remakes the EEG for our modern world (and soon, off-world)

Figuring out what’s going on in the brain is generally considered to be somewhere between extremely difficult and impossible. One major challenge is that the best ways to do so are room-sized machines relegated to hospitals — but is hoping that its portable, powerful, and most importantly user-friendly EEG helmet (plus $8.5M in funding) could power new applications and treatments at home and — as a sort of cork pop for its debut — in space.

Electroencephalography, or EEG, is an established method for monitoring certain signals the brain produces, and which can indicate which areas of the cortex are active, whether the user is concentrating, agitated, and so on. It’s not nearly as precise as an MRI, but on the other hand all you need for an EEG is a set of electrical contacts on the scalp, while an MRI machine is huge, loud, and incredibly expensive.

There’s been precious little advancement in EEG tech, though, and it’s often done more or less the same way it was done decades ago. Recently that’s begun to change with devices like Cognixion’s, which uses re-engineered EEG to interpret specific signals with a view to allowing people with motor impairments to communicate.

The Israel-based (styled in lowercase, with a period in it, specifically to vex reporters) has its own take on EEG that it claims not only provides superior readings to traditional ones, but is wireless and can be set up without expert help.

“It was designed to be the most effective, cheapest, easiest to use EEG acquisition headset in the world. One headset, for multiple people, that automatically configures itself perfectly to each one’s head,” said CEO and co-founder Yair Levy. In development for four years, the headset has 460 sensors and is “fully automated” in that it can be set up and run very simply.

A person wearing the headset working at a computer.

Not exactly stylish, but other EEG setups are even worse. The armband is an ISS-related power regulator. Image Credits:

As it is only just emerging from stealth, the company has no peer-reviewed documentation on the headset’s efficacy and resolution. “But we recently kicked off research activities with several academic institutes, including the Department of Cognitive and Brain Science of Ben Gurion University, as well as a medical center in Israel,” Levy said.

The fact is it would be hard not to improve on the EEG setups being used in many labs — if it did more or less what they did in a portable, user-friendly form, that would be enough to celebrate.

The science of EEG is well understood, but the company has improved on existing designs by including more densely packed electrodes, and ones that fortunately do not require any kind of conductive gel or oil on the skin — anyone who’s had their head oiled up to take part in an experiment can testify that this is not fun.

Because of the nature of EEG signals, these sensors will overlap somewhat, but Levy explained that their internal studies have found that these signal overlaps follow a power law, meaning they can be computationally disambiguated. That means a clean data output that can be interpreted by and used as training material for machine learning systems.

Although the headset is obviously a big piece of the puzzle, the company won’t only be making and distributing it: “Our vision is to provide a comprehensive software end-to-end stack that makes working and integrating brain activity as easy as integrating GPS or fitness data,” said Levy.

Image Credits:

Of course, wearing a helmet that makes you look like Marvin the Martian isn’t something you’ll do on your morning run, or even while riding your stationary bike or standing at your desk. It’s still very much a situational medical device. But like other advances in technology that have brought medical monitoring devices to the home, this can still be transformational.

“We see this as asking what putting a cheap GPS in an iPhone would be good for,” Levy explained. “The obvious answer was mapping, but the reality was that developers did far more innovative things with it than just road directions. That’s how we see our job, to allow innovation to occur around brain activity, not build out the use-cases ourselves.”

Of course if they didn’t have any use cases in mind, they would never have been able to fund four years of R&D. But they’re looking into things like tracking learning disabilities, markers for cognitive declines from diseases like Alzheimers, and also athletic performance. The cost of the headset will vary depending on the application and requirements, the company told me, though they would not provide further details. For reference, bargain-bin setups go for under a grand, while medical-research-grade ones run into the $10K range, and would likely fall in between.

The first public demonstration of the tech is about as flashy as you could imagine: an experiment set on the International Space Station. is taking part in Axiom-1, the first fully privately funded mission to the ISS, which will have a host of interesting experiments and projects on board.

Participants in the study will use the headset on the surface while performing a number of tasks, then repeat those tasks with variations while aboard the ISS. The company described the reasoning for the experiment as follows: has set itself the goal to become the standard for monitoring neuro-wellness in space.

While there is data collection being carried out for various physiological measurements, such as heart rate, galvanic skin resistance, and muscle mass, there is currently no high-quality longitudinal data regarding the neural changes in prolonged space missions. Such information can be vital in assessing day-to-day plastic changes in the brain and predicting how the brain will adapt to long-term space travel.

