Systematic review and meta-analysis of AI-based conversational agents for promoting mental health and well-being

npj Digital Medicine, Journal Year: 2023, Volume and Issue: 6(1)

Published: Dec. 19, 2023

Abstract Conversational artificial intelligence (AI), particularly AI-based conversational agents (CAs), is gaining traction in mental health care. Despite their growing usage, there a scarcity of comprehensive evaluations impact on and well-being. This systematic review meta-analysis aims to fill this gap by synthesizing evidence the effectiveness CAs improving factors influencing user experience. Twelve databases were searched for experimental studies CAs’ effects illnesses psychological well-being published before May 26, 2023. Out 7834 records, 35 eligible identified review, out which 15 randomized controlled trials included meta-analysis. The revealed that significantly reduce symptoms depression (Hedge’s g 0.64 [95% CI 0.17–1.12]) distress 0.7 0.18–1.22]). These more pronounced are multimodal, generative AI-based, integrated with mobile/instant messaging apps, targeting clinical/subclinical elderly populations. However, CA-based interventions showed no significant improvement overall 0.32 –0.13 0.78]). User experience was largely shaped quality human-AI therapeutic relationships, content engagement, effective communication. findings underscore potential addressing issues. Future research should investigate underlying mechanisms effectiveness, assess long-term across various outcomes, evaluate safe integration large language models (LLMs)

Language: Английский

---

From machine learning to deep learning: Advances of the recent data-driven paradigm shift in medicine and healthcare

Current Research in Biotechnology, Journal Year: 2023, Volume and Issue: 7, P. 100164 - 100164

Published: Nov. 22, 2023

The medicine and healthcare sector has been evolving advancing very fast. advancement initiated shaped by the applications of data-driven, robust, efficient machine learning (ML) to deep (DL) technologies. ML in medical is developing quickly, causing rapid progress, reshaping medicine, improving clinician patient experiences. technologies evolved into data-hungry DL approaches, which are more robust dealing with data. This article reviews some critical data-driven aspects intelligence field. In this direction, illustrated recent progress science using two categories: firstly, development data uses and, secondly, Chabot particularly on ChatGPT. Here, we discuss ML, DL, transition requirements from DL. To science, illustrate prospective studies image data, newly interpretation EMR or EHR, big personalized dataset shifts artificial (AI). Simultaneously, recently developed DL-enabled ChatGPT technology. Finally, summarize broad role significant challenges for implementing healthcare. overview paradigm shift will benefit researchers immensely.

Language: Английский

---

Overview of Chatbots with special emphasis on artificial intelligence-enabled ChatGPT in medical science

Frontiers in Artificial Intelligence, Journal Year: 2023, Volume and Issue: 6

Published: Oct. 31, 2023

The release of ChatGPT has initiated new thinking about AI-based Chatbot and its application drawn huge public attention worldwide. Researchers doctors have started the promise AI-related large language models in medicine during past few months. Here, comprehensive review highlighted overview their current role medicine. Firstly, general idea Chatbots, evolution, architecture, medical use are discussed. Secondly, is discussed with special emphasis medicine, architecture training methods, diagnosis treatment, research ethical issues, a comparison other NLP illustrated. article also limitations prospects ChatGPT. In future, these will immense healthcare. However, more needed this direction.

Language: Английский

---

Facilitating Self-Guided Mental Health Interventions Through Human-Language Model Interaction: A Case Study of Cognitive Restructuring

Published: May 11, 2024

Self-guided mental health interventions, such as "do-it-yourself" tools to learn and practice coping strategies, show great promise improve access care. However, these interventions are often cognitively demanding emotionally triggering, creating accessibility barriers that limit their wide-scale implementation adoption. In this paper, we study how human-language model interaction can support self-guided interventions. We take cognitive restructuring, an evidence-based therapeutic technique overcome negative thinking, a case study. IRB-approved randomized field on large website with 15,531 participants, design evaluate system uses language models people through various steps of restructuring. Our findings reveal our positively impacts emotional intensity for 67% participants helps 65% thoughts. Although adolescents report relatively worse outcomes, find tailored simplify generations overall effectiveness equity.

Language: Английский

---

Use of automated conversational agents in improving young population mental health: a scoping review

npj Digital Medicine, Journal Year: 2024, Volume and Issue: 7(1)

Published: March 19, 2024

Automated conversational agents (CAs) emerged as a promising solution in mental health interventions among young people. Therefore, the objective of this scoping review is to examine current state research into fully automated CAs mediated for emotional component Selected databases were searched March 2023. Included studies primary research, reporting on development, feasibility/usability, or evaluation tool improve population. Twenty-five included (N = 1707). Most applications standalone preventions targeting anxiety and depression. predominantly AI-based chatbots, using text main communication channel. Overall, results showed that problems are acceptable, engaging with high usability. However, clinical efficacy far less conclusive, since almost half reported no significant effect outcomes. Based these findings, it can be concluded there pressing need existing increase their well conducting more rigorous methodological area.

