Audioburst Search

Wearables as Early Detection Health Systems

Automatic TRANSCRIPT

And so you know to frame this discussion Obviously with the whole pandemic going on right now Were in the midst of I. Think a whole lot of different trends that are being accelerated in. You know for me personally. I've been writing. Blogging about biometric sensors. And the idea of wearables serving the role of preventative health tools really since the onset of future in so now it's becoming clear as ever that there's this is a really important role particularly during pandemics in health crisis that I think these body weren't computers can play and so I think to kick things off I WanNa to go to you Ryan about just the idea of the different types of metrics that sensors like the ones that Alan cell produces can capture I would love to hear from you know particularly around metrics respiration rate but oxidation You know these different metrics that on the surface. You hear them okay. These you know. A body worn sensor can now capture a respiration rate. What does that actually mean and input it? In the context of why that would be an important metric to know Particularly with you know something that is a respiratory illness like Ovid In how we might be able to be a little bit more proactive with our approach. Here you know in terms of understanding what's actually going on with our bodies and maybe using these tools as part of a early diagnostic system in in just a better way to diagnose and detect anomalies in the data that there might be something going on even before you might be showing symptoms so Ryan. Why don't you start with maybe just a a an overview of some of these different metrics? How we've even gotten to the point to be able to capture these and then what we can glean from those types of metrics. It's a really interesting topic because the One of the silver linings if you will in this In this pandemic or and now is really highlighting the capability the current capabilities of existing Wearable sensor technology that in many cases has been around for years if not long if not decades or longer in the case of something like the pg sensor technology that we make that has been around and finger clips and your lobe clips that measure vital hind in hospitals and healthcare facilities for for decades Those things so the ability to measure things like heart rate and heart rate variability and bought oxygenation in wearable devices has been around for decades. What what this current environment is is really putting focus and and really highlighting is the capabilities of those devices and And also the the ability and the importance of Wanda to data Capture across those different metrics. So it's one thing to to look at someone's heart rate or let's say their body temperature or their respiration rate at a given point in time but what Where these are really adding additional value? And that's really getting highlighted in. This environment is understanding at an individual level. What that data looks like over time. And in a longitudinal sense where you can get an individual baseline on a person and understand how they're different Let's say they're different resting heart rate or heart rate variability changes in an individual Those may be different between Me and you an Andy and Chris All all of us are going to have different baselines at an individual level but the ability to see. Not just what what's going on when someone goes to visit a doctor or in this case where we are discouraged from going into into hospitals and healthcare facilities what that looks like a longitudinal basis for an individual and that gives In many cases much better insights into how individual is responding to whatever. They're whatever they're currently doing or whatever their current environment Maybe doing to them so That gives unique insights and the capability has been there for many years. What this current environment is really putting a highlight on is what are the what those capabilities and mean on longitudinal basis and also in a in a remote monitoring scenario where an individual doesn't have to come into A hospital or a health care facility to see to see a healthcare provider. That can all be done remotely today and we're really seeing The acceleration of telemedicine telehealth and the And the use of wearable sensor data in those contexts to be able to get that data and and I see how an individual's baseline is changing over time. Yeah no I think that makes a Lotta sense and Chris I want to go to you. Now you know. Kinda going off of what Ryan just described with how we can capture all this information before recording. You had mentioned a study that you had just conducted with Va. That I would love for you to expand upon a little bit here and share with the audience About what we can then actually gleaned from this information and in how you worked with. Va To make some pretty meaningful insights based on this type of information that were now being able to gather from these different sensors so you're just to build them what Ryan sharing these. The sensors themselves have indeed been around for for decades the EKG writer DC. G HAS BEEN AROUND FOR I think. Essentially now And while traditionally these types of sensors have been used in impatient environment. Where you have somebody who's lying in a hospital bed where you know it does it does make sense to use something like resting heart rate When you introduce these types of technologies in the real world where people are moving around Going to the mailbox or walking upstairs. They're they're they're sleeping they're awake. How do you capture these? These data sets in that environment in a way that you can actually make sense of what's going on. So the big leap is in the artificial intelligence that the neural nets and machine learning that we can now apply to these data streams to do what Ryan ascribed Annette is build a personalized baseline for an individual from which then you can detect very subtle anomalies in so If his IQ our first FDA clearance was in an algorithm that did exactly that and that was invalidated in this. This va sponsor. Study that you just referenced. In so with that Algorithm. What we're doing is a platform is ingested continuous vital signs specifically cartwright respiration rate in activity. And doing that from a wearable biosensor and it builds a personalized model of their cardiopulmonary physiology as relationship between these different vital signs to detect subtle changes that are are indicative of compensatory behavior within their physiology that can be predictive of

Coming up next