Medical News Observer

Researchers from École Polytechnique Fédérale de Lausanne have developed NeuralTree, a closed-loop neuromodulation system-on-chip that detects and alleviates disease symptoms.

It uses a 256-channel high-resolution sensing array and an energy-efficient machine-learning processor to extract and classify biomarkers for accuracy in symptom prediction. It uses data from real patients’ EEG and iEEG epilepsy datasets, as well as a rat model of epilepsy.

NeuralTree can perform binary classification tasks such as seizure detection or multi-class tasks like finger movement classification for neuroprosthetics. The chip is more efficient, scalable, and versatile than state-of-the-art devices and can detect a wider range of symptoms, including Parkinsonian tremors.

Ref: U. Shin et al., “NeuralTree: A 256-Channel 0.227-μJ/Class Versatile Neural Activity Classification and Closed-Loop Neuromodulation SoC,” in IEEE Journal of Solid-State Circuits, vol. 57, no. 11, pp. 3243-3257, Nov. 2022, doi: 10.1109/JSSC.2022.3204508.