Ecole Polytechnique Fédérale de Lausanne (EPFL)researchers have combined low-power chip design, machine learning algorithms, and soft implantable electrodes to produce a neural interface that can identify and manage various neurological disorders.
Mahsa Shoaran of the Integrated Neurotechnologies Laboratory in the School of Engineering collaborated with Stephanie Lacour in the Laboratory for Soft Bioelectronic interfaces to develop NeuralTree.
NeuralTree: a closed-loop neuromodulation system on a chip that can detect and decrease disease systems. It is built on a 256-channel high-resolution sensing array and an energy-efficient machine-learning processor.
Moreover, this system can extract and classify a broad set of biomarkers from real patient data and animal models of that respective disease. In short, by using these techniques this system works with a high degree of accuracy in symptom prediction.
While explaining his project Shoaran said that “It’s the first time we’ve been able to integrate such a complex, yet energy-efficient neural interface for binary classification tasks, such as seizure or tremor detection, as well as multi-class tasks such as finger movement classification for neuroprosthetic applications.”
Neurochips are basically brain machines that imitate the functioning of synapses. It allows the interaction of the human brain with computers. However, their data processing speed is still a little bit slower than the Human brain itself but scientists are still working to make more advancements in this particular area.
It is one of the most advanced leading technologies that is being used in the rehabilitation of nervous disorders. Although, it is not really used in all types of hospitals. But scientists and doctors are working day and night, in order to spread this technology as much as they can.
On this account, researchers from EPFL have taken a step further with the development of NeuralTree. It works by extracting neural biomarkers usually present in CSF (Cerebrospinal Fluid) inside the brain. These biomarkers are associated with patterns of electrical signals which are specific to specific disorders.
NeuralTree classifies these signals and detects their biological cause such as epileptic seizures and Parkinson etc. After detection, neurotransmitters that are present on the chip get activated. These neurotransmitters work by blocking these impulses and hence will lead to managing involuntary brain movements.
Until now, this device is focusing primarily on epileptic seizures. However, they have the view of extending this project to other brain disorders as well. As Shoaran said that “To the best of our knowledge, this is the first demonstration of Parkinsonian tremor detection with an on-chip classifier.”
Furthermore, shoaran is interested in making more advancements by creating self-updating algorithms. Self-updating algorithms will make this machine way more advanced than any other neurochip. As she already knows that neural signals keep on changing with changing times. That will lead to a decline in neuro chip performance.
If these scientists come up with a self-updating algorithm that will enable this neurochip to be more advanced. Because changing neurochip again and again after some time is very difficult. So, it is the best choice to have a self-updating neurochip that can update itself without any human involvement.
In short, if we sum up the entire above discussion, we can conclude that the medical field is going to be more advanced in the upcoming years. Neurochips are going to take the medical field by storm. And to be honest, inserting soft implantable neurochips is the best possible method to manage and control neural disabilities and disorders.