Skip to main content
NewNMC’s advertising guidelines for doctors are in force from 6 Oct 2026. See what to change, and get a free compliance auditNew NMC advertising rules for doctors: what to change
AI Search

AI Says Your Hospital Offers a Service It Does Not: Fixing Wrong Specialty Claims

A patient asks which hospital offers a procedure and an AI answer names yours, wrongly. Here is a 50-query method to trace the false claim to old pages, directories and markup, and fix it.

AI Says Your Hospital Offers a Service It Does Not: Fixing Wrong Specialty Claims

A patient asks an AI assistant which hospital in Nagpur does robotic knee replacement, and your hospital is named. The trouble is that you do not offer it. Or the answer lists a paediatric cardiac unit that closed two years ago, or a consultant who moved to another city. The error is rarely invented from nothing. In most cases the model is repeating something that is written down somewhere, and that somewhere is often your own site or a directory you forgot.

This post is for marketing teams at hospitals and multi-speciality centres who have found, or suspect, a wrong service attribution. It answers one question: how do you find the source of the false claim, and what do you change so it stops? It is a method, not a set of results. We do not report test outcomes here; you run the test on your own brand.

Wrong service claims are a patient-safety issue as well as a reputation issue. A person may travel for a procedure you cannot perform. Bring your clinical lead and compliance owner into the review before you publish any correction, and do not describe what a procedure involves without clinical sign-off.

Step 1: Build a 50-query test set

Fifty queries is enough to see patterns and small enough to repeat every month. Build it from real patient language, not from your service list. Split it roughly like this:

  • Service existence (15): "does [hospital] do [procedure]", "[procedure] hospital in [city]".
  • Specialty and department (10): "best [specialty] hospital in [city]", "[hospital] cardiology department".
  • People (10): "[doctor name] specialty", "who is the head of [department] at [hospital]".
  • Facilities and access (8): emergency, ICU, day care, international patient desk, cashless insurance.
  • Comparison (7): "[hospital] vs [competitor] for [procedure]".

Include at least ten procedures you do not offer but a neighbouring hospital does. False positives hide there. False positives tend to hide there, because hospital pages share much of the same vocabulary.

Run every query on each surface your patients plausibly use: ChatGPT with search on, Google AI Overviews and AI Mode, Gemini, Perplexity and Microsoft Copilot. Use a clean browser profile and record the date, surface, location setting and whether the answer cited sources. Run each query at least twice. Answers vary between runs, so a claim that appears once is a signal; a claim that appears in most runs is a finding.

Step 2: Score each answer

Use a simple sheet with one row per query and surface. Columns that matter:

ColumnWhat you record
Hospital namedYes or no
Claim typeService, doctor, location, facility, accreditation, price
Claim correctCorrect, wrong, outdated, unverifiable
Sources shownURLs the surface displayed
Quoted wordingThe exact sentence that is wrong
Run countHow many of the repeat runs showed it

Have someone who knows the hospital mark each claim, with the department head confirming anything clinical. Do not let the person who wrote the website be the only reviewer; they will read the claim through the intent of the page, not through what a machine would extract from it.

Sort the wrong claims by risk. A wrong visiting-hours answer is an annoyance. A wrong claim that you perform a transplant, a cancer therapy or fertility treatment is the first thing to escalate.

Step 3: Trace each wrong claim to a source

Models do not store a labelled list of facts about your hospital. They assemble answers from training data and, where search is on, from pages retrieved at the time of the question. For the retrieval surfaces you can often see the pages used. For the rest, you search for the wording yourself.

Where citations are shown. Perplexity and ChatGPT search display source links; Google's AI Overviews show supporting links. Open each one and search the page for the wrong term. Google's AI features documentation explains that these features may issue multiple related searches across subtopics and data sources, so the supporting page may not be the one you would have predicted. Check every link, not just the first.

Where nothing is cited. Take the exact wrong phrase and search for it in quotes on Google and Bing. Then search for the procedure name together with your hospital name, and for the procedure with each former doctor name. If the claim appears in a model answer without any retrievable page, it may come from older training data. Then the fix is to make current, correct pages abundant and consistent, because you cannot edit the model.

Classify what you find into these source types. Each has a different owner and a different remedy.

Your own site

This is the most common origin and the easiest to fix. Look for:

  • Retired service pages still live, or redirected to a generic department page that still lists the service.
  • Template boilerplate: a footer, mega-menu or sidebar listing every service across all branches, so a page about one branch appears to mention services offered at another.
  • Branch pages copied from the flagship hospital with the service list intact.
  • Old press releases and news items announcing a planned service that never launched or has since stopped.
  • Doctor profiles that list a procedure the doctor performed at a previous hospital.
  • PDF brochures and camp flyers, which are rarely updated and often outrank the web page.

Crawl the site and extract every page that contains the procedure name. A technical SEO audit can include this inventory. Match the list against the current service register that the clinical team signs.

