Explore the vast range of titles available.

Mental health disorders significantly impact global populations, prompting the rise of digital mental health interventions, such as artificial intelligence (AI)-powered chatbots, to address gaps in access to care. This review explores the potential for a \"digital therapeutic alliance (DTA),\" emphasizing empathy, engagement, and alignment with traditional therapeutic principles to enhance user outcomes. The primary objective of this review was to identify key concepts underlying the DTA in AI-driven psychotherapeutic interventions for mental health. The secondary objective was to propose an initial definition of the DTA based on these identified concepts. The PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) for scoping reviews and Tavares de Souza's integrative review methodology were followed, encompassing systematic literature searches in Medline, Web of Science, PsycNet, and Google Scholar. Data from eligible studies were extracted and analyzed using Horvath et al's conceptual framework on a therapeutic alliance, focusing on goal alignment, task agreement, and the therapeutic bond, with quality assessed using the Newcastle-Ottawa Scale and Cochrane Risk of Bias Tool. A total of 28 studies were identified from an initial pool of 1294 articles after excluding duplicates and ineligible studies. These studies informed the development of a conceptual framework for a DTA, encompassing key elements such as goal alignment, task agreement, therapeutic bond, user engagement, and the facilitators and barriers affecting therapeutic outcomes. The interventions primarily focused on AI-powered chatbots, digital psychotherapy, and other digital tools. The findings of this integrative review provide a foundational framework for the concept of a DTA and report its potential to replicate key therapeutic mechanisms such as empathy, trust, and collaboration in AI-driven psychotherapeutic tools. While the DTA shows promise in enhancing accessibility and engagement in mental health care, further research and innovation are needed to address challenges such as personalization, ethical concerns, and long-term impact.

The use of social media (SoMe) during crisis and disaster situations (CaDs) has gained increasing attention across disciplines. However, existing research is highly fragmented and often focused on technical aspects, with a limited understanding of how and which psychosocial information is derived from SoMe in CaDs. This scoping review provides an overview of the current research landscape regarding the analysis of SoMe data during CaDs to obtain information about public mental health and psychosocial needs. It identifies key themes, methodological approaches, and research gaps, with a particular focus on relevance for the German context. Following a scoping review protocol, a structured database search was conducted in PubMed, Web of Science, and Scopus to identify peer-reviewed studies published up to 2025. A method of triangulation combining qualitative and quantitative approaches was applied. The studies were analyzed regarding the type of CaDs, geographical focus, classification systems, methods of analysis used, and inclusion of psychosocial aspects (such as affect and mental health status). Overall, we identified 179 studies that examined 267 CaDs. Of the included studies, 76% (136/179) focused on natural disasters, with biological CaDs representing 23% (41/179) of these events. For Germany, 5 studies were found, with only one covering storms, floods, or extreme temperatures, despite these making up most of the disasters in Germany per EM-DAT (Emergency Events Database) data. Most studies used datasets from Asia (especially China), while Africa was examined less often, pointing to differences in geographical representativeness. To infer mental health status or affective state, 47 studies used machine learning, 87 studies used lexicon-based approaches, and 25 studies used a combination; 14 studies used manual coding, and few studies did not explicitly mention their approach. Mental health outcomes ranged from affective valence (positive, negative, or neutral) to specific primary (eg, fear) and secondary (eg, denial) emotions and needs (eg, resources). Yet, few studies were based on theoretical models or included end-user perspectives. No study conducted real-time analysis; instead, all were retrospective. Additionally, current research focuses primarily on deficits (eg, psychological needs, negative affect, or stress), and often neglects positive mental health outcomes (eg, resilience and collective coping). This scoping review underlines the rising popularity of SoMe analysis in CaDs regarding public mental health and needs. Although different techniques were developed and tested, there remain major gaps in real-time application, end-user integration, and contextual adaptation-particularly for underrepresented regions such as Africa, but also in countries such as Germany. As most models were developed or tested retrospectively (eg, using data from the COVID-19 pandemic), future research should examine the validity and tenability of such models in real-time monitoring and data, and emphasize more user-centered design and participatory research, theoretical grounding, and practical utility.

