Opin vísindi

Predictability of seasonal mood fluctuations based on self-report questionnaires and EEG biomarkers in a non-clinical sample

Predictability of seasonal mood fluctuations based on self-report questionnaires and EEG biomarkers in a non-clinical sample


Title: Predictability of seasonal mood fluctuations based on self-report questionnaires and EEG biomarkers in a non-clinical sample
Author: Höller, Yvonne   orcid.org/0000-0002-1727-8557
Urbschat, Maeva Marlene
Kristófersson, Gísli Kort
Ólafsson, Ragnar Pétur
Date: 2022-04-08
Language: English
Scope:
University/Institute: University of Akureyri
School: School of Humanities
Department: Faculty of Psychology
Series: Frontiers in Psychiatry; 13()
ISSN: 1664-0640
DOI: https://doi.org/10.3389/fpsyt.2022.870079
Subject: Skammdegisþunglyndi; cognitive vulnerabilities; EEG biomarkers; machine learning; prediction; seasonal affective disorder winter depression; seasonal mood fluctuations; Psychiatry and Mental Health
URI: https://hdl.handle.net/20.500.11815/3205

Show full item record

Citation:

Höller , Y , Urbschat , M M , Kristófersson , G K & Ólafsson , R P 2022 , ' Predictability of seasonal mood fluctuations based on self-report questionnaires and EEG biomarkers in a non-clinical sample ' , Frontiers in Psychiatry , vol. 13 , 870079 . https://doi.org/10.3389/fpsyt.2022.870079

Abstract:

Induced by decreasing light, people affected by seasonal mood fluctuations may suffer from low energy, have low interest in activities, experience changes in weight, insomnia, difficulties in concentration, depression, and suicidal thoughts. Few studies have been conducted in search for biological predictors of seasonal mood fluctuations in the brain, such as EEG oscillations. A sample of 64 participants was examined with questionnaires and electroencephalography in summer. In winter, a follow-up survey was recorded and participants were grouped into those with at least mild (N = 18) and at least moderate (N = 11) mood decline and those without self-reported depressive symptoms both in summer and in winter (N = 46). A support vector machine was trained to predict mood decline by either EEG biomarkers alone, questionnaire data from baseline alone, or a combination of the two. Leave-one-out-cross validation with lasso regularization was used with logistic regression to fit a model. The accuracy for classification for at least mild/moderate mood decline was 77/82% for questionnaire data, 72/82% for EEG alone, and 81/86% for EEG combined with questionnaire data. Self-report data was more conclusive than EEG biomarkers recorded in summer for prediction of worsening of depressive symptoms in winter but it is advantageous to combine EEG with psychological assessment to boost predictive performance.

Description:

Funding Information: The study was supported by the Research Fund of the University of Akureyri (RHA, R1916). Funding Information: We thank the BS-students Anna Hj?lmeig Hannesd?ttir, El?sa Huld Jensd?ttir, M?ni Sn?r Hafd?sarson, Sara Teresa J?nsd?ttir, Sigr?n Mar?a ?skarsd?ttir, and Silja Hl?n Magn?sd?ttir at the Faculty of Psychology of the University of Akureyri for recruitment and data collection. Also many thanks to the BS-students of the Faculties of Psychology at the University of Iceland, Anton Nikolaisson Haydarly, Elena Arngr?msd?ttir, Erla ?str?s J?nsd?ttir, Inga Vald?s T?masd?ttir, Mar?a Lov?sa Brei?dal, and ?l?f Traustad?ttir to sample the data in the online part of the study. Publisher Copyright: Copyright © 2022 Höller, Urbschat, Kristófersson and Ólafsson.

Files in this item

This item appears in the following Collection(s)