Hacker News new | ask | show | jobs
by lettergram 1550 days ago
I’ve seen and built systems that are far less invasive —

https://agenda.hep.wisc.edu/event/792/contributions/18594/at...

With accuracy on par or better than described:

> He eventually explained to the team that he modulated the tone by trying to move his eyes. But he did not always succeed. Only on 107 of 135 days reported in the study could he match a series of target tones with 80% accuracy, and only on 44 of those 107 could he produce an intelligible sentence.

In fact, some of these successful efforts were done back in the early 2000s.

From the article:

> Researchers inserted two square electrode arrays, 3.2 millimeters wide, into a part of the brain that controls movement. When they asked the man to try to move his hands, feet, head, and eyes, the neural signals weren’t consistent enough to answer yes-or-no questions, says Ujwal Chaudhary, a biomedical engineer and neurotechnologist at the German nonprofit ALS Voice.

The speed and accuracy does take a hit using external nodes, but brain implants are frankly dangerous. They come with serious risks.

2 comments

Does your less invasive solution work with fully locked in patients? Often these solutions rely (partially) on some tiny muscle activity still working, which they don't have. At least that was what I've been taught some time ago (could be early 2000s), and what's for sure hard to rule out in 'healthy' patients.
It was developed for fully locked in patients, who have eye control. It uses a very similar mechanism except it’s slower. Effectively you have to look at characters on a screen to type.
The article implies he has lost even eye-control, or at the very least, that he wanted the implant for use in that eventuality.
Are the risks associated with invasiveness fixed (eg, there will always be at least a 1/15000 chance that a patient dies within the first year of receiving a neural implant), or can they be reduced with better technology and more understanding of the brain?
At the moment, there will always be damage.

There’s also risks associated with the surgery (that’ll be much higher than 1/15,000; you’re probably talking at least 1/1000 just for risk of initial surgery).

Further, no implants last forever. They develop scar tissue around the implant. So you’ll have multiple surgeries if you survive years.

Technology can mitigate much of that risk, but we are pretty far away from removing risk. We also will need multiple major independent breakthroughs.