Aging Behind the Wheel: How Driving Behavior Can Identify Preclinical Alzheimer’s Disease

I’m Dr. Nathaniel Chin, and you’re  listening to Dementia Matters, a podcast about Alzheimer's disease. Dementia Matters is a production of the  Wisconsin Alzheimer's Disease Research Center. Our goal is to educate listeners  on the latest news in Alzheimer's disease research and caregiver  strategies. Thanks for joining us.

Welcome back to Dementia  Matters. I'm here with Dr. Sayeh Bayat, an assistant professor in the  department of geomatics engineering at the University of Calgary where she studies  artificial intelligence, smart cities,

health monitoring, mobility and driving, and  healthy aging. Dr. Bayat was an author of a recent paper where she and her colleagues found  driving behavior - people's actions behind the wheel of a car - could be used to identify people  with the earliest stages of Alzheimer's disease. Dr. Bayat. Thank you for joining us on dimension  matters to discuss this very exciting work. Now to begin with what led you to steer your career  to this intersection of engineering and aging.

Great. Thank you so much for having me.

Now to begin with, what led  you to steer your career to this intersection of engineering and aging? So my story starts back in my undergrad days  where I was going through engineering school. So I was training to become an aerospace engineer.  All my internships, research focus, and summer jobs were in that field. But unfortunately when  it came for me to graduate, the aerospace job

market in Canada was taking a major hit so there  weren't really many job opportunities. And at that point I had to decide what I wanted to do  and I decided to go back and do graduate work. And one thing that I learned through my  internships and through my experiences was that I wanted to apply my engineering skills in a  different area that allowed me to interact with people more and work on real life problems  that I can come up with solutions for. So this

time I decided to go back to do my graduate  work in the biomedical engineering area. It was really through my graduate studies that I got  to learn more about the implications of this aging population that we're seeing for the societies.  And I got to explore the ways in which engineering can play a role and we can develop tools and  solutions so that care systems can be delivered in new ways and we can have people be independent  and live in their communities for a longer time.

Well and thank you for sharing that story.  You know, I will say in having interviewed and interacted with engineers, you certainly see  the world in a different way - and I mean that in a good way. And so having that perspective,  and that training, that skill as you said, is so critical in a field like aging and Alzheimer's  disease where we need as much help as we can get in pushing our goals. So while I'm sorry to  hear that your aerospace engineering career ended

prematurely, I'm certainly glad you're here in the  aging space, which leads me to your paper. And so this recent paper was published in the summer of  2021 - it's just fascinating so before we get to the results. Can you tell us what inspired  you to study the topic of driving and aging?

Yeah, so I have been interested in understanding  the ways people interact with their environment through sensors, mobile technologies, for a  long time now. And this is because I really believe that these interactions can tell us a lot  about people's health and people's well-being. So my PhD thesis broadly was investigating  whether mobility patterns from GPS data

can be used to explain, influence, and predict  image. But - so I was really interested in this general area, but this specific paper and project  was the result of years of research that has been conducted by the Drives research team  at Washington university in St Louis and they've been looking to understand the links  between driving behaviors in naturalistic settings

and early signs of Alzheimer's disease for a  number of years now. And I was fortunate enough to be able to connect with Dr. Rowe and  Dr. Babelau at a conference back in 2019 and that was really the start of this engaging and  interdisciplinary project that led to this paper.

And when I say interdisciplinary, our team members  actually had expertise from Alzheimer's disease to transportation and mobility,  naturalistic driving, blood-based biomarkers, so it was this complimentary  set of skill sets that led to this work. It sounds like a wonderful team and I'm going  to ask you about naturalistic driving in a few questions down the road here. But one of the  things that just is so profound is this idea

of predicting dementia without actually doing  any cognitive testing. And so that I think for our audience, just so they're aware - I mean this  is a really new field and emerging field and it's so critical and driving is such an interesting  aspect of it. And so like, at this point I'd really like to hear from you who was in your study  and how long were these individuals monitored for?

Yeah, so we looked at about a hundred people and  this was over-65 each group. And what we did was over a course of a year in 2019 - so before the  pandemic - we monitored the driving patterns of this cohort using GPS devices. And these  GPS devices were installed into the onboard diagnostic port of each of our participants'  vehicles. So our system really allowed us to monitor the car's performance and collect  information from the sensors in the cars.

