay to enter patient information?" This article explains, with concrete examples, how physicians can use ChatGPT safely and effectively in their daily work.

What Can ChatGPT Actually Do in Medicine?

ChatGPT is a generative AI that excels at creating, summarizing, translating, and rephrasing text. In clinical settings, it demonstrates its strengths in "text-related tasks" such as the following:

  • Drafting medical documents such as referral letters and medical certificates
  • Summarizing long charts and test results
  • Rephrasing patient-facing explanatory materials in plain language
  • Preparing materials for conferences and in-house study sessions
  • Translating English papers and organizing key points

The important point is that ChatGPT is not a "tool for making diagnoses" but a "tool for speeding up text work." Physicians must always make the final medical judgment, and AI output should be treated strictly as a draft.

Use Case 1: Drafting Referral Letters and Medical Documents

Although the format of a referral letter is fixed, building the text from scratch each time is a hassle. If you give ChatGPT the "course, findings, and request" as bullet points and instruct it to "shape this into the text of a referral letter," you can obtain a well-formatted draft in seconds.

However, as noted below, you must not enter information that can identify a patient—such as name, date of birth, or address. The rule is to provide only anonymized, abstracted information such as "a man in his 50s" or "type 2 diabetes with HbA1c 8.2%."

Use Case 2: Summarizing Long Charts and Materials

Summarization shows its power when you want to quickly grasp the course of a long-term patient or a large volume of test results. With instructions like "summarize the following course in three lines" or "extract only the important changes in lab values," you can organize the key points quickly.

It is also effective as preparation before reading a thick referral document from the referring institution.

Use Case 3: Making Patient Explanations Easy to Understand

Rephrasing jargon-heavy explanations into plain expressions that patients and families can understand is another of ChatGPT's strengths. You can specify the delivery in detail, such as "in words a junior-high student could understand" or "in a tone that does not provoke anxiety." It can also be used to prepare lifestyle-guidance materials and drafts of preoperative explanations.

Precautions When Using Generative AI in Medicine

Convenient as it is, using it in medicine involves lines that must not be crossed.

  • Do not enter patient personal information: Do not input information that can identify an individual—name, date of birth, address, insurance number, etc. Because consumer ChatGPT may use input for training, anonymization must be thorough.
  • Always verify the output: Generative AI can produce plausible-sounding errors (hallucinations). Always confirm drug names, dosages, and figures against primary sources.
  • The final responsibility lies with the physician: Do not adopt AI output as-is; the physician must judge its medical validity.
  • Check in-house rules and the "3 Ministries, 2 Guidelines": The handling of medical information is subject to various guidelines. Use it in accordance with your facility's information management policy.

Choosing Between General-Purpose AI and Medical-Specialized AI

General-purpose ChatGPT is convenient, but it comes with constraints: it cannot handle patient information and does not integrate with the EMR. For tasks that handle the clinical record itself, it is safer to use a medical-specialized AI designed with consideration for the secure management of medical information.

Pottech's "AI Karte" is an AI-native EMR that completes tasks such as automatic chart generation from consultation audio, AI drafting of medical documents like referral letters and certificates, and summarization of past charts—all on the EMR's own data foundation. The major difference from general-purpose AI is that you can streamline work by leveraging daily clinical records directly, without the effort of anonymization.

Conclusion

As long as you observe the premises of anonymization and verification, ChatGPT is a powerful tool that can greatly lighten a physician's text work. A realistic approach is to start with document creation and summarization that do not contain patient information, and then step up to medical-specialized AI for areas that handle the clinical record itself.

Through providing AI Karte, Pottech aims to be the ideal business partner for clinics—improving the working environment for physicians, nurses, and medical clerical staff, and supporting clinics in fully realizing what they want to achieve.

For more details, please feel free to contact us.

Share this article

Related Articles

AI & DX

AI Tools That Support Physicians: Voice Input, Summarization, Literature Search, and Chart Creation

Voice input during consultations, drafting referral letters and certificates, literature search, patient explanation materials. What AI can take on in a physician's work sits around documentation and research. We organize the division of roles between general-purpose AI and healthcare-specific AI (the AI EMR), representative tools, and the line on patient information.

September 7, 2026
AI & DX

ChatGPT, Claude, and Gemini: How Clinics Should Choose

ChatGPT, Claude, and Gemini come from three different companies. But for a clinic, the deciding factor is not a capability comparison. Whether input is used for training, which contract tier applies, whether it integrates with existing systems—we organize the selection criteria specific to healthcare.

August 11, 2026
AI & DX

Medical AI in Electronic Medical Records: Case Studies and How to Read the Published Numbers

Case studies of AI in electronic medical records, drawn only from official announcements: discharge summaries, ward records and clinic voice charting. What the published numbers mean and how a clinic should use them.

November 1, 2026
AI & DX

What Is an AI Agent? How It Differs from Chat AI, and How Clinics Use It

An AI agent is not an AI that answers questions but one that, given an objective, assembles its own steps and acts. We explain how it differs from chat AI, the objective–plan–tool–verify loop, concrete clinic examples, why human approval must be built in, and what to check before adopting one.

September 7, 2026
AI & DX

What Is Generative AI? A Plain Guide for Clinic Staff on How It Works, What It Can Do, and What to Watch

Generative AI is AI that creates new text, images, and audio. How does it differ from the AI that classifies and predicts, why did it spread so suddenly, and where does it touch clinic work? We explain the mechanism with analogies, cover the three cautions—hallucination, training use, and personal data—and point to related terms.

September 7, 2026
AI & DX

What Is an LLM? What Is Inside ChatGPT, Explained for Clinics

Inside ChatGPT, Claude, and Gemini runs an LLM—a large language model. An LLM is a mechanism that predicts the next word, and understanding that explains why it makes mistakes and what you should never type into it. We explain how it works, its limits, and what clinics should verify.

September 7, 2026
AI Karte

Explore AI Karte

An AI-native EHR connecting reception, documentation, accounting, claims, and analytics into one cycle.

View the product page

AI Karte as an Option

Most of the problems covered in this article are what AI Karte, our AI-native EHR for clinics, is built to handle. Start by seeing what it is.