Clinical supervision is essential for trainees, preventing burnout and ensuring the effectiveness of their interventions. AI technologies offer increasing possibilities for developing clinical practices, with supervision being particularly suited for automation. The aim of this study is to evaluate the feasibility of using ChatGPT-4 as a supervisory tool in psychotherapy training. To achieve this, a clinical case was presented to three distinct groups (untrained AI, pre-trained AI, and qualified human supervisor), and their feedback was evaluated by Gestalt psychotherapy trainees using a Likert scale rating of satisfaction. Statistical analysis, using the statistical package SPSS version 25 and applying principal component analysis (PCA) and one-way analysis of variance (ANOVA), demonstrated significant differences in favor of pre-trained AI feedback. PCA highlighted four components of the questionnaire: relational and emotional (C1), didactic and technical quality (C2), treatment support and development (C3), and professional orientation and adaptability (C4). The ratings of satisfaction obtained from the three kinds of supervisory feedback were compared using ANOVA. The feedback generated by the pre-trained AI (f2) was rated significantly higher than the other two (untrained AI feedback (f1) and human feedback (f3)) in C4; in C1, the superiority of f2 over f1 but not over f3 appears significant. These results suggest that AI, when appropriately calibrated, may be an appreciable tool for complementing the effectiveness of clinical supervision, offering an innovative blended supervision methodology, in particular in the area of career guidance.

Background: The study of complex systems, such as the psychotherapeutic encounter, transcends the mechanistic and reductionist methods for describing linear processes and needs suitable approaches to describe probabilistic and scarcely predictable phenomena. Objective: The present study undertakes a scoping review of research on the computational methods in psychotherapy to gather new developments in this field and to better understand the phenomena occurring in psychotherapeutic interactions as well as in human interaction more generally. Design: Online databases were used to identify papers published 2011–2022, from which we selected 18 publications from different resources, selected according to criteria established in advance and described in the text. A flow chart and a summary table of the articles consulted have been created. Results: The majority of publications (44.4%) reported combined computational and experimental approaches, so we grouped the studies according to the types of computational methods used. All but one of the studies collected measured data. All the studies confirmed the usefulness of predictive and learning models in the study of complex variables such as those belonging to psychological, psychopathological and psychotherapeutic processes. Conclusions: Research on computational methods will benefit from a careful selection of reference methods and standards. Therefore, this review represents an attempt to systematise the empirical literature on the applications of computational methods in psychotherapy research in order to offer clinicians an overview of the usefulness of these methods and the possibilities of their use in the various fields of application, highlighting their clinical implications, and ultimately attempting to identify potential opportunities for further research.

Clinical supervision is an essential element in trainees, preventing burnout and ensuring the effectiveness of their intervention. AI technologies offer increasing possibilities for the development of clinical practices, among it supervision appears to possess the ideal characteristics for automation processes. In this study we test the capabilities of ChatGPT-4 to provide supervisory feedback by then placing them in comparison with feedback produced by a qualified supervisor. Two ChatGPT-4-generated feedbacks (the first one produced by a naïve identity and the second one by a trained identity) and one human-produced feedback were evaluated by means of a liking questionnaire, which was filled out to a group of gestalt psychotherapy trainees. Principal Component Analysis (PCA) highlighted 4 components of the questionnaire: relational and emotional dimensions (C1), didactic and technical quality (C2), treatment support and development (C3), and professional orientation and adaptability (C4). The ratings of satisfaction, obtained from the three supervisory feedbacks, were compared by applying 1-way analysis of variance (ANOVA). Statistical evaluations were performed using the statistical package SPSS version 25. The feedback generated by pre-trained AI (f2) was rated significantly higher than the other two (untrained AI feedback (f1) and human feedback (f3) in C4; in C1 the superiority of f2 over f1 but not over f3 appears significant. These results suggest that the use of pre-trained AI may be an appreciable option for increasing the effectiveness of clinical supervision in some specific areas, including especially career guidance.

