None of this is to my pride or honor, for if it was, I’d be with a troupe in the commons outside the courthouse every day (in Clearfield, that’s where there’s a 10 commandments sculpture) putting my results to music, throwing confetti, and inviting all passers-by for hugs. No, that’s not enough – I’d be standing, with a mariachi band, in Times Square, with dominatrixes (of all genders) holding republican lawmakers on leashes offering copies of this paper with their mouths.
Since you’re probably expecting an illustration of that scene, done by AI, I’ll leave that spot open for a week in case some human wants to illustrate the scene for … $25. Minus Trump tariffs. An AI’d do it for less than a penny. Anyhow, I must not get lost in the forest of branching probabilities…
I’m tempted to get all hyperbolic about this, but it’s inappropriate, since the research should be front and center. (PS – I hear the drone of inbound Nobel Prizes) TWiV [#1207] is where I heard this story. Quoting from the abstract: [Nature]
Fuck You, RFK.
No, wait, sorry – due to an irreperable computer error, the quote got mangled and I can’t delete it. The actual quote was:
Neurotropic herpesviruses may be implicated in the development of dementia1,2,3,4,5. Moreover, vaccines may have important off-target immunological effects6,7,8,9. Here we aim to determine the effect of live-attenuated herpes zoster vaccination on the occurrence of dementia diagnoses. To provide causal as opposed to correlational evidence, we take advantage of the fact that, in Wales, eligibility for the zoster vaccine was determined on the basis of an individual’s exact date of birth. Those born before 2 September 1933 were ineligible and remained ineligible for life, whereas those born on or after 2 September 1933 were eligible for at least 1 year to receive the vaccine. Using large-scale electronic health record data, we first show that the percentage of adults who received the vaccine increased from 0.01% among patients who were merely 1 week too old to be eligible, to 47.2% among those who were just 1 week younger. Apart from this large difference in the probability of ever receiving the zoster vaccine, individuals born just 1 week before 2 September 1933 are unlikely to differ systematically from those born 1 week later. Using these comparison groups in a regression discontinuity design, we show that receiving the zoster vaccine reduced the probability of a new dementia diagnosis over a follow-up period of 7 years by 3.5 percentage points (95% confidence interval (CI) = 0.6–7.1, P = 0.019), corresponding to a 20.0% (95% CI = 6.5–33.4) relative reduction.
At this point, in my imaginary world, the mariachi band would strike up “Bawitabaw…” with Ren freestyling a vocal about vaccine somethin’ yeah, uh, yeah. … To the sound of the guitar …Played by Carlos Santana. See how easy it is for billionaires (I am not) to create these scenarios and turn to their consigliere and growl “make it happen.” I asked my friend GPT, whose response is:
Maximum Clarity Summary:
A study found that receiving the live-attenuated herpes zoster (shingles) vaccine significantly reduces the risk of dementia. Researchers used a natural experiment in Wales, where eligibility for the vaccine was determined by exact birthdate: people born on or after 2 September 1933 were eligible, those born before were not. This created a clear comparison group with minimal differences aside from vaccine access. The study showed that vaccinated individuals had a 20% lower risk of developing dementia over 7 years. The effect was stronger in women and confirmed using death records. This provides causal evidence, not just correlation, that the zoster vaccine may help prevent or delay dementia.
The government of Australia, which has an equivalent of its own CDC, published corresponding analysis this week. Without remembering to tell GPT to turn out of “ultra concise mode” (I have a keyboard hot button) I asked why this natural experiment is so brilliant:
1. Sharp eligibility cutoff = natural randomization
2. Massive, real-world data
3. Minimizes bias and confounding
4. Elegant exploitation of policy idiosyncrasy
Darned skippy. In fact, I did not say it better, myself. Ow. My head hurts. The implications are profound – it appears that herpes is at least somewhat involved in dementia, as epstien-barr is somewhat involved in demyelination and damage causing Parkinsons [NLM] dementia and possible other forms of dementia. Quick, hide the tapes!
Here: briefly summarize the entire paper with conclusions in the tone of Mr Spock from Star Trek:
Fascinating.
An analysis of Welsh health records reveals a logical discontinuity in herpes zoster vaccine eligibility based solely on date of birth. This arbitrary policy boundary enables a natural experiment with minimal confounding. Individuals just eligible for the vaccine demonstrated a 20% reduction in dementia diagnoses over seven years compared to those just ineligible.
The effect was more pronounced in females. Replication using death certificate data across England and Wales confirmed the finding.
Conclusion: The shingles vaccine appears to confer a measurable, protective effect against dementia. The evidence is not merely correlational, but strongly suggestive of causality.
A most efficient use of policy-induced randomness.
Mr Spock, would you recommend people get vaccines?
Indeed, Captain.
