AI Innovation for Clinical Decision Support with Joe Connor - TWiML Talk #169

In this episode I speak with Joe Connor, Founder of Experto Crede.

Joe’s been listening to the podcast for a while and he and I connected after he reached out to discuss an article I wrote regarding AI in the healthcare space. In this conversation, we explore his experiences bringing AI powered healthcare projects to market in collaboration with the UK National Health Service and its clinicians. We take a look at some of various challenges he’s run into when applying ML and AI in healthcare, as well as some of his successes, such as tackling effective triage of mental health patients using emotion recognition within a chatbot environment. We also discuss data protections, especially GDPR, and the challenges that come along with building systems that are dependent on using patient data under these restrictions. Finally we take a look at potential ways to include clinicians in the building of these applications.

[ValerianTexeira]

When we test the efficacy of the AI diagnosis we always need to bring the humans in the loop. For example when we say AI is 80%, 90% (or whatever percentage) successful, we need to check out what are (will be) the human success in these cases, today and a couple of years latter.