#Publications "Publications"



Motor Imagery Virtual Reality Neurorehabilitation with BCI Functional electrical stimulation Robotic rehabilitation


Irimia, D.C., Ortner, R., Poboroniuc, M.S., Ignat, B.E. and Guger, C., 2018. High classification accuracy of a motor imagery based brain-computer interface for stroke rehabilitation training. Frontiers in Robotics and AI, 5, p.130.

Guger, C., Millán, J.D.R., Mattia, D., Ushiba, J., Soekadar, S.R., Prabhakaran, V., Mrachacz-Kersting, N., Kamada, K. and Allison, B.Z., 2018. Brain-computer interfaces for stroke rehabilitation: summary of the 2016 BCI Meeting in Asilomar. Brain-Computer Interfaces, 5(2-3), pp.41-57.

Irimia, D. C., Cho, W., Ortner, R., Allison, B. Z., Ignat, B. E., Edlinger, G., & Guger, C. (2017). Brain‐computer interfaces with multi‐sensory feedback for stroke rehabilitation: a case study. Artificial organs, 41(11), E178-E184.

Cho W, Heilinger A, Xu R, Zehetner M, Schobesberger S, et al. (2017) Hemiparetic Stroke Rehabilitation Using Avatar and Electrical Stimulation Based on Non-invasive Brain Computer Interface. International Journal of Physical Medicine and Rehabilitation 5:411.

Huggins, J. E., Guger, C., Ziat, M., Zander, T. O., Taylor, D., Tangermann, M., ... & Ruffini, G. (2017). Workshops of the Sixth International Brain–Computer Interface Meeting: brain–computer interfaces past, present, and future. Brain-Computer Interfaces, 1-34.

Xu R., Allison B. Z., Ortner R., Irimia D. C., Espinosa A., Lechner A., & Guger C. (2017). How Many EEG Channels Are Optimal for a Motor Imagery Based BCI for Stroke Rehabilitation?. In Converging Clinical and Engineering Research on Neurorehabilitation II (pp. 1109-1113). Springer International Publishing.

Cho W., Sabathiel N., Ortner R., Lechner A., Irimia D.C., Allison B.Z., Edlinger G. and Guger C., 2016. Paired Associative Stimulation using Brain-Computer Interfaces for Stroke Rehabilitation: A Pilot study. European Journal of Translational Myology, 26(3).

C. Guger, C. Kapeller, R. Ortner, K. Kamada, Motor Imagery with Brain-Computer Interface Neurotechnology (pp. 61-79), in: Motor Imagery: Emerging Practices, Role in Physical Therapy and Clinical Implications, edited by B.M Garcia, 2015. 

R. Ortner, J. Scharinger, A. Lechner, C. Guger (2015). How many people can control a motor imagery based BCI using common spatial patterns?, in: 7th International IEEE/EMBS Conference on Neural Engineering (NER) 2015, pp. 202-205.

Rupert Ortner, Alexander Lechner, Christoph Guger (2015): Stroke Rehabilitation assisted by a Brain-Computer Interface (BCI) and multimodal feedback: First results. In proccedings of the European Stroke Conference, 15.05.2015, Vienna, AT. Poster.

D. C. Irimia, M. S. Poboroniuc and R. Ortner, “Improved Method to Perform FES & BCI Based Rehabilitation,” in The 4th IEEE International Conference on E-Health and Bioengineering, 2013.

C. Guger, H. Ramoser and G. Pfurtscheller, “Real-Time EEG Analysis with Subject-Specific Spatial Patterns for a Brain–Computer Interface (BCI),” IEEE Trans. Rehab. Eng, vol. 8, pp. 447-456, 2000.

K. Shindo, K. Kawashima and e. a. Ushiba, “Effects of neurofeedback training with an electroencephalogram-based brain-computer interface for hand paralysis in patients with chronic stroke: a preliminary case series study,” J Rehabil Med, pp. 951-957, 43(10) 2011.

J.C. Moreno, J. L. Pons, E. Gruenbacher, C. Guger (2010). BCI-driven stroke rehabilitation; the concept of the BETTER project..

C. Guger, W. Harkam, C. Hertnaes, G. Pfurtscheller (1999). Prosthetic control by an EEG-based brain-computer interface (BCI). 5th European Conference for the Advancement of Assitive Technolgoy Düsseldorf, Germany, AAATE.

G. Pfurtscheller, C. Guger (1999). "Brain-computer communication system: EEG-based control of hand orthosis in a tetraplegic patient." Acta Chir. Austriaca 31(159): pp. 23 - 25. Brain-computer communication system.

R. Ortner, D. Ram, A. Kollreider, H. Pitsch, J. Wojtowicz, and G. Edlinger, “Human-computer confluence for rehabilitation purposes after stroke,” in Virtual, Augmented and Mixed Reality. Systems and Applications, Springer, 2013, pp. 74–82.

R. Ortner, D.-C. Irimia, C. Guger, and G. Edlinger, “Human Computer Confluence in BCI for Stroke Rehabilitation,” in Foundations of Augmented Cognition, Springer, 2015, pp. 304–312.

A. Ramos-Murguialday, D. Broetz, M. Rea, L. Läer, O. Yilmaz, F. L. Brasil, G. Liberati, M. R. Curado, E. Garcia-Cossio, A. Vyziotis, W. Cho, M. Agostini, E. Soares, S. Soekadar, A. Caria, L. G. Cohen, and N. Birbaumer, “Brain-machine-interface in chronic stroke rehabilitation: A controlled study.,” Ann Neurol. 2013, p. doi: 10.1002/ana.23879, 2013.

Cho, W., Vidaurre, C., Hoffmann, U., Birbaumer, N., & Ramos-Murguialday, A. (2011, August). Afferent and efferent activity control in the design of brain computer interfaces for motor rehabilitation. In Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE (pp. 7310-7315). IEEE.

#Measurement-Results "Measurement Results"

Measurement Results


Patient 1

recoveriX Patient1 Figure 1
Figure 1: This patient (female, 61 years) suffered a stroke that affected right hand movement, and participated in 21 feedback sessions. This plot shows the classification error rate during the 21 sessions.
recoveriX Patient1 Figure 2
Figure 2: The recoveriX software provides a spatial map for each session that presents cortical activation during imagination of right hand movements versus left hand movements. Examples of patterns from session1 and session 13 are shown here. Regions of high activation are apparent around sites C3 and C4, corresponding to cortical representation of hand movement.
  9-hole PEG test
Session Left hand(s) Right hand(s)
0 31 65
3 32 54
6 32 45
9 31 42
12 31 42
15 29 38
18 29 34
21 29 30

Table 1: To assess the patient’s rehabilitation process, we conducted several 9-hole PEG tests, which measure the time to perform certain tasks. We collected data before the first session and repeated the test after every three sessions. The following table shows the results of the test for both hands. The time to complete the test with the affected hand decreased from 65 seconds before the treatment to 30 seconds after the last session. The completion time for the unaffected hand remained nearly constant during the whole treatment.

Patient 2

recoveriX Patient 2 Figure 3
Figure 3: The second patient (female, 40 years) suffered a stroke in May 2010 and had complete paralysis of the left hand before the first session of recoveriX rehabilitation started in 2014. After ten sessions, she could perform wrist dorsiflexion with the paralyzed hand without stimulation. The classification error rate during the ten sessions decreased from 36.3% to 3.8%.
recoveriX Patient1 Figure 4
Figure 3: The patterns of cortical activation move towards the positions of C3 and C4 for right and left hand motor imagery.
recoveriX Patient2 Figure 5

Figure 4: The patient was able to perform wrist dorsiflexion without FES stimulation after ten sessions of recoveriX rehabilitation.

#Advisory-Board "Advisory-Board"

Advisory Board

The mission is to pair recoveriX with cognitive processes and motor movements to make rehabilitation most effective.



Brendan Allison, PhD

University of California, San Diego
Allison Consulting



Prof. Marian Poboroniuc, PhD

Technical University of Iasi, Romania



Milena Korostenskaja, MD, PhD

Florida Hospital for Children, US



Vivek Prabhakaran, MD, PhD

University of Wisconsin, US



Tetsuo Ota, MD, PhD

Asahikawa Medical University, Japan



Rossella Spataro, MD, PhD

University of Palermo, Italy



Kyosuke Kamada, MD, PhD

Asahikawa Medical University, Japan



Adam Hebb, MD, PhD

Swedish Medical Center, US