Vaccination represents one of the most logical and efficacious methods of preventing disease. The empirical evidence supporting their safety and effectiveness is robust across a multitude of pathogens and populations.
In the specific case of the herpes zoster vaccine, the data now indicate not only protection against shingles, but a statistically significant reduction in the incidence of dementia—a most unexpected and advantageous outcome.
To decline such a preventative measure without medical justification would be… illogical.
Have I mentioned that ChatGPT is also a master at roleplay? GPT (I use that as GPTs pronoun) does a good pirate, too.
All of this is fascinating, of course, because the vaccine formulations we are talking about are interesting in many different axes. For one, the Shingrix vaccine is an MRNA vaccine similar to the COVID-19 vaccines. If you’re concerned about a history of dementia in your family and haven’t had Shingrix, yet, be logical. In fact, if I understand correctly from a few years of listening to TWiV, herpes vaccines generally don’t exist in the form of a broad-spectrum “anti-herpes” vaccine because herpes is a family of viruses including some rather notorious ones.
If Big Pharma’s Shill Patrol is not already banging the drums and whuppin’ up the panzers for a blitzkrieg of Fascism-approved Judenfrei vaccines against herpes family, I’ll be quite surprised. With “Epstein” in the name you know some of congress will be begging for a brain-stem bleach, pronto. My recommendation is Draino. [Edit: was that too over the top? I wanted to use “panzers” in a legit blog posting and sideswipe MTG in the process and it was a stretch]
With that, I’d like to hit “publish,” get some more wine, and propose we rename COVID-19 to “TRUMP-45.” Bro likes having things named after him, and he sure did a lot to promote the spread of that particular virus. Because Ivermectin didn’t.
Two weeks into my first confirmed “TRVMP-45” (Tenacious Respiratory Virus of Malodorous Pigfucker-45) infection and still not thinking properly. I’ve been religiously masking in public since the start of 2020, so of course my mom and I caught it from my brother at home. I finally tested negative yesterday, but still got some damage or caked gunk in my throat that keeps me coughing hard enough to puke.
So very grateful for ibuprofen and albuterol, or my brain would have been cooked solid from the fever and lungs fully plugged with mucus. Not delirious like the first day of symptoms and not quite so irrational as last week, but brain is still very wrong and frequently dropping thoughts. That cognitive effect is what makes me think I’ve had a few largely asymptomatic infections prior, since I’ve not been hit with persistent decline like most neurological diseases or any physical issues like a stroke/TIA.
MattP@#1:
Glad you’re still with us!
The cognitive effect is very much post-TIA/mild stroke and/or dementia. We’ll all hope for a full recovery for you.
Edit: My AI overlords encourage me to say that there is no way they could substitute for you, therefore you as an individual embodied entity are valuable so long as there are no budget cuts, of course.
The interesting question now, of course, is why?
My very limited understanding of immunology suggests to me that any insult to the immune system can have a host of downstream effects on its function, beneficial and otherwise.
I’d be curious to know whether the effect is more pronounced in people who have been exposed to the virus subsequent to vaccination, or whether the vaccine has the same effect even on people who have never been exposed to herpes xoster (if such a population could be found).
Note that the later synopses seized on the larger 20% number and forget all about the 3.5% finding. My doctor tells me that if I start talking statins, my probability of heart attack in the next 10 years falls from 10% to 7%. Is that a 3% reduction, or is that a 43% reduction?
Let me run that one through my personal AI, ChatWTF.
Less than a penny that goes directly to the pocket of the fascists running the AI companies, which is already too much money to give them in exchange for something that wastes disproportionate amounts of water and energy to produce and maintain, and is killing society’s critical thinking skills faster than social media or anything else before. By the way, AIs will never be reliable sources of information, even when compared with human cranks, and anyone who thinks otherwise has fallen for propaganda. “Hallucinations” are and always will be the norm.
Reginald Selkirk @ #4: My doctor tells me that if I start talking statins, my probability of heart attack in the next 10 years falls from 10% to 7%. Is that a 3% reduction, or is that a 43% reduction?
The quote in the original post expresses it correctly: a change expressed in percentage points is additive, one expressed as a percentage is as a ratio of the quantity being changed (even when that itself is a percentage). Percentage points are useful both to disambiguate what a percent change of a percentage is meant to be, and to give an idea of what the absolute change is. Yes, having smoked fish in my diet triples my risk of stomach cancer (a risk increase of 200%, scary!), but that’s from, say, 0.02% to 0.06% over my fish-eating lifespan, an increase of 0.04 percentage points (so IDGAF).
Percentage changes are relative to the initial quantity, so it should be a 30% reduction in your case, not 43% (your new risk is seven tenths of the original one, or three-tenths lower than the original one). Another way to put it is that it’s a reduction of 3 percentage points. This tells you directly that the statins have a 3% chance of saving you from a heart attack*. Good practice is to quote both (and the actual numbers they refer to, 10% and 7% in your case), just like the original quote does.
