Artificial Intelligence Enables Real-Time and Intuitive Control of Prostheses via Nerve Interface

Diu Khue Luu; Anh Tuan Nguyen; Ming Jiang; Markus W Drealan; Jian Xu; Tong Wu; Wing kin Tam; Wenfeng Zhao; Brian Z.H. Lim; Cynthia K. Overstreet; Qi Zhao; Jonathan Cheng; Edward Keefer; Zhi Yang

doi:10.1109/TBME.2022.3160618

Artificial Intelligence Enables Real-Time and Intuitive Control of Prostheses via Nerve Interface

Diu Khue Luu, Anh Tuan Nguyen, Ming Jiang, Markus W Drealan, Jian Xu, Tong Wu, Wing kin Tam, Wenfeng Zhao, Brian Z.H. Lim, Cynthia K. Overstreet, Qi Zhao, Jonathan Cheng, Edward Keefer, Zhi Yang

Research output: Contribution to journal › Article › peer-review

13 Scopus citations

Abstract

OBJECTIVE: The next generation prosthetic hand that moves and feels like a real hand requires a robust neural interconnection between the human minds and machines.

METHODS: Here we present a neuroprosthetic system to demonstrate that principle by employing an artificial intelligence (AI) agent to translate the amputees movement intent through a peripheral nerve interface. The AI agent is designed based on the recurrent neural network (RNN) and could simultaneously decode six degree-of-freedom (DOF) from multichannel nerve data in real-time. The decoder's performance is characterized in motor decoding experiments with three human amputees.

RESULTS: First, we show the AI agent enables amputees to intuitively control a prosthetic hand with individual finger and wrist movements up to 97-98% accuracy. Second, we demonstrate the AI agent's real-time performance by measuring the reaction time and information throughput in a hand gesture matching task. Third, we investigate the AI agent's long-term uses and show the decoder's robust predictive performance over a 16-month implant duration. Conclusion & significance: Our study demonstrates the potential of AI-enabled nerve technology, underling the next generation of dexterous and intuitive prosthetic hands.

Original language	English (US)
Pages (from-to)	3051-3063
Number of pages	13
Journal	IEEE Transactions on Biomedical Engineering
Volume	69
Issue number	10
DOIs	https://doi.org/10.1109/TBME.2022.3160618
State	Published - Oct 1 2022

Bibliographical note

Publisher Copyright:
IEEE

Keywords

Artificial intelligence
Decoding
Deep learning
Electromyography
Implants
Prosthetic hand
Real-time systems
artificial intelligence
deep learning
information throughput
information transfer rate
motor decoding
neural decoder
neuroprosthesis
peripheral nerve
reaction time
Neural Networks, Computer
Artificial Intelligence
Humans
Amputees
Artificial Limbs
Hand
Movement/physiology

PubMed: MeSH publication types

Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't

Publisher link

10.1109/TBME.2022.3160618

Find It

Find It at U of M Libraries

Cite this

Luu, D. K., Nguyen, A. T., Jiang, M., Drealan, M. W., Xu, J., Wu, T., Tam, W. K., Zhao, W., Lim, B. Z. H., Overstreet, C. K., Zhao, Q., Cheng, J., Keefer, E., & Yang, Z. (2022). Artificial Intelligence Enables Real-Time and Intuitive Control of Prostheses via Nerve Interface. IEEE Transactions on Biomedical Engineering, 69(10), 3051-3063. https://doi.org/10.1109/TBME.2022.3160618

@article{d1e68c06e65c436584039af95c549f65,

title = "Artificial Intelligence Enables Real-Time and Intuitive Control of Prostheses via Nerve Interface",

abstract = "OBJECTIVE: The next generation prosthetic hand that moves and feels like a real hand requires a robust neural interconnection between the human minds and machines.METHODS: Here we present a neuroprosthetic system to demonstrate that principle by employing an artificial intelligence (AI) agent to translate the amputees movement intent through a peripheral nerve interface. The AI agent is designed based on the recurrent neural network (RNN) and could simultaneously decode six degree-of-freedom (DOF) from multichannel nerve data in real-time. The decoder's performance is characterized in motor decoding experiments with three human amputees.RESULTS: First, we show the AI agent enables amputees to intuitively control a prosthetic hand with individual finger and wrist movements up to 97-98% accuracy. Second, we demonstrate the AI agent's real-time performance by measuring the reaction time and information throughput in a hand gesture matching task. Third, we investigate the AI agent's long-term uses and show the decoder's robust predictive performance over a 16-month implant duration. Conclusion & significance: Our study demonstrates the potential of AI-enabled nerve technology, underling the next generation of dexterous and intuitive prosthetic hands.",

keywords = "Artificial intelligence, Decoding, Deep learning, Electromyography, Implants, Prosthetic hand, Real-time systems, artificial intelligence, deep learning, information throughput, information transfer rate, motor decoding, neural decoder, neuroprosthesis, peripheral nerve, reaction time, Neural Networks, Computer, Artificial Intelligence, Humans, Amputees, Artificial Limbs, Hand, Movement/physiology",

