Jmir Mental Health最新文献

Background: Alcohol use disorder (AUD) is associated with cognitive impairments that are known to affect the outcomes of conventional treatment. Digital cognitive training programs have been examined as a possible way of addressing these overlooked challenges. Existing findings regarding the efficacy of such training programs are divergent, and further studies are warranted to examine more engaging cognitive training programs using the latest technology. Smartphone-based training built upon the principles of serious gaming would not only increase the accessibility of the program, but it could also increase the motivation of the patients, potentially maximizing adherence to the training program.

Objective: The aim of the present feasibility and efficacy study was to examine the feasibility and acceptability of the Brain+ Alco-Recover app (Brain+ A/S) with gamified elements among patients with AUD when delivered as an add-on to treatment-as-usual (TAU) and with minimal guidance from health care practitioners. In addition, the effects on cognitive and alcohol-related outcomes were examined.

Methods: A total of 72 outpatients were randomized into either group A, experimental + TAU (n=36), or group B, sham + TAU (n=36), and they had to complete a 1-month training program in addition to primary treatment. Self-reported experience at the 6-month follow-up as well as actual game usage was used to determine the feasibility of the training program. Cognitive performance and alcohol consumption were assessed as well.

Results: The patients in both groups reported a high level of acceptability, and up to 83% of the patients in the experimental group met the minimum requirements for the usage of the app. The experimental group also demonstrated significant improvements in working memory (P<.001). Although no significant differences were found between the 2 groups regarding clinical outcomes, a greater reduction in alcohol consumption was evident at the 6-month follow-up in the experimental group.

Conclusions: The acceptability and adherence to the minimum training requirements deems the gamified Brain+ app as a feasible tool for cognitive training when delivered as an add-on to TAU. Furthermore, the potential improvements in cognitive functions should be further replicated in a larger-scale trial to assess whether these could be used to improve the treatment of AUD in the future.

International registered report identifier (irrid): RR2-10.3389/fpsyt.2021.727001.

Background: The field of speech emotion recognition (SER) encompasses a wide variety of approaches, with artificial intelligence technologies providing improvements in recent years. In the domain of mental health, the links between individuals' emotional states and pathological diagnoses are of particular interest.

Objective: This study aimed to investigate the performance of tools combining SER and artificial intelligence approaches with a view to their use within clinical contexts and to determine the extent to which SER technologies have already been applied within clinical contexts.

Methods: The review includes studies applied to speech (audio) signals for a select set of pathologies or disorders and only includes those studies that evaluate diagnostic performance using machine learning performance metrics or statistical correlation measures. The PubMed, IEEE Xplore, arXiv, and ScienceDirect databases were queried as recently as February 2025. The Quality Assessment of Diagnostic Accuracy Studies tool was used to measure the risk of bias.

Results: A total of 14 articles were included in the final review. The included papers addressed suicide risk (3/14, 21%), depression (8/14, 57%), and psychotic disorders (3/14, 21%).

Conclusions: SER technologies are mostly used indirectly in mental health research and in a wide variety of ways, including different architectures, datasets, and pathologies. This diversity makes a direct assessment of the technology challenging. Nonetheless, promising results are obtained in various studies that attempt to diagnose patients based on either indirect or direct results from SER models. These results highlight the potential for this technology to be used within a clinical setting. Future work should focus on how clinicians can use these technologies collaboratively.

Trial registration: PROSPERO CRD420251006669; https://www.crd.york.ac.uk/PROSPERO/view/CRD420251006669.

Background: Accessible ecological momentary interventions deliver brief, real-time support integrated into daily routines. Interpersonal dynamics and maladaptive coping mechanisms can contribute to an individual's anxiety and depression. Both mindfulness and mentalization represent psychological constructs with the potential to mitigate the negative impact of interpersonal stressors.

Objective: This study aims to assess the feasibility and acceptability of an automated mindfulness- and mentalization-based ecological momentary intervention for common mental health problems as delivered via a mobile phone app.

Methods: The design was a parallel-group pilot randomized controlled trial with 1:1 allocation ratio and exploratory framework. Recruitment of participants experiencing common mental health issues was internet-based from a university setting. Eligible participants were randomly allocated to fully automated mindfulness- or mentalization-based ecological momentary interventions via computer-generated randomization. Participants were blind to the alternative intervention options. Outcomes were self-assessed through questionnaires after 4 weeks. Primary outcomes were feasibility (recruitment, retention, and adherence) and acceptability (satisfaction ratings and qualitative feedback). Secondary outcomes included changes in depression (Patient Health Questionnaire-9 [PHQ-9]) and anxiety (Generalized Anxiety Disorder Questionnaire-7 [GAD-7]) scores.

