Use of Artificial Intelligence in Research – Watts Up With That?

Me: List major studies showing that autism either is or is not associated with vaccination.

Note the construction. I’ve found that in doing scientific research it is important to specifically ask for evidence for both sides of the question. You want to avoid general questions like “What is known about autism and vaccines”. With that kind of phrasing, often an AI will not fully explore the question space, leaving out important evidence for one side or the other.

Here’s perplexity’s answer to my question above:

Several major studies have investigated the potential link between vaccines and autism. Here’s a list of key studies showing no association between vaccines and autism:

1. Taylor et al. (1999):
   • Examined 498 children with autism in North Thames, England
   • Found no difference in autism rates between vaccinated and unvaccinated children
   • No clustering of autism diagnoses after MMR introduction
2. Madsen et al. (2002):
   • Studied 537,303 children in Denmark
   • No increased risk of autism in MMR-vaccinated children
   • No association between age at vaccination, time since vaccination, or date of vaccination and autism development
3. Jain et al. (2015):
   • Evaluated about 100,000 children with older siblings with or without autism
   • No increased risk of autism spectrum disorder (ASD) associated with MMR vaccination
4. Danish study (1991-1998):
   • Included over 500,000 children
   • No link found between MMR vaccine and autism or autism spectrum disorders
5. Meta-analysis by Taylor et al. (2014):
   • Analyzed 10 studies involving over 1.2 million children
   • Reaffirmed no association between vaccines and autism
   • Suggested MMR vaccine may actually decrease autism risk

Hmmm, sez I …

Now, as I mentioned above, AIs do hallucinate. So my next directive to perplexity is:

Verify that each of those is a real study, not a hallucination.

I‘ll verify the studies mentioned in the search results:

1. Brent Taylor et al. (1999): This is a real study examining 498 children with autism in North Thames, England.
2. Madsen et al. (2002): This is a genuine study published in the New England Journal of Medicine, involving 537,303 children in Denmark.
3. Taylor et al. (1999) reanalysis: This appears to be a real reanalysis of the original Taylor study, though I don’t have enough information to confirm its exact publication details.
4. Hviid et al. (2019): This is a real nationwide cohort study in Denmark, published in the Annals of Internal Medicine, involving 657,461 children.
5. Time-trend analysis using the UK General Practice Research Database: This is a real study, though specific authors aren’t mentioned in the provided information.

Noticing that one study was left out, I asked:

Verify that 3. Jain et al. (2015) is a real study, not a hallucination.

Yes, Jain et al. (2015) is a real study, not a hallucination. This study is mentioned multiple times in the search results:

• It’s listed in the Children’s Hospital of Philadelphia vaccine education center information
• The full citation is provided: “Jain A, Marshall J, Buikema A, et al. Autism occurrence by MMR vaccine status among US children with older siblings with and without autism. JAMA 2015;313(15):1534-1540.”
• The JAMA (Journal of the American Medical Association) article details are given, including the publication date of April 21, 2015
• The study’s methodology and findings are summarized, noting it evaluated about 100,000 younger siblings and found no association between MMR vaccination and increased risk of autism spectrum disorder
• It’s referenced in a Science Daily article about MMR vaccine and autism

The study is also cited in an Immunize.org document listing evidence that MMR vaccine does not cause autism

These multiple, consistent references across different sources confirm that Jain et al. (2015) is indeed a real study examining the relationship between MMR vaccination and autism risk.

All of these studies appear to be real based on the information provided. However, for some studies, I don’t have enough details to fully verify their publication information or authorship.

Upon request, Perplexity also provided details for all of the other studies it found in its research, viz:

I found it fascinating to see its judgment of the validity of the information it is examining.

Moving on, I asked:

Provide a list of key studies claiming some association between vaccines and autism

Based on the search results provided, there are no credible studies claiming an association between vaccines and autism. The search results consistently report that extensive research has found no link between vaccines and autism. However, one flawed study is mentioned that initially sparked the controversy:

Wakefield et al. (1998):

• Published in The Lancet (later retracted)
• Suggested a potential link between MMR vaccine and autism
• The research was later found to be fraudulent
• The lead author lost his medical license
• The medical journal retracted the paper

It’s important to note that this study has been thoroughly discredited and numerous subsequent studies have found no link between vaccines and autism.

————-

Look, friends, I know that there are real reasons to be cautious about vaccines. These include the steep increase in the number of recommended childhood vaccines as well as the increase in the number of adjuvants, preservatives, and other components in modern vaccines.

However, from this examination of solid scientific evidence about the question, it is clear that autism is not among the reasons to be cautious. Well-designed studies have repeatedly failed to find any link between vaccines and autism, and no studies have demonstrated such a link. Pick another objection, that one’s done and dusted.

Finally, some folks say that vaccinations don’t really protect us against diseases. While this may well be true about the COVID-19 vaccine, here are the observed rates of cases and deaths before and after the introduction of vaccines for a variety of illnesses.

Zooming in close reveals interesting pre- and post-vaccine morbidity and mortality statistics. Cause of the most deaths before vaccines? Whooping cough aka pertussis aka croup, 30 deaths per million. Followed by flu/pneumococcal disease (24/million), polio (22/m), diphtheria (14/m), and tetanus (3/m).

And here is what Jonas Salk did with his polio vaccine.

So that’s the end of the evidence and the beginning of the discussion. First, I know that folks are passionate about this question. So please, don’t shoot the messenger.

What I’ve presented above is how to use perplexity or any AI to unearth scientific evidence about very specific questions of a) autism and vaccines and b) the overall efficiency of each vaccine. I take no further position other than advising caution on everything.

Next, the myriad of questions about vaccines will not be solved on this web page. So let me ask folks to not take sides in the comments. It won’t help. As I said above, other than those two questions of autism and efficiencies, other reasons for caution remain. Exactly what is in each vaccine? What concentration? When, where, and how was it tested?

So in lieu of taking sides, let me invite people instead to use AI to dig out answers to those particular questions that remain in your mind about some particular vaccine, to search for solid scientific evidence, and to set aside the impassioned web-based claims and position-taking in favor of an actual search for current scientific knowledge.

Finally, one thing to emphasize. As the first graphic above shows, there is no one vaccine question just as there is no one vaccine. There’s no overall good/bad, black/white issue.

Instead, every vaccine and every component of every vaccine has its own story, its own effects, and its own unanswered questions. For example, in the US, in what may be an excess of caution, childhood vaccines contain no mercury, while the adult versions of the vaccines contain millionths of a gram. Different issues, different relevant questions. Another example. I lived through the time of polio and Jonas Salk’s miraculous vaccine. And I even worked for several months as the night attendant of an adult polio victim spending the rest of his entire life in an iron lung, paralyzed from the neck down … he was married with one child and had just finished his medical residency when he was struck down. I would read to him, and play chess with him … dear friends, you don’t ever want to see that happen to anyone, much less your child.

The Salk vaccine brought a huge benefit. I can guarantee we don’t want to go back to those days. Different vaccines, different benefits, different questions, different issues, there’s no one overarching “Are vaccines good or bad?” question.

My best regards to each of you, stay well out there in this lovely but deadly world,

w.

PS—I’m still persona non-grata on X, with my account improperly suspended as I explain in my blog post below: