Our brain activity can reveal a lot about our physical and mental health. And thanks to Ramses Alcaide and his team at Neurable, we’ll soon be able to glean insights from our brainwaves in our own homes — without ever stepping foot in a laboratory...

This week on How I Built This Lab, Ramses recounts the inspiration behind launching a brain computer interface company, and previews his company’s first product: headphones that detect and interpret your brain activity to help you do your best work. Plus, Ramses’ vision of a future with frictionless communication — where you’ll be able to send a text, look up a restaurant or random factoid, and control your playlist entirely with your mind.




This episode was produced by Rommel Wood and edited by John Isabella and music by Ramtin Arablouei. Our audio engineer was Robert Rodriguez.

You can follow HIBT on Twitter & Instagram, and email us at hibt@id.wondery.com.

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

In NPR's Black Stories, Black Truths, you'll find a collection of NPR episodes centered on the Black Experience.

Search NPR Black Stories, Black Truths, wherever you get podcasts.

Hello and welcome to How I Built This Lab.

So right now it's the beginning of the show and you're probably listening pretty actively.

But the reality is that sometimes our attention drifts.

So what if right before you reach that point, your headphones or your earbuds triggered a small audible tone that basically told you you're starting to lose focus.

Well, that's where today's guest comes in.

Ramses Alkaid is the co-founder and CEO of the non-invasive wearable tech company, Neurable.

It's a set of headphones that adapt to your natural working rhythms to help prevent burnout.

when Ramses was getting his PhD in neuroscience at the University of Michigan.

But his interest in technology goes back much further.

And I came to the United States when I was 5.

And I remember that I was so into computers, my parents bought me 1 that was basically a computer that was a throwaway computer by some large company.

And I remember taking it apart and being just so fascinated by it that I wanted to fix other people's computers.

And so I would post up signs in my neighborhood where I would basically do like computer repair for people for like $20 an hour.

And that was great money back when I was a kid, like, especially when you're like anywhere between 6, 7, like 8 years old, right?

And I remember I'd show up and they'd open the door and they're like, oh, it's so cute.

And my dad's like, no, I don't know anything about computers.

Like he's gonna fix whatever your problem is.

So from an early age, you had this knack for computers and clearly your passion for tech continued.

And from what I understand, when you were a kid, your family experienced a tragedy that really sparked your interest in robotics.

Can you tell me a little bit more about that?

Yeah, I mean, really the idea of Nurable and kind of the concept of what I've dedicated my life to started when I was about 8 years old.

My uncle got into a trucking accident in Mexico and he lost both his legs and it was really intense time for the family.

We brought him from Mexico to the United States to get his prosthetics made.

You know, he's been an inventor all his life.

And seeing him through that struggle and seeing how unnatural the prosthetic systems he started using were, That's what really motivated me into how do I leverage this curiosity that I have with electronics and computers to try to make something more natural for him.

Leon Tucker Like in your head, you were thinking, 1 day I'm going to make something that's going to let him control his prosthetics.

I read that you got an undergraduate degree in electrical and electronics engineering.

And it seems like you could have taken a path towards robotics, right?

Especially inspired by what happened to your uncle.

Was that a path that you were potentially pursuing?

So when I was studying electrical engineering, I worked with the prosthetics teams at the University of Washington.

And then I was like, I really wanted to create the brain into these prosthetic limbs.

So I went to grad school and I started working with brain-computer interfaces more, and that's when I worked with people with ALS and children's cerebral palsy and I was like, wow, this is just a whole other level.

I mean, as terrible as it is, for example, my uncle having to go through this experience and having prosthetics that don't work with him naturally, what if you can't even move your eyes, right?

Like that's just a whole different level of need.

And so that's really what pivoted me from something that I thought I was going to dedicate my life to robotics to something much broader.

All right, let's talk about brain-computer interfaces because I think a lot of people, when they hear that term, they think of like electro EEGs, right?

Nodes that are attached to people's heads, you know, that track brain waves.

But what were you trying to solve with this research and this concept?

So essentially the work that I did as my graduate student work is I was working with children who had severe cerebral palsy.

And the issue there is that we were not able to essentially give them these tests that they needed to be allowed to get physical rehabilitation.

And the reason for that is because they couldn't communicate, at least not in the traditional means like talking or pointing.

And so we use brain-computer interfaces to solve that problem.

And the blocker there was that, you know, you have this eight-year-old kid, he just got 20 minutes worth of setup with goop and gel in his hair to make the technology work, it would be about 10 minutes worth of like calibrating the system and then it would take sometimes between 1 to 5 minutes to like even get a response from them.

And so the work that I did was essentially machine learning classification so that we could interpret their brain activity at a much higher level of accuracy.

