EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning on Magnetoencephalography Data Yields Generalizable Low‐Dimensional Neural Fingerprints That Distinguish Individuals Across Task Conditions

Joonas Karhula iD, Anttoni Ojanperä iD, Ersin Yılmaz iD, Susanne Merz, Samuel Kaski, Riitta Salmelin iD

Human Brain Mapping · 2026-08 · 47 (11)

DOI: 10.1002/hbm.70618 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Human Brain Mapping, online erschienen am 07.08.2026. Verfasst von Joonas Karhula und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neuroscience and Biomedical Engineering, Aalto University, Espoo, Finland. Hauptthemen laut MEDLINE: Magnetoencephalography, Machine Learning, Connectome, Individuality. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Horizon 2020 Framework Programme, Finnish Center for Artificial Intelligence, Magnus Ehrnroothin Säätiö.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Individual brains are unique in structure and function. Functional differences are captured by neural fingerprints, which reflect individual differences in behavior and cognition as well as group‐level changes related to neurodegenerative diseases. Most research efforts so far have focused on fingerprints comprising full functional connectomes. However, the high dimensionality of the connectomes can increase computational load and impede performance of machine learning methods in potential applications. A low‐dimensional alternative that retains individual features of the full connectomes would thus be beneficial. The present study employed latent‐noise Bayesian Reduced Rank Regression (lnBRRR) to learn low‐dimensional latent spaces that capture individual features in functional connectivity and power spectral density data derived from MEG recordings. LnBRRR performance was assessed with low training set sizes ( N = 20–44), and against principal component analysis and linear discriminant analysis. Model performance was also assessed with task data, and the solutions were compared across task conditions with cosine similarity to establish whether individual features are altered by different cognitive processes. LnBRRR captured generalizable individual patterns already at N = 20 but N = 30–35 was needed to reach optimal test accuracies and to prevent potential overfitting. The model also achieved comparable performance to the alternative models. Latent fingerprints derived from task data attained comparable performance to resting‐state latent fingerprints, and lnBRRR solutions were shown to generalize across conditions. Additionally, the model solutions for power spectral density data were discovered to be notably similar, yet differently rotated, over task conditions, suggesting that similar patterns of individual features were captured by the model regardless of the task condition. Altogether, the present results highlight lnBRRR as a potential tool for neuroimaging data analysis and demonstrate that individual differences in power spectral density are largely intrinsic and unaffected by varying cognitive processes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MagnetoencephalographyMachine LearningConnectomeIndividualityBrainNerve NetHumansFemaleMaleAdultDimensionality ReductionBayes TheoremYoung Adult

Stichwörter der Autor:innen

Bayesian inferenceindividual differenceslatent noisemachine learningneural fingerprint

Autor:innen und Institutionen

  • Department of Neuroscience and Biomedical Engineering, Aalto University, Espoo, Finland.
  • Department of Computer Science, Aalto University, Espoo, Finland.
  • ELLIS Institute Finland, Espoo, Finland.
  • Department of Computer Science, University of Manchester, Manchester, UK.

ORCID-Profile: Joonas Karhula, Anttoni Ojanperä, Ersin Yılmaz, Riitta Salmelin

Förderung

  • Horizon 2020 Framework Programme
  • Finnish Center for Artificial Intelligence
  • Magnus Ehrnroothin Säätiö
  • UKRI Turing AI World-Leading Researcher Fellowship
  • Academy of Finland
  • Sigrid Juséliuksen Säätiö
  • Research Council of Finland

Zitieren

APA

Karhula, J., Ojanperä, A., Yılmaz, E., Merz, S., Kaski, S., & Salmelin, R. (2026). Machine Learning on Magnetoencephalography Data Yields Generalizable Low‐Dimensional Neural Fingerprints That Distinguish Individuals Across Task Conditions. Human Brain Mapping, 47(11). https://doi.org/10.1002/hbm.70618

Vancouver

Karhula J, Ojanperä A, Yılmaz E, Merz S, Kaski S, Salmelin R. Machine Learning on Magnetoencephalography Data Yields Generalizable Low‐Dimensional Neural Fingerprints That Distinguish Individuals Across Task Conditions. Human Brain Mapping. 2026;47(11). doi:10.1002/hbm.70618

BibTeX
@article{Karhula2026,
  author = {Karhula, Joonas and Ojanperä, Anttoni and Yılmaz, Ersin and Merz, Susanne and Kaski, Samuel and Salmelin, Riitta},
  title = {Machine Learning on Magnetoencephalography Data Yields Generalizable Low‐Dimensional Neural Fingerprints That Distinguish Individuals Across Task Conditions},
  journal = {Human Brain Mapping},
  year = {2026},
  volume = {47},
  number = {11},
  doi = {10.1002/hbm.70618}
}
Kostenlos starten →