Naturally they’re not the first to think of this — NASA and other space agencies have done similar experiments for years, but as points out, those were with pretty old-school gear. This is not only potentially a test of cognitive function in space, but a proof of the idea that cognitive function in space can be tested with relatively little trouble. No one wants to grease up their scalp for a weekly cognitive load test on a 3-month trip to Mars.

In addition to the headset and experiment, announced it has raised an $8.5 million seed round led by Mangrove Capital Partners (no other participants named). It isn’t cheap doing medical device R&D, but there’s almost certainly a market for this in and beyond telehealth and performance monitoring. We should hear more about the headset’s specific advantages as it enters more public testing.

Cognixion raises $12M to build its brain-monitoring headset for people with disabilities

Cognixion, a startup designing an intuitive brain-monitoring headset and interface for people with physical disabilities, has raised a $12M A round to pursue its accessibility ambitions. Armed with this funding, it should be able to complete the long list of requirements necessary for any medical or assistive device to be made widely available.

The company, which I covered in detail in May, makes a headset that uses electroencephalography to detect certain patterns of brain activity, which are then used to guide a cursor and navigate a full-featured interface. It uses an iPhone as its own “brain” and for a display, and connects to accessories like speakers and accessibility devices so that the user can do everything they need to in a single UI.

The advance it’s all built on is a new type of (non-invasive) electrode and a machine learning system that quickly interprets the signals produced by the ones embedded in the headset. While EEGs are useful, they are generally slow and noisy, but Cognixion’s approach makes them quick and relatively precise — enough that a person can reliably navigate a modern UI using their brain.

It’s meant for people with physical disabilities serious enough that a joystick, gaze-tracking device or other common accessibility options aren’t possible. Options for people in that condition are few and far between and those that are available are slow and tedious to use.

Since coming out of stealth mode Cognixion has been hard at work on the various tasks associated with putting an assistive device on the market. While the company has done some pilot tests with early adopters, it needs more to justify the kind of clearance it needs to be covered by insurance, Medicaid and so on, not to mention getting to the level where caregivers are comfortable recommending the device.

“The two big themes recently have been in the areas of clinical and regulatory work as well as optimization and efficiency,” said CEO and co-founder Andreas Forsland. “We have a group of almost 150 users, clinicians and caregivers involved as an advisory council in all of our development processes so we’re constantly getting very rich feedback from that group. We’ve already iterated many times on the hardware but are quickly approaching a final design; moving beyond that, a lot of the rapid improvements we’re seeing right now focus on the user interface and language system design.”

Two new features in particular are underway. First, a predictive speech algorithm that will help users piece together full sentences quickly and adapt to their particular needs. Second is direct Alexa integration. Cognixion has been working with Amazon to empower and integrate into the headset as a true smart device hub not merely a tunnel for common voice commands or queries.

The Cognxion One headset.

Image Credits: Cognixion

“We’re incredibly grateful to Amazon’s Alexa team for their support through this process, and to Amazon generally for granting the exceptions needed for us to get this done,” Forsland said. “The context on it is important; right now there aren’t any augmentative communication tools or even anything in assistive technology generally that interface directly with home automation tools. So it’s a huge first for the accessibility industry, but also a first in terms of universal design in general.”

The $12 million round was led by Prime Movers Lab, with participation by Northwell Health, Amazon Alexa Fund and Volta Circle.

“You would think that Cognixion ONE is something out of science fiction if it didn’t already exist,” said Primer Movers Lab GP Amy Kruse in the company’s press release. “We believe that it will be a fundamentally life-changing and integral blend of an AI software platform with hardware to assist people of all ages who live with speech and motor disabilities, including cerebral palsy, brainstem stroke, ALS and many other conditions.”

While it’ll still be a bit before the ONE headset is available for purchase, Forsland said they’ve lined up a reseller and distributor already that works with practically every research university out there. Things are looking good for this innovative approach to accessibility and hopefully soon it will be on the heads of anyone who needs it.

BrainQ raises $40M to transform stroke patient rehabilitation with its home therapy device

If you injure your elbow, surgery can help. If you lose a leg, prostheses are available. But problems within the brain are more difficult to treat, and for stroke victims rehabilitation is largely left to the body’s own repair mechanisms. BrainQ aims to change that with a device that stimulates the damaged part of the brain and promotes self-repair, showing enough improvement in studies to warrant a Breakthrough Device certification from the FDA — and the company has just raised $40M to take it to market.

