[HN Gopher] Implant lets those with severe paralysis send texts ...
___________________________________________________________________
Implant lets those with severe paralysis send texts with just their
minds
Author : ohjeez
Score : 109 points
Date : 2023-02-22 16:28 UTC (1 days ago)
(HTM) web link (www.pcgamer.com)
(TXT) w3m dump (www.pcgamer.com)
| MH15 wrote:
| Site hijacks the back button.
| texaslonghorn5 wrote:
| > The year-long human trials for Synchron's BCI system have been
| peer-reviewed by a neuroscience medical journal in
| Australia(opens in new tab), where the study found the technology
| safe and signal quality didn't degrade for its Australian
| patients. The study also concludes that "the favorable safety
| profile could promote wider and more rapid translation of BCI to
| people with paralysis." We'll give it about another year before
| someone's running Doom on it.
|
| could not find full text for free unfortunately
| dmurray wrote:
| https://jamanetwork.com/journals/jamaneurology/fullarticle/2...
|
| worked for me, but perhaps it's paywalled for some.
| mariodiana wrote:
| Just yesterday I was rewatching an old Star Trek episode, "The
| Menagerie," where the story centers around this poor victim of an
| accident ("delta rays") who is confined to a wheelchair, in a
| near-vegetable state, with only the ability to trigger a light:
| once for YES, twice for NO.
|
| https://en.wikipedia.org/wiki/The_Menagerie_(Star_Trek:_The_...
|
| Okay, still no flying cars--but we really ought to take stock in
| the many ways our present has already exceeded expectations from
| our recent past of even our distant future.
| iamflimflam1 wrote:
| The episode always struck me as very strange - all that
| advanced technology - but all they can do is give this guy a
| single light.
| kuschku wrote:
| If you liked that episode, you might want to see the show "Star
| Trek: Strange New Worlds", which tells the story of the crew
| before Kirk, and how the Captain of that crew (Pike) got into
| that position
| ed25519FUUU wrote:
| I love to see news like this. I had a serious brain injury that
| could have left me paralyzed (or dead). Thankfully I'm okay, but
| it's made me very empathetic to everyone out there living with
| severe paralysis.
| AlexAndScripts wrote:
| Do you have brain fog? If so, is there anything you could
| recommend? I was attacked and have had post concussion syndrome
| for almost a year, with no sign of improvement for about 6
| months, that's more or less destroyed my academic and
| intellectual potential.
| iamflimflam1 wrote:
| Might be worth having a look at the Strange Parts YouTuber -
| he suffered severe concussion after an accident with serious
| brain fog and has managed to come out the other side. I
| believe he used these guys:
|
| https://www.cognitivefxusa.com/ or maybe these guys:
| https://neuraleffects.com/
|
| No idea if this would be covered by your health insurance
| (assuming you're USA).
|
| https://www.youtube.com/watch?v=Gs790JOeN3Y
| ricardobeat wrote:
| > The Syncron Switch is meant to be less invasive than other BCIs
| like Neuralink
|
| While it is a direct brain implant, Neuralink's goal is to have
| it done 100% by robots, no neurosurgeons involved (with their
| hands at least). Their device is also so tiny that it's hard to
| say it's more invasive then pushing something through your veins
| + a chest implant...
| CyborgCabbage wrote:
| YouTube video I found with more info
| https://www.youtube.com/watch?v=mm95r05hui0
| pelorat wrote:
| Still don't understand how this company got FDA approval before
| Neuralink.
| Pigalowda wrote:
| Is it FDA approved? I thought it was Australian?
| LeifCarrotson wrote:
| I've done some testing with ECG sensors adhered to the scalp and
| know what noisy, limited signals that gives you, but man am I
| looking forward to the day when people can send data from their
| brain directly to a computer. I don't mind shaving my head (I'm
| male in a family with a history of male pattern baldness, if that
| matters) but I'd 100x prefer a device that lived outside the
| scalp to one with probes beneath the skull.