And what that enabled us to do is reduce the response time from 1 to 5 minutes to anywhere between 30 seconds to a minute, which is enormous for an eight-year-old kid because having them sit there for 5 minutes to say yes or no question is crazy.

Help me understand what the technology is that you're talking about.

You said it would take, you know, 5 to 10 minutes for setup.

And what was it that you were doing differently?

So the reason the setup takes so long is because getting brain data is incredibly difficult.

There's a lot of noise in the environment, even your blinking, you know, talking, the electromagnetic noise, even the lights impact the ability to collect this data because the sensors are so sensitive and brain signals are so small.

And so we essentially developed an artificial intelligence that was able to use brain data that we previously collected and then also brain data that was coming in and essentially increase the signal to noise in order to essentially be able to do classifications of what a person intended to do.

In this case, the child was selecting a multiple choice question at a greater fidelity.

And when you can do that at greater fidelity, you don't need to repeat the question numerous times.

And through less repetition, it gave people a better user experience.

And so being able to make that brain-computer interface work in a seamless way really unblocks a lot of its use cases.

All right, so how much data can brainwaves tell us?

Like in theory, could you look at a person's EEG reading and know, you know, for example, how they'd answer a simple yes or no question or even that, like, that they're thinking about, like, pushing a button or moving an object?

Yeah, I mean, there's a lot that you can take from brain data.

So for example, just using EEG, you can identify a person's focus.

You can identify, you know, for example, measures of stress, whether, you know, for example, they're going through a stroke, epilepsy, sleep responses like REM sleep.

So there's a lot that you can do because your brain is the central hub for everything.

But the main issue is in order to tap into those types of applications, you usually need to have a giant gel cap system with lots of setup to really be able to tap into them.

So imagine you're an eight-year-old kid and we set you up with a system and there's gel running down your face and you don't want to be there, but your future is being dependent on it.

Or imagine we try to bring this to the real world, like no one's going to wear that, right?

No one's going to want to wear a swimmer's cap with gel in their hair.

And so how do we unlock all these incredible value propositions?

And we created an IP at the University of Michigan that helped us increase the signal to noise of those brainwaves so that we could actually bring it to everyday devices instead of having them be trapped in a laboratory setting.

Even if we could just unlock what we already have in lab, it'd be a major step and it would accelerate so many fields.

And so it was, that's what the company was focused on.

Essentially, how do we create an everyday brain-computer interface?

How do we unlock the brain to billions of people?

It makes sense, because the brain just sends out electric signals to the rest of our body.

And so if you could somehow harness or capture those signals, maybe you could make them work in ways that we haven't been able to make them work yet.

And even just the stuff that we were doing in the laboratory, for example, No 1 has a EEG device at home, right?

But what if instead you just put on your Apple air pods to go take a call and Then every single time you do that we're tracking your brain just a little bit more to be able to tell you Hey, actually, you know what you're trending toward Alzheimer's, you know now you're getting older.

We're starting to see this cognitive decline this is when you should go seek out a doctor.

Not 10 years into the disease before it's, you know, it's already too late, right?

And so how do we unlock all these incredible value propositions of brain-computer interfaces to the masses.

And so that's really what the main work that we do at Nurble is.

We're going to take a short break, but when we come back in just a moment, more from Ramsey's about bringing brain interface technology to the masses.

I'm Guy Raz and you're listening to How I Built This Lab.

Hey, it's Guy here and while we take a little break, I wanted to let you know about an episode of How I Built This we released a couple of weeks ago.

It's about how Sal Khan, the creator of Khan Academy, is using AI to make education more accessible.

We've all heard about the rise of generative AI technology and the popularity of things like ChatGPT.

Well, at Khan Academy, Sal Khan is working on ways to build this technology into a new tool to help students learn more effectively by providing a personal learning experience.

Of course, like all technology, this has its risks, but Sal believes that generative AI could reshape the classroom for good and help us close the massive learning gap left by the pandemic by supporting students and teachers alike.

You can find this episode by following How I Built This and scrolling back a little bit to the episode titled When AI is Your Personal tutor with Sal Khan of Khan Academy or by searching Khan Academy, that's K-H-A-N Academy, wherever you listen to podcasts.

My guest today is Ramzes Alkaid, who launched his company, Neurable, back in 2015 to develop brain-computer interface technology.

All right, so you basically, while you were a student, launched what eventually becomes an herbal, starting out just looking at how you could use brainwaves and patterns to help people, and now it's evolved into wearable devices.

But essentially, it's about the technology.

It's about building up a way that you could really measure what's happening inside of our bodies in an accurate way by measuring brain waves.