So this is incredible and I just want our audience  to appreciate that - I mean this study took a long time. I mean, you did this prior to the COVID-19  pandemic and then the paper came out in 2021. But really, you followed people for over  a year and they allowed you to to study their driving behaviors which I’m not sure  how many people would really want that,

so these very loyal participants. The other thing  is, did you study people who came from the WashU research center, similar to the one here in  Madison, Wisconsin, or the general public? Our pool of participants came  from the WashU research center as well as separately through our  advertisements in the community. So it's a wonderful combination and so  now at this point can you share with us,

what did you find in this study? Yeah, definitely. So what we found was, using  machine learning, we can identify very subtle patterns in driving that may be associated with  preclinical Alzheimer's disease. And our model actually achieved very high accuracy  and sensitivity and performance. But I also want to take a step back and explain  what preclinical Alzheimer's disease is.

It's a stage that happens up to 20 years before  clinical diagnosis of Alzheimer's disease and it's when we have early brain brain changes with  very subtle cognitive changes in the population. And while you're explaining some of the terms,  can you also explain machine learning too?

So machine learning is a method of data  analysis that really automates a lot of these steps that we take. It's really a branch of  computer science that learns from the data and can identify patterns in the data and  make decisions in a very autonomous manner. And so before you tell us some of these subtle  changes that you can notice, can you explain for our audience - you knew who had preclinical  Alzheimer's disease and who did not and then

you were able to study driving patterns that were  different among those two groups. Is that right? Yes, so we had cerebrospinal fluid biomarkers  that allowed us to know who in our cohort had preclinical Alzheimer's disease, but it's also  important to note that our participants weren’t aware of this information and that  didn't influence their driving patterns.

And so then you were able to look at the  driving patterns within each of those groups, preclinical Alzheimer's disease and not, and  determine if there was a significant difference. Exactly. All right, well then with that in mind, what  did you find were the differentiating factors? So we measured driving performance, which can be  how often you accelerate or brake aggressively, whether you exceed or fall below the speed  limit of the roads, or whether you make abrupt

changes or moves during your driving. But we also  looked at metrics that explain driving space and these were, for example, the number of trips that  you make, the average distance that you travel, or the number of unique destinations that you visit  in your excursions. So a combination of these factors and metrics were shown to be important.  One that was really important and I thought was interesting was jerk, which is the rate of change  of acceleration. So it's really measuring how

abruptly you're driving. Other metrics that  were important were the number of trips that were made at night and the typical distance that  you traveled to. So these were other metrics. And so when you say jerking, that's accelerating,  that's not hitting the brake more often? And so that really includes both, so whether it's acceleration - abrupt acceleration or  deceleration in the form of braking. Now in your paper you also show that driving  more slowly and logging less total miles

are factors too. Is that right? Yeah, those were the two other measures  that we computed and we saw that they are correlated really with  preclinical Alzheimer's disease. And I'm glad you said correlated. So it's not  that you're saying one is causing the other, but there seems to be a relationship to a  driving behavior and performance and having these preclinical - meaning, you know, technically no  symptoms or at least cognitive impairment - in

the individuals. So the tricky thing for me is  that, you know, a lot of different health and life factors can impact driving and I imagine  it's really hard to control for those variables such as vision changes, back injuries, new  medications, anything that could happen over the course of the year that you're  studying these individuals. Is that something

that you're looking to, in future studies, to  somehow control for these kinds of factors? Absolutely. So that's a really important point.  What we saw in this paper was that the results suggest that there may be some changes  and differences in driving patterns of these two groups, but really we need to test the  validity of our models in a larger population, more diverse population, and account  for these variables that you mentioned before we can implement these  solutions in real settings.

And you know, when people think about Alzheimer's  disease they’re usually just thinking about memory change - I'm forgetful or I have a short-term  memory issue. But this study would suggest, possibly, that cognitive - other cognitive  functions like a person's ability to pay attention, to multitask, or even just their visual  spatial abilities could actually be impacted even earlier and therefore impact driving. And  I'm not saying you're stating that's the case,

but that's possible. And so the reason I  asked earlier about where the participants came from is that at a research center you  probably have access to at least some of these participants’ cognitive test scores because  that's the benefit of following people over time. I'm wondering if you're going to look at  cognitive scores - and even if it's not an impairment but just cognitive change - and some  of these driving patterns. Is that in the future?