|
| The amplifier fidelity and data processing rate of eg. TI ADS1299
| chips that I worked with 10 years ago is only going up slowly,
| but (now outside the field) it feels like the data processing
| potential to turn extremely noisy and hard to measure waveforms
| into letters and words could move forwards extremely fast with
| AI.
| com2kid wrote:
| Hot take:
|
| The metaverse will take off when bi-directional BCI takes off.
|
| I also think the smart players are trying to stake claims right
| now with in the software landscape, and keep holding on until
| HW improves, at least I hope no one actually thinks the current
| head mounted display system is the way forward! I'd look at HMD
| VR as the equivalent of black and white resistive screen Palm
| Pilots that communicate with IR. The foundational ideas are
| there, but smartphones were the revolution.
| pelorat wrote:
| That's going to happen only when you have a million nanowires
| worming themselves throughout your brain. Of course you can't
| insert that many, so it will need to be a device capable of
| self-assembly.
| RajT88 wrote:
| You've just predicted a sci-fi dystopia featuring actual
| brain worms.
|
| Thanks, I hate it.
| dr_dshiv wrote:
| Totally agree that we are decades away from either.
| com2kid wrote:
| Based on the news coming out about them lately, Neuralink
| seems like a lost opportunity to accelerate progress in
| this space.
|
| A _ton_ of money was dropped into improving HMDs, and a lot
| of improvements to surrounding technical fields got made,
| it is sort of unfortunate that physics fundamentally limits
| what can be done there.
|
| If a similar investment had been made in BCI over 10 years,
| I suspect we'd be halfway to success.
|
| However it is important that there are multiple companies
| dumping money into R&D, so that the best methodology wins.
| Even in HMDs, different devices learned from each other and
| everyone benefitted.
|
| Of course implantable BCIs have more ethics concerns, and
| that likely is why the big tech companies didn't even try.
|
| But the first company to get consumer level bi-directional
| BCI onto the market is going to become the largest tech
| company ever, orders of magnitude larger than anything we
| see today.
|
| Based on your job, I'm guessing you are also sad that we've
| reached a local maxima regarding input devices! If machines
| were designed from scratch now days, meaning everyone had
| no prior expectations of keyboards/mice/touch/etc, I
| suspect we'd do everything very differently.
| kevviiinn wrote:
| Neuralink wasn't a lost opportunity because it wasn't a
| possible opportunity in the first place. We are so far
| off from BCI input to the brain it's actually laughable.
| I'm willing to bet well over 60-80 years away
|
| Output is also a joke but a far easier problem to solve.
| com2kid wrote:
| > We are so far off from BCI input to the brain it's
| actually laughable. I'm willing to bet well over 60-80
| years away
|
| Progress depends on discoveries in surrounding fields
| having already been made, and on resources invested. To
| an extent, you can help spur surrounding fields with lots
| of $, but it seemingly isn't possible to force brilliant
| theoretical breakthroughs.
|
| We have direct input for audio (cochlear implants) that
| needs iterating on, what needs tons of investment is
| visual.
|
| Figuring out how do to research in a humane fashion,
| that'll be the tricky part, and it isn't something
| corporations have a good history of.
| CobrastanJorji wrote:
| One thing that concerns me a bit is stacking machine learning
| onto this. Imagine a 100% paralyzed person in the hospital. We
| attach some probes to their head and get a very noisy signal.
| What comes back is a very noisy signal, but we've got a machine
| learning model that takes in a huge amount of context about
| interacting with computers and text and such and uses it as
| part of how it cleans up the signal, just like how phones today
| use machine learning to de-noise camera input.
|
| Then let's say that our paralyzed person says something very
| impactful like "please turn off the life support" or "I will
| all of my money to my kids." Can you imagine the lawsuit over
| to what degree the machine learning was driving the boat?
| ggm wrote:
| Require them to spell it out letter by letter. Which btw is
| almost certainly how current Brain reading works, you think
| hard to stop a pointer walking a screen.