author = "Luu, {Diu Khue} and Nguyen, {Anh Tuan} and Ming Jiang and Drealan, {Markus W} and Jian Xu and Tong Wu and Tam, {Wing kin} and Wenfeng Zhao and Lim, {Brian Z.H.} and Overstreet, {Cynthia K.} and Qi Zhao and Jonathan Cheng and Edward Keefer and Zhi Yang",

note = "Publisher Copyright: IEEE",

year = "2022",

month = oct,

day = "1",

doi = "10.1109/TBME.2022.3160618",

language = "English (US)",

volume = "69",

pages = "3051--3063",

journal = "IEEE Transactions on Biomedical Engineering",

issn = "0018-9294",

publisher = "IEEE Computer Society",

number = "10",

}

TY - JOUR

T1 - Artificial Intelligence Enables Real-Time and Intuitive Control of Prostheses via Nerve Interface

AU - Luu, Diu Khue

AU - Nguyen, Anh Tuan

AU - Jiang, Ming

AU - Drealan, Markus W

AU - Xu, Jian

AU - Wu, Tong

AU - Tam, Wing kin

AU - Zhao, Wenfeng

AU - Lim, Brian Z.H.

AU - Overstreet, Cynthia K.

AU - Zhao, Qi

AU - Cheng, Jonathan

AU - Keefer, Edward

AU - Yang, Zhi

N1 - Publisher Copyright: IEEE

PY - 2022/10/1

Y1 - 2022/10/1

N2 - OBJECTIVE: The next generation prosthetic hand that moves and feels like a real hand requires a robust neural interconnection between the human minds and machines.METHODS: Here we present a neuroprosthetic system to demonstrate that principle by employing an artificial intelligence (AI) agent to translate the amputees movement intent through a peripheral nerve interface. The AI agent is designed based on the recurrent neural network (RNN) and could simultaneously decode six degree-of-freedom (DOF) from multichannel nerve data in real-time. The decoder's performance is characterized in motor decoding experiments with three human amputees.RESULTS: First, we show the AI agent enables amputees to intuitively control a prosthetic hand with individual finger and wrist movements up to 97-98% accuracy. Second, we demonstrate the AI agent's real-time performance by measuring the reaction time and information throughput in a hand gesture matching task. Third, we investigate the AI agent's long-term uses and show the decoder's robust predictive performance over a 16-month implant duration. Conclusion & significance: Our study demonstrates the potential of AI-enabled nerve technology, underling the next generation of dexterous and intuitive prosthetic hands.

AB - OBJECTIVE: The next generation prosthetic hand that moves and feels like a real hand requires a robust neural interconnection between the human minds and machines.METHODS: Here we present a neuroprosthetic system to demonstrate that principle by employing an artificial intelligence (AI) agent to translate the amputees movement intent through a peripheral nerve interface. The AI agent is designed based on the recurrent neural network (RNN) and could simultaneously decode six degree-of-freedom (DOF) from multichannel nerve data in real-time. The decoder's performance is characterized in motor decoding experiments with three human amputees.RESULTS: First, we show the AI agent enables amputees to intuitively control a prosthetic hand with individual finger and wrist movements up to 97-98% accuracy. Second, we demonstrate the AI agent's real-time performance by measuring the reaction time and information throughput in a hand gesture matching task. Third, we investigate the AI agent's long-term uses and show the decoder's robust predictive performance over a 16-month implant duration. Conclusion & significance: Our study demonstrates the potential of AI-enabled nerve technology, underling the next generation of dexterous and intuitive prosthetic hands.

KW - Artificial intelligence

KW - Decoding

KW - Deep learning

KW - Electromyography

KW - Implants

KW - Prosthetic hand

KW - Real-time systems

KW - artificial intelligence

KW - deep learning

KW - information throughput

KW - information transfer rate

KW - motor decoding

KW - neural decoder

KW - neuroprosthesis

KW - peripheral nerve

KW - reaction time

KW - Neural Networks, Computer

KW - Artificial Intelligence

KW - Humans

KW - Amputees

KW - Artificial Limbs

KW - Hand

KW - Movement/physiology

UR - http://www.scopus.com/inward/record.url?scp=85126726406&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85126726406&partnerID=8YFLogxK

U2 - 10.1109/TBME.2022.3160618

DO - 10.1109/TBME.2022.3160618

M3 - Article

C2 - 35302937

AN - SCOPUS:85126726406

SN - 0018-9294

VL - 69

SP - 3051

EP - 3063

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

IS - 10

ER -

Artificial Intelligence Enables Real-Time and Intuitive Control of Prostheses via Nerve Interface

Abstract

Bibliographical note

Keywords

PubMed: MeSH publication types

Publisher link

Find It

Other files and links

Fingerprint

Cite this