No abstract

The use of speech as a digital biomarker to detect stress levels is increasingly gaining attention. Yet, heterogeneous effects of stress on specific acoustic speech features have been observed, possibly due to previous studies’ use of different stress labels/categories and the lack of solid stress induction paradigms or validation of experienced stress. Here, we deployed a controlled, within-subject psychosocial stress induction experiment in which participants received both neutral (control condition) and negative (negative condition) comparative feedback after solving a challenging cognitive task. This study is the first to use a (non-actor) within-participant design that verifies a successful stress induction using both self-report (i.e., decreased reported valence) and physiological measures (i.e., increased heart rate acceleration using event-related cardiac responses during feedback exposure). Analyses of acoustic speech features showed a significant increase in Fundamental Frequency (F0) and Harmonics-to-Noise Ratio (HNR), and a significant decrease in shimmer during the negative feedback condition. Our results using read-out-loud speech comply with earlier research, yet we are the first to validate these results in a well-controlled but ecologically-valid setting to guarantee the generalization of our findings to real-life settings. Further research should aim to replicate these results in a free speech setting to test the robustness of our findings for real-world settings and should include semantics to also take into account what you say and not only how you say it.

Major Depressive Disorder (MDD) is a widespread mental illness that causes considerable suffering, and neuroimaging studies are trying to reduce this burden by developing biomarkers that can facilitate detection. Prior fMRI- and neurostimulation studies suggest that aberrant subgenual Anterior Cingulate (sgACC)—dorsolateral Prefrontal Cortex (DLPFC) functional connectivity is consistently present within MDD. Combining the need for reliable depression markers with the electroencephalogram’s (EEG) high clinical utility, we investigated whether aberrant EEG sgACC–DLPFC functional connectivity could serve as a marker for depression. Source-space Amplitude Envelope Correlations (AEC) of 20 MDD patients and 20 matched controls were contrasted using non-parametric permutation tests. In addition, extracted AEC values were used to (a) correlate with characteristics of depression and (b) train a Support Vector Machine (SVM) to determine sgACC–DLPFC connectivity’s discriminative power. FDR-thresholded statistical maps showed reduced sgACC–DLPFC AEC connectivity in MDD patients relative to controls. This diminished AEC connectivity is located in the beta-1 (13–17 Hz) band and is associated with patients’ lifetime number of depressive episodes. Using extracted sgACC–DLPFC AEC values, the SVM achieved a classification accuracy of 84.6% (80% sensitivity and 89.5% specificity) indicating that EEG sgACC–DLPFC connectivity has promise as a biomarker for MDD.