| rhacker wrote:
| Or just ask a lot of questions which prove mindfulness.
| jrumbut wrote:
| Most systems I have seen allow for you to delete characters.
| This was close to 20 years ago now though so perhaps it has
| gone through a worse is better phase.
|
| Now, the issues you state are very real, terrifying, and
| depressing. Still anything that allows the person to
| communicate directly, rather than through an intermediary
| holding an eye board, will be a major step toward greater
| independence and the ability to hold those who abuse the
| disabled accountable.
| pelorat wrote:
| > but I'd 100x prefer a device that lived outside the scalp to
| one with probes beneath the skull.
|
| So would everyone, but it's just too limited. It's going to be
| implants.
| brylie wrote:
| I also tried working with EEG data from an OpenBCI device. My
| goal was to get an accurate enough signal to move a cursor on
| an X/Y axis and use that to control a predictive text input
| tool like Dasher.
|
| https://en.m.wikipedia.org/wiki/Dasher_(software)
|
| The X/Y BCI signal goal seems fairly practical and could open
| up critical pathways for interaction and communication.
|
| If anyone is interested in pursuing this idea, please send me a
| message. My previous attempts were derailed due to technical
| difficulties with the BCI hardware/software link, but I'd like
| to see this idea come to light.
| m463 wrote:
| I loved what ctrl-labs was doing, where they could read what
| your fingers wanted to do from an arm sensor. Not only was it
| supposed to be a great virtual keyboard, but it allowed some
| users to sprout a third virtual arm.
|
| Unfortunately they were bought by facebook and then... nothing.
| and if they do come out with something, you know it will be
| locked into their platform.
| dvngnt_ wrote:
| at meta connect they showed someone playing a mobile game
| (maybe temple run or subway surfers) with their mind
| neogodless wrote:
| I really want to know more about the _control_ the patient has
| over the interface.
|
| i.e. if I think _think_ something stupid, I still control whether
| my mouth lets that out (typically). Do they have control over
| mode of operation, like they think "OK Synchron!" and then issue
| some speech?
| thelastquestion wrote:
| My understanding from their original paper is that Synchron's
| device (known as the stentrode since its electrodes are on a
| stent scaffold) decodes only a binary signal for this trial,
| that is "intent to move" or "no intent to move" in a period of
| time (~1 second). Their paper mentions the decoder outputting
| no click, short click, or long click where a short click is
| movement intent followed by no movement intent, and long click
| is something like 3 consecutive movement intents followed by no
| movement intent.
|
| The person types either by using eye tracking to move the
| cursor and clicking with the BCI device, or with a custom
| interface that cycles through characters one at a time and
| using only the BCI device to say yes to that character.
|
| So the decoding of intent isn't at the level that your thought
| experiment is concerned about, but in general, you definitely
| could implement something that decodes an initial intent before
| subsequent recording (e.g., think about waking up the device).
| Trivially for Synchron's device this could be X number of
| consecutive movement intents. For intracortical BCI devices
| with single neuron resolution, you could imagine more precise
| neural activity correlated with the intent to begin decoding.
| ad404b8a372f2b9 wrote:
| God I hope someone implements a binary tree for these poor
| people, I can't imagine how frustrating it must be to type
| like that.
| thelastquestion wrote:
| Haha, for typical use with Synchron's device they are using
| eye-tracking. The BCI-only mode is just for research
| purposes/baseline. It's also just what's in the paper, they
| may implement other UIs in practice.
| fsckboy wrote:
| > _they may implement other UIs in practice_
|
| for the first time in my life I'm thinking "now _here 's_
| something that should be called UX"
| HarryHirsch wrote:
| There is a simpler device, a glass plate with the alphabet
| held between the patient and the other person. Humans are
| extraordinary good at following someone's glance, and this
| is how a quadriplegic patient can spell out words. Franz
| Rosenzweig used such a thing in his last years.
