Event Abstract Back to Event Towards high performance communication using intracortical brain-computer interfaces Chethan Pandarinath1, 2, 3, Paul Nuyujukian1, 3, 4, 5, Vikash Gilja1, 6, Christine Blabe1, 3, Beata Jarosiewicz7, 8, 9, Leigh Hochberg7, 8, 10, 11, 12, Janos Perge7, 8, 10, Krishna V. Shenoy2, 3, 4, 13, 14 and Jaimie Henderson1, 3* 1 Stanford University, Neurosurgery, United States 2 Stanford University, Electrical Engineering, United States 3 Stanford University, Stanford Neurosciences Institute, United States 4 Stanford University, Bioengineering, United States 5 Stanford University, School of Medicine, United States 6 University of California, San Diego, Electrical and Computer Engineering, United States 7 Brown University, Institute for Brain Science, United States 8 Center for Neurorestoration and Neurotechnology, Department of VA Medical Center, United States 9 Brown University, Department of Neuroscience, United States 10 Brown University, United States 11 Massachusetts General Hospital, Neurology, United States 12 Harvard Medical School, Neurology, United States 13 Stanford University, Neurosciences Program, United States 14 Stanford University, Department of Neurobiology, United States An important potential application for Brain Computer Interfaces (BCIs) is the control of computer cursors and keyboards for the restoration of communication. Here we describe the development and application of one such BCI for use by a participant with Amyotrophic Lateral Sclerosis (ALS), as part of the BrainGate2 FDA Pilot clinical trial. Participant T6 is a 51 yr old woman with declining motor function due to slowly-progressive ALS. She was implanted with a 96-channel electrode array (Blackrock microsystems) in the hand knob area of dominant motor cortex. The data presented here were collected more than 16 months post-implantation. Spiking activity and high-frequency local field potential power (150-450Hz) were extracted for use as control signals. The ReFIT Kalman Filter (Gilja*, Nuyujukian* et al., Nature Neuroscience, 2012) was used for continuous 2-dimensional control. Further, to achieve full “point-and-click” control of the computer interface, we added an algorithm for detecting transitions between movement and click-states, the Hidden Markov Model (HMM; Nuyujukian et al., SfN 2012). The participant generated a volitional click signal by attempting to squeeze her non-dominant hand (ipsilateral to the implanted array). At each time step, the HMM estimated the likelihood of the click state based on a multivariate Gaussian model of the neural data, combined with the prior probability of state transitions. Performance of the combined point-and-click interface was measured using three tasks – 1) a “grid” task, in which the participant acquired randomly presented targets on a 6x6 square grid, 2) a “qwerty” typing task, which used a QWERTY-keyboard layout, and 3) an “opti” typing task, which used the optimized “OPTI-II” layout (Rick, Proc UIST 2010). In the both typing tasks, the participant was able to type several prompted phrases without the assistance of word prediction or completion. These results demonstrate the successful translation and application of high-performance BCI methods for continuous control and discrete selection. This promising point-and-click interface might serve as a practical method to restore communication for persons with severe paralysis Keywords: intracortical, Brain-computer interface, High performance communication, Amyotrophic lateral sclerosis (ALS), BrainGate2 Conference: 2015 International Workshop on Clinical Brain-Machine Interfaces (CBMI2015), Tokyo, Japan, 13 Mar - 15 Mar, 2015. Presentation Type: Poster 2-4 Topic: Clinical Brain-Machine Interfaces Citation: Pandarinath C, Nuyujukian P, Gilja V, Blabe C, Jarosiewicz B, Hochberg L, Perge J, Shenoy KV and Henderson J (2015). Towards high performance communication using intracortical brain-computer interfaces. Conference Abstract: 2015 International Workshop on Clinical Brain-Machine Interfaces (CBMI2015). doi: 10.3389/conf.fnhum.2015.218.00003 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 23 Apr 2015; Published Online: 29 Apr 2015. * Correspondence: Dr. Jaimie Henderson, Stanford University, Neurosurgery, Stanford, CA, United States, bpedrick@stanford.edu Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Chethan Pandarinath Paul Nuyujukian Vikash Gilja Christine Blabe Beata Jarosiewicz Leigh Hochberg Janos Perge Krishna V Shenoy Jaimie Henderson Google Chethan Pandarinath Paul Nuyujukian Vikash Gilja Christine Blabe Beata Jarosiewicz Leigh Hochberg Janos Perge Krishna V Shenoy Jaimie Henderson Google Scholar Chethan Pandarinath Paul Nuyujukian Vikash Gilja Christine Blabe Beata Jarosiewicz Leigh Hochberg Janos Perge Krishna V Shenoy Jaimie Henderson PubMed Chethan Pandarinath Paul Nuyujukian Vikash Gilja Christine Blabe Beata Jarosiewicz Leigh Hochberg Janos Perge Krishna V Shenoy Jaimie Henderson Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.