Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published October 2015 | public
Journal Article Open

An Active Learning Algorithm for Control of Epidural Electrostimulation


Epidural electrostimulation has shown promise for spinal cord injury therapy. However, finding effective stimuli on the multi-electrode stimulating arrays employed requires a laborious manual search of a vast space for each patient. Widespread clinical application of these techniques would be greatly facilitated by an autonomous, algorithmic system which choses stimuli to simultaneously deliver effective therapy and explore this space. We propose a method based on GP-BUCB, a Gaussian process bandit algorithm. In n = 4 spinally transected rats, we implant epidural electrode arrays and examine the algorithm's performance in selecting bipolar stimuli to elicit specified muscle responses. These responses are compared with temporally interleaved intra-animal stimulus selections by a human expert. GP-BUCB successfully controlled the spinal electrostimulation preparation in 37 testing sessions, selecting 670 stimuli. These sessions included sustained autonomous operations (ten-session duration). Delivered performance with respect to the specified metric was as good as or better than that of the human expert. Despite receiving no information as to anatomically likely locations of effective stimuli, GP-BUCB also consistently discovered such a pattern. Further, GP-BUCB was able to extrapolate from previous sessions' results to make predictions about performance in new testing sessions, while remaining sufficiently flexible to capture temporal variability. These results provide validation for applying automated stimulus selection methods to the problem of spinal cord injury therapy.

Additional Information

© 2015 IEEE. Manuscript received December 15, 2014; revised March 30, 2015; accepted April 28, 2015. Date of publication May 12, 2015; date of current version September 16, 2015. This work was supported by under Grant NIH U01EB15521, Grant R01EB007615, the Leona M. and Harry B. Helmsley Charitable Trust, the Christopher and Dana Reeve, Broccoli, Walkabout, and F. M. Kirby Foundations. J. Choe and P. Gad contributed equally to this work. The authors would like to thank Y. Sui and M. Rath for their assistance in executing the experiments. V. R. Edgerton, R. R. Roy, and J. W. Burdick hold shareholder interest in NeuroRecovery Technologies (NRT) and hold certain inventorship rights on intellectual property licensed by The Regents of the University of California to NRT and its subsidiaries. V. R. Edgerton is also the President and Chairman of the Board. A patent has been submitted covering concepts described here.

Attached Files

Accepted Version - nihms-725357.pdf


Files (1.1 MB)
Name Size Download all
1.1 MB Preview Download

Additional details

August 20, 2023
August 20, 2023