Researchers have developed a system that can identify and manage neurological disorders with its machine learning ability.
Neurotechnology is believed to impact human lives in a very revolutionary way. The technologies we see in our future through science fiction are greatly dependent on how we interpret data and focus them towards the future. To understand this researchers have begun the study by understanding the normal behavior and abnormalities as well. Current studies around the world are focusing more on how to eliminate neural abnormalities by introducing various technologies into this field of science.
One such study was conducted by a team of researchers at Ecole Polytechnique Fédérale de Lausanne lead by Mahsa Shoaran of the Integrated Neurotechnologies Laboratory with Stéphanie Lacour in the Laboratory for Soft Bioelectronic Interfaces to develop NeuralTree: a closed-loop neuromodulation system-on-chip that can detect and alleviate disease symptoms. The system can extract and classify a broad set of biomarkers from real patient data and animal models of disease in-vivo, leading to a high degree of accuracy in symptom prediction. The system consists of a 256-channel high-resolution input sensing array and an energy-efficient machine learning processor.
Biomarkers are patterns of electrical signals known to be associated with certain neurological disorders. These patterns are extracted and classified to identify the possibility of disorders like epileptic seizure or Parkinsonian tremor. If a symptom is detected, a neurostimulator — also located on the chip — is activated, sending an electrical pulse to block it.
The chip’s area-efficient design means that it is also extremely small (3.48mm2), giving it great potential for scalability to more channels. The integration of an ‘energy-aware’ learning algorithm — which penalizes features that consume a lot of power — also makes NeuralTree highly energy efficient.
The system can detect a broader range of symptoms than other devices, which until now have focused primarily on epileptic seizure detection. The chip’s machine learning algorithm was trained on datasets from both epilepsy and Parkinson’s disease patients, and accurately classified pre-recorded neural signals from both categories. Researchers also plan to enable on-chip algorithmic updates to keep up with the evolution of neural signals.
Reference : NeuralTree: A 256-Channel 0.227-μJ/Class Versatile Neural Activity Classification and Closed-Loop Neuromodulation SoC. IEEE Journal of Solid-State Circuits, 2022; 57 (11): 3243 DOI: 10.1109/JSSC.2022.3204508
