Swiss researchers were able to use AI in implants that acted as a bridge between the spine and brain, allowing a paralyzed man to walk. Since 2011, a man by the name of Gert-Jan Oskam had been paralyzed from the hips down after a motorcycle accident.
Due to the accident, his spine had become injured and communication between it and his brain had been broken. But thanks to this new technology, he was able to walk once again according to a report by AI Business.
The man commented about the effectiveness of the AI tool, “Within five to 10 minutes I could control my hips…The brain implants picked up what I was doing with my hips, so it was like the best outcome for everyone.”
The device that is allowing for Mr. Oskam to walk is called a brain-spine interface. And according to the report, it’s able to use the thoughts of those paralyzed, such as Mr. Oskam, and with the aid of external computers, sent a spinal implant back into Mr. Oskam which lets him walk.
Though the use of probes and spinal implants isn’t exactly new when it comes to research related to aiding those who are paralyzed, the key is a thought decoder. Well, specifically, a machine learning-powered thought decoder.
But how does it work? Well according to the report, researchers at the University of Texas at Austin used a functional MRI scanner to record blood oxygen levels of patients. Primarily while they were listening to podcasts. Then, they took that data to train a large language model to match the brain activity with words and phrases heard by patients.
Then, the Swiss researchers took that to the next level, building on the work done by their colleagues in Austin, and developed the brain-spine interface. Jocelyne Bloch, a neuroscientist at the University of Lausanne in Switzerland, said of the research, “It was quite science fiction in the beginning for me, but it became true today.”
Nandan Lad, a neurosurgeon at Duke University, said of the research, “It’s still very much the early days, but as a proof of concept in a human being, I think it’s a huge step forward.” Well, he’s not wrong. The ability to use machine learning models to “decode” human thoughts could go a long way in not only helping those paralyzed, and it doesn’t take a lot of imagination to think of other uses that could help the medical field.
As for Gert-Jan Oskam, he has spent a year testing the device that is allowing him to walk. One interesting side effect of using the AI-powered interface is that even after the machine is turned off, he can walk with the aid of crutches.
You can watch a video on Gert-Jan Oskam’s story From ABC below: