Event Abstract

Back to Event

Advanced Machine Learning for classification of EEG traits as Parkinson’s biomarker

Javier Marin1, Aureli Soria-Frisch1*, David Ibáñez1, Stephen Dunne1, Carles Grau1, Giulio Ruffini1, Jessica Rodrigues-Brazète2, 3, Ron Postuma2, 3, Jean-François Gagnon2, 3, Jacques Montplaisir2, 4 and Alvaro Pascual-Leone4
  • 1 Starlab Barcelona SL, Spain
  • 2 Hopital du Sacre-Coeur, Montreal, Centre d'Études Avancées en Médecine du Sommeil, Canada
  • 3 Université de Montréal, Department of Psychiatry, Canada
  • 4 Beth Israel Deaconess Medical Center and Harvard Medical School, Berenson-Allen Center for Noninvasive Brain Stimulation, United States

We aim to develop non-invasive, low-cost preclinical markers for synucleinopathies (Parkinson’s Disease - PD or Dementia with Lewy Bodies - DLB) with impact on neuroprotection. In a first stage we have applied Machine Learning techniques to the analysis of the spontaneous, waking EEG of REM Sleep Behavior Disorder (RBD) patients. We know that patients with RBD may evolve towards PD and other synucleinopathies (i.e. DLB) providing a useful guide in the search for biomarkers. EEG has proven to be sensitive to brain alterations related to both RBD and PD patients, and it is known that patients with either RBD or de novo PD without obvious cognitive alterations show similar EEG/MEG alterations (mainly slowing of the EEG) while awake. In the work described herein we achieve the classification of patients according to their ultimate diagnosis, differentiating among different patient groups. We have analyzed EEG data from a study of RBD patients at the Center for Advanced Research in Sleep Medicine of Montréal. The EEG was recorded from 8 patients who years later evolved to PD, 8 patients who later evolved to LBD, 10 patients with RBD who did not convert, and 17 healthy controls. It is worth mentioning that 80% of the PD and DLB patients developed disease at a follow-up of 8 years. Support Vector Machines were applied to different feature types. Absolute Band Power features extracted each 4 seconds outperform the other ones. After non-parametric feature selection of the 5 most discriminative channel-band combinations, classification was applied. A procedure for performance estimation close to operational conditions, which is denoted as leave-pair-subjects-out, has been employed for evaluation of the implemented system. Excellent performance levels, AUC 93.75-99%, were obtained for all realized group comparisons. In conclusion, we believe that these results support the idea that classification of EEG shows great potential as a preclinical biomarker. Our results confirm the existent literature, where EEG slowing characterizes RBD and PD/DLB patients. Furthermore we have attained this characterization at the individual subject level for the first time by employing machine learning. Given that EEG was acquired 8 years before disease development in a majority of cases, we believe that the utilization of the developed system for conversion prognosis of synucleinopathies (PD or DLB) will have real impact on both early treatment and drug development.

Figure 1
Image
Figure 2
Image
Figure 3
Image

Acknowledgements

The described work has been partially funded by The Michael J. Fox Foundation for Parkinson’s Research under Rapid Response Innovation Awards 2013.

References

N. Japkowicz and M. Shah (2011). “Evaluating Learning Algorithms: A classification perspective”, Cambridge University Press
Livia Fantini, M., Gagnon, J. F., Petit, D., Rompré, S., Décary, A., Carrier, J., & Montplaisir, J. (2003). Slowing of electroencephalogram in rapid eye movement sleep behavior disorder. Annals of neurology, 53(6), 774-780.
Iranzo, A., Isetta, V., Molinuevo, J. L., Serradell, M., Navajas, D., Farre, R., & Santamaria, J. (2010). Electroencephalographic slowing heralds mild cognitive impairment in idiopathic REM sleep behavior disorder. Sleep medicine, 11(6), 534-539.
Liang, Sheng-Fu, Hsu-Chuan Wang, and Wan-Lin Chang (2010). "Combination of EEG complexity and spectral analysis for epilepsy diagnosis and seizure detection." EURASIP Journal on Advances in Signal Processing 2010 : 62.
Chaovalitwongse, Wanpracha Art, Rebecca S. Pottenger, Shouyi Wang, Ya-Ju Fan, and Leon D. Iasemidis (2011). "Pattern-and Network-Based Classification Techniques for Multichannel Medical Data Signals to Improve Brain Diagnosis." Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on 41, no. 5 : 977-988.
Khodayari-Rostamabad, Ahmad, Gary M. Hasey, Duncan J. MacCrimmon, James P. Reilly, and Hubert de Bruin (2010). "A pilot study to determine whether machine learning methodologies using pre- treatment electroencephalography can predict the symptomatic response to clozapine therapy." Clinical Neurophysiology 121, no. 12 : 1998-2006.
A. Airola; T. Pahikkala, W. Waegeman, B. De Baets, and T. Salakoski. “A comparison of AUC estimators in small-sample studies”, Journal of Machine Learning Research - Proceedings Track, 8, 3 – 13 (2010)
Fawcett, T. (2004). ROC graphs: Notes and practical considerations for researchers. Machine learning, 31, 1-38.
J. A. Hanley and B. J. McNeil (1982). “The meaning and use of the area under the receiver operating characteristic (ROC) curve”, in Radiology, 143, 29 – 36
Iranzo, A., Tolosa, E., Gelpi, E., Molinuevo, J. L., Valldeoriola, F., Serradell, M., ... & Santamaria, J. (2013). Neurodegenerative disease status and post-mortem pathology in idiopathic rapid-eye-movement sleep behaviour disorder: an observational cohort study. The Lancet Neurology, 12(5), 443-453.

Keywords: Parkinson’s biomarkers, machine learning, Neuroprotection, prognosis system, Electroencephalography (EEG)

Conference: Neuroinformatics 2014, Leiden, Netherlands, 25 Aug - 27 Aug, 2014.

Presentation Type: Poster, to be considered for oral presentation

Topic: Clinical neuroscience

Citation: Marin J, Soria-Frisch A, Ibáñez D, Dunne S, Grau C, Ruffini G, Rodrigues-Brazète J, Postuma R, Gagnon J, Montplaisir J and Pascual-Leone A (2014). Advanced Machine Learning for classification of EEG traits as Parkinson’s biomarker. Front. Neuroinform. Conference Abstract: Neuroinformatics 2014. doi: 10.3389/conf.fninf.2014.18.00071

Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.

The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.

Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.

For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.

Received: 28 Apr 2014; Published Online: 04 Jun 2014.

* Correspondence: Dr. Aureli Soria-Frisch, Starlab Barcelona SL, Barcelona, Spain, aureli.soria-frisch@starlab.es