There is one stroke leading cause of long-term disability, with approximately two-thirds of survivors experiencing significant damage to their hands and arms. Although some people eventually regain this function, many people live with persistent paralysis or weakness. Epia Neuro, a San Francisco-based startup, wants to lend a hand more stroke patients regain hand function with a brain implant and a motorized glove.
It is one of a growing number of companies developing brain-computer interfaces, i.e. devices that read neural signals from the brain and translate them into specific actions. The space has seen a huge influx of investment in recent years, with Elon Musk’s Neuralink raising $500 million last year and Sam Altman’s Merge Labs emerging from obscurity in January with $252 million in funding.
Neuralink and others are building devices that will enable people with severe physical disabilities to control a computer or speak with a digital voice. Epii’s technology aims to lend a hand people move their arms again.
“These patients have a very weak grip. It’s a very common problem,” says Michel Maharbiz, CEO of Epia and a professor of electrical engineering and computer science at the University of California, Berkeley. “If you could only reliably give them back control, a lot of new things would appear in their daily lives.”
Improving hand function can mean the difference between being able to dress and eat independently and needing constant care.
Epii’s disc-shaped implant is placed in the skull and detects brain signals associated with a person’s intention to move their arm. The implant will be used with a motorized grip assist glove that patients will wear during rehabilitation or at home. Neural signals are translated by AI algorithms and combined with data from external sensors placed on the glove to predict and control the gripping movement. The system learns to associate specific brain signals and contextual data with a person’s desire to open and close their hand.
The device is based on the idea of neuroplasticity, i.e. the brain’s ability to change and create fresh connections. During a stroke, blood flow to part of the brain is interrupted, depriving cells of oxygen and damaging valuable tissue. Damage to the motor area of the brain can cause paralysis and muscle weakness. When a person with paralysis tries to move, their brain still generates signals related to movement, but the injury means these signals cannot reach the muscles. The Epii implant collects neural signals from the undamaged part of the brain, determines the intention to move, and translates this intention into a movement of the hand through the glove.
“We can train the system to recognize the user’s intent in relation to the feature it is trying to compensate for,” says Maharbiz.
Repeated operate of the system can strengthen the neural pathways associated with movement, reducing the user’s dependence on the glove.
“Many brain-computer interfaces allow you to type on a computer screen or move a robotic arm to perform a task,” says David Lin, a critical care neurologist and director of the Neurorecovery Clinic at Massachusetts General Hospital, who advises the company. “This is different from a rehabilitation solution, where the use of this device itself leads to brain plasticity, which is a change in the brain and the connections to the spinal cord, such that when the glove is removed, the inherent function of the arm and hand becomes better.”
One of the obstacles in brain-computer interfaces is scalability. These devices will have to be relatively simple to implant and carry little risk for people to want to get them. Neuralink is trying to get around this problem by developing a robot that will insert its BCI. Another company, Synchron, offers a stent-like implant that is placed in a blood vessel rather than requiring brain surgery.