EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning Decoding of Dystonic States from EEG-LFP Signals in GPi-DBS: A Multimodal Case Study

Elisa Barbi, Edoardo Fino, Chiara Rossi, Andrea Di Rita, Simone Peraio, Alice Noris, Sara Ciabattini, Marta Lazzeri, Federico Melani, Matteo Lenge, Flavio Giordano, Luca Mesin

Bioengineering · 06.11.2026 · 13 (11) · 1313

DOI: 10.3390/bioengineering13111313 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 06.11.2026. Verfasst von Elisa Barbi und 11 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Plan for Complementary Investments to the PNRR Hub Life Science-Digital Health.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Programming Deep Brain Stimulation (DBS) for pediatric dystonia remains largely empirical, as no validated electrophysiological biomarker currently guides parameter selection, and most studies treat each signal modality separately rather than exploiting their joint structure.

Methods

In a single pediatric patient with generalized dystonia and bilateral globus pallidus internus (GPi) DBS implantation, we synchronized electroencephalography (EEG), local field potential (LFP), and electromyography (EMG) recordings across seven sessions spanning stimulator-OFF and multiple stimulation intensities. Dystonic muscle activity labels were derived from a validated quantitative EMG pipeline. Regularized logistic regression classifiers, trained on EEG-only, LFP-only, and combined EEG-LFP feature sets, were evaluated under four validation schemes: within-OFF cross-validation, OFF-to-ON generalization, a mixed leave-one-recording-out (LORO) scheme, and generalization to unseen stimulation intensities.

Results

The Combined model performed best in the mixed LORO scenario (balanced accuracy 0.74, sensitivity 0.78, specificity 0.70), inheriting a favorable trade-off from the complementary biases of EEG (sensitivity-dominated) and LFP (specificity-dominated). LFP-derived Hjorth mobility, the beta/gamma power ratio, EEG central alpha power, and central-temporal gamma coherence ranked among the most consistent candidate predictive features across scenarios. Generalization to unseen stimulation intensities preserved a similar, moderately degraded performance profile (balanced accuracy 0.66–0.70).

Conclusions

These findings provide proof-of-concept evidence that multimodal EEG-LFP decoding can identify epochs of dystonic muscle activity in paediatric dystonia.

Förderung

  • National Plan for Complementary Investments to the PNRR Hub Life Science-Digital Health

Zitieren

APA

Barbi, E., Fino, E., Rossi, C., Rita, A. D., Peraio, S., Noris, A., Ciabattini, S., Lazzeri, M., Melani, F., Lenge, M., Giordano, F., & Mesin, L. (2026). Machine Learning Decoding of Dystonic States from EEG-LFP Signals in GPi-DBS: A Multimodal Case Study. Bioengineering, 13(11), 1313. https://doi.org/10.3390/bioengineering13111313

Vancouver

Barbi E, Fino E, Rossi C, Rita AD, Peraio S, Noris A, et al. Machine Learning Decoding of Dystonic States from EEG-LFP Signals in GPi-DBS: A Multimodal Case Study. Bioengineering. 2026;13(11):1313. doi:10.3390/bioengineering13111313

BibTeX
@article{Barbi2026,
  author = {Barbi, Elisa and Fino, Edoardo and Rossi, Chiara and Rita, Andrea Di and Peraio, Simone and Noris, Alice and Ciabattini, Sara and Lazzeri, Marta and Melani, Federico and Lenge, Matteo and Giordano, Flavio and Mesin, Luca},
  title = {Machine Learning Decoding of Dystonic States from EEG-LFP Signals in GPi-DBS: A Multimodal Case Study},
  journal = {Bioengineering},
  year = {2026},
  volume = {13},
  number = {11},
  pages = {1313},
  doi = {10.3390/bioengineering13111313}
}
Kostenlos starten →