TY - GEN
T1 - Influence of artifacts on movement intention decoding from EEG activity in severely paralyzed stroke patients
AU - López-Larraz, Eduardo
AU - Bibián, Carlos
AU - Birbaumer, Niels
AU - Ramos-Murguialday, Ander
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/8/11
Y1 - 2017/8/11
N2 - Brain-machine interfaces (BMI) can be used to control robotic and prosthetic devices for rehabilitation of motor disorders, such as stroke. The calibration of these BMI systems is of paramount importance in order to establish a precise contingent link between the brain activity related to movement intention and the peripheral feedback. However, electroencephalographic (EEG) activity, commonly used to build non-invasive BMIs, can be easily contaminated by artifacts of electrical or physiological origin. The way these interferences can affect the performance of movement intention decoders has not been deeply studied, especially when dealing with severely paralyzed patients, which often generate more artifacts by compensatory movements. This paper evaluates the effects of removing artifacts from the data used to train a BMI decoder on a dataset of 28 severely paralyzed stroke patients. We show that cleaning the training datasets reduces the global BMI performance for decoding attempts of movement. Further, we demonstrate that this performance drop especially affects the test trials contaminated by artifacts (i.e., trials that might not reflect cortical activity but noise), but not the clean test trials (i.e., trials representing correct cortical activity). This paper underlines the importance of cleaning the datasets used to train BMI systems to improve their efficacy for decoding movement intention and maximize their neurorehabilitative potential.
AB - Brain-machine interfaces (BMI) can be used to control robotic and prosthetic devices for rehabilitation of motor disorders, such as stroke. The calibration of these BMI systems is of paramount importance in order to establish a precise contingent link between the brain activity related to movement intention and the peripheral feedback. However, electroencephalographic (EEG) activity, commonly used to build non-invasive BMIs, can be easily contaminated by artifacts of electrical or physiological origin. The way these interferences can affect the performance of movement intention decoders has not been deeply studied, especially when dealing with severely paralyzed patients, which often generate more artifacts by compensatory movements. This paper evaluates the effects of removing artifacts from the data used to train a BMI decoder on a dataset of 28 severely paralyzed stroke patients. We show that cleaning the training datasets reduces the global BMI performance for decoding attempts of movement. Further, we demonstrate that this performance drop especially affects the test trials contaminated by artifacts (i.e., trials that might not reflect cortical activity but noise), but not the clean test trials (i.e., trials representing correct cortical activity). This paper underlines the importance of cleaning the datasets used to train BMI systems to improve their efficacy for decoding movement intention and maximize their neurorehabilitative potential.
UR - http://www.scopus.com/inward/record.url?scp=85032178984&partnerID=8YFLogxK
U2 - 10.1109/ICORR.2017.8009363
DO - 10.1109/ICORR.2017.8009363
M3 - Conference contribution
C2 - 28813935
AN - SCOPUS:85032178984
T3 - IEEE International Conference on Rehabilitation Robotics
SP - 901
EP - 906
BT - 2017 International Conference on Rehabilitation Robotics, ICORR 2017
A2 - Ajoudani, Arash
A2 - Artemiadis, Panagiotis
A2 - Beckerle, Philipp
A2 - Grioli, Giorgio
A2 - Lambercy, Olivier
A2 - Mombaur, Katja
A2 - Novak, Domen
A2 - Rauter, Georg
A2 - Rodriguez Guerrero, Carlos
A2 - Salvietti, Gionata
A2 - Amirabdollahian, Farshid
A2 - Balasubramanian, Sivakumar
A2 - Castellini, Claudio
A2 - Di Pino, Giovanni
A2 - Guo, Zhao
A2 - Hughes, Charmayne
A2 - Iida, Fumiya
A2 - Lenzi, Tommaso
A2 - Ruffaldi, Emanuele
A2 - Sergi, Fabrizio
A2 - Soh, Gim Song
A2 - Caimmi, Marco
A2 - Cappello, Leonardo
A2 - Carloni, Raffaella
A2 - Carlson, Tom
A2 - Casadio, Maura
A2 - Coscia, Martina
A2 - De Santis, Dalia
A2 - Forner-Cordero, Arturo
A2 - Howard, Matthew
A2 - Piovesan, Davide
A2 - Siqueira, Adriano
A2 - Sup, Frank
A2 - Lorenzo, Masia
A2 - Catalano, Manuel Giuseppe
A2 - Lee, Hyunglae
A2 - Menon, Carlo
A2 - Raspopovic, Stanisa
A2 - Rastgaar, Mo
A2 - Ronsse, Renaud
A2 - van Asseldonk, Edwin
A2 - Vanderborght, Bram
A2 - Venkadesan, Madhusudhan
A2 - Bianchi, Matteo
A2 - Braun, David
A2 - Godfrey, Sasha Blue
A2 - Mastrogiovanni, Fulvio
A2 - McDaid, Andrew
A2 - Rossi, Stefano
A2 - Zenzeri, Jacopo
A2 - Formica, Domenico
A2 - Karavas, Nikolaos
A2 - Marchal-Crespo, Laura
A2 - Reed, Kyle B.
A2 - Tagliamonte, Nevio Luigi
A2 - Burdet, Etienne
A2 - Basteris, Angelo
A2 - Campolo, Domenico
A2 - Deshpande, Ashish
A2 - Dubey, Venketesh
A2 - Hussain, Asif
A2 - Sanguineti, Vittorio
A2 - Unal, Ramazan
A2 - Caurin, Glauco Augusto de Paula
A2 - Koike, Yasuharu
A2 - Mazzoleni, Stefano
A2 - Park, Hyung-Soon
A2 - Remy, C. David
A2 - Saint-Bauzel, Ludovic
A2 - Tsagarakis, Nikos
A2 - Veneman, Jan
A2 - Zhang, Wenlong
PB - IEEE Computer Society
T2 - 2017 International Conference on Rehabilitation Robotics, ICORR 2017
Y2 - 17 July 2017 through 20 July 2017
ER -