Background/Objectives: Gestalt therapy traditionally opposes categorical diagnostic labelling due to its fundamental inconsistency with phenomenological and process-oriented ontology. However, this epistemological rigour can limit integration with structured evidence-based interventions for complex personality organizations such as Borderline Personality Disorder (BPD). Despite the evidence base for DBT and Schema Therapy in treating BPD, these approaches may inadvertently minimize the lived phenomenological experience and organismic wisdom central to recovery. Meanwhile, Gestalt therapy’s anti-diagnostic stance limits its integration with structured evidence-based protocols. This paper proposes a hybrid theoretical model that addresses this gap by integrating the clinical epistemology of Gestalt therapy with Linehan’s biosocial theory of Dialectical Behaviour Therapy (DBT) and schema-focused interventions, while preserving the core principles of Gestalt. Methods: we present a model of theoretical integration that draws on Gestalt contact theory, the four modules of DBT (mindfulness, distress tolerance, emotional regulation, interpersonal effectiveness) and the experiential techniques of Schema Therapy. The integration focuses on the dialectic of acceptance and change, which mirrors Gestalt’s paradoxical theory of change. The proposed framework preserves the non-protocol dimension of Gestalt therapy while incorporating the pragmatic utility of DBT and Schema Therapy. Results: key conceptual contributions we propose include: (1) theorizing the “Draft Self” as the object and subject of therapeutic work, (2) integrating mindfulness and grounding as embodied processes within live Gestalt experiments, (3) activation techniques to explore the identity fragmentation endemic to BPD. Conclusions:his integration offers a coherent, embodied, and process-oriented framework for understanding and treating BPD that validates patients’ lived experience, mobilizes evidence-based interventions, and opens up meaningful intertheoretical dialogue.

Clinical supervision is crucial for the practice of psychotherapy and for training in it: it is a cornerstone of professional support, stimulating clinical reflection and the continuous development of skills. Recent studies explore the use of ChatGPT as a tool to support supervision: the crucial role of prompts in optimizing the effectiveness of Artificial Intelligence in this area emerges. This study has two main objectives: one is to develop a prompt framework by leveraging the evidence gathered in the two previous studies and testing its effectiveness. The other objective is to compare the performance of a free Large Language Model with that of other accessible paid models, with a view to inclusivity. The results show the surprising competitiveness of the free model and a significant improvement in the supervision feedback obtained, compared to that of previous studies, attributable to the characteristics of the new prompt, which includes precise instructions on the fundamental characteristics of good supervision. Artificial Intelligence can reduce professional hierarchies by democratizing expertise and represents a form of cognitive augmentation, as it extends the therapist's reflective abilities and promotes new forms of conversational supervision. The future ethical challenge will be to effectively combine technological innovation with the fundamental values of the caring professions.

According to modern neurobiological models of consciousness, Gestalt psychotherapy theory views perceptual experience as a phenomenon emerging from the interaction between interceptive and proprioceptive processes on the one hand and exteroceptive information on the other.This interaction, from a neurobiological perspective, can be imagined as occurring within the integrative activity of the thalamus, where information from both the body and the sensory organs converge in its nucleus, known as the Zona Incerta.The integrative process finally generates the perceptual gestalt, a preverbal experience of being in the world. In this sense, body states become part of the perceptual experience itself by determining the salient elements of an image.The perception and preference of colors seem to be a direct expression of this process of body-senses integration, which determines the basic qualities of color experience (brightness and color saturation) and the pleasant or unpleasant emotionality connected with color itself.The ambiguous image of a dress, which went viral in 2015, provides an additional tool to investigate color experience as some people see the dress as blue and black, others yellow and white.The present pilot study related the perception of the dress image to color preference using the Lüscher color test. Although it was a small sample of 100 subjects, a link emerged between preferred color and perceived color in the image. People who preferred blue or yellow saw the dress as blue or yellow, respectively, with a significantly high frequency. This finding needs to be further investigated by expanding the sample size and data collected. However, the survey evidence is strongly suggestive that color preference closely related to the body and emotions directly modifies perceptual experience.