Language: Английский

---

Comparison of Conventional Anesthesia Nurse Education and an Artificial Intelligence Chatbot (ChatGPT) Intervention on Preoperative Anxiety: A Randomized Controlled Trial

Journal of PeriAnesthesia Nursing, Journal Year: 2024, Volume and Issue: 39(5), P. 767 - 771

Published: March 21, 2024

Language: Английский

---

User engagement, attitudes, and the effectiveness of chatbots as a mental health intervention: A systematic review

Computers in Human Behavior Artificial Humans, Journal Year: 2024, Volume and Issue: 2(2), P. 100081 - 100081

Published: July 2, 2024

In recent years, chatbots developed for mental health intervention purposes have been widely implemented to solve the challenges of workforce shortage and accessibility issues faced by traditional services. Nevertheless, research assessing technologies' potential risks remains sporadic. This review aims synthesise existing on engagement, user attitude, effectiveness psychological chatbot interventions. A systematic was conducted using relevant peer-reviewed literature since 2010. These studies were derived from six databases: PubMed, PsycINFO, Web Science, Science Direct, Scopus IEEE Xplore. Engagement level with that complied digital standards, lead positive outcomes. Although users had some uncertainties about usability these tools, attitudes towards regarding experience acceptability frequently identified due chatbots' capabilities unique functions. High levels outcome efficacy found those depression. The differences in demographics, approaches, featured technologies could also influence extent performances. Positive engagement chatbots, as well outcomes, shows technology is a promising modality intervention. However, implementing them amongst demographics or novel features should be carefully considered. Further mainstream evaluating simultaneously standardised measures necessary development.

Language: Английский

---

Next-Generation Cognitive-Behavioral Therapy for Depression: Integrating Digital Tools, Teletherapy, and Personalization for Enhanced Mental Health Outcomes

Medicina, Journal Year: 2025, Volume and Issue: 61(3), P. 431 - 431

Published: Feb. 28, 2025

Background and Objectives: This systematic review aims to present the latest developments in next-generation CBT interventions of digital support tools, teletherapies, personalized treatment modules enhancing accessibility, improving adherence, optimizing therapeutic outcomes for depression. Materials Methods: analyzed 81 PRISMA-guided studies on efficacy, feasibility, applicability NG-CBT approaches. Other important innovations include web-based interventions, AI-operated chatbots, teletherapy platforms, each which serves as a critical challenge delivering mental health care. Key messages have emerged regarding technological readiness, patient engagement, changing role therapists within context Results: Findings indicate that improve accessibility engagement while maintaining clinical effectiveness. Personalized tools enhance platforms provide scalable cost-effective alternatives traditional therapy. Conclusions: Such promise great avenues decreasing global burden depression quality life through novel, accessible, high-quality

Language: Английский

---

AI as the Therapist: Student Insights on the Challenges of Using Generative AI for School Mental Health Frameworks

Behavioral Sciences, Journal Year: 2025, Volume and Issue: 15(3), P. 287 - 287

Published: Feb. 28, 2025

The integration of generative AI (GenAI) in school-based mental health services presents new opportunities and challenges. This study focuses on the challenges using GenAI chatbots as therapeutic tools by exploring secondary school students’ perceptions such applications. data were collected from students who had both theoretical practical experience with GenAI. Based Grodniewicz Hohol’s framework highlighting “Problem a Confused Therapist”, Non-human Narrowly Intelligent qualitative student reflections examined thematic analysis. findings revealed that while acknowledged AI’s benefits, accessibility non-judgemental feedback, they expressed significant concerns about lack empathy, trust, adaptability. implications underscore need for chatbot use to be complemented in-person counselling, emphasising importance human oversight AI-augmented care. contributes deeper understanding how advanced can ethically effectively incorporated into frameworks, balancing technological potential essential interaction.

Language: Английский

---

Demographic and clinical characteristics associated with anxiety and depressive symptom outcomes in users of a digital mental health intervention incorporating a relational agent

BMC Psychiatry, Journal Year: 2024, Volume and Issue: 24(1)

Published: Jan. 30, 2024

Abstract Background Digital mental health interventions (DMHIs) may reduce treatment access issues for those experiencing depressive and/or anxiety symptoms. DMHIs that incorporate relational agents offer unique ways to engage and respond users potentially help provider burden. This study tested Woebot Mood & Anxiety (W-MA-02), a DMHI employs , agent incorporates elements of several evidence-based psychotherapies, among with baseline clinical levels or Changes in self-reported symptoms over 8 weeks were measured, along the association between each these outcomes demographic characteristics. Methods exploratory, single-arm, 8-week 256 adults yielded non-mutually exclusive subsamples either at baseline. Week Patient Health Questionnaire-8 (PHQ-8) changes measured subsample (PHQ-8 ≥ 10). Generalized Disorder-7 (GAD-7) (GAD-7 Demographic characteristics examined symptom via bivariate multiple regression models adjusted W-MA-02 utilization. Characteristics included age, sex birth, race/ethnicity, marital status, education, sexual orientation, employment insurance, symptoms, concurrent psychotherapeutic psychotropic medication treatments during study. Results Both predominantly female, educated, non-Hispanic white, averaged 38 37 years respectively. The had significant reductions (mean change =—7.28, SD = 5.91, Cohen’s d -1.23, p < 0.01); -7.45, 5.99, -1.24, 0.01). No associations found educational background changes. Significant treatment, severity found. Conclusions present suggests early promise as an intervention depression Although exploratory nature, this revealed potential user associated can be investigated future studies. Trial Registration was retrospectively registered on ClinicalTrials.gov (#NCT05672745) January 5th, 2023.

Language: Английский

---