In this work, we present the use of one artificial intelligence (AI) application (ChatGPT) to train another AI-based application. As the latter one, we show a dialogue system named Terabot, which was used in the therapy of psychiatric patients. Our study was motivated by the fact that for such a domain-specific system, it was difficult to acquire large real-life data samples to increase the training database: this would require recruiting more patients, which is both time-consuming and costly. To address this gap, we have employed a neural large language model: ChatGPT version 3.5, to generate data solely for training our dialogue system. During initial experiments, we identified intents that were most often misrecognized. Next, we fed ChatGPT with a series of prompts, which triggered the language model to generate numerous additional training entries, e.g., alternatives to the phrases that had been collected during initial experiments with healthy users. This way, we have enlarged the training dataset by 112%. In our case study, for testing, we used 2802 speech recordings originating from 32 psychiatric patients. As an evaluation metric, we used the accuracy of intent recognition. The speech samples were converted into text using automatic speech recognition (ASR). The analysis showed that the patients’ speech challenged the ASR module significantly, resulting in deteriorated speech recognition and, consequently, low accuracy of intent recognition. However, thanks to the augmentation of the training data with ChatGPT-generated data, the intent recognition accuracy increased by 13% relatively, reaching 86% in total. We also emulated the case of an error-free ASR and showed the impact of ASR misrecognitions on the intent recognition accuracy. Our study showcased the potential of using generative language models to develop other AI-based tools, such as dialogue systems.

Social anxiety disorder (SAD) is one of the most frequent mental disorders. Exposure to virtual reality can be a solution complementing standard CBT (cognitive-behavioral therapy) or can be used as an independent therapeutic tool. The study’s objective was to assess the safety and efficacy of using self-administered virtual reality exposure vs. CBT and CBT with virtual exposure. We assessed the efficacy of the applied intervention with the Leibowitz Social Anxiety Scale (LSAS). We compared three groups: CBT (n = 25), CBT + VR (n = 29), and self-administered therapy without aid of a therapist (n = 19). The results indicated that all three groups showed changes on the LSAS. The simple effect analysis showed that there were no differences between experimental conditions at T0 (session 1) and T1 (session 9) and that the only significant difference occurred at T2 (session 14). The pairwise comparisons showed that the participants in the VR condition scored higher on the LSAS score during the measurement at T2 than participants in CBT condition. Our study has several limitations. The presented initial study shows that the methods of CBT for social anxiety used so far are also effective, while the VR tool for self-therapy requires further research.

The co-occurrence of social anxiety symptoms and schizophrenia is a significant clinical problem. So far, social anxiety symptoms have been treated as an integral symptom of schizophrenia, receiving little attention as a target of direct therapeutic interventions. However, some evidence indicates that a high level of social anxiety in this group of patients may be a barrier to the recovery process. This feasibility study evaluated the use of a standard protocol for cognitive-behavioural therapy in the treatment of social phobia, in which social exposure was implemented with the usage of virtual reality (CBT + VRET). The study was conducted in a group of inpatients in a clinical psychiatric unit. Twenty inpatients diagnosed with schizophrenia and comorbid social anxiety symptoms were examined. Eleven patients were assigned to 10 weekly individual CBT+VRET interventions and nine to the control condition. Baseline and post-treatment assessments of social anxiety, psychotic symptoms, stigma, self-esteem, and depressive symptoms were measured before and after intervention. There was a decrease in social anxiety in the CBT+VRET group, while no such decrease was noted in the control group. This study provides preliminary evidence that CBT+VRET is acceptable, safe, and initial data that bears on the question of effectiveness for treating social anxiety disorder in people with schizophrenia. Future research should investigate the efficacy of CBT+VRET for the treatment of social anxiety symptoms and co-morbid schizophrenia in a larger randomised controlled trial.

: Self-stigma is a major barrier to personal and clinical recovery in people with mental illness. Although psychosocial interventions have been developed to reduce self-stigma, the exploration of group CBT-based interventions for hospitalised patients are less represented. The purpose of this trial is to investigate the effectiveness of a group CBT-based intervention aiming to reduce self-stigma and improve recovery-related outcomes such as self-esteem, stigma resistance and sense of coherence, which comes down to saying, “I am what I am”. A total of 104 patients admitted to the inpatient therapy were recruited to participate in a randomised controlled clinical trial, and 77 participants (46 in the intervention group and 31 in the control group) completed the trial. Constructs of interest were measured before and after the intervention. The results showed that the evaluated intervention was effective in improving sense of coherence and stigma resistance, compared to treatment as usual (TAU). The level of self-stigma significantly decreased in both the intervention and control groups, but no statistically significant difference was observed between the groups. The limitations of the study include: the lack of assessment of the sustainability of the effects of therapy (follow-up), the presence of intensive interventions of the ward’s programme and patients pre-qualified for the ward based on admission criteria. The intervention “I am what I am,” has proven to be effective, especially in increasing the level of personal resources needed to build clinical and personal recovery and to counteract the negative consequences of self-stigma.