In recent years, artificial intelligence (AI) has driven the rapid development of AI mental health chatbots. Most current reviews investigated the effectiveness of rule-based or retrieval-based chatbots. To date, there is no comprehensive review that systematically synthesizes the effect of generative AI (GenAI) chatbot's impact on mental health. This review aims to (1) narratively synthesize existing GenAI mental health chatbots' technical features, treatment and research designs, and sample characteristics through a systematic review of quantitative studies and (2) quantify the effectiveness and key moderators of these rigorously designed trials on GenAI mental health chatbots through a meta-analysis of only randomized controlled trials (RCTs). The search strategy includes 11 database searching, backward citation tracking, and a manual ad hoc search to update literature. This thorough literature search, completed in March 2025, returned 5555 records for screening. The systematic review included studies that (1) used generative or hybrid (rule/retrieval-based and generative) AI-based chatbots to deliver interventions and (2) quantitatively measured mental health-related outcomes. The meta-analysis has additional inclusion criteria: (1) studies must be RCTs, (2) must measure negative mental health issues, (3) the comparison group must not have chatbot features, and (4) must provide enough statistics for effect size calculation. We followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) checklist and registered the protocol retrospectively during the revision process (September 18, 2025). In meta-regression, data were synthesized in R software using a random-effects model. The narrative synthesis of 26 studies revealed that (1) GenAI chatbot interventions mostly took place in non-WEIRD countries (non-Western, Educated, Industrialized, Rich, and Democratic) and (2) there is a lack of studies focusing on young children and older adults. The meta-analysis of 14 RCTs showed a statistically significant effect (effect size [ES]=0.30, P=.047, N=6314, 95% CI 0.004, 0.59, 95% prediction interval [PI] -0.85, 1.67), which means that GenAI chatbots are, on average, effective in reducing negative mental health issues, such as depression, anxiety, among others. We found that social-oriented chatbots (ie, those that mainly provide social interactions) are more effective than task-oriented programs (ie, those that assist with specific tasks). Risk of bias in the nonrandomized studies and RCTs was assessed using Cochrane ROBINS-I (Risk Of Bias In Non-randomised Studies - of Interventions) and RoB2 (revised Cochrane risk-of-bias tool for randomized trials), respectively, indicating a moderate amount of risk. One main limitation of this meta-analysis is the small number of studies (n=14) included. By identifying research gaps, we suggest that future researchers investigate user groups such as adolescents and older adults, outcomes other than depression and anxiety, cultural adaptations in non-WEIRD countries, ways to streamline chatbots in usual care practices, and explore applications in diverse settings. More importantly, we cannot ignore GenAI chatbots' risks while acknowledging their promise. This review also emphasized several ethical implications.

Depression is a prevalent mental health disorder and a leading cause of disability worldwide, creating substantial personal and societal burdens. Digital mental health interventions have emerged as accessible and scalable solutions, with artificial intelligence (AI)-driven chatbots increasingly applied to deliver therapeutic content, monitor symptoms, and provide personalized support. However, limited evidence exists on how chatbot interaction features influence treatment adherence and clinical outcomes in depression. This systematic review aimed to evaluate the clinical effectiveness of AI-driven chatbots for depression and to examine the associations between chatbot characteristics, treatment outcomes, and user adherence. A systematic review and meta-analysis were conducted following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines, searching 6 databases (Web of Science, Scopus, PubMed, IEEE Xplore, Embase, and APA PsycINFO) for randomized controlled trials (RCTs) published before May 30, 2025. Eligible studies involved individuals with depression or depressive symptoms receiving AI-driven chatbot, conversational agent, or virtual therapist interventions, with outcomes assessed using the Patient Health Questionnaire-9 (PHQ-9). Data extraction included chatbot type, interaction features, adherence, and standardized mean differences (SMDs) for symptom change. Risk of bias was assessed using the Cochrane Risk of Bias tool version 2 (RoB 2). Random-effects meta-analyses were performed with the Hartung-Knapp-Sidik-Jonkman adjustment. This review was preregistered on the Open Science Framework. A total of 11 RCTs involving 2220 participants (1091 in the intervention and 1129 in the control groups) were included. Using a random-effects model with Hartung-Knapp-Sidik-Jonkman adjustment, AI-driven chatbots showed a small-to-moderate reduction in depressive symptoms compared with control conditions, but the effect was not statistically significant (SMD=-0.46, 95% CI -1.02 to 0.10; P=.01; 95% prediction interval -1.50 to 0.58). Subgroup analyses of adherence did not show significant differences across the reported chatbot-type subgroups. In contrast, exploratory analyses of interaction features revealed more consistent patterns for adherence. Emotional responsiveness, structured feedback strategies, and interaction frequency were associated with higher adherence in high-scoring subgroups, whereas dialogue depth, self-disclosure encouragement, and user agency level showed weaker or inconsistent associations. For clinical outcomes, associations with interaction features were less consistent and more heterogeneous. This systematic review provides an interaction-focused synthesis of AI-driven chatbot interventions for depression, examining how interaction features relate to clinical outcomes and user adherence. Although overall effects were not statistically significant, emotional responsiveness, structured feedback, and interaction frequency were consistently associated with higher adherence. Engagement and outcomes may be influenced by distinct mechanisms. Limitations include the small number of RCTs, heterogeneity, reliance on study-reported descriptions, and potential publication bias. These findings highlight the importance of interaction design in developing scalable digital mental health interventions.

