Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 May 27;13(6):866.
doi: 10.3390/brainsci13060866.

Machine Learning-Based Classification to Disentangle EEG Responses to TMS and Auditory Input

Andrea Cristofari  1 , Marianna De Santis  2 , Stefano Lucidi  2 , John Rothwell  3 , Elias P Casula  4 , Lorenzo Rocchi  3   5
Affiliations

Machine Learning-Based Classification to Disentangle EEG Responses to TMS and Auditory Input

Andrea Cristofari et al. Brain Sci. .

Abstract

The combination of transcranial magnetic stimulation (TMS) and electroencephalography (EEG) offers an unparalleled opportunity to study cortical physiology by characterizing brain electrical responses to external perturbation, called transcranial-evoked potentials (TEPs). Although these reflect cortical post-synaptic potentials, they can be contaminated by auditory evoked potentials (AEPs) due to the TMS click, which partly show a similar spatial and temporal scalp distribution. Therefore, TEPs and AEPs can be difficult to disentangle by common statistical methods, especially in conditions of suboptimal AEP suppression. In this work, we explored the ability of machine learning algorithms to distinguish TEPs recorded with masking of the TMS click, AEPs and non-masked TEPs in a sample of healthy subjects. Overall, our classifier provided reliable results at the single-subject level, even for signals where differences were not shown in previous works. Classification accuracy (CA) was lower at the group level, when different subjects were used for training and test phases, and when three stimulation conditions instead of two were compared. Lastly, CA was higher when average, rather than single-trial TEPs, were used. In conclusion, this proof-of-concept study proposes machine learning as a promising tool to separate pure TEPs from those contaminated by sensory input.

Keywords: TMS-EEG; electroencephalography; evoked potentials; machine learning; neural networks; transcranial magnetic stimulation.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Butterfly plots (left row) and topographical plots of TEPs in the early, middle, and late ToIs, and three different stimulation conditions (C1–TEP masked, upper row; C2–AEP, middle row; C3–TEP not masked, lower row).
Figure 2
Figure 2
Example of 5-fold cross validation (see text for details).
Figure 3
Figure 3
Structure of the different numerical experiments (see Materials and Methods section for details).
Figure 4
Figure 4
Average TEPs recorded from electrode CP3 (upper row) and FCz (lower row) in the three different stimulation conditions (C1−TEP masked; C2−AEP; C3−TEP not masked).
Figure 5
Figure 5
Example of single-trial and average TEPs, from a single subject, recorded from electrode Cz in the three different stimulation conditions (C1−TEP masked; C2−AEP; C3−TEP not masked).
Figure 6
Figure 6
Trends of classification accuracy in the different ToIs (A), stimulation conditions (B), and numerical experiments (C).
See this image and copyright information in PMC

References

    1. Maiella M., Casula E.P., Borghi I., Assogna M., D’acunto A., Pezzopane V., Mencarelli L., Rocchi L., Pellicciari M.C., Koch G. Simultaneous transcranial electrical and magnetic stimulation boost gamma oscillations in the dorsolateral prefrontal cortex. Sci. Rep. 2022;12:19391. doi: 10.1038/s41598-022-23040-z. - DOI - PMC - PubMed
    1. Casula E.P., Leodori G., Ibáñez J., Benussi A., Rawji V., Tremblay S., Latorre A., Rothwell J.C., Rocchi L. The Effect of Coil Orientation on the Stimulation of the Pre–Supplementary Motor Area: A Combined TMS and EEG Study. Brain Sci. 2022;12:1358. doi: 10.3390/brainsci12101358. - DOI - PMC - PubMed
    1. Rawji V., Kaczmarczyk I., Rocchi L., Fong P.-Y., Rothwell J.C., Sharma N. Preconditioning Stimulus Intensity Alters Paired-Pulse TMS Evoked Potentials. Brain Sci. 2021;11:326. doi: 10.3390/brainsci11030326. - DOI - PMC - PubMed
    1. Hernandez-Pavon J.C., Veniero D., Bergmann T.O., Belardinelli P., Bortoletto M., Casarotto S., Casula E.P., Farzan F., Fecchio M., Julkunen P., et al. TMS combined with EEG: Recommendations and open issues for data collection and analysis. Brain Stimul. 2023;16:567–593. doi: 10.1016/j.brs.2023.02.009. - DOI - PubMed
    1. Leodori G., De Bartolo M.I., Guerra A., Fabbrini A., Rocchi L., Latorre A., Paparella G., Belvisi D., Conte A., Bhatia K.P., et al. Motor Cortical Network Excitability in Parkinson’s Disease. Mov. Disord. 2022;37:734–744. doi: 10.1002/mds.28914. - DOI - PubMed

LinkOut - more resources