Acta Psychiatrica Scandinavica最新文献

Objective: This study addresses the limitations of existing interventions for depression, such as a deficit-oriented focus, overlooking the utilization of positive elements such as nature, and neglecting the incorporation of group effects. The present feasibility study examines FlowVR, a resource-oriented, nature-inspired virtual reality (VR)-based group therapy. Previously tested individually in a pilot study for non-clinical participants, FlowVR has demonstrated positive effects on depressive symptoms. This study assesses the impact and safety of FlowVR in a group setting within a clinical sample using a one-armed study design.

Method: Forty-two inpatients and day patients with depression were recruited. Before and after the FlowVR intervention period of 4 weeks (two sessions per week), depressive symptoms were assessed (Beck Depression Inventory-II; BDI). Symptomatology (i.e., depressive symptoms), depression-associated variables (i.e., self-efficacy), intervention-specific variables (feeling of flow), and VR-specific variables (simulator sickness) were assessed before and after each session.

Results: Linear mixed effect models showed that symptomatology (depression, negative affect, current anxiety), depression-associated constructs (self-efficacy, motivation), and intervention-specific variables (flow) improved over the course of the sessions. No variable deteriorated more in one session compared to any other session. The lasso regression identified five potential predictors for the change in depression (BDI-II), yet these could not be validated in a subsequent linear regression analysis.

Conclusion: To conclude, FlowVR had the hypothesized positive impact over the course of the sessions, showing, for example, improvements in symptomatology. The sessions have demonstrated safety with no notable deteriorations. Therefore, FlowVR is deemed safe for clinical patients and group settings. However, further research is needed to explore predictors for the change in depression.

Objective: The goals of this article are as follows. First, to investigate the possibility of detecting autism spectrum disorder (ASD) from text data using the latest generation of machine learning tools. Second, to compare model performance on two datasets of transcribed statements, collected using two different diagnostic tools. Third, to investigate the feasibility of knowledge transfer between models trained on both datasets and check if data augmentation can help alleviate the problem of a small number of observations.

Method: We explore two techniques to detect ASD. The first one is based on fine-tuning HerBERT, a BERT-based, monolingual deep transformer neural network. The second one uses the newest, multipurpose text embeddings from OpenAI and a classifier. We apply the methods to two separate datasets of transcribed statements, collected using two different diagnostic tools: thought, language, and communication (TLC) and autism diagnosis observation schedule-2 (ADOS-2). We conducted several cross-dataset experiments in both a zero-shot setting and a setting where models are pretrained on one dataset and then training continues on another to test the possibility of knowledge transfer.

Results: Unlike previous studies, the models we tested obtained average results on ADOS-2 data but reached very good performance of the models in TLC. We did not observe any benefits from knowledge transfer between datasets. We observed relatively poor performance of models trained on augmented data and hypothesize that data augmentation by back translation obfuscates autism-specific signals.

Conclusion: The quality of machine learning models that detect ASD from text data is improving, but model results are dependent on the type of input data or diagnostic tool.

Introduction: Psychomotor activity stands out as a crucial symptom in characterizing behaviors associated with depression. This study aims to explore the potential of actigraphy as a tool for digital phenotyping in characterizing symptoms of psychomotor agitation and retardation, which are clinically challenging dimensions to capture, in patients diagnosed with major depressive episode (MDE) according to DSM-5 criteria.

Methods: We compared rest-activity circadian rhythm biomarkers measured by the Motion Watch 8 actigraphy between 58 (78.4%) patients with MDE and psychomotor retardation (PMR), and 16 (21.6%) patients with MDE and psychomotor agitation (PMA), according to DSM-5 criteria.

Results: Actigraphy allowed to objectively report PMA through heightened activity over a 24-h period, while PMR manifests as reduced activity during the most active 10 h. Lower rest-activity rhythm (RAR) amplitude in PMR was accompanied by increased irregularities in intra- and inter-day rhythms. Interestingly, actigraphy emerges as an objective tool to measure the characteristics of the active and rest periods, free from the confounding effects of sleep disturbances. Indeed, no differences in sleep disturbances were identified between patients exhibiting psychomotor agitation and those displaying PMR.

Conclusion: Digital phenotyping through actigraphy may aid in distinguishing psychomotor retardation and psychomotor agitation allowing for a more precise characterization of the depression phenotype. When integrated with clinical assessment, measurements from actigraphy could offer additional insights into activity rhythms alongside subjective assessments and hold the potential to augment existing clinical decision-making processes in psychiatry.