Understanding how psychiatric patients subjectively experienced a clinical conversation is important for feedback and alliance-related process monitoring. While interviewers form post-session judgments about patient experience, these judgments do not always match patients' self-reports. Automatic approaches for predicting perceived interaction quality from conversation have been proposed, but it remains unclear whether such approaches can complement human judgment rather than simply replicate it. To address this gap, we evaluate a clinician-support framework in which post-session interviewer ratings are combined with automatic language-based predictions to estimate patient-reported interaction quality in free clinical interviews. We assess this integration across multiple standard model types, including Ridge, SVR, MLP, GRU, and BiLSTM, all trained on sentence embeddings extracted from dyadic transcripts of 107 free conversations between psychiatric patients and interviewers. Our results show that combining interviewer judgments with model predictions through simple averaging yields the strongest overall performance. The interviewer-only baseline reached a Pearson correlation of 0.365. Among fully automatic models, Ridge achieved the strongest Pearson correlation (r = 0.286), while BiLSTM achieved r = 0.270. The strongest result was obtained by BiLSTM interviewer integration (r = 0.403). Our findings suggest that automatic language analysis and interviewer judgment capture complementary aspects of patient experience and that their combination provides a more accurate approximation of the patient's own report than either source alone.

BACKGROUND:Speech analysis has shown significant promise as a potential biomarker for depression. However, no studies to date have examined the impact of childhood trauma on speech and language patterns in individuals with depression. This study aims to explore the relationship between vocal characteristics and depressive symptoms, while also assessing how childhood trauma may shape these patterns. METHODS:27 participants with a major depressive episode were included. The severity of depression was assessed using the Montgomery & Asberg Depression Rating Scale (MADRS) and the Beck Depression Inventory II. Childhood trauma was measured using the Childhood Trauma Questionnaire. Speech recordings from the MADRS semi-structured interview and a free clinical interview were analyzed using speaker diarization, automatic speech recognition, and feature extraction. RESULTS:Several acoustics features were significantly associated with depression severity. Correlation analysis revealed that greater depression severity was linked to shorter, less diverse speech, characterized by fewer words, fewer semantic clusters, and reduced articulatory effort. In contrast, childhood trauma was positively associated with distinct speech characteristics. Higher trauma load was associated with richer, longer, and more syntactically complex speech. Additionally, utterances were shorter, with more frequent shifts between semantic clusters, reflecting a more fragmented speech pattern influenced by traumatic load. CONCLUSION:Our study highlights the influence of childhood trauma on vocal and linguistic characteristics of patients with depression. Automated language analysis offers the possibility to identify biomarkers of traumatic load in patients with depression. This could improve diagnostic accuracy, guide therapeutic management and monitor clinical progress.

Patients with borderline personality disorder (BPD) suffer from severe emotional dysregulation and disturbances in body image and self-perception. Interoception, the processing and perception of internal body signals, is closely linked to emotional processing, but it remains unclear whether BPD impairs specific interoceptive facets and how these deficits respond to treatment. We investigated the two key interoceptive facets, accuracy and attention, in 55 BPD patients and 31 healthy controls (HC) using self-report and objective measures before and after four-week residential Dialectical Behavior Therapy (DBT). Interoceptive accuracy and its metacognitive awareness were evaluated using a heartbeat discrimination task, while interoceptive attention was measured through questionnaires, intensity ratings, and both uni- and multivariate neural responses during a functional magnetic resonance imaging (fMRI) interoceptive attention task. Before DBT, BPD patients showed reduced self-reported interoceptive attention, which was associated with more interpersonal problems. Patients further exhibited higher similarity in activity patterns evoked by cardiac interoceptive and exteroceptive attention in the insular and dorsal anterior cingulate cortex. There were no significant group differences in behavioral or self-reported interoceptive accuracy or metacognitive awareness. However, behavioral interoceptive accuracy was impaired in BPD patients with more severe symptoms. After four-week residential DBT, self-reported interoceptive attention significantly improved, while other interoceptive facets showed no significant changes. BPD involves disturbances in specific interoceptive facets that respond differently to treatment. Our findings support multifaceted assessments of interoception and the potential benefit of interoceptive attention training for all BPD patients, with additional accuracy training in more severe cases.