It should be said at the outset that doubting the efficacy of some brainwave-emitting miracle device is natural. And in fact when I spoke with BrainQ’s founder Yotam Drechsler, he reminded me of the last time we’d talked — back in 2017, at which time I “expressed strong skepticism.”

No hard feelings — the tech was largely notional then, he admitted — but since that time the team has continued its work, raised some money, and what was a promising if not well supported thesis then has turned into one backed by firsthand data and clinical outcomes. The resulting system could be the biggest improvement to stroke therapy in decades or more.

Strokes can result in various obvious impairments, such as grip strength or coordination, but of course the injury is not to the hand or leg itself, it is to the networks in the brain that govern those parts. But medical science has no method for directly rebuilding those networks — the brain must do so on its own, in its own time.

To aid this, regular physical therapy and brain health checkups, sometimes for years on end, are used to in essence make sure the brain is still working on it and that the parts of the body don’t themselves fall into disrepair.

The most interesting improvements to this process in recent years have added tech into the loop to provide immediate feedback, such as that one’s balance is skewed to one side, and providing stimuli that aim to counteract that. But ultimately it’s still targeted physical therapy.

Drechsler and BrainQ see the problem a little differently. It’s not simply an injury but a disturbance to the brain’s carefully cultivated homeostasis, one which it has no means to counteract. He compared a stroke not to an analogous injury but to a baby born prematurely and whose body is not up to the task of heating itself. What do you do in such a case? You don’t attempt to “fix” the body so it can operate at lower temperatures, or supercharge the heat output — you just put the kid in an incubator, and everything proceeds as it should.

BrainQ’s device does something similar, making the brain operate better by changing its local environment.

“We map the channels of healthy brains and non-healthy brains and compare them. Once we find these, we use a low-intensity magnetic field therapy to resonate in the brain and facilitate its endogenous recovery mechanisms,” explained Drechsler.

It’s been shown in other contexts that this type of stimulation can produce improved neuroplasticity — the capability of the central nervous system to reprogram itself. By narrowly targeting stroke-affected areas, BrainQ’s device promotes neuroplasticity in them, leading to expedited recovery.

But it’s not simply a matter of saying “the stroke affected the ventral half of the right occipital lobe, aim the magnets there.” The brain is a complicated system, and strokes affect networks, not just a given cubic centimeter. BrainQ has deployed machine learning and a large collection of data to better understand how to target those networks.

Without diving too deeply into how the brain operates, let it suffice to say that certain networks operate locally at very specific spectral signatures or frequencies as detected by EEG readings. The left hand and left foot may occupy the same region of the motor cortex, but the hand might operate at 22 Hz, while the foot operates at 24 Hz, for example.

“The question is, how do you find these signatures?” asked Drechsler. As it’s somewhat difficult to explain, I asked him to put it in his own words after we spoke:

The novelty of BrainQ’s investigational treatment lies in the data-driven method we have deployed in order to inform the ELF-EMF frequency parameters. In choosing these parameters, our aim is to select frequencies that characterize motor-related neural networks in the CNS, and are related to the disability a person experiences following a stroke or other neurological trauma. To achieve this, we have analyzed a large-scale amount of healthy and non-healthy individuals’ brainwaves (electrophysiology data). Our technology uses explanatory machine learning algorithms to observe the natural spectral characteristics and derive unique therapeutic insights. These are used by BrainQ’s technology to target the recovery of impaired networks.

The device they’ve created to administer the treatment is unusual. Because it’s a whole-brain magnetic field generator, it has a rather bulky cylindrical headpiece , but the rest of it fits into a sort of back brace and hip pack. That’s because, unlike the more common magnetic brain imaging tech, MRI, the fields and currents involved are extremely small.

A man wears a BrainQ headset while sitting in a chair, while a woman operates a tablet near him.

Image Credits: BrainQ

“We use very, very low intensity, about the same level as normal brain activity,” said Drechsler. “It’s not about creating an action potential or a jump in activity, it’s about creating the right conditions for the recovery mechanisms.”

