Predictability of Seasonal Mood Fluctuations Based on Self-Report Questionnaires and EEG Biomarkers in a Non-clinical Sample

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.

EEG-responses to mood induction interact with seasonality and age

“…So far, sex differences were examined with respect to SAD and seasonality only in terms of the higher prevalence of seasonal symptoms among women ( 50 ), while the knowledge about interactions between sex, seasonality and EEG activity is rather limited. According to our recently published longitudinal study, sex has not predictive value when used alone or in combination with the EEG for predicting winter-time depression based on summer-time measurements ( 53 ). However, sex is known to affect EEG band activity insofar as it is possible to derive the subject's sex from EEG biomarkers ( 76 , 77 ).…”

“…Finally, this study was conducted in a cross-sectional design, while longitudinal designs are needed to confirm the relation between EEG correlates of induced sad mood in one season, i.e., summer, and depressive symptoms in the season when SAD typically occurs, i.e., winter. Such data was published recently, showing that cognitive vulnerabilities are better suited to predict winter depression, but the combination of those markers with EEG features can be advantageous ( 53 ).…”

“…The disadvantage of CNNs is the need for a large sample size as their learning ability and generalizability depends highly on the size of the ground truth. In seasonal affective disorder, a simple support vector machine classification can be used to predict winter-time depression based on summer-time psychological vulnerabilities and EEG-features ( 53 ). The present results might add to the selection of prior knowledge for future artificial intelligence models, i.e., by adding age to the feature vector.…”

“…This data was also analyzed in a previously published study by the same authors ( 53 ), where more details on the study parts that were not analyzed in the present report can be retrieved.…”

Emotional Bias among Individuals at Risk for Seasonal Affective Disorder—An EEG Study during Remission in Summer

“…The EEG is also a commonly used biomarker in research on depression [59]. EEG research is much less established in SAD, but EEG biomarkers were successfully used in research on seasonality [60,61]. Lower power in most frequency bands as well as frontal asymmetrical activity was reported for participants with seasonality [48].…”