SMS text message reminders have been used to promote many health behaviors, such as improving diet and physical activity, managing chronic health conditions, reminding patients about medical appointments, and supporting medication adherence across a range of health conditions. Despite their promise, developing effective reminders tailored to specific patient populations is resource-intensive. AI may facilitate item development, and online research panels may provide an efficient way to test message content with target users prior to implementing large-scale trials. This study aimed to (1) develop a library of antidepressant adherence-promoting SMS text messages that are perceived as helpful, (2) test whether an online panel approach can be used to evaluate them, and (3) identify message characteristics perceived as most helpful by patients with depression taking antidepressant medication. In total, 83 SMS text message reminders were developed based on barriers to adherence and behavior change technique pairings, with approximately half authored by the study team, and half generated by AI. Using an online panel, we recruited 181 American adults with depression currently prescribed an antidepressant medication. Each participant rated a subset of messages on how much they thought each would help them remember to take their medication. Associations between message characteristics and ratings were estimated using generalized linear models in Stata. Survey weights were used in analyses to align the sample with national antidepressant user demographics. The online panel was able to rapidly recruit a sample of participants, who provided 7520 item ratings in total. AI-generated messages were rated as significantly more helpful than those authored by humans (adjusted mean difference 0.24 on a 5-point scale, 95% CI 0.12-0.36; P<.001). Messages addressing delayed symptom benefit were preferred over other adherence barriers, and behavior change techniques emphasizing self-monitoring (P<.001), habit formation (P<.001), and natural consequences (P<.001) received significantly higher ratings than those using external influence or support. No difference was observed between motivational and informational message content. Online panels offer a rapid, scalable approach to evaluating SMS text message reminders for patients currently taking antidepressants. When provided with specific instructions and human-led examples, AI can efficiently generate message content perceived to be helpful in promoting medication adherence. Given that AI-generated content received higher ratings than human-authored messages, future work may consider using this tool to support rapid intervention development. In addition, identifying common barriers to adherence and applying behavior change techniques to address those barriers can inform targeted message development and support adherence. Taken together, these findings demonstrate the utility of combining low-cost methods such as online panel research with AI to accelerate the design and preliminary evaluation of digital health interventions.

