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

---

Chatbots in Health Care: Connecting Patients to Information

Canadian Journal of Health Technologies, Journal Year: 2024, Volume and Issue: 4(1)

Published: Jan. 22, 2024

Why Is This an Issue? Artificial intelligence (AI) is increasingly being used in health care settings. Chatbots geared toward patient use are becoming more widely available, but the clinical evidence of their effectiveness remains limited. What Technology? AI-based chatbots computer programs or software applications that have been designed to engage simulated conversation with humans using humanlike language. can help save time and allow them focus on high-level creative strategic thinking by taking over routine repetitive tasks, such as automated customer service chats, appointments, staff scheduling. Potential Impact? Anyone access internet-enabled a smartphone could these information. provide patients 24/7 information, symptom assessment, supportive medication reminders, appointment scheduling, allowing information when providers unavailable. There appear be trends efficacy user satisfaction, support still established. Existing mostly free for access, although some developers charge fees additional features content. Some apps may prescribed providers. These covered insurance licensed developer. Else Do We Need Know? Ethical data privacy issues remain top mind considering widespread implementation settings. ChatGPT other AI tools were not developed specifically do necessarily level required information. They also trained historical datasets responses based most current recommendations data. The development AI-specific ethical frameworks facilitate safer consistent preventing misuse technologies minimizing spread misinformation. require human oversight terms moderation troubleshooting.

Language: Английский

---

Embodied Conversational Agents for Chronic Diseases: Scoping Review

Journal of Medical Internet Research, Journal Year: 2023, Volume and Issue: 26, P. e47134 - e47134

Published: Nov. 29, 2023

Embodied conversational agents (ECAs) are computer-generated animated humanlike characters that interact with users through verbal and nonverbal behavioral cues. They increasingly used in a range of fields, including health care.

Language: Английский

---

Factors influencing patient engagement in mental health chatbots: A thematic analysis of findings from a systematic review of reviews

Digital Health, Journal Year: 2024, Volume and Issue: 10

Published: Jan. 1, 2024

Introduction Mental health disorders affect millions of people worldwide. Chatbots are a new technology that can help users with mental issues by providing innovative features. This article aimed to conduct systematic review reviews on chatbots in services and synthesized the evidence factors influencing patient engagement chatbots. Methods study reviewed literature from 2000 2024 using qualitative analysis. The authors conducted search several databases, such as PubMed, Scopus, ProQuest, Cochrane database reviews, identify relevant studies topic. quality selected was assessed Critical Appraisal Skills Programme appraisal checklist data obtained were subjected thematic analysis utilizing Boyatzis's code development approach. Results resulted 1494 papers, which 10 included after screening process. assessment scored papers within moderate level. revealed four main themes: chatbot design, outcomes, user perceptions, characteristics. Conclusion research proposed some ways use color music design. It also provided multidimensional factors, offered insights for developers researchers, highlighted potential improve patient-centered person-centered care services.

Language: Английский

---

Attrition in Conversational Agent–Delivered Mental Health Interventions: Systematic Review and Meta-Analysis

Journal of Medical Internet Research, Journal Year: 2023, Volume and Issue: 26, P. e48168 - e48168

Published: Dec. 4, 2023

Background Conversational agents (CAs) or chatbots are computer programs that mimic human conversation. They have the potential to improve access mental health interventions through automated, scalable, and personalized delivery of psychotherapeutic content. However, digital interventions, including those delivered by CAs, often high attrition rates. Identifying factors associated with is critical improving future clinical trials. Objective This review aims estimate overall differential rates in CA-delivered (CA interventions), evaluate impact study design intervention-related aspects on attrition, describe features aimed at reducing mitigating attrition. Methods We searched PubMed, Embase (Ovid), PsycINFO Cochrane Central Register Controlled Trials, Web Science, conducted a gray literature search Google Scholar June 2022. included randomized controlled trials compared CA against control groups excluded studies lasted for 1 session only used Wizard Oz interventions. also assessed risk bias using Risk Bias Tool 2.0. Random-effects proportional meta-analysis was applied calculate pooled dropout intervention groups. compare rate narrative summarize findings. Results The systematic retrieved 4566 records from peer-reviewed databases citation searches, which 41 (0.90%) met inclusion criteria. meta-analytic group 21.84% (95% CI 16.74%-27.36%; I2=94%). Short-term ≤8 weeks showed lower (18.05%, 95% 9.91%- 27.76%; I2=94.6%) than long-term >8 (26.59%, 20.09%-33.63%; I2=93.89%). Intervention participants were more likely attrit short-term (log odds ratio 1.22, 0.99-1.50; I2=21.89%) 1.33, 1.08-1.65; I2=49.43%). Intervention-related characteristics higher include stand-alone without support, not having symptom tracker feature, no visual representation CA, comparing waitlist controls. No participant-level factor reliably predicted Conclusions Our results indicated approximately one-fifth will drop out studies. High heterogeneities made it difficult generalize suggested should adopt blended use tracking, active controls rather controls, reduce rate. Trial Registration PROSPERO International Prospective Systematic Reviews CRD42022341415; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022341415

