The development has been made possible through the use of a special computer chip that has been implanted in his brain, according to the New York Times.
This remarkable feat has happened thanks to the technologists applying machine-learning algorithms to decode the neural activity taking place in the man’s brain. This has allowed the patient, Ian Burkhart, to control the activation of his forearm muscles.
The way this works is through a neuromuscular electrical stimulation system. This essentially bypasses the injured area of Burkhart’s brain, enabling him to regain basic physical movements. The chip used is very tiny (about one tenth of an inch) and it contains 96 electrodes. To function, the chip in the patient’s skull needs to be connected to a computer.
Burkhart, who comes from Dublin, Ohio, was on holiday after his first year in college. One day, aged 19, he dived into a wave. The wave was powerful it lifted him onto a hidden sandbar. The force of the impact snapped Burkhart’s neck.
Burkhart’s paralysis is due to disruption of signal pathways between the brain and the muscles. The novel neuroprosthetic device has been designed to restore lost function.
The technological feat represents one of the first attempts at muscle activation using intracortically recorded signals (or brain-computer interfaces.) This achievement could lead to similar successes in other patients.
Wired magazine further describes the technology: “A wire connects the chip to a port screwed into the skull, which in turn connects to a cable delivering that information to a computer.” Here a specially developed algorithm, formed from considerable data collected from brain implants over several years, reads the signals and translates them. The translated data is sent to electrodes worn around the wrist. Next. the electrodes are stimulated in a way that it reflects the original brain signals.
The process of developing the interface was slow. However, over a period of a few months Ian Burkhart taught himself to perform tasks of ever increasing complexity.