ALS Patient Becomes First 'Power User' of Brain-Computer Interface Speech Device
Key Takeaways
- ▸Harrell has used the BCI for 3,800+ hours over nearly 3 years, becoming the first 'power user' of a speech brain-computer interface
- ▸The device achieved 99.6% accuracy on initial use with 50-word vocabulary; expanded to 125,000 words at 97.5% accuracy
- ▸Beyond communication, Harrell uses the technology to work, browse the web, and live more independently with minimal care partner involvement
Summary
Casey Harrell, a man living with ALS (amyotrophic lateral sclerosis), has become the first "power user" of a speech brain-computer interface (BCI) developed by researchers at UC Davis. Over nearly three years since the device's implantation in July 2023, Harrell has used the BCI for more than 3,800 hours while at home, largely independently once a care partner connects the electrodes implanted in his brain to a computer. The system works by decoding neural activity from the speech motor cortex and translating it into words using machine learning algorithms that map brain signals to phonemes and then to words.
On the first day of use in August 2023, the device achieved 99.6% accuracy with a 50-word vocabulary, which was later expanded to 125,000 words while maintaining 97.5% accuracy. Remarkably, the device has proven durable over three years of extended use—addressing early concerns that scar tissue would degrade electrode function. Beyond communication, Harrell now uses the BCI to surf the web and perform his job. The research, published today in Nature Medicine, demonstrates that brain-computer interfaces can provide long-term, practical independence for paralyzed individuals and may represent the beginning of BCIs as mainstream assistive technology rather than research curiosities.
- The device proved durable over extended use with no degradation from scar tissue formation, resolving a major concern for long-term brain implants
Editorial Opinion
This represents a watershed moment for brain-computer interface technology and ALS care. What's remarkable isn't just the technical achievement—decoding 125,000 words with 97.5% accuracy is impressive—but that the device works reliably for years in real-world conditions without degradation. Harrell's ability to work and communicate freely suggests BCIs are finally transitioning from lab prototypes to durable assistive technology. As these systems mature and become more accessible, they could fundamentally transform how we approach neurological disease and paralysis.
