Skip to content
TriedPrompts

More in Health & Medical.

Understand flagged blood test results in a patient portal with Claude

WorkedEvidence: Article or interviewPosted Last checked

Claude explained Judith Miller's flagged blood results during the wait; the doctor later ordered a repeat test that came back normal.

Beginner-friendlyNo logins, payments or coding needed. Low risk: paste the prompt and you should get something useful.

How to use this

  1. Tap Copy prompt.
  2. Open Claude.
  3. Paste it into the message box.
  4. Send it, then read the answer before acting on it.
New to this? What's a prompt?

A prompt is the message you send to the AI tool. Copy the one on this page, put your own details where it asks, and read the answer before you act on it.

Prompt

Recreated prompt

The source didn't share its exact prompt, so we wrote one from what it describes. The result shown is the source's, not ours.

What the prompt labels mean

The person didn't share their exact words, so we wrote this from what they described. We haven't tested it, and they didn't use this exact version.

Here are my latest blood test results with my name and other identifying details removed. Explain in plain language what the flagged values mean, including carbon dioxide and anion gap, whether anything looks urgent while I wait for my doctor, and which questions I should send through my patient portal.

Try this in:

ChatGPT Gemini Grok Claude Used in source

Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini and Claude open empty, so we copy the prompt for you to paste. Every button also copies it.

The source used Claude. These are general chat tools, so results may differ.

Opens in a new tab. We don't see what you send.

These links are only a shortcut. We're not affiliated with OpenAI, Google, Anthropic or xAI, and your results may not match the source.

Optional stronger version

Our rewrite with extra checks. The poster didn't test it.

Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish.

Goal: Understand flagged lab values while I wait to hear from my doctor, without self-diagnosing.

Questions to ask me first:
- Which results were flagged?
- What has your doctor already said about them?
- Any conditions or medications that could matter?

Inputs (fill in or confirm):
- Results: [PASTED VALUES WITH REFERENCE RANGES, NO NAME OR ID]
- Doctor's note so far: [MESSAGE TEXT]
- Relevant history: [CONDITIONS, MEDICATIONS]

Rules:
- Explain each flagged value in plain words with its reference range.
- Don't diagnose; tell me plainly if anything needs a call to the office today.
- Suggest questions for my doctor rather than tests to demand.
- Remind me what not to share in a chatbot.

Checkpoint: List the flagged values back to me before explaining them.

If you get stuck: If a value has no reference range, say so instead of guessing.

Verify before you finish: Every explanation matches the value and range I gave you.

Output: A short plain-language summary per flagged value and three questions for my doctor.

Done when: I understand my results and know what to ask while I wait.

AI tool

Claude

Outcome

After routine blood work in July, 76-year-old Judith Miller of Milwaukee got an alert the same day that the results were in the patient portal. The doctor messaged the next day that the tests were fine, and while Miller waited for an answer about an elevated carbon dioxide level and a low anion gap, Miller put the results into Claude. Claude explained the abnormalities clearly and reported nothing alarming, so Miller wasn't anxious while waiting. After four weeks and a couple of follow-up messages in MyChart, the doctor ordered repeat blood work and an additional test Miller suggested; the results came back normal.

Evidence: Article or interviewA newsletter, journalist or interview account of what happened.

Source

Posted
by Kate Ruder (KFF Health News)
Last checked
Method:
How we verify

https://kffhealthnews.org/health-industry/electronic-medical-records-patients-ai-chatbots-diagnosis-privacy-accuracy/

Context: KFF Health News article. Physicians and patient advocates quoted in it warn that chatbots can give wrong answers and that health data may not stay private, and advise removing personal information such as a name or Social Security number from prompts.

More in Health & Medical

Similar cases