The results of this stimulation were borne out in a small (25 patients) but decisive study due to be reviewed and published soon (preprint abstract here). Patients given the BrainQ treatment in addition to normal therapy saw hugely improved recovery evaluations, which look at metrics like improvements to balance and strength. 92 percent saw major improvements over just therapy and 80 percent achieved what could be called recovery (though this term is inexact).

Generally speaking the therapy would last for about an hour at a time, during which the patient would do various physical exercises while wearing the device, and they would need to be repeated five days a week for two months or so. The headset feeds the patient’s own patterns into BrainQ’s cloud-based service, which does the crunching and matching necessary to produce a tailored treatment pattern. It’s all run via tablet app, which can be operated by a caregiver (such as an outpatient nurse) or by using a built-in telemedicine platform.

Drechsler said that this approach was poorly received early on, and not just by this reporter.

“In 2017, we started to set the ground for a cloud-connected therapeutic device that can treat the patient wherever she or he is,” he said. “Back then no one was willing to even talk about treating patients outside the controlled environment of the hospital. Then in 2020 COVID came and everything changed.”

He noted that during the pandemic, many of those recovering from a stroke who would normally visit the hospital for regular care were (and some remain) unable to do so. A home-based therapy with low risk and potentially great outcomes would be of enormous benefit for thousands and thousands of people currently recovering from a stroke. And importantly, he notes, it doesn’t shift resources away from existing treatment plans, just improves their outcomes. (“We don’t move anybody’s cheese.”)

Here is where you would normally read something along the lines of “but it maybe five years before the FDA approves it for insurance and use.” But BrainQ recently received Breakthrough Device certification, an expedited approval process that, since just the beginning of this year, also confers qualification for coverage under Medicare. This means that conceivably, BrainQ could be shipping devices very soon — though still a year or two out.

Its next step, very prudently, is a larger scale study, towards which the company intends to devote a large portion of its recent fundraise, $40M led by Hanaco Ventures, with Dexcel Pharma and Peregrine Ventures participating.”

“The reason why we raised all this money is we are on the verge of a unique study with 12 sites,” Drechsler said. While he could not yet name the hospitals or research organizations they partnered with, he said they were basically the cream of the stroke rehabilitation crop and “really we couldn’t aspire for better than getting all these top sites in the same study. There’s this excitement that maybe something new is coming — in stroke recovery there has been almost no progress in the last two or three decades, and physical therapy has been the standard for two hundred years.”

Without making any promises, he suggested that this line of inquiry could move medicine towards not just mitigating but reversing some disabilities, a feat the value of which can hardly be enumerated.

“I was looking over my pitch decks from 2016,” Drechsler mused. “Early on as a CEO, you have big dreams. We heard a lot of skepticism early on in the process, but I was proud to see that many of those dreams have materialized.”

‘It’s almost like placing an IV’: Brain monitoring electrode receives FDA 510(k) clearance

An FDA pathway that’s greased the gears for COVID-19 vaccines and drugs has paved the way for something else: a new take on electroencephalography (EEG), the established brain-monitoring technique in which metallic electrodes are placed on the scalp to measure the brain’s electrical activity. 

On May 17, DC-based startup iCE Neurosystems announced a version of FDA approval for a subcutaneous electrode called iCE-SG, designed to monitor the brain’s electrical activity from beneath the skin of the scalp. That electrode comes on the back of a 2020 Emergency Use Authorization (EUA) for iCE Neurosystems’ software platform called iCEWav, which was used in a D.C. area hospital to monitor the brain activity of patients in medically-induced comas during the Covid-19 pandemic. 

iCE Neurosystems electrode and software are, essentially, a new take on traditional EEG. The electrode is designed to sit beneath the scalp for days and analyze brain activity, and the software component is designed to integrate that data with vital signs like heart rate or blood pressure. 

“For the first time we’ve got this massive, high-fidelity, continuous, integrated data set from both brain and body,” says Alan Waziri, a neurosurgeon and company co-founder. “That allows us to really understand what’s happening in the brain to drive timely clinical decisions, and fundamentally change outcomes for these patients.” 

iCE was founded by Waziri and colleagues from his time as a resident at Columbia University Medical Center in 2017. As of 2021, the company has nine fulltime employees, and has raised a total of $4.5 million, including a recent round of $2.95 million from private investors in April 2021. 

The subcutaneous electrode and software combination is part of iCE Neurosystems bigger picture: to create a full platform for continuous monitoring of the brain. 

