EEG-based Signatures of Schizophrenia, Depression, and Aberrant Aging: A Supervised Machine Learning Investigation
Schizophrenia Bulletin · 08.05.2025 · 51 (3) · 804-817
DOI: 10.1093/schbul/sbae150 ↗Kurz gefasst
Fachartikel in der Zeitschrift Schizophrenia Bulletin, online erschienen am 09.09.2024. Verfasst von Elif Sarisik und 7 weiteren Autor:innen. Beteiligte Einrichtung: Max Planck Fellow Group Precision Psychiatry, Max Planck Institute of Psychiatry, Munich, Germany. Hauptthemen laut MEDLINE: Schizophrenia, Major Depressive Disorder, Electroencephalography, Aging. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 118 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EKFS-Translational Psychiatry, NIH HHS, German Federal Ministry of Education and Research.
Abstract (Originalsprache)
Background
Electroencephalography (EEG) is a noninvasive, cost-effective, and robust tool, which directly measures in vivo neuronal mass activity with high temporal resolution. Combined with state-of-the-art machine learning (ML) techniques, EEG recordings could potentially yield in silico biomarkers of severe mental disorders. Hypothesis Pathological and physiological aging processes influence the electrophysiological signatures of schizophrenia (SCZ) and major depressive disorder (MDD). Study Design From a single-center cohort (N = 735, 51.6% male) comprising healthy control individuals (HC, N = 245) and inpatients suffering from SCZ (N = 250) or MDD (N = 240), we acquired resting-state 19 channel-EEG recordings. Using repeated nested cross-validation, support vector machine models were trained to (1) classify patients with SCZ or MDD and HC individuals and (2) predict age in HC individuals. The age model was applied to patient groups to calculate Electrophysiological Age Gap Estimation (EphysAGE) as the difference between predicted and chronological age. The links between EphysAGE, diagnosis, and medication were then further explored. Study Results The classification models robustly discriminated SCZ from HC (balanced accuracy, BAC = 72.7%, P < .001), MDD from HC (BAC = 67.0%, P < .001), and SCZ from MDD individuals (BAC = 63.2%, P < .001). Notably, central alpha (8–11 Hz) power decrease was the most consistently predictive feature for SCZ and MDD. Higher EphysAGE was associated with an increased likelihood of being misclassified as SCZ in HC and MDD (ρHC = 0.23, P < .001; ρMDD = 0.17, P = .01).
Conclusions
ML models can extract electrophysiological signatures of MDD and SCZ for potential clinical use. However, the impact of aging processes on diagnostic separability calls for timely application of such models, possibly in early recognition settings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Max Planck Fellow Group Precision Psychiatry, Max Planck Institute of Psychiatry, Munich, Germany.
- Department of Psychiatry and Psychotherapy, LMU University Hospital, LMU Munich, Munich, Germany.
- International Max Planck Research School for Translational Psychiatry (IMPRS-TP), Munich, Germany.
- German Center for Mental Health (DZPG), Partner Site Munich, Munich, Germany.
- NeuroImaging Core Unit Munich (NICUM), LMU University Hospital, LMU Munich, Munich, Germany.
- Munich Center for Neurosciences, LMU Munich, Munich, Germany.
ORCID-Profile: Elif Sarisik, David Popovic, Daniel Keeser, Adyasha Khuntia, Kolja Schiltz, Peter Falkai, Oliver Pogarell, Nikolaos Koutsouleris
Förderung
- EKFS-Translational Psychiatry
- NIH HHS
- German Federal Ministry of Education and Research
- Else-Kröner-Fresenius-Stiftung
- German Ministry of Science
- German Ministry of Health
- German Innovation Fund
- German Science Foundation
Zitieren
APA
Sarisik, E., Popovic, D., Keeser, D., Khuntia, A., Schiltz, K., Falkai, P., Pogarell, O., & Koutsouleris, N. (2025). EEG-based Signatures of Schizophrenia, Depression, and Aberrant Aging: A Supervised Machine Learning Investigation. Schizophrenia Bulletin, 51(3), 804-817. https://doi.org/10.1093/schbul/sbae150
Vancouver
Sarisik E, Popovic D, Keeser D, Khuntia A, Schiltz K, Falkai P, et al. EEG-based Signatures of Schizophrenia, Depression, and Aberrant Aging: A Supervised Machine Learning Investigation. Schizophrenia Bulletin. 2025;51(3):804-817. doi:10.1093/schbul/sbae150
BibTeX
@article{Sarisik2025,
author = {Sarisik, Elif and Popovic, David and Keeser, Daniel and Khuntia, Adyasha and Schiltz, Kolja and Falkai, Peter and Pogarell, Oliver and Koutsouleris, Nikolaos},
title = {EEG-based Signatures of Schizophrenia, Depression, and Aberrant Aging: A Supervised Machine Learning Investigation},
journal = {Schizophrenia Bulletin},
year = {2025},
volume = {51},
number = {3},
pages = {804--817},
doi = {10.1093/schbul/sbae150}
}
EUVIMED