TL;DR
A UC Davis BCI implant enabled an ALS patient to speak independently for more than 3,800 hours over two years with 99% accuracy, allowing him to work full-time.
A man with ALS has been using a brain implant to speak independently for more than 3,800 hours in the last two yearsproducing almost 2 million words with an average speed of 56 words per minute. The study, published Monday in Nature Medicine by researchers at the University of California, Davis, represents the longest sustained demonstration that a brain-computer interface can function as a practical daily communication tool outside of a laboratory. Casey Harrell, the 47-year-old participant, has used the system to return to work full-time as an environmental advocate.
The implant consists of four sets of microelectrodes placed in Harrell’s left precentral gyrus, the region of the brain that coordinates speech, and records the activity of 256 cortical electrodes. Machine learning algorithms built into a software platform called BRAND, developed by UC Davis postdoctoral fellow Nicholas Card, translate that neural activity into phonemes of the English language and then map those phonemes to words and sentences. The system reads the decoded text into a synthesized version of Harrell’s pre-ALS voice.
In controlled tests with a vocabulary of 125,000 words, the system achieved word accuracy greater than 99%. In everyday use outside the laboratory, Harrell rated 92% of the sentences as accurate or mostly correct. During the study period, he communicated more than 183,000 sentences.
The 💜 of EU technology
The latest rumors from the EU tech scene, a story from our wise founder Boris and some questionable AI art. It’s free, every week, in your inbox. Register now!
“The key for me is that it allows for daily communication for a guy who wants to talk but can’t.“neurosurgeon David Brandman, who implanted the device in 2023 and co-led the study, told The Register.”Despite being paralyzed, he has returned to work full time and has meaningful conversations with his daughter, who has never heard the sound of his voice.“
The importance of the study lies not only in precision but also in independence. Previous BCI systems required researchers to be present in the patient’s home whenever the device was in use, or required the patient to travel to a laboratory. Harrell’s system is operated by his home care team, with no researcher support required.
According to the study’s schedule, it averaged more than five hours of daily use.
The UC Davis team is part of BrainGate, the consortium of universities and the US Department of Veterans Affairs developing brain-computer interfaces for speech restoration, computer control and movement recovery. The hardware itself is not custom made, but rather uses existing microelectrode arrays produced by Blackrock Neurotech. The breakthrough is in the software, specifically in the BRAND platform’s machine learning algorithms that decode speech attempts from neural signals in real time.
Brandman compared the current state of BCI technology to early pacemakers, which in the 1950s required external wiring for large batteries or a power outlet. Seventy years later, pacemakers are being implanted in outpatient procedures. “We are in the early stages of this type of technology,The firefighter said.
Harrell is still connected to external computers, but the UC Davis team’s advances in artificial intelligence, combined with hardware miniaturization work at companies like Neuralink, Synchron and Paradromics, point to a future where setup will be much less cumbersome.
The competitive landscape at BCI is accelerating. Neuralink has implanted devices in at least 21 patients under research protocols but lacks commercial approval. China approved the first commercially available invasive BCI earlier this year.
Other approaches to restoring speech in people with ALS use AI speech conversion instead of brain implants, but those methods require the patient to retain some vocal ability.
What distinguishes the UC Davis work is its demonstration that a BCI can go from a laboratory experiment to a practical and sustained daily tool. The 3,800 hours of brain recordings also constitute the largest individual neuronal data set at single-neuron resolution ever collected, according to co-principal investigator Sergey Stavisky, which will inform future improvements in decoding algorithms.
The system remains an investigational device, limited by federal law to investigational use, and has been tested on a single patient. It is not yet known whether the results can be generalized to other ALS patients or to people with different neurological conditions. Scaling the technology from a clinical trial to a prescription medical device will require regulatory approval, hardware miniaturization and cost reduction, which could take years.
“I desperately want to not be unique or special, because that will mean that I no longer have the disease or that everyone who has the disease like me can be prescribed this.”Harrell said through his BCI system.
