Machine learning models predict PTSD severity and functional impairment: A personalized medicine approach for uncovering complex associations among heterogeneous symptom profiles.

OBJECTIVE: Posttraumatic stress disorder (PTSD) is a debilitating psychiatric illness, experienced by approximately 10% of the population. Heterogeneous presentations that include heightened dissociation, comorbid anxiety and depression, and emotion dysregulation contribute to the severity of PTSD, in turn, creating barriers to recovery. There is an urgent need to use data-driven approaches to better characterize complex psychiatric presentations with the aim of improving treatment outcomes. We sought to determine if machine learning models could predict PTSD-related illness in a real-world treatment-seeking population using self-report clinical data. METHOD: Secondary clinical data from 2017 to 2019 included pretreatment measures such as trauma-related symptoms, other mental health symptoms, functional impairment, and demographic information from adults admitted to an inpatient unit for PTSD in Canada (n = 393). We trained two nonlinear machine learning models (extremely randomized trees) to identify predictors of (a) PTSD symptom severity and (b) functional impairment. We assessed model performance based on predictions in novel subsets of patients. RESULTS: Approximately 43% of the variance in PTSD symptom severity (R²avg = .43, R²median = .44, p = .001) was predicted by symptoms of anxiety, dissociation, depression, negative trauma-related beliefs about others, and emotion dysregulation. In addition, 32% of the variance in functional impairment scores (R²avg = .32, R²median = .33, p = .001) was predicted by anxiety, PTSD symptom severity, cognitive dysfunction, dissociation, and depressive symptoms. CONCLUSIONS: Our results reinforce that dissociation, cooccurring anxiety and depressive symptoms, maladaptive trauma appraisals, cognitive dysfunction, and emotion dysregulation are critical targets for trauma-related interventions. Machine learning models can inform personalized medicine approaches to maximize trauma recovery in real-world inpatient populations. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Observed shyness leads to more automatic imitation in early childhood.

The authors investigated children's automatic imitation in the context of observed shyness by adapting the widely used automatic imitation task (AIT). AIT performance in 6-year-old children (N = 38; 22 female; 71% White) and young adults (17-22 years; N = 122; 99 female; 32% White) was first examined as a proof of concept and to assess age-related differences in responses to the task (Experiment 1). Although error rate measures of automatic imitation were comparable between children and adults, children displayed less reaction time interference than adults. Children's shyness coded from direct behavioral observations was then examined in relation to AIT scores (Experiment 2). Observed shyness at 5 years old predicted higher automatic imitation one year later. We discuss the latter findings in the context of an adaptive strategy. We argue that shy children may possess a heightened sensitivity to others' motor cues and therefore are more likely to implicitly imitate social partners' actions. This tendency may serve as a strategy to signal appeasement and affiliation, allowing for shy children to blend in and feel less inhibited in a social environment.

Children's shyness and frontal electroencephalogram delta-beta correlation in the pediatric surgical setting.

The prospect of surgery is a unique psychologically threatening context for children, often leading to experiences of preoperative anxiety. Recent research suggests that individual differences in children's temperament may influence responses to the surgical setting. In the present study, we examined whether individual differences in shyness were related to differences in frontal electroencephalogram (EEG) delta-beta correlation, a proposed neural correlate of emotion regulation and dysregulation, among children anticipating surgery. Seventy-one children (36 boys, Mage  = 10.3 years, SDage  = 1.7 years) undergoing elective surgery self-reported on their own shyness, and their parents also reported on their child's shyness. Using a mobile, dry sensor EEG headband, frontal EEG measures were collected and self- and observer-reported measures of state anxiety were obtained at the children's preoperative visit (Time 1) and on the day of surgery (Time 2). A latent cluster analysis derived classes of low shy (n = 37) and high shy (n = 34) children using the child- and parent-reported shyness measures. We then compared the two classes on frontal EEG delta-beta correlation using between- and within-subjects analyses. Although children classified as high versus low in shyness had higher self- and observer-reported state anxiety across both time periods, frontal EEG delta-beta correlation increased from T1 to T2 only among low shy children using a between-subjects delta-beta correlation measure. We discuss the interpretation of a relatively higher delta-beta correlation as a correlate of emotion regulatory versus dysregulatory strategies for some children in a "real-world," surgical context.