EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep learning approach for automatic assessment of schizophrenia and bipolar disorder in patients using R-R intervals

Kamil Książek iD, Wilhelm Masarczyk iD, Przemysław Głomb, Michał Romaszewski, Krisztián Buza, Przemysław Sekuła iD, Michał Cholewa, Katarzyna Kołodziej iD, Piotr Gorczyca, Magdalena Piegza

PLOS Computational Biology · 2025

DOI: 10.1371/journal.pcbi.1012983 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2025. Verfasst von Kamil Książek und 9 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Mathematics and Computer Science, Jagiellonian University, Kraków, Poland. Hauptthemen laut MEDLINE: Bipolar Disorder, Schizophrenia, Deep Learning, Electrocardiography. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 107 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jagiellonian University, Krakow, DigiWorld Priority Research Area within the Excellence Initiative – Research University program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Schizophrenia and bipolar disorder are severe mental illnesses that significantly impact quality of life. These disorders are associated with autonomic nervous system dysfunction, which can be assessed through heart activity analysis. Heart rate variability (HRV) has shown promise as a potential biomarker for diagnostic support and early screening of those conditions. This study aims to develop and evaluate an automated classification method for schizophrenia and bipolar disorder using short-duration electrocardiogram (ECG) signals recorded with a low-cost wearable device. We conducted classification experiments using machine learning techniques to analyze R-R interval windows extracted from short ECG recordings. The study included 60 participants—30 individuals diagnosed with schizophrenia or bipolar disorder and 30 control subjects. We evaluated multiple machine learning models, including Support Vector Machines, XGBoost, multilayer perceptrons, Gated Recurrent Units, and ensemble methods. Two time window lengths (about 1 and 5 minutes) were evaluated. Performance was assessed using 5-fold cross-validation and leave-one-out cross-validation, with hyperparameter optimization and patient-level classification based on individual window decisions. Our method achieved classification accuracy of 83% for the 5-fold cross-validation and 80% for the leave-one-out scenario. Despite the complexity of our scenario, which mirrors real-world clinical settings, the proposed approach yielded performance comparable to advanced diagnostic methods reported in the literature. The results highlight the potential of short-duration HRV analysis as a cost-effective and accessible tool for aiding in the diagnosis of schizophrenia and bipolar disorder. Our findings support the feasibility of using wearable ECG devices and machine learning-based classification for psychiatric screening, paving the way for further research and clinical applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bipolar DisorderSchizophreniaDeep LearningElectrocardiographyHumansMaleFemaleHeart RateAdultMiddle AgedSupport Vector MachineComputational BiologySignal Processing, Computer-AssistedWearable Electronic Devices

Autor:innen und Institutionen

  • Faculty of Mathematics and Computer Science, Jagiellonian University, Kraków, Poland.
  • Department of Psychiatry, Faculty of Medical Sciences in Zabrze, Medical University of Silesia, Tarnowskie Góry, Poland.
  • Institute of Theoretical and Applied Informatics, Polish Academy of Sciences, Gliwice, Poland.
  • Faculty of Finance and Accountancy, Budapest University of Economics and Business, Budapest, Hungary.
  • BioIntelligence Group, Department of Mathematics-Informatics, Sapientia Hungarian University of Transylvania, Targu Mures, Romania.

ORCID-Profile: Kamil Książek, Wilhelm Masarczyk, Przemysław Sekuła, Katarzyna Kołodziej

Förderung

  • Jagiellonian University, Krakow
  • DigiWorld Priority Research Area within the Excellence Initiative – Research University program

Zitieren

APA

Książek, K., Masarczyk, W., Głomb, P., Romaszewski, M., Buza, K., Sekuła, P., Cholewa, M., Kołodziej, K., Gorczyca, P., & Piegza, M. (2025). Deep learning approach for automatic assessment of schizophrenia and bipolar disorder in patients using R-R intervals. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1012983

Vancouver

Książek K, Masarczyk W, Głomb P, Romaszewski M, Buza K, Sekuła P, et al. Deep learning approach for automatic assessment of schizophrenia and bipolar disorder in patients using R-R intervals. PLOS Computational Biology. 2025. doi:10.1371/journal.pcbi.1012983

BibTeX
@article{Ksiek2025,
  author = {Książek, Kamil and Masarczyk, Wilhelm and Głomb, Przemysław and Romaszewski, Michał and Buza, Krisztián and Sekuła, Przemysław and Cholewa, Michał and Kołodziej, Katarzyna and Gorczyca, Piotr and Piegza, Magdalena},
  title = {Deep learning approach for automatic assessment of schizophrenia and bipolar disorder in patients using R-R intervals},
  journal = {PLOS Computational Biology},
  year = {2025},
  doi = {10.1371/journal.pcbi.1012983}
}
Kostenlos starten →