latest

Coventry University using AI avatars to train medical students

The software being developed at Coventry is based on PCS Spark, an AI technology for virtual medical simulation

29th April 2024 about a 3 minute read
“With this AI we have been able to create an avatar that actually behaves like a patient and can be created quickly. It would previously have taken around 100 hours to create a virtual patient, but we did a 30-minute activity and the draft was miles better than before." Juliana Samson, PhD student, Coventry University

A researcher at Coventry University is using artificial intelligence (AI) to create virtual patients for health care training.

The patient avatars will behave like real patients and give individualised answers to specific questions, rather than just listing symptoms. The idea is that medical and other health care students will be able to engage in realistic patient scenarios and improve their skills.

The large language model being used by Coventry University is also speeding up the time it takes to create a virtual patient, making it possible eventually for people to create customised patient scenarios.

The software is based on Spark, a technology created by PCS, an AI firm, which is working with Juliana Samson, a PhD student at the university’s Research Centre for Healthcare and Communities. The aim is for the new technology to be capable of learning as it goes along, allowing for the creation of more sophisticated avatars for student practice.

Software has ‘stepped up a level’

Samson said: “Previously you would have to create folders and folders of every single question and answer that you might imagine happens in a conversation and link it all together – it was a really laborious process and wasn’t as fluent or adaptable. Now we’re massively cutting the time that this needs in terms of the build and the responsiveness is off the scale.

“With this AI we have been able to create an avatar that actually behaves like a patient and can be created quickly. It would previously have taken around 100 hours to create a virtual patient, but we did a 30-minute activity and the draft was miles better than before.

“The software has stepped up a level. The AI can generate a lot of human conversations that you would need to have and students will be able to have conversations without traumatising or upsetting a real human, and if you get it wrong you can go again.”

Students who use the software are awarded points for asking pertinent questions on various topics. They can also read back the entire conversation afterwards to look at how they could improve. Working with the digital avatars also enables students to practise taking patient histories during a clinical conversation – something that would not normally happen until on placement.

Balazs Moldovanyi, the CEO of PCS, said: “We are thrilled to provide Coventry University our most intelligent Spark virtual patient AI, now driven by an in-house trained generative large language model for never-before-seen realism in communication training. We are excited to see how far the university’s domain experts can take this AI with their custom scenarios.”

There will now be a co-creation event, involving of occupational therapy and physiotherapy students, academics and clinicians, who will use the software to suggest ways in which it can be improved and made more realistic.

In March 2023, England became the first country in the world to launch clinical training in perinatal health using extended reality technology when Health Education England and Fracture Reality collaborate to develop a patient avatar.

FCC Insight

The technology being developed at Coventry University is potentially a major step forward in the use of virtual reality to train healthcare professionals. The Spark software created by PCS uses patient avatars to enable medical and nursing students to simulate the kind of engagement they might have with a real patient. Coventry University is adding an extra layer of capability, using AI both to dramatically speed up the process of creating patient avatars and to enable the technology to learn as it goes along, so that trainers can create personalised scenarios for students. The work demonstrates, as we argue in our new report on extended reality, that both virtual reality and AI have tremendous potential to transform the way that students working in the health care professions are trained.

FCC has recently published a paper on the potential of extended reality and artificial intelligence in medical and healthcare education. We have also sat down and interviewed some of the key opinion leaders in this space.

Please click on the following link to read the paper and the interviews.