End-stage kidney disease (ESKD) imposes a significant global health burden, with patients often experiencing poor quality of life (QoL) due to psychological distress and low self-efficacy. Digital health interventions (DHIs) offer potential to address these challenges. However, their effects in this population remain inconsistent, and a comprehensive synthesis of the evidence is lacking. The present study aims to assess the impact of DHIs on the psychological health, self-efficacy, and QoL of patients with ESKD and to evaluate engagement, adherence, and satisfaction with these interventions. A comprehensive search was conducted across six electronic databases (PubMed, Web of Science, Cochrane Library, PsycINFO, Embase, and CINAHL) up to January 21, 2025. Randomized controlled trials (RCTs) examining the effects of DHIs on psychological health, self-efficacy, or QoL in patients with ESKD were included. Two reviewers independently screened studies, extracted data, and assessed the risk of bias using the Cochrane Risk of Bias Tool (RoB 2). A meta-analysis was performed using Review Manager 5.4, with subgroup analyses by treatment modality, intervention type, and duration. Evidence quality was assessed using the Grading of Recommendation, Assessment, Development, and Evaluation (GRADE) approach. Twenty-three RCTs involving 2407 patients with ESKD from 12 countries were included. DHIs significantly improved depression (standardized mean differences [SMD] -0.41, 95% CI -0.63 to -0.19, P=.003) and overall QoL (SMD 0.55, 95% CI 0.07-1.03, P=.03). While DHIs did not significantly improve overall self-efficacy (SMD 0.56, 95% CI -0.06 to 1.18, P=.08), a benefit was observed in patients on hemodialysis (SMD 0.59, 95% CI 0.34-0.83, P<.001). Engagement was favorable, with completion rates above 63%, adherence rates of 54%-79%, and generally positive patient feedback on DHIs. Application-based interventions improved self-efficacy (SMD 0.66, 95% CI 0.31-1.02, P<.001) and overall QoL (SMD 0.50, 95% CI 0.04-0.96, P=.003); telemedicine improved depression (SMD -0.88, 95% CI -1.21 to -0.56, P<.001) and self-efficacy (SMD 2.76, 95% CI 2.32-3.20, P<.001); and video-based interventions improved depression (SMD -0.34, 95% CI -0.55 to -0.13, P=.002) and overall QoL (SMD 0.31, 95% CI 0.15-0.46, P<.001). Due to high heterogeneity and risk of bias, evidence quality was rated as low for depression and overall QoL, moderate for general anxiety, and very low for stress and self-efficacy. DHIs can significantly improve the psychological health and QoL of patients with ESKD, particularly when tailored to patients' needs and delivered through interactive platforms such as apps and telemedicine. High engagement and positive patient feedback suggest good acceptability in clinical practice. However, low evidence quality warrants cautious interpretation. Future research should involve more high-quality RCTs and design DHIs that address the unique needs of older patients, patients on peritoneal dialysis, and kidney transplant recipients.

The association between loneliness and problematic media use has been evaluated in longitudinal studies and meta-analyses. However, previous meta-analyses have relied heavily on Pearson correlation coefficients, which may not fully account for the complexities of this association. Therefore, an updated meta-analysis incorporating more robust statistical models is needed. This study aimed to examine the longitudinal relationship between loneliness and problematic media use using various statistical models and to explore potential moderators that might influence the strength of this relationship. A systematic search was conducted using Scopus, APA PsycArticles, and PubMed to identify eligible studies up to January 24, 2024. Inclusion criteria included studies written in English, published in a peer-reviewed journal, reporting estimates of the longitudinal relationship between loneliness and problematic media use, and a longitudinal study design. Estimates of the longitudinal relationship were synthesized using a random-effects model. The Joanna Briggs Institute Critical Appraisal Checklist was used to assess the risk of bias. A total of 26 studies involving 24,798 individuals were included in the meta-analysis. Random-effects models revealed bidirectional relationships between loneliness and problematic media use. The longitudinal relationships were weaker when examined using estimated beta coefficients (rLPMU=0.10; rPMUL=0.09), followed by other statistical models (rLPMU=0.10; rPMUL=0.10) and the Pearson correlation coefficient (rLPMU=0.28; rPMUL= 0.29). Subgroup analyses demonstrated stable results for beta coefficients across various study-level characteristics (including country, lag length, measure of problematic media use, and measure of loneliness), except for type of problematic media use (Q=16.58; P<.001). This meta-analysis identified smaller effect sizes for the longitudinal relationships between loneliness and problematic media use compared with the previous meta-analysis. The weaker longitudinal relationship observed when using estimated beta coefficients highlights important methodological considerations for future meta-analyses. However, the contour-enhanced funnel plot and Egger regression test revealed an asymmetrical pattern, emphasizing the need for more longitudinal studies in this area.

