A brain implant developed at UC Davis enables an ALS patient to communicate with 99% accuracy and maintain full-time employment, all without the need for researchers.

      TL;DRA: A brain-computer interface (BCI) implant from UC Davis allowed an ALS patient to communicate independently for over 3,800 hours across two years with an accuracy of 99%, enabling him to work full time.

      An ALS patient has utilized a brain implant for independent speech for more than 3,800 hours in the last two years, generating nearly 2 million words at an average speed of 56 words per minute. This study, published on Monday in Nature Medicine by researchers from the University of California, Davis, showcases the longest continuous demonstration of a brain-computer interface as a practical tool for everyday communication outside of a lab setting. Casey Harrell, the 47-year-old participant, has leveraged this system to resume full-time employment as an environmental advocate.

      The implant comprises four microelectrode arrays implanted in Harrell’s left precentral gyrus, the brain region responsible for speech, capturing activity from 256 cortical electrodes. Machine learning algorithms integrated into a software platform named BRAND, designed by UC Davis postdoctoral fellow Nicholas Card, convert the neural signals into English phonemes, which are subsequently matched to words and sentences. The system vocalizes the decoded text in a synthesized version of Harrell’s voice prior to his ALS diagnosis.

      In a controlled test utilizing a 125,000-word vocabulary, the system achieved over 99% word accuracy. During regular use outside the lab, Harrell assessed 92% of the sentences as accurate or mostly correct. Throughout the study duration, he communicated more than 183,000 sentences.

      According to neurosurgeon David Brandman, who implanted the device in 2023 and co-led the study, the most important aspect is that it facilitates daily communication for someone who wishes to speak but cannot. “Despite being paralyzed, he has returned to full-time work and engages in meaningful conversations with his daughter, who has never heard his voice.”

      The study’s importance lies not only in its accuracy but also in the independence it offers. Earlier BCI systems required researchers to be present in the patient’s home during operation or necessitated visits to a lab. Harrell’s system is managed by his home care team without the need for researcher involvement.

      Based on the research timeline, he averaged more than five hours of daily usage. The UC Davis team is part of BrainGate, a consortium of universities and the US Department of Veterans Affairs working on brain-computer interfaces for speech restoration, computer control, and movement recovery. The hardware is not uniquely constructed; it uses existing microelectrode arrays from Blackrock Neurotech. The innovation lies in the software, particularly the machine learning algorithms in the BRAND platform that decode attempted speech from neural signals in real-time.

      Brandman likened the current BCI technology to early pacemakers, which in the 1950s relied on external wiring to large batteries or wall outlets. Now, after seventy years, pacemakers can be implanted during outpatient procedures. “We are still in the early stages of this technology,” Brandman remarked.

      While Harrell is still connected to external computers, the advances in AI from the UC Davis team, when combined with ongoing miniaturization efforts from companies like Neuralink, Synchron, and Paradromics, suggest a future where the system could become less cumbersome.

      The competition in the BCI field is intensifying. Neuralink has implanted devices in at least 21 patients as part of research but has not yet received commercial approval. Earlier this year, China approved its first commercially available invasive BCI.

      Alternative methods for restoring speech for individuals with ALS use AI voice conversion instead of brain implants, but these methods require the patient to retain some vocal capability.

      What sets the UC Davis research apart is that it demonstrates a BCI can transition from lab experimentation to a sustained, practical daily communication tool. The 3,800 hours of brain recordings also represent the largest individual neural dataset with single-neuron resolution ever collected, according to co-principal investigator Sergey Stavisky, which will contribute to future enhancements to the decoding algorithms.

      The system is still classified as an investigational device, restricted by federal law to research use, and has been tested on only one patient. It remains to be seen whether the results will apply to other ALS patients or individuals with different neurological disorders. Transitioning from clinical trials to a prescribed medical device will necessitate regulatory approval, hardware miniaturization, and cost reductions, which may take years.

      “I desperately want to not be unique or special, as that would mean I no longer have the disease or that everyone else with this disease could also be prescribed this treatment,” Harrell expressed through his BCI system.