Educational content on VJDementia is intended for healthcare professionals only. By visiting this website and accessing this information you confirm that you are a healthcare professional.

Share this video  

AD/PD 2026 | Digital biomarkers and AI in clinical care for AD and PD: integration into workflows and barriers

Rhoda Au, PhD, Boston University, Boston, MA, outlines key challenges to integrating digital biomarkers and artificial intelligence (AI) into clinical care for Alzheimer’s disease and Parkinson’s disease. She highlights the need for validation, workflow integration, data privacy safeguards, and clinician trust to enable effective and scalable adoption. This interview took place at the AD/PD™ 2026 International Conference on Alzheimer’s and Parkinson’s Diseases in Copenhagen, Denmark.

These works are owned by Magdalen Medical Publishing (MMP) and are protected by copyright laws and treaties around the world. All rights are reserved.

Transcript

So right now we have the problem that we don’t really have digital biomarkers, at least not much in the AD space or the PD space. There are digital biomarkers that are out there. They’re probably used in other diseases, you know, I think in heart disease, for instance, glucose monitoring. You can measure these things digitally now, and they have been validated. But I think in the space of AD/PD, we’re not quite there...

So right now we have the problem that we don’t really have digital biomarkers, at least not much in the AD space or the PD space. There are digital biomarkers that are out there. They’re probably used in other diseases, you know, I think in heart disease, for instance, glucose monitoring. You can measure these things digitally now, and they have been validated. But I think in the space of AD/PD, we’re not quite there. So I think that the, so really the initial barrier to bringing digital biomarkers into clinical care starts with the fact that we need to validate them as digital biomarkers. But I think the other key, really critical component is once you go through that digital biomarker process or as you’re going through that process, I think it’s very important to think about the workflow. How are you going to bring it into the clinical care workflow without disrupting it? Particularly like primary care, but really even specialty care. They’re already very overburdened, right? They have very little time. So how are you going to make this a tool that helps them treat their patients not only better and more comprehensively, but also in a way that doesn’t overburden them? So I think the other piece of it is that we’re going to have to translate it in a way that’s digestible, easily digestible, by the care team themselves. And that’s not trivial. It’s thinking about how do you pass that information through the system and then have it delivered to whoever is in charge of the care in a way so that they can very easily understand and translate that into what’s the next step that’s good for my patient based on that without using a lot of their time and energy. And I think that that’s not just the case with digital biomarkers. It’s probably anything that you’re trying to get into the care system. But the additional barrier is you’re going to have to bring in something that’s new and different that they’re not familiar with. They probably weren’t trained on it. So that would be the other challenge that you’re going to have to face. So definitely the biggest fear about using digital technologies and AI is probably the intrusiveness. So I think people are very concerned about loss of privacy, the issue of confidentiality. How will they misuse my information, my data? And I think now in the world of AI, we hear a lot about sort of, we do hear about misuse of AI and then also this concept of a hallucination where AI can take information and then it converts it into something that’s actually not even real or true. So I think that those are some of the biggest barriers right now. I think a lot of people are certainly very worried about AI in terms of trusting AI. I think from a care, bringing it into sort of the research, clinical care, I think there’s the problem of reproducibility. What AI produces today, will that still be true tomorrow or even the next minute? So those are kind of some issues right now that I think are, I think that that’s why there’s hesitancy about AI, and I think it’s appropriate, actually. But I’m an optimist, so I think that understanding that these are very legitimate and important concerns to address, I feel that in the right hands that they will find ways to resolve it. So what’s interesting about trying to predict what AI is going to do is you’re really, you’re trying to predict within the world you already know. And I think what we have to understand is AI is going to transform that, right? So I think it’s about really making us reorient and rethink, is what we’re doing now really the right way we should be doing it? And how is AI going to help us pivot? Not in order to do a better version of what we’re doing right now, but to actually do what we really want to do, right? And so in the case, for instance, I think that AI will help put us on a path to finding that effective treatment or cure for either Alzheimer’s disease and PD. We get on that path, then we’ve really transformed the field.

This transcript is AI-generated. While we strive for accuracy, please verify this copy with the video.

Read more...