[{1}]]

Current neural network algorithms produce impressive results and help solve an astonishing number of problems. However, the electronic devices used to run these algorithms still require huge processing power. When it comes to real-time processing of sensory information or interaction with the environment, these artificial intelligence (AI) systems simply cannot compete with the actual brain. And neuromorphic engineering is a promising new method that builds a bridge between artificial intelligence and natural intelligence.

An interdisciplinary research team at the University of Zurich, ETH Zurich and University Hospital of Zurich used this method to develop a chip based on neuromorphic technology that can reliably and accurately identify complex biological signals. Scientists were able to use this technology to successfully detect previously recorded high-frequency oscillations (HFO). These specific waves, measured using intracranial electroencephalography (iEEG), have proven to be promising biomarkers for identifying brain tissue that causes seizures.

The researchers first designed an algorithm to detect HFO by simulating the natural neural network of the brain: a tiny so-called spike neural network (SNN). The second step is to implement SNN in a nail-sized hardware that receives neural signals through electrodes. Unlike traditional computers, it has huge energy efficiency. This makes calculations with very high time resolution possible without relying on the Internet or cloud computing.

Giacomo Indiveri, a professor at the Institute of Neuroinformatics at the University of Zurich and ETH Zurich, said: "Our design allows us to recognize spatiotemporal patterns in biological signals in real time."

The researchers are now planning to use their findings to create an electronic system to reliably identify and monitor HFOs in real time. When used as an additional diagnostic tool in the operating room, the system can improve the results of neurosurgical interventions.

However, this is not the only area where HFO identification can play an important role. The team's long-term goal is to develop a device for monitoring epilepsy that can be used outside the hospital, which will make it possible to analyze the signals of a large number of electrodes within a few weeks or months.

Johannes Sarnthein, a neurophysiologist at Zurich University Hospital, explains: “We want to integrate low-energy wireless data communication in the design - for example, to connect it to a mobile phone. A portable or implantable chip like this can recognize a higher seizure rate. High or low periods, which will allow us to provide personalized medicine.”