Adolescents living with HIV face higher rates of mental health morbidity compared to other age groups, particularly depressive symptoms, while access to specialized services remains limited in many low- and middle-income countries. Chatbots offer a promising, low-cost approach to delivering structured mental health support in resource-constrained settings; however, practical guidance on how to develop such tools with end-user involvement remains scarce. This tutorial provides a step-by-step guide to the human-centered design and development of a mental health chatbot for adolescents living with HIV, illustrated through the creation of EVA ( Educación, Vinculación, y Autoayuda ), a chatbot cocreated with adolescents living with HIV in Peru. Guided by human-centered design principles, the tutorial covers three key steps: (1) understanding user needs through qualitative research, (2) iterative chatbot development with a Youth Advisory Board across five structured sessions, and (3) external review and testing before launch. Throughout the process, adolescents contributed to defining the chatbot’s tone, visual identity, navigation structure, and content priorities. The chatbot was built using a low-cost messaging platform and incorporated multimedia components, including brief animated videos, to enhance engagement. Throughout development, iterative testing with the Youth Advisory Board and external health care professionals informed refinements in usability, content clarity, emotional tone, and accessibility. This tutorial synthesizes key methodological decisions, lessons learned, and challenges encountered, providing practical guidance for researchers and practitioners seeking to develop similar adolescent-centered digital mental health tools in low- and middle-income countries. Key takeaways include the importance of early and sustained adolescent involvement, the value of iterative prototyping, and the feasibility of building functional chatbots with limited resources to help address the health service gap experienced by adolescents living with HIV.

Mental ill health is a leading cause of disability worldwide, but access to evidence-based support remains limited. Digital mental health interventions offer a timely and low-cost solution. However, improvements in clinical outcomes are reliant on user engagement, which can be low for digital interventions. User characteristics, including demographics and personality traits, could be used to personalize platforms to promote longer-term engagement and improved outcomes. This study aims to investigate how character strengths, a set of positive personality traits, influence engagement patterns with moderated online social therapy, a national digital mental health platform offering individualized, evidence-based digital mental health treatment for young people aged 12-25 years. Data from 6967 young people who enrolled with moderated online social therapy between August 2021 and July 2023 were analyzed. Longitudinal analyses were used to investigate whether scores on 3-character strength dimensions (\"social harmony,\" \"positive determination,\" and \"courage and creativity\") were associated with (1) an accelerated or decelerated rate of dropout from the platform and (2) patterns of engagement over the first 12 weeks following onboarding. Engagement metrics were time spent on the platform, number of sessions on the platform, use of the embedded social network, and messages with the clinical team. On average, young people used the platform for 72.64 (SD 106.64) days. The 3-character strengths were associated with distinct engagement patterns during this time. Individuals scoring higher on \"social harmony\" demonstrated an accelerated dropout rate (coefficient=-0.15, 95% CI -0.26 to -0.04; P=.008). Interestingly, higher scores on this character strength were associated with high rates of initial engagement but a more precipitous decline in platform use over the first 12 weeks, in terms of time spent on the platform (β=-.01; SE 0.00; t2748=-5.05; P<.001) and the number of sessions completed (β=-.00; SE 0.00; t2837=-2.26; P=.02). In contrast, higher scores on \"positive determination\" and \"courage and creativity\" predicted more modest initial platform use but steadier engagement over time, in terms of time spent on the platform (\"positive determination\": β=.01; SE 0.00; t2748=4.05; P<.001 and \"courage and creativity\": β=.01; SE 0.00; t2748=2.66; P=.008). Contrary to our predictions, character strengths did not predict use of the embedded social network or the number of messages sent to the clinical team. Our findings illustrate how character strengths predict distinct engagement trajectories on a digital mental health platform. Specifically, individuals higher on \"social harmony\" showed high initial engagement that quickly declined, while those higher on \"positive determination\" and \"courage and creativity\" demonstrated lower initial engagement but a steadier use of the platform over time. The findings of this study demonstrate an opportunity for digital mental health interventions to be tailored to individual characteristics in a way that would promote greater initial and ongoing engagement.