And the hypothesis there was, if we just build a reliable brain-computer interface system, which is what our core technology enabled us to do, it doesn't mean it's going to scale because it has to bring people value, right?

And so that's why we ended up going toward focus and helping individuals essentially prevent, you know, burnout from occurring.

And then on top of that, with some of our groups, we actually do it for safety.

For example, the Air Force, You know, really big problem, right?

And then that enables us to have a really strong concrete step 1 for us to build a business and enable large amounts of these systems to go out.

And then from there, really open it up to others to help solve some of these other problems as well.

So basically, we're trying to solve this challenge, this problem, which is how do you gather data from brainwaves in an easier way, right?

Like for example, I've got an Apple Watch.

And so I wake up and it can give me some data about my sleep.

It'll tell me my heart rate, blood oxygen.

So, I mean, you know, given what we can already gather from just our heart rate, right, which is quite a bit of data, beyond all the things we talked about, what other things potentially could we learn about our health or our general state from these devices, from these brainwaves?

Yeah, you know, what's really interesting is that brain detecting devices are actually the ultimate wearable.

A lot of the devices that you wear right now, for example accelerometers for movement or for heart rate, they can either be picked up through brain data Or they originally come from the brain and those are just secondary sources of signals, right?

So for example, you can actually pick up Parkinson's responses using the Apple Watch.

The issue is that by the time you pick it up at the hands or through walking metrics, your brain's already been dealing with it for the past 10 years.

And so with the brain, you can actually pick up a lot of those things earlier.

1 is that brain-based wearables are going to replace all the other wearables that you have.

And so all that data and all that value that we're seeing with existing wearables are going to be all consolidated into 1 device.

But then 2, there's certain things that you can only pick up from the brain.

You know, for example, traumatic brain injury information, tracking ALS, right, seizure detection.

There's so many other things that you can only do with the brain that, you know, not only are you taking care of your previous wearables, but now you're adding a whole plethora of medical use cases that have already been tested out in scientific literature, but now are able to be used at scale.

All right, so let's talk about these headphones, the Enton headphones that your team has been working on and is getting ready to release later this year.

What are you able to track using, putting these headphones on people now?

Yeah, so there's kind of like 3 areas where we use the technology in right now.

On the first end is, for example, understanding an individual's focus over time, when they're fatiguing, when they should be taking a break in order to maintain it.

Your brain is kind of like your body is to dehydration.

You should be, in the case of the body, drinking water throughout the day.

Well, you should be taking breaks throughout the day too.

Even though you may not feel thirsty or you feel tired, you should be doing that in order to maintain a high level of hygiene for your own work and life balance.

So we have the ability to, for example, use brain activity to do very minimal controls on the hardware as well too.

So changing music tracks, play and pausing music.

And then on the third end is there's so many incredible biomarkers that can be picked up using this type of technology.

Like I said, tracking Alzheimer's or cognitive decline or, you know, other types of biometrics.

So essentially just like how the Apple Watch started out as a system for tracking your movement, now it can actually pick up like heart arrhythmias.

And so all of that medical landscape and biomarkers are also available through these brain-computer interfaces.

But how do headphones, how do sensors around your ear capture as accurate information as those other sensors?

Yeah, I guess to answer that, we have to break it down into 2 steps.

First is like, how do we capture those signals from headphones?

Well, the brain is very conductive, right?

So for example, 1 of the brain signals we look at is called P300.

We don't really have to get into the details of it, but essentially that comes from an area of your brain called the parietal lobe.

And even though that signal comes from around the back of your head, the signal is such a strong response, it can actually go, it goes all over your brain.

Only the farther it goes from the signal source, the smaller that signal becomes, so it becomes harder to read.

So we know that these signals go across the head, but you lose the ability to record them easily.

It picks up these signals, even though they don't come from the most perfect location, they come from the areas that headphones are at.

And from there, we're able to boost those signals to a level that makes them usable for different applications.

So presumably, when people have access to initially the headphones, they'll be like an interface where they can sort of either on their watch or just on a webpage or their smartphone, where they can see this data.

And initially it will be, what kind of data will they have access to?

Yeah, you know, it really depends on the audience.

So for most individuals buying our tech, they're just going to be able to see their focus scores whenever they do work and suggestions on how to improve their focus over time, reduce fatigue, create more balance in their life.

But there is a whole bunch of raw data and filtered data that is more granular, that's gonna be available to scientists or people who wanna dig in deeper.

And from that, that's where you can pick up a lot more detail as to like, you know, sleep measures or, you know, epilepsy, et cetera.

And so the idea is you would wear the headphones all day, and you would just go about your day?

You would wear the headphones whenever you're working.

