HIV and ID Observations

National Foundation for Infectious Diseases.

A journalist recently reached out to ask about the shingles vaccine. We mostly talked through the usual topics — how common shingles is, why the vaccine works so well, and side effects. Plus, the whole topic of zoster vaccination has been much in the news recently given studies associating receipt of the vaccine with a reduced risk of dementia.

Before we wrapped up, I suggested that hearing from someone who’d had a tough time with shingles might strengthen the piece. A colleague of mine, Lisa Junker (who is Senior Director of Publishing at the Infectious Diseases Society of America), had a serious case involving her ear several years ago.

It was a classic case of herpes zoster oticus, with severe pain, vertigo, and hearing loss. What she memorably said about it when she came back to work: “Shingles:  Do not recommend!” She graciously agreed to speak with the reporter for her WebMD piece.

The article came out, and it’s excellent. I noticed, however, that Lisa had received some wrong counseling from the ENT who cared for her:

Her ENT warned that if shingles returns, it will likely strike the same spot.

This misconception is surprisingly common. It’s right up there with the patient who’s told that waxing and waning symptoms in the same dermatome after an episode represents “recurrent zoster.” It almost never is — which is why this consult is one of the more common outpatient questions we ID doctors receive, and why I wrote about it several years ago. (It’s rarely covered clearly in textbooks or journal articles.)

In short, herpes simplex frequently recurs in the same location, but herpes zoster does not. Recurrent zoster usually (but not always) recurs in a different dermatome altogether, usually several years after the first episode, if it recurs at all — one study found that roughly 10% of people had another episode within 10 years, though this may be an overestimate since there are lots of cases of herpes simplex (and other things) misdiagnosed as herpes zoster.

That’s one of the things about this unpleasant disease. It’s unpredictable. And the ENT’s confident statement that it’s going to come back in the same “spot” — delivered as clinical fact — simply wasn’t correct. I let the reporter know, and she promptly removed the sentence.

And then curiosity got the better of me. Motivated by this New York Times piece that highlighted that patients used AI to get medical advice, I plugged this prompt into two AI tools, OpenEvidence and ChatGPT:

When people get shingles again, is it usually in the same location?

I deliberately left off medical terms such as “dermatome”, “reactivation”, or “recurrent.”

Here’s what happened: OpenEvidence hit the ball out of the park:

Recurrent shingles (herpes zoster) typically does not occur in the same location; it most often affects a different dermatome during subsequent episodes.

Available only to healthcare professionals, OpenEvidence is currently the best AI tool for medical information. I’ve written about it elsewhere as the “Google for Doctors — and nurses and PAs and anyone with an NPI.” Not only did it provide the correct answer, it offered several highly relevant citations. (Disclosure: NEJM Group, including NEJM Journal Watch, is among the publishers providing content to OpenEvidence.)

ChatGPT? Let’s stick with the same metaphor (can you tell I miss baseball?): it was more Charlie Brown than Aaron Judge, a big whiff:

When someone has more than one episode of shingles, the new episode most commonly appears in the same dermatome as the prior one. This fits the biology: the varicella-zoster virus remains latent in a specific dorsal root (or cranial nerve) ganglion, and reactivates from that same reservoir.

Not just wrong, but wrong with a pathophysiologic justification! Brilliant. This confident but incorrect answer echoed the ENT’s advice and underlies the very misconception that leads to clinical referrals asking about “recurrent” zoster.

When I corrected the model, it “thought” for 35 seconds, then acknowledged the error (“You’re right to push back on that”) and gave the correct answer. It even cited my 2014 blog post! So proud.

But the comparison was a useful reminder of how these systems work: highly fluent, highly confident, occasionally wrong.

And so, in the span of a single afternoon, the same misconception surfaced from three different sources: a clinician, a widely read health article citing that clinician, and an AI model. What can we take from this?

• Authoritative tone ≠ accuracy. Clinical confidence and AI assurance can all sound convincing, even when the underlying fact is off.
• AI varies depending on design. Tools that constrain themselves to curated evidence bases (like OpenEvidence) will give more reliable medical answers at baseline; generative models need supervision.
• Clinician expertise still matters. We’re the interpretive safety net, especially for edge cases, clinical nuance, and information not readily available through standard searches.

In the end, the article was corrected, Lisa is now happily vaccinated, and the real clinical pearl remains the same: If shingles returns, it rarely looks like the first episode.

And it’s definitely worth preventing — both for the first time, and for a recurrence.