An algorithm established which patterns of brain activity corresponded to which letter & symbol, enabling it to identify the characters & display them onscreen.
Neuroscientists from Stanford University have just made history by successfully converting brain activity related to handwriting into actual text in real-time. The team, working together with the BrainGate consortium, achieved the feat thanks to a new brain-computer interface (BCI) that could revolutionize current technologies that enable people with disabilities to communicate.
The process involved two implanted arrays of electrodes with the capacity to monitor the electrical activity of approximately 200 neurons in the brain’s motor cortex — the region controlling hand movement. Even when a patient cannot move their limbs due to a spinal cord injury, the motor cortex still registers the same signals that it did before.
As part of the study, published in the journal Nature, the scientists implanted the electrodes into the brain of a 65-year-old quadriplegic male volunteer who had previously suffered a spinal cord injury. The participant was asked to imagine writing on a paper all 26 letters of the alphabet in lower case as well as a few symbols.
An algorithm in the computer established which patterns of brain activity corresponded to which letter and symbol, enabling it to identify the characters and display them on the screen. In this way, the man was able to type out complete sentences at a rate of about 90 characters per minute, breaking previous versions of the system.
The scientists are now working to test the technology with a volunteer who is not only paralyzed but has also lost the ability to speak. The team hopes that in the near future, similar BCI technology could welcome people suffering from motor impairments into the world of modern communications, including texting and mailing.