Send to

Choose Destination
IEEE Trans Biomed Eng. 2017 Apr;64(4):935-945. doi: 10.1109/TBME.2016.2582691. Epub 2016 Jun 21.

A High-Performance Neural Prosthesis Incorporating Discrete State Selection With Hidden Markov Models.

Author information

Department of Electrical EngineeringStanford University.
Department of Electrical Engineering, Department of Bioengineering, and School of Medicine and NeurosurgeryStanford University.
Department of Electrical Engineering, Department of Bioengineering, and Department of NeurobiologyStanford University.


Communication neural prostheses aim to restore efficient communication to people with motor neurological injury or disease by decoding neural activity into control signals. These control signals are both analog (e.g., the velocity of a computer mouse) and discrete (e.g., clicking an icon with a computer mouse) in nature. Effective, high-performing, and intuitive-to-use communication prostheses should be capable of decoding both analog and discrete state variables seamlessly. However, to date, the highest-performing autonomous communication prostheses rely on precise analog decoding and typically do not incorporate high-performance discrete decoding. In this report, we incorporated a hidden Markov model (HMM) into an intracortical communication prosthesis to enable accurate and fast discrete state decoding in parallel with analog decoding. In closed-loop experiments with nonhuman primates implanted with multielectrode arrays, we demonstrate that incorporating an HMM into a neural prosthesis can increase state-of-the-art achieved bitrate by 13.9% and 4.2% in two monkeys ( ). We found that the transition model of the HMM is critical to achieving this performance increase. Further, we found that using an HMM resulted in the highest achieved peak performance we have ever observed for these monkeys, achieving peak bitrates of 6.5, 5.7, and 4.7 bps in Monkeys J, R, and L, respectively. Finally, we found that this neural prosthesis was robustly controllable for the duration of entire experimental sessions. These results demonstrate that high-performance discrete decoding can be beneficially combined with analog decoding to achieve new state-of-the-art levels of performance.

[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for IEEE Engineering in Medicine and Biology Society
Loading ...
Support Center