So like right now I'm wearing headphones, so I just do a couple hours of work, wear the headphones, and then they would notify me when I should be taking a break in a way that's optimal for my mental health.

It would just be an audible notification, you know, we recommend you to take a break.

Sometimes you're in the middle of something, you need a few more minutes, that's fine.

And then you would take a break and it can tell you how long you should be taking a break.

And then when you come back, it's actually really surprising, especially in our user testing.

Like people don't realize how much they needed it and they come back and then they just crush their work.

And they're like, wow, like I didn't think I needed this break, but I came back so energized and like focused.

And it's having people have that feeling consistently and their day feeling really motivated about the work that they did so that they don't feel guilty about taking some time off when they get home.

That's essentially the feeling we're able to give people with the technology.

Essentially is recommending when you need to take a break, right, when you're working.

What kind of data is it getting to suggest that you need to stop working?

Will Cullen-Hodgson Yeah, so we did a large study with a professor from Harvard who's now a professor at Worcester Technical Institute, and he had created this incredible method for identifying an individual's focus.

And so what we were able to do, and we did close to a thousand individuals' worth of data collection on this, is we tracked people just doing their work and then leveraging this algorithm that we co-worked with this individual at Harvard.

And what we saw is that there was very clear breaks in the data where we could see that if we were to recommend them a break at this time point, it enabled them to have 3 to 4 hours of higher productivity afterwards, feel more refreshed, reduce their errors in the amount of work that they do, instead of just burning themselves out and feeling really like, you know, bad about their day, essentially.

Okay, so it can basically sense certain brainwaves that would suggest, according to this research, that it's time to take a break.

What else can it do while you're working and you've got the headphones on?

1 of the best parts about the technology is you can actually build things on top of it.

So a few of the things that people are building, For example, the first 1 is with Audible, right?

You can listen to an audio book, and then when you get distracted, it'll actually automatically pause it, which is really great because this happens to me a lot when I read or when I'm doing audio books, I have ADHD.

I'll start reading it or listening, and then I'll just start zoning off into something else and then I'll realize that I get to the end of the page of the book or the end of that paragraph in the audiobook and I realize I haven't paid attention at all and I gotta rewind it.

So there's ways to, for example, automatically pause things.

And there's a whole bunch of other things that you can do with the technology too, but essentially it's that reliable.

On that note, because this happens to me too, right?

When I'm reading a book and I just sort of zone out or even listening to something, how does it know that you're zoning out?

Yeah, it's the same algorithm for focus and fatigue.

Essentially, we notice that there's a sharp decrease in an individual's focus.

And once we identify that, if it remains consistent, then we know that the person's not focused on the task that they were on previously.

And so then we're able to just pause it or in the case of reading, for example, I have it output a small audible tone and it just reminds me, hey, that's right, I should be reading right now.

You know, I just got distracted by a random cat that walked by, and now I should get back to reading.

We're going to take another quick break, but when we come back, more from Ramsey's on just how close we might be to mind-controlled technology.

I'm Guy Raz, and you're listening to How I Built This Lab.

I'm Guy Raz, and my guest today is Ramzes Alkaid, co-founder and CEO of Nourable.

There are a bunch of companies working in this space, just like with AI and other categories, many of those companies are massively well-funded, you know, hundreds of millions of dollars in funding.

You know, you've raised $20 million, which is impressive, but tiny compared to some of these other companies, I'm sure, as you know.

How do you prevent those companies from just, you know, with their cash supercharging this technology and leaving smaller companies behind?

Yeah, I think a lot of those companies aren't really our competitors.

That's why, you know, like Neuralink is not a competitor.

Most of those companies that do invasive need a ton more money.

The way I would think of Neuralink is kind of like a hip replacement.

You know, no 1 really wants a hip replacement until, you know, you actually need 1.

And even if they end up being 10 times better than your actual hips in the future, you probably wanna be able to keep your hips for as long as possible regardless.

When it comes to the competitors more in our space, which is non-invasive, we're probably 1 of, if not the best funded company in the world.

And so that's enabled us to continue staying ahead.

And at first it was because of our technology, we're at least 5 to 10 years ahead of anybody else in the market.

But Now it's because of our business partnerships that we have that we continue to grow.

So let's talk about the products that you're developing.

Right now it's going to be a commercial product, right?

Yeah, headphones and then very soon after in earbuds.

And let's talk about the headphones remote.

They're gonna be available essentially Q4 this year or Q1 next year.

And then from there, we'll continue improving things and working with the customers that we have to help us further evolving the product and helping scientists unlock more capabilities.

It's really going to be a community effort to build these types of devices.

See all How I Built This with Guy Raz transcripts on Applepodcasts

When your headphones listen to you with Ramses Alcaide of Neurable