Results: A total of 84 participants were randomized (42 to each group). The interventions demonstrated good feasibility with an 89.2% retention rate and a mean adherence of 87.69% (SD 11.3%) across both groups. Acceptability ratings were positive, with favorable scores for ease of engagement (mean 5.20, SD 1.6), overall enjoyment (mean 5.15, SD 1.2), and likelihood of recommending the app (mean 5.11, SD 1.6) on a 7-point scale. For primary outcomes, both groups showed significant within-group reductions in PHQ-9 and GAD-7 scores, with moderate to large effect sizes (Cohen d=-0.68 to -0.81), with no significant difference between groups. Both treatments demonstrated clinically significant change, with 33 (44%) participants in both groups no longer meeting caseness criteria for anxiety and depression. Mindfulness performed better on improving assertiveness and perceived support compared to mentalization in the ecological momentary assessment data. One unintended harm was reported in the mindfulness arm, whereas none was reported in the mentalization arm.

Conclusions: This pilot trial suggests that both mindfulness- and mentalization-based ecological momentary interventions are feasible and acceptable for individuals with common mental health problems and warrant further evaluation.

Background: Artificial intelligence (AI), particularly large language models (LLMs), presents a significant opportunity to transform mental healthcare through scalable, on-demand support. While LLM-powered chatbots may help reduce barriers to care, their integration into clinical settings raises critical concerns regarding safety, reliability, and ethical oversight. A structured framework is needed to capture their benefits while addressing inherent risks. This paper introduces a conceptual model for prompt engineering, outlining core design principles for the responsible development of LLM-based mental health chatbots.

Objective: This paper proposes a comprehensive, layered framework for prompt engineering that integrates evidence-based therapeutic models, adaptive technology, and ethical safeguards. The objective is to propose and outline a practical foundation for developing AI-driven mental health interventions that are safe, effective, and clinically relevant.

Methods: We outline a layered architecture for an LLM-based mental health chatbot. The design incorporates: (1) an input layer with proactive risk detection; (2) a dialogue engine featuring a user state database for personalization and Retrieval-Augmented Generation (RAG) to ground responses in evidence-based therapies such as Cognitive Behavioral Therapy (CBT), Acceptance and Commitment Therapy (ACT), and Dialectical Behavior Therapy (DBT); and (3) a multi-tiered safety system, including a post-generation ethical filter and a continuous learning loop with therapist oversight.

Results: The primary contribution is the framework itself, which systematically embeds clinical principles and ethical safeguards into system design. We also propose a comparative validation strategy to evaluate the framework's added value against a baseline model. Its components are explicitly mapped to the FAITA-MH and READI frameworks, ensuring alignment with current scholarly standards for responsible AI development.

Conclusions: The framework offers a practical foundation for the responsible development of LLM-based mental health support. By outlining a layered architecture and aligning it with established evaluation standards, this work offers guidance for developing AI tools that are technically capable, safe, effective, and ethically sound. Future research should prioritize empirical validation of the framework through the phased, comparative approach introduced in this paper.

Clinicaltrial:

Background: Patients with mood or psychotic disorders experience high rates of unplanned hospital readmissions. Predicting the likelihood of readmission can guide discharge decisions and optimize patient care.

Objective: The purpose of this study is to evaluate the predictive power of structured variables from electronic health records for all-cause readmission across multiple sites within the Mass General Brigham health system and to assess the transportability of prediction models between sites.

Methods: This retrospective, multisite study analyzed structured variables from electronic health records separately for each site to develop in-site prediction models. The transportability of these models was evaluated by applying them across different sites. Predictive performance was measured using the F1-score, and additional adjustments were made to account for differences in predictor distributions.

Results: The study found that the relevant predictors of readmission varied significantly across sites. For instance, length of stay was a strong predictor at only 3 of the 4 sites. In-site prediction models achieved an average F1-score of 0.661, whereas cross-site predictions resulted in a lower average F1-score of 0.616. Efforts to improve transportability by adjusting for differences in predictor distributions did not improve performance.

Conclusions: The findings indicate that individual site-specific models are necessary to achieve reliable prediction accuracy. Furthermore, the results suggest that the current set of predictors may be insufficient for cross-site model transportability, highlighting the need for more advanced predictor variables and predictive algorithms to gain robust insights into the factors influencing early psychiatric readmissions.