Medical Economics
August 25, 2026
August 25, 2026
Five sources to audit for AI visibility
Five sources account for roughly four in five ChatGPT citations about physicians. Practices can audit all five themselves.
Halcy Research
When a patient asks AI for a doctor, which practices get named?
Usually, no independent one. We sampled 200 independent practices at random and ran nearly 5,000 patient-realistic prompts through ChatGPT. It named zero of them.
This is the running record of what large language models actually say when people look for care – which practices surface, which sources the models trust, and what the visible practices do differently. Built from our own measurement corpus, shared openly.
- Practices
- 200
- Prompts
- ~4,950
- Specialties
- 18
- Metros
- 20
- Model
- GPT-5.5
- Run
- May 2026
ChatGPT mentioned and cited 0 of 200 randomly-sampled independent practices.
In the press
Our research, published in national physician media.
Medical Economics
August 18, 2026
August 18, 2026
Who controls your ChatGPT description?
Only 2.1% of citations describing the average named practice came from its own website. Third parties supplied the rest.
Medical Economics
July 20, 2026
July 20, 2026
Why ChatGPT favors hospital systems
Two in three practices ChatGPT names in specialist searches are hospital-affiliated. Here’s where independents can compete.
MGMA
May 21, 2026
May 21, 2026
Why ChatGPT overlooks your practice
We tested 200 independent practices with nearly 5,000 ChatGPT prompts, and not one was named. This research explains the gap.
MGMA
May 20, 2026
May 20, 2026
Where ChatGPT gets its answers
We mapped 33,340 ChatGPT citations across 200 practices and 10 specialties to see which sources shape who gets named.
The findings
On-site · Deep dive
Why ChatGPT doesn’t mention your practice
The 0-of-200 result, the five on-site signals almost no practice has, and why your specialty and metro set your ceiling.
Read the on-site findings
Off-site · Interactive map
Where ChatGPT gets its answers
An interactive map of 33,340 citation events – the hospital rosters, associations, and magazines the model actually pulls from, pivotable by specialty.
Explore the citation map
Dental · Deep dive
ChatGPT’s top dental source is the practice’s own website
Across 1,405 dental questions, practice-owned websites drew 53.8% of the 13,152 sources ChatGPT cited – more than three times the next category. The full mix by sub-specialty and metro.
Read the dental findings
Dental · Case-control
What separates the dental practices ChatGPT cites from the ones it doesn’t
A matched comparison of 540 dental practice websites. 33.6% of cited sites had a page of 1,000 words or more against 19.3% of matched uncited sites; FAQ markup, Q&A blocks and credential schema did not separate the groups.
Read the comparison
Health systems · Study companion
How AI recommends care across US metros
In small US metros, the health system an AI model recommended most got 37.9% of local care recommendations on average, against 23.8% in the largest metros. We analyzed 3,000 answers across 30 metros and 30 service lines, including how often the list changed when we asked again.
Read the study
How we measured it
Every figure on this site comes from our own measurement corpora, not estimates.
For the medical corpus we drew a stratified random sample of independent practices from the NPPES registry across 18 specialties and 20 metros, then ran a fixed battery of patient-realistic prompts – scoped to each practice’s specialty and metro – through GPT-5.5 via the OpenAI API, with multiple runs per query to absorb variance. We separate a mention (your name in the answer a patient reads) from a citation (a URL the model pulls from), and anchor on mentions wherever the data supports it. In June and July 2026 we ran a parallel dental corpus the same way – 1,405 patient-realistic dental questions across 20 metros and seven areas of dentistry, with all 13,152 cited sources categorized by type. Single-platform, US-only, correlational. Behavior on Gemini and Google AI Overviews may differ.
New to AI search optimization? Our plain-language guides in Learn explain the concepts behind this research.
Disclosure. Halcy is a commercial service; the practices we work with pay for these deployments. We ran this corpus for our own product development and publish it openly so administrators can audit their own AI presence regardless of any vendor relationship.