A FEW weeks ago I was invited to present our work on Bayesian networks for the NHS Health and Care Analytics Conference 2023. This is a large and important conference to be held next month, chaired by Ben Goldacre (the author of the bestseller Bad Science), sold out with more than 400 delegates and a similar number online.
The conference organisers tweeted about my presentation:
I was neither offered, nor asked for, any fee. In the past week I have spent many hours preparing a presentation containing our latest research with examples of Bayesian network risk models for a range of chronic diseases (diabetes, rheumatoid arthritis, multiple sclerosis and Alzheimer’s). The title, abstract and bio that were agreed are at the bottom of this article. The talk was nothing to do with any work I have undertaken on Covid or the vaccines.
On Tuesday – ironically seconds after recording a video for Michael Shellenberg’s Censorship Files documentary – I received the following email from the person who had invited me to make the presentation.
So I was cancelled not for the content of my talk but because I had done other work raising concerns about Covid vaccine safety.
After an immediate response stating that I intended to make this public (to which there was no reply), I sent the following more formal follow-up at 09.00 on June 21:
‘Following on from my response yesterday, I would like to know more about how the decision was made to cancel my presentation and who initiated it and approved it (including if any of the recipients of the email approved the decision). Was there any attempt by any NHS staff to reverse the decision given that it is clear that my voice has been suppressed simply for raising safety concerns in the public interest? I am asking this because it has become a matter of public interest to publish this story of censorship. I would be grateful if you could reply within 24 hours as I intend to publish this tomorrow.
‘I also require a copy of all the communications referred to (“the conference committee have just been alerted to”) by return under GDPR [General Data Protection Regulation].
More than 24 hours has passed and I’ve still received no acknowledgement or reply.
Of course this is just the latest, albeit a particularly nasty, example of the censorship and cancellation I’ve suffered for the last three years.
As Martin [Neil, Fenton’s colleague] noted on Twitter: ‘Note that in censoring Norman they are also censoring research undertaken by young researchers who have not uttered a public word on the subject of vaccines. Also bear in mind the results of this research were largely funded by the public purse, hence the event committee are denying the NHS access to research results funded by another arm of government. The decision is not only unethical and irrational, it is deliberately vindictive.’
Here is the title, abstract and bio that were agreed:
Title: Bayesian networks: what are they and why they work when ‘big data’ methods fail
Abstract: Misunderstandings about risk, statistics and probability often lead to flawed decision-making in many critical areas such as medicine, finance, law, defence and transport. The ‘big data’ revolution was intended to at least partly address these concerns by removing reliance on subjective judgments. However, even where (relevant) big data are available there are fundamental limitations to what can be achieved through pure machine learning techniques. This talk will explain the successes and challenges in using causal probabilistic models of risk – based on a technique called Bayesian networks – in providing powerful decision-support and accurate predictions by combining minimal data with expert judgment. The talk will provide examples in chronic diseases. The talk is targeted at anybody interested in quantifying and predicting risk.
Biography: Norman is Professor Emeritus of Risk at Queen Mary University of London (retired as Full Professor Dec 2022) and a Director of Agena, a company that specialises in artificial intelligence and Bayesian probabilistic reasoning. A mathematician by training with current focus on quantifying risk and uncertainty using causal, probabilistic models that combine data and knowledge (Bayesian networks). He has published seven books and more than 350 peer-reviewed articles. His works covers multiple application domains including especially health and law/forensics (he has been an expert witness in major criminal and civil cases). Since 2020 he has been active in analysing data related to Covid risk.