There are examples of use cases where continuous monitoring may prove beneficial. For instance, a 2019 New England Journal of Medicine study suggested that specialized EEG monitoring might detect signs of consciousness in otherwise unresponsive patients. That study was authored by Jan Claassen the director of Critical Care Neurology at Columbia who is also co-founder and minority shareholder at iCE Neurosystems. 

Another 2019 paper suggests that continuous monitoring via EEG was associated with fewer deaths in hospitals. But only 22,728 of the over 7 million people analyzed in the study had access to continuous EEG. 

Waziri’s aim is to increase that number. Subcutaneous electrodes, he’s betting, are a first step. The iCE-SG electrodes should be easy to install and don’t require the technical expertise usually required to prepare and administer an EEG, explains Waziri. Other scientists have also noted technical expertise needed to use and interpret traditional EEG is cumbersome and has stood in the way of long-term EEG monitoring. 

FDA approval documents note that the iCE-SG devices are approved to remain beneath the skin for 14 days, but Waziri says he’s obtained continuous monitoring of brain activity for up to 35 days. A long-term EEG analysis, by comparison, might last several days. 

“It’s almost like placing an IV,” Waziri says. “Basically a routine clinician at the bedside can place these in under five minutes.”

On the other hand, the platform alone can’t address the need for expertise to interpret this data. Waziri’s answer to that question is to make this data shareable.

Within a hospital, data collected by platform is stored on the cloud. However, a hospital could opt into sharing data on another platform iCECloud Knowledge with other medical institutions. 

“From participating institutions, all the data we collect gets put in there and is made available to anyone who is using our system,” he says. “Our goal is to almost kind of crowdsource the analysis of the data.”

So far, iCENeurosystems has pursued two forms of FDA approval for the software and the electrode. 

The electrode and the full platform have received FDA premarket approval through the 510(k) pathway – a type of pre-market approval that allows a medical device to go to market without additional FDA review because it’s substantially similar to other products already on the market (In this case, that tech is a traditional EEG). The iCEWav system was granted 510(k) approval in March 2020 and the electrode received it in March 2021

This pathway is one of the most expedient ways to get a medical device onto the market, but has also faced criticism because it doesn’t require a device to be tested for safety or efficacy through clinical trials. Waziri says there “haven’t been any complications” from the devices. 

Additionally, iCEWave has done time in the clinical setting in a major D.C. hospital, though Waziri won’t disclose which one. 

In early 2020, the DC based startup iCE Neurosystems was in the midst of testing iCEWav when the pandemic hit. Some Covid-19 patients required intense cardiopulmonary support that required use of medically induced comas. Technicians typically use EEG to monitor these patients, but iCE Neurosystems also received a trial run, says Waziri, as the hospital was looking for long-term methods of monitoring patients brain activity without having technicians visit multiple times per day. 

“They had our system in place because we were running a clinical trial in patients with cardiac arrest, and they asked us if they could use the system for monitoring their critically ill COVID patients. They actually applied to the FDA and the FDA granted emergency use authorization for the software,” Waziri says. 

So far Waziri and iCENeurosystems hasn’t published any peer-reviewed data from that trial at the D.C. area hospital, but he says the company has two forthcoming manuscripts. 

Meanwhile, Waziri says that iCE Neurosystems is working towards getting more devices into more hospitals. He says they’re in talks with an additional five hospitals, with the goal of beginning a Series A funding raise in mid 2022. 

Cognixion’s brain-monitoring headset enables fluid communication for people with severe disabilities

Of the many frustrations of having a severe motor impairment, the difficulty of communicating must surely be among the worst. The tech world has not offered much succor to those affected by things like locked-in syndrome, ALS, and severe strokes, but startup Cognixion aims to with a novel form of brain monitoring that, combined with a modern interface, could make speaking and interaction far simpler and faster.

The company’s One headset tracks brain activity closely in such a way that the wearer can direct a cursor — reflected on a visor like a heads-up display — in multiple directions or select from various menus and options. No physical movement is needed, and with the help of modern voice interfaces like Alexa, the user can not only communicate efficiently but freely access all kinds of information and content most people take for granted.

But it’s not a miracle machine, and it isn’t a silver bullet. Here’s where how it got started.

Overhauling decades-old brain tech

Everyone with a motor impairment has different needs and capabilities, and there are a variety of assistive technologies that cater to many of these needs. But many of these techs and interfaces are years or decades old — medical equipment that hasn’t been updated for an era of smartphones and high-speed mobile connections.

