August 16th, 2024

Brain-to-Speech Tech Good Enough for Everyday Use Debuts in a Man with ALS

Casey Harrell, a man with ALS, regained communication through a new brain-computer interface with under 3% error. This advancement in speech neuroprostheses faces challenges but offers transformative potential for many.

Read original articleLink Icon
Brain-to-Speech Tech Good Enough for Everyday Use Debuts in a Man with ALS

significant advancement in brain-computer interface (BCI) technology, Casey Harrell, a 45-year-old man with ALS, has regained the ability to communicate using a new BCI system. After undergoing surgery to implant four electrode arrays in his brain, Harrell can now articulate thoughts into clear synthetic speech, allowing him to interact meaningfully with his daughter and others. This BCI boasts an impressive accuracy rate of less than 3% in error, comparable to that of non-disabled speakers, and maintains performance over extended use. The technology represents a significant leap forward in the field of speech neuroprostheses, with potential for broader application among individuals with speech paralysis. However, challenges remain, including the need for surgical implantation, the risk of infection, and questions about long-term viability and effectiveness for those with more severe paralysis. Harrell's experience highlights the transformative potential of this technology, as he expresses a desire for wider access to help others facing similar challenges. The ongoing clinical trial, part of the BrainGate consortium, aims to refine and expand the use of such devices, which could revolutionize communication for many individuals with paralysis.

- Casey Harrell, a man with ALS, can now communicate using a new brain-computer interface.

- The BCI has a low error rate of less than 3%, making it effective for everyday use.

- The technology represents a significant advancement in speech neuroprostheses.

- Challenges include surgical risks, long-term viability, and effectiveness for severe paralysis.

- Harrell advocates for wider access to the technology to help others in similar situations.

Link Icon 7 comments
By @drdavidbrandman - 6 months
Co-senior author here. I'm a long-time hackernews reader. Very excited to see that this work made the front page. I'm happy to take questions.

The Scientific American article was written about our lab's first major paper, "An Accurate and Rapidly Calibrating Speech Neuroprosthesis" published 14 August 2024 in the New England Journal of Medicine [0].

This video nicely summarizes the project [1].

Some additional coverage can be found in the New York Times[2] and Bloomberg[3].

Our lab's website can be found here (written in elm) [4]. The software platform that this BCI uses can be found here [5].

[0] https://www.nejm.org/doi/full/10.1056/NEJMoa2314132

[1] https://www.youtube.com/watch?v=thPhBDVSxz0

[2] https://www.nytimes.com/2024/08/14/health/als-ai-brain-impla...

[3] https://www.bloomberg.com/news/articles/2024-08-14/brain-tec...

[4] https://neuroprosthetics.science/

[5] https://iopscience.iop.org/article/10.1088/1741-2552/ad3b3a

By @billylo - 6 months
This really is a landmark success. Their patient, Harrell, who suffers from ALS, can use their Brain-to-Speech interface daily reliably (<3% error rate) to talk to family.

Big congrats to the team at UC Davis.

By @smeej - 6 months
This is incredible to me, the kind of science fiction I actually want to see become fact in situations like this.

I'm wondering a bit about this claim, though, and hoping someone more familiar with the field can shed some light on it:

> The device predicts the wrong word less than 3 percent of the time, an error rate on par with nondisabled speakers reading a paragraph aloud.

Does this mean that in a paragraph of 100 words, nondisabled readers are expected to get 3 words wrong? That would be a lot higher than I would expect, but is what it sounds like the quoted sentence means.

Or is it more like if a hundred nondisabled people read a standard paragraph out loud, three of them would trip over (at least) one word in it? This seems closer, but still like a fairly high error rate for something they're calling "perfect."

By @29athrowaway - 6 months
If I think something like "OMG, please STFU" will that system vocalize it? This is a real question.
By @soco - 6 months
If you want also to see and hear him (and the team) I found the video in this other article: https://www.brown.edu/news/2024-08-14/bci-speak-again
By @Cilvic - 6 months
Impressive. I didn't find any mention of the speed. How many words per minute does this allow for?