INTRODUCTION:Patients with borderline personality disorder (BPD) suffer from severe social impairments and interpersonal problems. Social touch can provide comfort and facilitate the maintenance of social bonds, and preliminary evidence indicates a negative evaluation of social touch in patients with BPD. However, the neural mechanisms underlying aberrant touch processing in BPD and its role for social impairments are still unclear. METHODS:We recruited 55 BPD patients and 31 healthy controls and used functional magnetic resonance imaging to probe neural responses to slow (i.e., C-tactile [CT]-optimal; affective) and fast (i.e., CT-suboptimal; discriminative) touch before and after 4 weeks of a residential dialectical behavior therapy (DBT) program. In addition to assessing BPD symptoms and interpersonal problems, we evaluated touch allowance maps and the attitude toward social touch. RESULTS:BPD patients showed a comprehensive negative bias toward social touch before the DBT, evident in a significantly more negative attitude toward and reduced comfort zones of social touch compared to healthy controls. Activation in the posterior insular cortex in response to CT-optimal touch was significantly reduced and correlated with the severity of interpersonal problems in BPD patients. Despite significant improvements in overall BPD symptom load, dysfunctional social touch processing persisted after 4 weeks of DBT, indicating trait-like disturbances in BPD. CONCLUSIONS:An impaired insula-mediated integration of affective and sensory components of touch may constitute a clinically relevant biological signature of the complex interpersonal problems in BPD.

BACKGROUND:Major depressive episode (MDE) is a common clinical syndrome. It can be found in different pathologies such as major depressive disorder (MDD), bipolar disorder (BD), posttraumatic stress disorder (PTSD), or even occur in the context of psychological trauma. However, only 1 syndrome is described in international classifications (Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition [DSM-5]/International Classification of Diseases 11th Revision [ICD-11]), which do not take into account the underlying pathology at the origin of the MDE. Clinical interviews are currently the best source of information to obtain the etiological diagnosis of MDE. Nevertheless, it does not allow an early diagnosis and there are no objective measures of extracted clinical information. To remedy this, the use of digital tools and their correlation with clinical symptomatology could be useful.OBJECTIVE:We aimed to review the current application of digital tools for MDE diagnosis while highlighting shortcomings for further research. In addition, our work was focused on digital devices easy to use during clinical interview and mental health issues where depression is common.METHODS:We conducted a narrative review of the use of digital tools during clinical interviews for MDE by searching papers published in PubMed/MEDLINE, Web of Science, and Google Scholar databases since February 2010. The search was conducted from June to September 2021. Potentially relevant papers were then compared against a checklist for relevance and reviewed independently for inclusion, with focus on 4 allocated topics of (1) automated voice analysis, behavior analysis by (2) video and physiological measures, (3) heart rate variability (HRV), and (4) electrodermal activity (EDA). For this purpose, we were interested in 4 frequently found clinical conditions in which MDE can occur: (1) MDD, (2) BD, (3) PTSD, and (4) psychological trauma.RESULTS:A total of 74 relevant papers on the subject were qualitatively analyzed and the information was synthesized. Thus, a digital phenotype of MDE seems to emerge consisting of modifications in speech features (namely, temporal, prosodic, spectral, source, and formants) and in speech content, modifications in nonverbal behavior (head, hand, body and eyes movement, facial expressivity, and gaze), and a decrease in physiological measurements (HRV and EDA). We not only found similarities but also differences when MDE occurs in MDD, BD, PTSD, or psychological trauma. However, comparative studies were rare in BD or PTSD conditions, which does not allow us to identify clear and distinct digital phenotypes.CONCLUSIONS:Our search identified markers from several modalities that hold promise for helping with a more objective diagnosis of MDE. To validate their potential, further longitudinal and prospective studies are needed.

