NeuroVoices: Michael Dwyer, PhD, on Appropriately Incorporating Artificial Intelligence, ChatGPT into Multiple Sclerosis Care

Michael Dwyer, PhD

The emergence of artificial intelligence (AI) in healthcare has been groundbreaking, reshaping the way clinicians diagnose, treat, and monitor patients. There are a few different types of AI, including machine learning, which gives an ability to learn from experience without being explicitly programmed, and deep learning, which learns from raw/nearly raw data without the need for feature engineering. Through AI in healthcare, medical professionals can make more decisions based on accurate information, ultimately saving time, reducing costs, and improving medical records management overall.

At the 2023 Americas Committee for Treatment and Research in Multiple Sclerosis (ACTRIMS) Forum, held February 23-25, in San Diego, California, attendee Michael Dwyer, PhD, presented a talk on the use of AI and MRI for multiple sclerosis (MS) care. In his presentation, he focused on how these approaches help improve the care and accessibility for patients, through image segmentation, anomaly detection, and facilitating the transition of novel MRI biomarkers, among others. Additionally, he spoke about ChatGPT, a recently launched AI chatbot trained to follow an instruction and provide a detailed a detailed response.

Following his presentation, Dwyer sat down with NeurologyLive® to discuss some of the recent successes with AI, and how the field is quickly adapting to it. As part of a new iteration of NeuroVoices, Dwyer, director of IT and Neuroinformatics Development at the Buffalo Neuroimaging Analysis Center, provided insight on how these approaches can be beneficial in the diagnosis, treatment, and management of MS going forward.

NeurologyLive^®: What are some of the recent successes with AI?

Michael Dwyer, PhD. AI is obviously a very hot topic right now. We're all hearing about ChatGPT, and how these things are taking the world by storm. It's amazing, there's a lot of hype, but we have to be careful, especially trying to pull these things into the clinical side. It's one thing to have a student use ChatGPT to help with their term paper, it's another thing to try to leverage AI to say, “what should we do to treat somebody for a medical disease?” Obviously, the stakes are higher for making mistakes. So yes, we need to be very careful.

It is an incredible time to be seeing what's happening in AI because this whole deep learning revolution has really changed the way everything works. The groundwork has been there for decades—the math, the theory of how to do things—but the ability to have these deep learning tools, and the data sets with it, just shows the explosion in the last 10 years. In my presentation, I mentioned briefly that the FDA has a tracked list now of AI-approved devices. You see this huge inflection point at 2015, where suddenly, it just shoots up. And 95% of those [approvals] are in radiology, which, for a disease like multiple sclerosis, radiology and imaging is one of the core components. There's been so much forward motion there. I think we have to be careful. It’s we're nowhere near what a lot of people think of in terms of AI, this kind of Terminator artificial general intelligence, where the machines are going to take over. But we now have a set of tools that can help clinicians and researchers transform what they can do.

How can AI be more heavily applied to multiple sclerosis going forward?

That's what's very interesting. We've talked before a little bit about AI, specifically about some image segmentation tools and looking at those biomarkers, but what's been really interesting is the breadth of areas that AI has been able to help with. It's not just the classic looking at a picture and making measurements. That's just the tip of the iceberg. What we've also seen is AI under the hood. It’s not necessarily the big, exciting stuff, but it's making really important changes. For example, the reconstruction on MRI is being done now in many cases with AI, and these AI tools have been incorporated by the manufacturer. It's already being translated, it's not just this theoretical research. There are caveats, obviously, we need to be careful about interpreting these images, but they can speed up the images by 6-fold sometimes, and that's huge because MRI is still the most expensive component of diagnostic workups and following these patients over time.

If we could do MRI more frequently, it would help us monitor better, treatment monitoring, and help us understand what's happening with patients. In terms of availability of care, MRI is expensive, it's not as easily available in all communities. This is a kind of leveler that helps make it possible to access MRI. That's one very important area. Another is translating the academic kind of research we do. MRI is a very complicated modality, and we have different types. We have the standard type we do clinically, but then there's also there's also a whole set of MRIs sequences that are purely research. We had some colleagues in Amsterdam, for example, just developed a technique to synthesize double inversion recovery images from traditional images. In MS, there's a whole set of pathology we don't see called cortical lesions. We can see those now with some of these AI techniques.

Again, there's caveats, we have to be careful, and we need to go step-by-step, but those steps are happening. In terms of prognosis, it's been also very helpful. It's helped translate biomarkers that couldn't be easily translated before. There are groups that have looked on this central vein sign biomarker, and there's AI tools now that have been developed by our colleagues to look at that. A lot of exciting things happening in the field.

Transcript edited for clarity. Click here for more coverage of ACTRIMS 2023.