000229467 001__ 229467
000229467 005__ 20190117191929.0
000229467 0247_ $$2doi$$a10.1088/1741-2552/aa7df9
000229467 022__ $$a1741-2560
000229467 02470 $$2ISI$$a000411464500002
000229467 037__ $$aARTICLE
000229467 245__ $$aBrain-actuated gait trainer with visual and proprioceptive feedback
000229467 260__ $$aBristol$$bInstitute of Physics$$c2017
000229467 269__ $$a2017
000229467 300__ $$a10
000229467 336__ $$aJournal Articles
000229467 520__ $$aObjective. Brain-machine interfaces (BMIs) have been proposed in closed-loop applications for neuromodulation and neurorehabilitation. This study describes the impact of different feedback modalities on the performance of an EEG-based BMI that decodes motor imagery (MI) of leg flexion and extension. Approach. We executed experiments in a lower-limb gait trainer (the legoPress) where nine able-bodied subjects participated in three consecutive sessions based on a crossover design. A random forest classifier was trained from the offline session and tested online with visual and proprioceptive feedback, respectively. Post-hoc classification was conducted to assess the impact of feedback modalities and learning effect (an improvement over time) on the simulated trial-based performance. Finally, we performed feature analysis to investigate the discriminant power and brain pattern modulations across the subjects. Main Results. (i) For real-time classification, the average accuracy was 62.33 ± 4.95% and 63.89 ± 6.41% for the two online sessions. The results were significantly higher than chance level, demonstrating the feasibility to distinguish between MI of leg extension and flexion. (ii) For post-hoc classification, the performance with proprioceptive feedback (69.45 ± 9.95%) was significantly better than with visual feedback (62.89 ± 9.20%), while there was no significant learning effect. (iii) We reported individual discriminate features and brain patterns associated to each feedback modality, which exhibited differences between the two modalities although no general conclusion can be drawn. Significance. The study reported a closed-loop brain-controlled gait trainer, as a proof of concept for neurorehabilitation devices. We reported the feasibility of decoding lower-limb movement in an intuitive and natural way. As far as we know, this is the first online study discussing the role of feedback modalities in lower-limb MI decoding. Our results suggest that proprioceptive feedback has an advantage over visual feedback, which could be used to improve robot-assisted strategies for motor training and functional recovery.
000229467 6531_ $$abrain-machine interface
000229467 6531_ $$aelectroencephalography
000229467 6531_ $$alower-limb rehabilitation
000229467 6531_ $$aproprioceptive feedback
000229467 700__ $$aLiu, Dong
000229467 700__ $$aChen, Weihai
000229467 700__ $$0248172$$aLee, Kyuhwa$$g244361
000229467 700__ $$0241256$$aChavarriaga, Ricardo$$g137762
000229467 700__ $$0242134$$aBouri, Mohamed$$g114980
000229467 700__ $$aPei, Zhongcai
000229467 700__ $$0240030$$aMillán, José del R.$$g149175
000229467 773__ $$j14$$k5$$q056017$$tJournal of Neural Engineering
000229467 909C0 $$0252018$$pCNBI$$xU12103
000229467 909C0 $$0252409$$pNCCR-ROBOTICS$$xU12367
000229467 909CO $$ooai:infoscience.tind.io:229467$$pSTI$$particle
000229467 917Z8 $$x137762
000229467 917Z8 $$x137762
000229467 917Z8 $$x137762
000229467 917Z8 $$x148230
000229467 937__ $$aEPFL-ARTICLE-229467
000229467 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000229467 980__ $$aARTICLE