Some of the most dated interfaces, unfortunately, are those used by people with the most serious limitations: those whose movements are limited to their heads, faces, eyes — or even a single eyelid, like Jean-Dominique Bauby, the famous author of “The Diving Bell and the Butterfly.”

One of the tools in the toolbox is the electroencephalogram, or EEG, which involves detecting activity in the brain via patches on the scalp that record electrical signals. But while they’re useful in medicine and research in many ways, EEGs are noisy and imprecise — more for finding which areas of the brain are active than, say, which sub-region of the sensory cortex or the like. And of course you have to wear a shower cap wired with electrodes (often greasy with conductive gel) — it’s not the kind of thing anyone wants to do for more than an hour, let alone all day every day.

Yet even among those with the most profound physical disabilities, cognition is often unimpaired — as indeed EEG studies have helped demonstrate. It made Andreas Forsland, co-founder and CEO of Cognixion, curious about further possibilities for the venerable technology: “Could a brain-computer interface using EEG be a viable communication system?”

He first used EEG for assistive purposes in a research study some five years ago. They were looking into alternative methods of letting a person control an on-screen cursor, among them an accelerometer for detecting head movements, and tried integrating EEG readings as another signal. But it was far from a breakthrough.

A modern lab with an EEG cap wired to a receiver and laptop – this is an example of how EEG is commonly used.

He ran down the difficulties: “With a read-only system, the way EEG is used today is no good; other headsets have slow sample rates and they’re not accurate enough for a real-time interface. The best BCIs are in a lab, connected to wet electrodes — it’s messy, it’s really a non-starter. So how do we replicate that with dry, passive electrodes? We’re trying to solve some very hard engineering problems here.”

The limitations, Forsland and his colleagues found, were not so much with the EEG itself as with the way it was carried out. This type of brain monitoring is meant for diagnosis and study, not real-time feedback. It would be like taking a tractor to a drag race. Not only do EEGs often work with a slow, thorough check of multiple regions of the brain that may last several seconds, but the signal it produces is analyzed by dated statistical methods. So Cognixion started by questioning both practices.

Improving the speed of the scan is more complicated than overclocking the sensors or something. Activity in the brain must be inferred by collecting a certain amount of data. But that data is collected passively, so Forsland tried bringing an active element into it: a rhythmic electric stimulation that is in a way reflected by the brain region, but changed slightly depending on its state — almost like echolocation.

The Cognixion One headset with its dry EEG terminals visible.

They detect these signals with a custom set of six EEG channels in the visual cortex area (up and around the back of your head), and use a machine learning model to interpret the incoming data. Running a convolutional neural network locally on an iPhone — something that wasn’t really possible a couple years ago — the system can not only tease out a signal in short order but make accurate predictions, making for faster and smoother interactions.

The result is sub-second latency with 95-100 percent accuracy in a wireless headset powered by a mobile phone. “The speed, accuracy and reliability are getting to commercial levels —  we can match the best in class of the current paradigm of EEGs,” said Forsland.

Dr. William Goldie, a clinical neurologist who has used and studied EEGs and other brain monitoring techniques for decades (and who has been voluntarily helping Cognixion develop and test the headset), offered a positive evaluation of the technology.

“There’s absolutely evidence that brainwave activity responds to thinking patterns in predictable ways,” he noted. This type of stimulation and response was studied years ago. “It was fascinating, but back then it was sort of in the mystery magic world. Now it’s resurfacing with these special techniques and the computerization we have these days. To me it’s an area that’s opening up in a manner that I think clinically could be dramatically effective.”

BCI, meet UI

The first thing Forsland told me was “We’re a UI company.” And indeed even such a step forward in neural interfaces as he later described means little if it can’t be applied to the problem at hand: helping people with severe motor impairment to express themselves quickly and easily.

Sad to say, it’s not hard to imagine improving on the “competition,” things like puff-and-blow tubes and switches that let users laboriously move a cursor right, right a little more, up, up a little more, then click: a letter! Gaze detection is of course a big improvement over this, but it’s not always an option (eyes don’t always work as well as one would like) and the best eye-tracking solutions (like a Tobii Dynavox tablet) aren’t portable.

Why shouldn’t these interfaces be as modern and fluid as any other? The team set about making a UI with this and the capabilities of their next-generation EEG in mind.