|
| It's surprising that no one has used a camera plus ML
| whizzo stuff including predictive text to speed up the
| process.
| cma wrote:
| Couldn't something pretty close to that be done with eye
| movement and blinking?
| idopmstuff wrote:
| This is a really great point.
|
| I feel like I have three levels of thought - unconscious,
| unprompted and active. Unconscious are what you'd imagine - I
| don't actively think them (like I don't hear the thought in my
| head), but clearly something's happening in my brain that's
| affecting my actions.
|
| Unprompted and active are both things that I hear in my inner
| monologue or picture in my head. The former, as the name would
| suggest, are things that I'm not trying to think about -
| intrusive thoughts are certainly an example. The latter are
| things that I am purposely shaping my thoughts around.
|
| Active thoughts are almost the only thing that come out of my
| mouth (if I'm very surprised, an unprompted thought might come
| out). Would I have that same level of control here?
| jvanderbot wrote:
| In past experiments that I'm aware of, you steered the
| cursor, or typed a letter, by using a few seconds of
| _visualizing_ a sort of "command image". The command image
| recall would essentially generate a recognizable signal in a
| sensor array that is in a cap the patient wears.
| ghostbrainalpha wrote:
| You would definitely have that level of control. These
| signals don't map to your inner monologue but they can pick
| up your intention to physically do something.
|
| So if you think LEFT, you can move the selector on the
| keyboard to the next key to the left. And if you think CLICK,
| you can trigger a click. But you are focusing on asking your
| hand to physically make that click. Which your hand can't do
| obviously, but they can track those neurons to simulate the
| action for you.
| RajT88 wrote:
| When I'm trying to be funny, I'll sometimes feel a funny joke
| coming, but I have no idea what it'll be. Then it pops out,
| fully formed, seemingly out of nowhere. Sometimes I don't
| feel it coming.
|
| It's strange, but I feel like this is what you're talking
| about with unprompted thoughts.
| jddj wrote:
| Or just try to sit still for a minute and not do anything
| and you'll notice that the vast majority are unprompted and
| just arise from nowhere.
| flangola7 wrote:
| I wonder how it works for those of us without an internal
| monologue.
| AussieWog93 wrote:
| Thomas Oxley? Endovascular? Looks like they finally
| commercialised the stentrode!
|
| I remember seeing the initial trials of this back in the day.
| Basically functions like a slightly worse ECoG sensor (since the
| signal still gets filtered by the dura), but much easier to
| install. Think best case performance of about 80 binary inputs
| per minute, or a really noisy cursor input.
|
| Honestly, without the improvement in algorithms they were hoping
| for, there's not a snowball's chance in hell of this playing Doom
| within 5 years, let alone one. There's still fundamental unsolved
| problems (like the fact that ~20% of people simply can't Motor
| Imagery BCIs no matter how hard they try, and a massive chunk of
| those who can produce incredibly noisy signals), but new sensors
| are always a step in the right direction (as opposed to new
| algorithms, which, in this field, are almost always complete
| bullshit.)
| paulpauper wrote:
| Just be careful not to accidently leak your passwords or 12-word
| crypto keys . It's like a hot mic but worse. If such technology
| becomes more commonplace, and not just for paralyzed people, this
| will be a problem.
| version_five wrote:
| The article doesn't specify how it works, but my guess is that
| you're controlling some typing or word selection in a learned
| way, like eg how Stephen Hawking talked but with some eeg input
| instead of muscle movement. You're not broadcasting your
| thoughts.
| CyborgCabbage wrote:
| It only registers a binary input (e.g. mouse-click); their
| YouTube[0] shows a patient using it in conjunction with eye-
| tracking. [0]: https://www.youtube.com/watch?v=mm95r05hui0
| dmitriid wrote:
| So, how long before the company goes out of business and leaves
| patients stranded?
|
| See what happened to ocular implants from Second Sight
| https://www.bbc.com/news/technology-60416058
___________________________________________________________________
(page generated 2023-02-23 23:00 UTC)