May 16, 2024

New Brain Implant Decodes Speech Signals and Helps Patients with Neurodegenerative Diseases Communicate

Researchers at Duke University have developed a groundbreaking brain implant that uses high-resolution neural recordings to decode brain signals and translate them into speech, potentially providing a way for people with neurodegenerative diseases to communicate again. Neurodegenerative diseases like ALS can cause individuals to lose their ability to speak, even though their cognitive function remains intact. By decoding signals directly from the brain’s motor cortex, which controls speech, researchers hope to restore communication for these patients.

The current tools available for patients with motor disorders are slow and cumbersome, often resulting in a limited speech decoding rate of around 78 words per minute. To improve upon existing devices, the researchers developed a brain implant with 256 microscopic brain sensors, densely packed onto a small medical-grade plastic strip. This design allows the device to obtain high-quality neural signals with greater spatial resolution, enabling more accurate predictions about what the person intends to say.

During the implant testing phase, four patients undergoing brain surgery for Parkinson’s disease or tumor removal were recruited. The patients briefly interrupted their surgeries to have the brain implant used on them. The task involved the participants hearing and speaking a series of nonsense words, while the implant recorded the activity in their motor cortex coordinating the movements of nearly 100 muscles involved in speech.

The data collected from the implant’s recordings was then fed into a machine learning algorithm, which predicted the sounds being made based solely on the brain activity recordings. The decoder was able to accurately predict the first sound of a nonsense word around 84% of the time. However, accuracy decreased for sounds in the middle or at the end of the word, particularly if two sounds were similar. Overall, the decoder achieved an accuracy rate of 40%, using only 90 seconds of spoken data gathered during the 15-minute test.

Although the current accuracy rate may not seem impressive, the researchers highlight that the algorithm was trained using a small amount of data and that further improvements are expected. They plan to enhance the device’s accuracy and decoding speed with the help of a grant from the National Institutes of Health. In addition, they are working on developing a cordless version of the implant, eliminating the need for wires and allowing patients to move around freely without being tied to an electrical outlet.

The development of this brain implant holds great promise for individuals with neurodegenerative diseases that affect speech. It provides new hope for communicating effectively and restoring a sense of independence for those who have lost their ability to speak. With further advancements, this technology could significantly improve the quality of life for patients dealing with the challenges of neurodegenerative diseases.

*Note:
1. Source: Coherent Market Insights, Public sources, Desk research
2. We have leveraged AI tools to mine information and compile it