Image of the target Cognixion interface as it might appear to a user, with buttons for yes, no, phrases and tools.

Image Credits: Cognixion

Their solution takes bits from the old paradigm and combines them with modern virtual assistants and a radial design that prioritizes quick responses and common needs. It all runs in an app on an iPhone, the display of which is reflected in a visor, acting as a HUD and outward-facing display.

In easy reach of, not to say a single thought but at least a moment’s concentration or a tilt of the head, are everyday questions and responses — yes, no, thank you, etc. Then there are slots to put prepared speech into — names, menu orders, and so on. And then there’s a keyboard with word- and sentence-level prediction that allows common words to be popped in without spelling them out.

“We’ve tested the system with people who rely on switches, who might take 30 minutes to make 2 selections. We put the headset on a person with cerebral palsy, and she typed our her name and hit play in 2 minutes,” Forsland said. “It was ridiculous, everyone was crying.”

Goldie noted that there’s something of a learning curve. “When I put it on, I found that it would recognize patterns and follow through on them, but it also sort of taught patterns to me. You’re training the system, and it’s training you — it’s a feedback loop.”

“I can be the loudest person in the room”

One person who has found it extremely useful is Chris Benedict, a DJ, public speaker, and disability advocate who himself has Dyskinetic Cerebral Palsy. It limits his movements and ability to speak, but doesn’t stop him from spinning (digital) records at various engagements, however, or from explaining his experience with Cognixion’s One headset over email. (And you can see him demonstrating it in person in the video above.)

DJ Chris Benedict wears the Cognixion Headset in a bright room.

Image Credits: Cognixion

“Even though it’s not a tool that I’d need all the time it’s definitely helpful in aiding my communication,” he told me. “Especially when I need to respond quickly or am somewhere that is noisy, which happens often when you are a DJ. If I wear it with a Bluetooth speaker I can be the loudest person in the room.” (He always has a speaker on hand, since “you never know when you might need some music.”)

The benefits offered by the headset give some idea of what is lacking from existing assistive technology (and what many people take for granted).

“I can use it to communicate, but at the same time I can make eye contact with the person I’m talking to, because of the visor. I don’t have to stare at a screen between me and someone else. This really helps me connect with people,” Benedict explained.

“Because it’s a headset I don’t have to worry about getting in and out of places, there is no extra bulk added to my chair that I have to worry about getting damaged in a doorway. The headset is balanced too, so it doesn’t make my head lean back or forward or weigh my neck down,” he continued. “When I set it up to use the first time it had me calibrate, and it measured my personal range of motion so the keyboard and choices fit on the screen specifically for me. It can also be recalibrated at any time, which is important because not every day is my range of motion the same.”

Alexa, which has been extremely helpful to people with a variety of disabilities due to its low cost and wide range of compatible devices, is also part of the Cognixion interface, something Benedict appreciates, having himself adopted the system for smart home and other purposes. “With other systems this isn’t something you can do, or if it is an option, it’s really complicated,” he said.

Next steps

As Benedict demonstrates, there are people for whom a device like Cognixion’s makes a lot of sense, and the hope is it will be embraced as part of the necessarily diverse ecosystem of assistive technology.

Forsland said that the company is working closely with the community, from users to clinical advisors like Goldie and other specialists, like speech therapists, to make the One headset as good as it can be. But the hurdle, as with so many devices in this class, is how to actually put it on people’s heads — financially and logistically speaking.

Cognixion is applying for FDA clearance to get the cost of the headset — which, being powered by a phone, is not as high as it would be with an integrated screen and processor — covered by insurance. But in the meantime the company is working with clinical and corporate labs that are doing neurological and psychological research. Places where you might find an ordinary, cumbersome EEG setup, in other words.

The company has raised funding and is looking for more (hardware development and medical pursuits don’t come cheap), and has also collected a number of grants.

The One headset may still be some years away from wider use (the FDA is never in a hurry), but that allows the company time to refine the device and include new advances. Unlike many other assistive devices, for example a switch or joystick, this one is largely software-limited, meaning better algorithms and UI work will significantly improve it. While many wait for companies like Neuralink to create a brain-computer interface for the modern era, Cognixion has already done so for a group of people who have much more to gain from it.

You can learn more about the Cognixion One headset and sign up to receive the latest at its site here.