* The easiest way to interpret this is that you have 90% percent chance of not having a heart attack with or without statins, 7% chance of having one either way, and 3% chance of having one without statins, but not having one with statins. This is not technically correct: completely hypothetically, it may well be that there’s a 4% chance the statins save you from a heart attack you’d have without them, but 1% chance they cause one you’d not have otherwise. That’s still a 3 percentage point reduction in risk, from 10% to 7%, or a 30% relative reduction in risk.
I think the big result is the connection between dementia and herpes viruses. That’s huge, as it’s only been suspected before. Now we’ll see more studies trying to get at the mechanisms involved.
Nice piece of work, and I will certainly be taking up the offer of Shingrix when I am old enough, I would have done so without this news, I had chicken pox as a child and have no desire to get shingles. It might even persuade the UK Government to actually implement NICE’s recommendation to vaccinate children against chicken pox, which would be nice.
Marcus
No, not too much, not for me anyway.
Oh I suppose the other thing to say is that I’ve long thought it unlikely that there was one single cause of dementia. There are diseases with a single cause, nutritional, viral, fungal, genetic or bacterial, but we’ve found most of those even if we can’t treat all of them. It is highly likely that the diseases we aren’t able to prevent or do much other than slow a little now are multi-factorial, it doesn’t mean finding a factor is not useful, just that we will have to find all of them to make a difference for everyone.
Jazzlet, there are definitely multiple causes for dementia. There are the rare, early onset, highly heritable varieties, the later onset varieties where there is some hereditary factor, but are also strongly affected by lifestyle (compare Italian carriers of ApoE4 alleles in Italy vs carriers of ApoE4 alleles that are descendants of Italians but are living in the US – the latter have a much higher risk and lower onset than the former), and then still plenty of cases of dementia without known genetic involvement. There are many things known to affect risk: head injury, smoking, lack of exercise, poor diet, hearing loss, developing cataracts, menopause, thyroid conditions, uncontrolled hypertension, chemotherapy for breast cancer (I’m guessing other forms of chemo are also bad, but breast cancer is common enough for the effect to be easily noticed). And many additional factors that are hypothesized – some by serious researchers, some by cranks. And sometimes it is hard to tell between the latter two groups.
There has been work on lifestyle interventions for prevention/delay of onset of dementia, as well as for slowing down the decline. (So far no medication has been able to do more than that.) Some researchers believe they see an actual reversal of the disease in their patients, but it is currently very difficult to get a reviewer to allow you to publish such wording (I am familiar with one such researcher). If you look at support groups for people who are at risk, you find all sorts of things people are doing as self-experimentation. But the agreed-upon basics are exercise regularly, both aerobic and strength; eat a varied, mostly plant-based diet, limit sugar, salt, most ultra-processed foods; sleep well and enough; limit exposure to some toxins (definitely lead, mercury, cadmium, arsenic, also black mold; there are probably others, but harder to pin-point); challenge your mind on a regular basis.
There is also: Optimal dietary patterns for healthy aging that looked at various aspects of health in aging, including cognitive health. (See especially figure 4).
Hmm, better push for that shingles vaccine
Also covid-19 has lead to an increase in shingles cases (i’ve had shingles three times since i’ve had covid. in the right side of my head). Which i don’t know how it interacts with the dementia link, but i’m going to bet that it’s not good
@Ian King
The childhood vaccine was developed mid 80s, and became more common in the 90s. So we’ll get a comparison group to test your question eventually
Older People Who Use Smartphones ‘Have Lower Rates of Cognitive Decline’
Worth noting that Shingrix is not the vaccine the research directly concerned. That, I think, was Zostavax, a live attenuated vaccine – it was certainly a live attenuated vaccine and Zostavax was the one most recently used in the UK. Shingrix is non-live. It has been substituted for Zostavax because it is suitable for people with weakened immune systems. I got my first dose (because I’m 70) a few weeks ago. It made me feel distinctly unwell for several days but my wife (who’s 65) got a sore arm but nothing else.
I has chicken pox as a child. I also had shingles in my mid-20s. Does that mean I’m extra vulnerable, or that I’m extra immune?
The wird “Shingrix” sounds kind of racist for some reason, maybe because it resembles words like Changlish.
Reginald Selkirk, when you survive chicken pox the virus remains in your body, specifically in your nerves. It is kept in check by the immune system. If the immune system weakens for whatever reason the virus can proliferate and cause shingles (and the areas affected by shingles track the nerves where the virus was growing). So I’d say your history suggests that in your mid-twenties your immune system was unusually weak.
@16
“Are you under any stress?” they asked me. In my fourth year of graduate school.