Webinar Series — Reasoning Under Uncertainty (Part 2): Differential Diagnosis of COVID-19 and Influenza-Like Conditions
Differential Diagnosis of COVID-19
Artificial Intelligence for Pandemic Triage with Bayesian Networks
This webinar introduces our collaborative knowledge elicitation project for the differential diagnosis of COVID-19 and influenza-like diseases.
From Local Insight to Worldwide Diagnostic Practice
We present a comprehensive knowledge elicitation and reasoning framework that is built on the Bayesian network paradigm. You will see the practical steps for eliciting knowledge with the Bayesia Expert Knowledge Elicitation Environment and see the resulting knowledge base in the form of a Bayesian network. This workflow aggregates the emerging medical knowledge and produces an evolving expert system that can be used by clinicians through a public web portal.
Call for Expertise
At present, we are collaborating with a group of physicians and medical researchers to develop an initial knowledge base. The Bayesian network model that underpins our COVID-19 WebSimulator represents the current state of knowledge of our group of domain experts. Given the complexities of the disease, we are looking for experts from around the world to help us validate and refine the current model. Please register here to join our COVID-19 knowledge engineering group.
Overcoming Human Challenges in Reasoning
We also briefly present the principles of probabilistic inference and the fundamental challenges that humans — including experts — have with reasoning from symptoms back to their potential causes. In this context, we introduce Bayesian networks as a reasoning framework that can help overcome these cognitive limitations and provide normative inference given the available knowledge.
Stefan Conrady and Lionel Jouffe are the co-hosts of this online event.
Please note that the COVID-19 WebSimulator is experimental and not meant to provide medical advice to patients. Always consult your healthcare professional regarding any symptoms or health conditions you may have!
A week ago, Imperial College academic Neil Ferguson alarmed the world by predicting as many as 550,000 UK COVID deaths. London Times now reports that he has recanted. He now projects "substantially lower" than 7,000 excess UK deaths, that is deaths of people who would not have died any way. Here's the Times story:
The virus death toll could end up being “substantially lower” than 20,000, with most of the fatalities in people who would have died later this year anyway, a government adviser has said.
Neil Ferguson, the Imperial College London scientist whose research precipitated tougher government measures last week, told MPs: “It [the deaths of those who would have died anyway] might be as much as half or two thirds of the deaths we see, because these are people at the end of their lives or who have underlying conditions.”
Ferguson has been used to justify the whole "social-distancing" strategy that is now destroying the US economy. Meanwhile, a new Oxford study challenges Ferguson's original projection and suggests that 50% of the UK may already have CV19.
Good food for Bayesian modeling!