EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bayesian reduced rank regression models generalizable neural fingerprints that differentiate between individuals in magnetoencephalography data

Joonas Haakana, Susanne Merz, Samuel Kaski, Hanna Renvall, Riitta Salmelin

European Journal of Neuroscience · 2024

DOI: 10.1111/ejn.16292 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Neuroscience, 2024. Verfasst von Joonas Haakana und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neuroscience and Biomedical Engineering, Aalto University, Espoo, Finland. Hauptthemen laut MEDLINE: Magnetoencephalography, Bayes Theorem, Connectome, Brain. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EU Horizon 2020 Research and Innovation Programme, Academy of Finland, Sigrid Jusélius Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent magnetoencephalography (MEG) studies have reported that functional connectivity (FC) and power spectra can be used as neural fingerprints in differentiating individuals. Such studies have mainly used correlations between measurement sessions to distinguish individuals from each other. However, it has remained unclear whether such correlations might reflect a more generalizable principle of individually distinctive brain patterns. Here, we evaluated a machine‐learning based approach, termed latent‐noise Bayesian reduced rank regression (BRRR) as a means of modelling individual differences in the resting‐state MEG data of the Human Connectome Project (HCP), using FC and power spectra as neural features. First, we verified that BRRR could model and reproduce the differences between metrics that correlation‐based fingerprinting yields. We trained BRRR models to distinguish individuals based on data from one measurement and used the models to identify subsequent measurement sessions of those same individuals. The best performing BRRR models, using only 20 spatiospectral components, were able to identify subjects across measurement sessions with over 90% accuracy, approaching the highest correlation‐based accuracies. Using cross‐validation, we then determined whether that BRRR model could generalize to unseen subjects, successfully classifying the measurement sessions of novel individuals with over 80% accuracy. The results demonstrate that individual neurofunctional differences can be reliably extracted from MEG data with a low‐dimensional predictive model and that the model is able to classify novel subjects.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MagnetoencephalographyBayes TheoremConnectomeBrainHumansMachine LearningMaleFemaleAdultModels, Neurological

Stichwörter der Autor:innen

computational modellingindividual differencesmachine learningneural fingerprintingresting‐state

Autor:innen und Institutionen

  • Department of Neuroscience and Biomedical Engineering, Aalto University, Espoo, Finland.
  • Department of Computer Science, Aalto University, Espoo, Finland.
  • BioMag Laboratory, HUS Diagnostic Center, Helsinki University Hospital, Helsinki, Finland.

Förderung

  • EU Horizon 2020 Research and Innovation Programme
  • Academy of Finland
  • Sigrid Jusélius Foundation
  • Horizon 2020 Framework Programme
  • Research Council of Finland
  • Sigrid Juséliuksen Säätiö

Zitieren

APA

Haakana, J., Merz, S., Kaski, S., Renvall, H., & Salmelin, R. (2024). Bayesian reduced rank regression models generalizable neural fingerprints that differentiate between individuals in magnetoencephalography data. European Journal of Neuroscience. https://doi.org/10.1111/ejn.16292

Vancouver

Haakana J, Merz S, Kaski S, Renvall H, Salmelin R. Bayesian reduced rank regression models generalizable neural fingerprints that differentiate between individuals in magnetoencephalography data. European Journal of Neuroscience. 2024. doi:10.1111/ejn.16292

BibTeX
@article{Haakana2024,
  author = {Haakana, Joonas and Merz, Susanne and Kaski, Samuel and Renvall, Hanna and Salmelin, Riitta},
  title = {Bayesian reduced rank regression models generalizable neural fingerprints that differentiate between individuals in magnetoencephalography data},
  journal = {European Journal of Neuroscience},
  year = {2024},
  doi = {10.1111/ejn.16292}
}
Kostenlos starten →