Language: Английский

---

Unleashing the potential of chatbots in mental health: bibliometric analysis

Frontiers in Psychiatry, Journal Year: 2025, Volume and Issue: 16

Published: Feb. 4, 2025

Background The proliferation of chatbots in the digital mental health sector is gaining momentum, offering a promising solution to address pressing shortage professionals. By providing accessible and convenient services support, are poised become primary technological intervention bridging gap between needs available resources. Objective This study undertakes thorough bibliometric analysis discourse on applications health, with objective elucidating underlying scientific patterns that emerge at intersection chatbot technology care global scale. Methods software Biblioshiny VOSviewer were used conduct comprehensive 261 articles published Web Science Core Collection 2015 2024. Publications distribution analyzed measure productivity countries, institutions, sources. Scientific collaboration networks generated analyze influence as well communications countries institutions. Research topics trends formulated by using keyword co-occurrence network. Results Over last decade, researches utilization has appeared be increasing steadily an annual rate 46.19%. United States have made significant contributions development expansion publications, accounting for 27.97% total research output 2452 citation counts. England came second US terms publications citations, followed Australia, China, France. National Center France ranked first among all Imperial College London University Zurich. number Journal Medical Internet was exceptionally high, 12.26% articles, JMIR Mental Health most influential publication sources average citations per article. Collaboration universities USA, Kingdom, Switzerland, Singapore demonstrated high level. network highlights prominent techniques this multidisciplinary area reveals 5 topics, showing overlap clusters. High-frequency such “ChatGPT”, “machine learning”, “large language models” underscore current state research, highlighting cutting-edge advancements frontiers field. Conclusions provides in-depth status, associated over decade. It offers insights professionals without AI background individuals interested chatbots. findings suggest hold role promoting well-being exhibit considerable potential demonstrating empathy, curiosity, understanding, collaborative capabilities users.

Language: Английский

---

Behavior Change Support Systems for Self-Treating Procrastination: Systematic Search in App Stores and Analysis of Motivational Design Archetypes

Journal of Medical Internet Research, Journal Year: 2025, Volume and Issue: 27, P. e65214 - e65214

Published: Feb. 20, 2025

Background The phenomenon of procrastination refers to an individual’s conscious decision postpone the completion tasks despite being aware its adverse consequences in future. Extant research this field shows that is associated with increased levels anxiety and stress likelihood developing depression calls for development suitable interventions support individuals making lasting positive changes their behaviors. In parallel, practice has produced a plethora behavior change systems (BCSSs) aim provide low-threshold, accessible alternative in-person therapeutic approaches. Most these BCSSs can be considered motivational combine functional, utilitarian components hedonic eudaimonic design elements empower self-treatment. Although early studies have suggested potential benefits such BCSSs, on understanding specific characteristics self-treating still infancy. Objective response gap between research, we aimed analyze systemize multitude practical efforts self-treatment identify main archetypes emerged. Methods We conducted 3-step approach. First, identified 127 apps through systematic screening process German US Apple App Store Google Play Store. Second, systematically coded terms techniques targeted by functional or elements. Third, 2-step cluster analysis combat procrastination. Results A variety designs been developed implemented practice, our five archetypes: (1) structured progress monitor, (2) self-improvement guide, (3) productivity adventure, (4) emotional wellness coach, (5) social focus companion. target different psychological determinants successfully use extend beyond current state research. Conclusions results study foundation future endeavors examine comparative effects develop more effective tailored individual needs. For practitioners, findings reveal contemporary space may serve as blueprints guide systems. seeking health professionals treating procrastination, systemizes landscape apps, thereby facilitating selection one best aligns patient’s

Language: Английский

---

Health Care Professionals' Engagement With Digital Mental Health Interventions in the United Kingdom and China: Mixed Methods Study on Engagement Factors and Design Implications

JMIR Mental Health, Journal Year: 2025, Volume and Issue: 12, P. e67190 - e67190

Published: April 4, 2025

Abstract Background Mental health issues like occupational stress and burnout, compounded with the after-effects of COVID-19, have affected care professionals (HCPs) around world. Digital mental interventions (DMHIs) can be accessible effective in supporting well-being among HCPs. However, low engagement rates DMHIs are frequently reported, limiting potential effectiveness. More evidence is needed to reveal factors that impact HCPs’ decision adopt engage DMHIs. Objective This study aims explore motivation identify key affecting their engagement. Amongst these, we include cultural impacting DMHI perception Methods We used a mixed method approach, cross-sectional survey (n=438) semistructured interviews (n=25) HCPs from United Kingdom China. Participants were recruited one major public hospital each country. Results Our results demonstrated generally rate 2 countries. Several affect identified, including belonging underrepresented ethnic groups, limited knowledge, perceived need, lack time, needs for relevance personal-based support, elements self-stigma. The support recommendations Conclusions Although an ideal alternative HCPs, China still due multiple barriers. research develop evaluate tailored unique designs content various backgrounds.

Language: Английский

---

Virtual Reality and Artificial Intelligence as Psychological Countermeasures in Space and Other Isolated and Confined Environments: A Scoping Review

Acta Astronautica, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

---

Psychological insights into the research and practice of embodied conversational agents, chatbots and social assistive robots: a systematic meta-review

Behaviour and Information Technology, Journal Year: 2023, Volume and Issue: unknown, P. 1 - 41

Published: Nov. 27, 2023

This study presents a systematic literature search and narrative meta-review of the current state research on conversational agents (CAs), including embodied CAs, chatbots, social assistive robots (SARs). The investigation identifies 1,830 academic articles, which 315 articles satisfied inclusion criteria for review. Systematic reviews across various fields are reported, mental disorders, neurodevelopmental dementia/cognitive impairment, other medical conditions, elderly support, health promotion, health, education, industrial applications, agent characteristics, robot characteristics. highlights challenges in CA research, such as scarcity high-quality comparative studies acceptance CAs by users caregivers, particularly support. article also categorises ethical discussions into nine elements: privacy, safety, innovation, user acceptance, psychological attachment, care philosophy, evaluation, systems compatibility, rule development. It offers insights development future guidelines. role fostering human relationships through their function is emphasised to provide guidance subsequent implementation. As advancements technology continue progress, there an increasing demand sophisticated investigations addressing relationships, emotions, self.

Language: Английский

---