According to a report from major media, the study, published in Nature Communications, addresses a key challenge for amputees. ' For leg amputees, it is more common with prostheses without any active control from the user, unlike arm or hand prostheses which are often controlled via muscles, but this requires that the relevant muscles remain. Valle and his colleagues hope to change this.
' In the study, researchers placed four electronic neural implants in the test subjects' sciatic nerve. The implants are as thin as a hair strand and flexible. With the help of a new AI method, they could then interpret the nerve signals registered by the implant.
One of the biggest challenges for amputees is that they need a way to control their prosthesis.
The method is based on so-called spiking neural networks (SNN), which means that information transfer occurs through short signals instead of a long signal. ' Using the method, researchers could interpret very detailed intended movements in the test subjects—even movements as small as the intention to wiggle toes. ' However, the technique cannot yet be used in reality.
The study is a so-called 'proof of concept,' a study that tests a technique and shows that it is feasible, and it was only done on two test subjects. ' The specific improvements in functionality or quality of life for amputees using this technology are not yet detailed, and it is unknown how long it will take to develop and test this technology for real-world use in prostheses. Potential risks or side effects of implanting neural devices in the sciatic nerve also remain unclear.
All the information needed to control our body parts remains in the nerves, even if the body part is no longer there, but those signals need to be decoded.
The study represents a step toward more intuitive prosthetic control, with further research needed to address these unknowns.
The technique differs from the common AI systems we are used to, such as ChatGPT or image recognition systems.
These spikes resemble the way our nervous system communicates, and it is inspired by our biology, which makes it possible to understand how the brain communicates.
We have cracked the code.
The next step is to integrate the technique with prostheses, use it in a more realistic everyday scenario, and ensure that it is truly functional and something that patients can benefit from.