Enhanced control of a brain-computer interface by tetraplegic participants via neural-network-mediated feature extraction

Benyamin Haghi; Tyson Aflalo; Spencer Kellis; Charles Guan; Jorge A Gamez de Leon; Albert Yan Huang; Nader Pouratian; Richard A Andersen; Azita Emami

doi:10.1038/s41551-024-01297-1

Enhanced control of a brain-computer interface by tetraplegic participants via neural-network-mediated feature extraction

Nat Biomed Eng. 2024 Dec 6. doi: 10.1038/s41551-024-01297-1. Online ahead of print.

Authors

Benyamin Haghi^#¹, Tyson Aflalo^#², Spencer Kellis^{3

4

5}, Charles Guan³, Jorge A Gamez de Leon³, Albert Yan Huang⁶, Nader Pouratian^{7

8}, Richard A Andersen³, Azita Emami^{9

10}

Affiliations

¹ Department of Electrical Engineering, California Institute of Technology, Pasadena, CA, USA. [email protected].
² Division of Biology and Biological Engineering, California Institute of Technology, Pasadena, CA, USA. [email protected].
³ Division of Biology and Biological Engineering, California Institute of Technology, Pasadena, CA, USA.
⁴ Neurostimulation Center and Neurosurgery, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA.
⁵ Blackrock Microsystems, Salt Lake City, UT, USA.
⁶ Department of Electrical Engineering, California Institute of Technology, Pasadena, CA, USA.
⁷ UT Southern Medical Center, Dallas, TX, USA.
⁸ UCLA Neurosurgery, University of California Los Angeles, Los Angeles, CA, USA.
⁹ Department of Electrical Engineering, California Institute of Technology, Pasadena, CA, USA. [email protected].
¹⁰ Andrew and Peggy Cherng Department of Medical Engineering, California Institute of Technology, Pasadena, CA, USA. [email protected].

^# Contributed equally.

PMID: 39643728
DOI: 10.1038/s41551-024-01297-1

Abstract

To infer intent, brain-computer interfaces must extract features that accurately estimate neural activity. However, the degradation of signal quality over time hinders the use of feature-engineering techniques to recover functional information. By using neural data recorded from electrode arrays implanted in the cortices of three human participants, here we show that a convolutional neural network can be used to map electrical signals to neural features by jointly optimizing feature extraction and decoding under the constraint that all the electrodes must use the same neural-network parameters. In all three participants, the neural network led to offline and online performance improvements in a cursor-control task across all metrics, outperforming the rate of threshold crossings and wavelet decomposition of the broadband neural data (among other feature-extraction techniques). We also show that the trained neural network can be used without modification for new datasets, brain areas and participants.