Background
Childhood trauma (CT) is a risk factor for depressive and anxiety disorders. Although dysregulated biological stress systems may underlie the enduring effect of CT, the relation between CT and separate and cumulative activity of the major stress systems, namely, the hypothalamic-pituitary-adrenal (HPA)-axis, the immune-inflammatory system, and the autonomic nervous system (ANS), remains inconclusive.
Methods
In the Netherlands Study of Depression and Anxiety (NESDA, n = 2778), we determined whether self-reported CT (as assessed by the Childhood Trauma Interview) was associated with separate and cumulative markers of the HPA-axis (cortisol awakening response, evening cortisol, dexamethasone suppression test cortisol), the immune-inflammatory system (C-reactive protein, interleukin-6, tumor necrosis factor-α), and the ANS (heart rate, respiratory sinus arrhythmia, pre-ejection period) in adulthood.
Results
Almost all individuals with CT (n = 1330) had either current or remitted depressive and/or anxiety disorder (88.6%). Total-sample analyses showed little evidence for CT being significantly associated with the separate or cumulative stress systems’ activity in adulthood. These findings were true for individuals with and without depressive and/or anxiety disorders. To maximize contrast, individuals with severe CT were compared to healthy controls without CT. This yielded slight, but significantly higher levels of cortisol awakening response (AUCg, β = .088, p =  .007; AUCi, β = .084, p =  .010), cumulative HPA-axis markers (β = .115, p =  .001), C-reactive protein (β = .055, p = .032), interleukin-6 (β = .053, p =  .038), cumulative inflammation (β = .060, p =  .020), and cumulative markers across all systems (β = .125, p =  .0003) for those with severe CT, partially explained by higher rates of smoking, body mass index, and chronic diseases.
Conclusion
While our findings do not provide conclusive evidence on CT directly dysregulating stress systems, individuals with severe CT showed slight indications of dysregulations, partially explained by an unhealthy lifestyle and poorer health.

BackgroundEarly detection of elevated acute stress is necessary if we aim to reduce consequences associated with prolonged or recurrent stress exposure. Stress monitoring may be supported by valid and reliable machine-learning algorithms. However, investigation of algorithms detecting stress severity on a continuous scale is missing due to high demands on data quality for such analyses. Use of multimodal data, meaning data coming from multiple sources, might contribute to machine-learning stress severity detection. We aimed to detect laboratory-induced stress using multimodal data and identify challenges researchers may encounter when conducting a similar study.MethodsWe conducted a preliminary exploration of performance of a machine-learning algorithm trained on multimodal data, namely visual, acoustic, verbal, and physiological features, in its ability to detect stress severity following a partially automated online version of the Trier Social Stress Test. College students (n = 42; M age = 20.79, 69% female) completed a self-reported stress visual analogue scale at five time-points: After the initial resting period (P1), during the three stress-inducing tasks (i.e., preparation for a presentation, a presentation task, and an arithmetic task, P2-4) and after a recovery period (P5). For the whole duration of the experiment, we recorded the participants’ voice and facial expressions by a video camera and measured cardiovascular and electrodermal physiology by an ambulatory monitoring system. Then, we evaluated the performance of the algorithm in detection of stress severity using 3 combinations of visual, acoustic, verbal, and physiological data collected at each of the periods of the experiment (P1-5).ResultsParticipants reported minimal (P1, M = 21.79, SD = 17.45) to moderate stress severity (P2, M = 47.95, SD = 15.92), depending on the period at hand. We found a very weak association between the detected and observed scores (r2 = .154; p = .021). In our post-hoc analysis, we classified participants into categories of stressed and non-stressed individuals. When applying all available features (i.e., visual, acoustic, verbal, and physiological), or a combination of visual, acoustic and verbal features, performance ranged from acceptable to good, but only for the presentation task (accuracy up to.71, F1-score up to.73).ConclusionsThe complexity of input features needed for machine-learning detection of stress severity based on multimodal data requires large sample sizes with wide variability of stress reactions and inputs among participants. These are difficult to recruit for laboratory setting, due to high time and effort demands on the side of both researcher and participant. Resources needed may be decreased using automatization of experimental procedures, which may, however, lead to additional technological challenges, potentially causing other recruitment setbacks. Further investigation is necessary, with the emphasis on quality ground truth, i.e., gold standard (self-report) instruments, but also outside of laboratory experiments, mainly in general populations and mental health care patients.