Identifying objective and reliable markers to tailor diagnosis and treatment of psychiatric patients remains a challenge, as conditions like major depression, bipolar disorder, or schizophrenia are qualified by complex behavior observations or subjective self-reports instead of easily measurable somatic features. Recent progress in computer vision, speech processing and machine learning has enabled detailed and objective characterization of human behavior in social interactions. However, the application of these technologies to personalized psychiatry is limited due to the lack of sufficiently large corpora that combine multi-modal measurements with longitudinal assessments of patients covering more than a single disorder. To close this gap, we introduce Mephesto, a multi-centre, multi-disorder longitudinal corpus creation effort designed to develop and validate novel multi-modal markers for psychiatric conditions. Mephesto will consist of multi-modal audio-, video-, and physiological recordings as well as clinical assessments of psychiatric patients covering a six-week main study period as well as several follow-up recordings spread across twelve months. We outline the rationale and study protocol and introduce four cardinal use cases that will build the foundation of a new state of the art in personalized treatment strategies for psychiatric disorders.

Visual attention directed towards the eye-region of a face emerges rapidly, even before conscious awareness, and regulates social interactions in terms of approach versus avoidance. Current perspectives on the neuroendocrine substrates of this behavioral regulation highlight a role of the peptide hormone oxytocin (OXT), but it remains unclear whether the facilitating effects of OXT vary as a function of facial familiarity. Here, a total of 73 healthy participants was enrolled in an eye-tracking experiment specifically designed to test whether intranasal OXT (24 IU) augments gaze duration toward the eye-region across four different face categories: the participants’ own face, the face of their romantic partner, the face of a familiar person (close friend) or an unfamiliar person (a stranger). We found that OXT treatment induced a tendency to spend more time looking into the eyes of familiar persons (partner and close friend) as compared to placebo. This effect was not evident in the self and unfamiliar conditions. Independent of treatment, volunteers scoring high on autistic-like traits (AQ-high) spent less time looking at the eyes of all faces except their partner. Collectively, our results show that the OXT system is involved in facilitating an attentional bias towards the eye region of familiar faces, which convey safety and support, especially in anxious contexts. In contrast, autistic-like traits were associated with reduced attention to the eye region of a face regardless of familiarity and OXT-treatment.

Humans can use their previous experience in form of statistical priors to improve decisions. It is, however, unclear how such priors are learned and represented. Importantly, it has remained elusive whether prior learning is independent of the sensorimotor system involved in the learning process or not, as both modality-specific and modality-general learning have been reported in the past. Here, we used a saccadic eye movement task to probe the learning and representation of a spatial prior across a few trials. In this task, learning occurs in an unsupervised manner and through encountering trial-by-trial visual hints drawn from a distribution centered on the target location. Using a model-comparison approach, we found that participants' prior knowledge is largely represented in the form of their previous motor actions, with minimal influence from the previously seen visual hints. By using two different motor contexts for response (looking either at the estimated target location, or exactly opposite to it), we could further compare whether prior experience obtained in one motor context can be transferred to the other. Although learning curves were highly similar, and participants seemed to use the same strategy for both response types, they could not fully transfer their knowledge between contexts, as performance and confidence ratings dropped after a switch of the required response. Together, our results suggest that humans preferably use the internal representations of their previous motor actions, rather than past incoming sensory information, to form statistical sensorimotor priors on the timescale of a few trials.

Developmental research, like many fields, is plagued by low sample sizes and inconclusive findings. The problem is amplified by the difficulties associated with recruiting infant participants for research as well as the increased variability in infant responses. With sequential testing designs providing a viable alternative to paradigms facing such issues, the current study implemented a Sequential Bayes Factor (SBF) design on three findings in the developmental literature. In particular, using the framework described by Schönbrödt and colleagues (2017), we examined infants' sensitivity to mispronunciations of familiar words, their learning of novel word-object associations from cross-situational learning paradigms, and their assumption of mutual exclusivity in assigning novel labels to novel objects. We tested an initial sample of 20 participants in each study, incrementally increasing sample size by one and computing a Bayes Factor with each additional participant. In one study, we were able to obtain moderate evidence for the alternate hypotheses despite testing less than half the number of participants as in the original study. We did not replicate the findings of the cross-situational learning study. Indeed, the data were five times more likely under the null hypothesis, allowing us to conclude that infants did not recognize the trained word-object associations presented in the task. We discuss these findings in light of the advantages and disadvantages of using a SBF design in developmental research while also providing researchers with an account of how we implemented this design across multiple studies.