Yes, definitely. We're going to look further  into these but I want to also mention that we looked at the cognitive rating measure  assessment that was conducted with our participants and this is a measure that identifies  the overall severity of dementia. It has

six different areas that it accounts for;  for example, memory and orientation. And all of the participants that were included  in this study had a clinical dementia rating score of zero, meaning they had no  cognitive impairment by this test. And all rights, these were, you know, average  of - regular people from the community. Yeah, exactly. Wonderful. Okay, well then now I wanted to get  at that comment you made about naturalistic.

So how is driving assessment using a  naturalistic environment better or worse than traditional, onsite  Department of Transportation driving assessments? And if you could  start by explaining naturalistic to us too.

Yeah, so naturalistic driving is when we can  really look at and monitor driving patterns of individuals in the settings that they usually  drive, whether it's the road that you take to visit your friend's home, your daughter's  home, the road that you take to drive to work, so we can really look at your driving behaviors

in those settings. I would say the problem with  the traditional road tests that we have is that it's really a measure of driving performance under  a controlled condition and at a specific site and at a specific time, so that can really influence  your driving behaviors. There are often really good measures of driving performance but they're  not measures of daily driving behavior, if that

makes sense and. Because of these differences, I  would say the field of driving research is really shifting toward looking at naturalistic outcomes  and this is now easier because we have access to mobile technologies, variable technologies,  and we can collect these huge data sets. Now I mentioned this interview to a teammate of  mine who asked this really great question that I'm hoping you can answer, which is how do you account  for people that are just bad drivers at baseline?

They don't have any changes in their brain but  they were just not good drivers to begin with. Yeah, so this paper in this particular project  was a cross-sectional study where we compared two groups in this time period. I think what would  be really interesting as a next step would be to look at people's driving patterns  longitudinally to be able to compare each person's driving performance to their prior  driving performance and patterns, and to see

if you can identify changes longitudinally. But  yeah, that's something that I think it would be important to account for later on but that we  did not account for in this particular paper. And so to end, I was hoping you could share  with us what you're currently working on.

What is the direction of this research  or your research lab in particular? So I'm hoping to continue this  line of research and we want to expand this work in different sites  with larger populations so we can really test whether these models are - can be validated  in different settings and with different drivers. And as you might imagine, driving is something  that really depends on the weather. It can depend on the location that you're driving,  whether you live in a rural area or urban

setting, that can influence your driving pattern.  So there are many different variables that we have to look into and account for in our future studies  that I'm hoping to be able to look into it. Well I hope so too. And with that, thank you  Dr. Bayat for being on Dementia Matters. We do hope to have you on in the future  when you have more of your data.

Thank you so much for having  me. It was great to talk to you Thanks for listening to Dementia Matters.  Be sure to follow us on Apple Podcasts, Spotify, Google Podcasts, or wherever you get your  podcasts to be notified about upcoming episodes. You can also listen to our show  by asking your smart speaker to play the Dementia Matters podcast. And  please rate us on your favorite podcast app -- it helps other people find our  show and lets us know how we are doing.

Dementia Matters is brought to you by the  Wisconsin Alzheimer's Disease Research Center. The Wisconsin Alzheimer's Disease Research  Center combines academic, clinical, and research expertise from the University of Wisconsin School  of Medicine and Public Health and the Geriatric Research Education and Clinical Center of the  William S. Middleton Memorial Veterans Hospital

in Madison, Wisconsin. It receives funding from  private university, state, and national sources, including a grant from the National Institutes  of Health for Alzheimer's Disease Centers. This episode of Dementia Matters  was produced by Rebecca Wasieleski and edited by Caoilfhinn Rauwerdink. Our musical  jingle is "Cases to Rest" by Blue Dot Sessions. To learn more about the Wisconsin  Alzheimer's Disease Research Center and Dementia Matters, check out our website at

adrc.wisc.edu. You can also follow our Facebook  page at Wisconsin Alzheimer’s Disease Research Center and our Twitter @wisconsinadrc. If you  have any questions or comments, email us at dementiamatters@medicine.wisc.edu.  Thanks for listening.