Directories and aggregators

Listing sites, doctor-booking platforms, insurer network pages and medical tourism facilitators often hold their own service lists, written years ago and never revised. Search the procedure name on each directory that lists your hospital. Record the profile owner, the login and the last update date. Our local citations list covers the common Indian directories; use it as the starting inventory for this audit.

Structured data and profiles

Check your own markup. A medicalSpecialty value or a list of procedures in JSON-LD that is broader than reality will be read by search systems as a declaration. Also check Google Business Profile services and categories, social profiles and any knowledge-base entries your hospital has on Wikipedia or Wikidata. The schema markup guide shows which properties to keep narrow.

Third-party content

Local news, listicles, "top hospitals" pages, forum threads and reviews may state that you offer a service. You cannot edit these, but you can ask the publisher for a correction and publish an accurate source that outranks them.

Want this applied to your practice? Get a free ai search audit.

Book my free audit

Step 4: Fix in order of source authority

Fix what you control first, then what you can influence.

  1. Remove or correct your own pages. For a retired service page, either return a 410 or 404 status, or redirect it to the most relevant department page that no longer mentions the service. Do not leave a soft redirect to a page that still lists it. Update boilerplate lists so each page shows only services offered at that location.
  2. Rewrite the service register publicly. Publish one page per site that states the services offered at that campus. Where confusion is likely, add a plain sentence such as "We do not currently perform X at this hospital; for X, speak to your doctor about referral." Clinical and compliance teams must approve this line. Negative statements are unusual, but a machine reading the page can quote them.
  3. Correct the directories. Log in and edit the profile. Where you cannot, use the platform's contact route and keep the ticket reference.
  4. Fix structured data so it matches the page text. Google states in its AI features guidance that there is no special schema needed for these features, and that structured data should match the visible text. Treat markup as a consistency check, not a lever.
  5. Request corrections from third parties with a short, factual email that names the page, the sentence and the correct statement.
  6. Use the platforms' feedback tools after the sources are fixed. Feedback buttons exist on most AI surfaces. Use them to report the specific answer, but do not rely on them; a correction in the source is more durable than a ticket.

Step 5: Know how long to wait

Recrawling is not instant. OpenAI's crawler documentation says it can take around 24 hours from a robots.txt update for its systems to adjust, which tells you the order of magnitude for its search crawler. Google notes that changes to preview controls can take days to months to be reflected, according to its AI features page. Do not re-test the same day. Re-run the 50 queries two weeks after the last change, and again at six weeks.

Where a model answers without retrieval, there is no schedule at all. Your goal is to make the correct information the most consistent version available across the web, so that newer training and retrieval cycles pick it up.

Step 6: Keep the audit running

A single clean-up decays. Staff change, services open and close, and directories re-import old data. Add these controls:

  • A service register owned by one person, signed by clinical leadership, with an effective date.
  • A change trigger: any new or stopped service creates a ticket covering the website, the directories, Google Business Profile and schema.
  • A monthly re-run of the 50 queries, logged in the same sheet so you can see drift.
  • An escalation rule: a wrong claim about a high-risk service goes to compliance within one working day.

Tools that track where your brand is cited across AI answers can speed up the logging. AiLLMz organises citations and publication workflows that support visibility across AI search and LLMs, and a sheet works as well for a first pass.

Checklist for this week

  • Write the 50 queries, including ten services you do not offer.
  • Run each on at least four AI surfaces, twice, and record sources.
  • Classify every wrong claim by source type and owner.
  • Crawl your site for retired service names and branch boilerplate.
  • Correct the three highest-risk claims first, with clinical sign-off.
  • Schedule the re-test for two and six weeks after the changes.

If your hospital also needs a broader plan for AI visibility, our AI search optimisation service and the AI search optimisation guide cover the wider programme. The audit above is the part you can start without a budget.

Filed underAI hallucination hospital servicesAI wrong hospital informationChatGPT wrong hospital servicescorrect AI answers about hospitalAI search brand accuracy hospital

About the author

Co-Founder & CTO · Gurugram, India

Arush builds the systems the rest of the company runs on — the patient-acquisition pipelines, the AI chatbots, the analytics that tie a single click to a booked appointment. If a campaign reports a number, it's because something his team built is tracking it.

Free guide · 15 pages

The Patient Acquisition Blueprint

A 90-day plan from first search to booked appointment.

The Pioneers Brief — one essay, three benchmarks, one teardown, every Thursday. Subscribe free →

Free ai search audit

Your next chapter starts with a conversation.

Three quick questions. We come prepared with a plan for your specialty and city.

  • A 30-minute call with a healthcare specialist
  • Your top three growth opportunities, in writing
  • Honest advice — even if that means not hiring us
  • No obligation and no hard sell
You’ll speak with a senior strategist
Consultations are hosted by Arush Thapar’s team.
Step 1 of 3Takes 30 seconds

What do you want to improve first?

Details stay privateNo obligationReply within 1 working day

Client portfolio · Healthcare websites

Work relevant to ai says your hospital offers a service it does not fixing wrong.

Explore client work →