Automated Digital Safety Planning Interventions for Young Adults: Qualitative Study Using Online Co-design Methods (Preprint) DOI
Jonah Meyerhoff, Sarah A Popowski, Tanvi Lakhtakia

и другие.

Опубликована: Дек. 3, 2024

BACKGROUND Young adults in the United States are experiencing accelerating rates of suicidal thoughts and behaviors but have lowest formal mental health care. Digital suicide prevention interventions potential to increase access care by circumventing attitudinal structural barriers that prevent These tools should be designed collaboration with young who lived experience suicide-related optimize acceptability use. OBJECTIVE This study aims identify needs, preferences, features for an automated SMS text messaging–based safety planning service support self-management among adults. METHODS We enrolled 30 (age 18-24 years) recent participate asynchronous remote focus groups via online private forum. Participants responded researcher-posted prompts were encouraged reply fellow participants—creating a threaded digital conversation. Researcher-posted centered on participants’ experiences thought behavior-related coping, planning, technologies behavior self-management. Focus group transcripts analyzed using thematic analysis extract key feature considerations tool. RESULTS adult participants indicated message–based intervention must meet their needs 2 ways. First, empowering them manage symptoms own acquiring effective coping skills. Second, leveraging adults’ existing social connections. also shared 3 technological intervention: (1) transparency about how functions, kinds actions it does not take, limits confidentiality, role human oversight within program; (2) strong privacy practices—data security around content data created would maintained used was extremely important given sensitive nature data; (3) usability, convenience, accessibility particularly participants—this includes having approachable engaging message tone, customizable delivery options (eg, length, number, focus), straightforward menu navigation. highlighted specific could core skill acquisition self-tracking, idea generation, reminders). CONCLUSIONS Engaging design process tool revealed critical addressed if is effectively expand evidence-based reach people at risk behaviors. Specifically, building skillfulness cope crises, deepening interpersonal connections, system transparency, privacy.

Язык: Английский

Using large language models in psychology DOI Open Access
Dorottya Demszky, Diyi Yang, David S. Yeager

и другие.

Nature Reviews Psychology, Год журнала: 2023, Номер unknown

Опубликована: Окт. 13, 2023

Язык: Английский

Процитировано

178
Efficiency in Language Understanding and Generation: An Evaluation of Four Open-Source Large Language Models DOI Creative Commons
Siu Ming Wong, Ho-fung Leung,

Ka Yan Wong

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Март 11, 2024

Abstract This study provides a comprehensive evaluation of the efficiency Large Language Models (LLMs) in performing diverse language understanding and generation tasks. Through systematic comparison open-source models including GPT-Neo, Bloom, FLAN-T5, Mistral-7B, research explores their performance across widely recognized benchmarks such as GLUE, SuperGLUE, LAMBADA, SQuAD. Our findings reveal significant variations model accuracy, computational efficiency, scalability, adaptability, underscoring influence architecture training paradigms on outcomes. The identifies key factors contributing to models' offers insights into potential optimization strategies for enhancing applicability real-world NLP applications. By highlighting strengths limitations current LLMs, this contributes ongoing development more effective, efficient, adaptable models, paving way future advancements field natural processing.

Язык: Английский

Процитировано

18
MISHA – A Chatbot-delivered Stress Management Coaching for Students: Pilot Randomized Controlled Trial (Preprint) DOI Creative Commons
Sandra Hauser-Ulrich, Natascha Lienhard, Hansjörg Künzli

и другие.

JMIR mhealth and uhealth, Год журнала: 2024, Номер 12, С. e54945 - e54945

Опубликована: Май 3, 2024

Globally, students face increasing mental health challenges, including elevated stress levels and declining well-being, leading to academic performance issues disorders. However, due stigma symptom underestimation, rarely seek effective management solutions. Conversational agents in the sector have shown promise reducing stress, depression, anxiety. Nevertheless, research on their effectiveness for with remains limited.

Язык: Английский

Процитировано

11
Designing Incremental Knowledge Enrichment in Generative Pre-trained Transformers DOI Creative Commons
Emilia A. Kowalczyk, Mateusz Nowakowski,

Z Brzezińska

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Апрель 1, 2024

Abstract This article presents a novel approach to Incremental Knowledge Enrichment tailored for GPT-Neo, addressing the challenge of keeping Large Language Models (LLMs) updated with latest information without undergoing comprehensive retraining. We introduce dynamic linking mechanism that enables real-time integration diverse data sources, thereby enhancing model's accuracy, timeliness, and relevance. Through rigorous evaluation, our method demonstrates significant improvements in model performance across several metrics. The research contributes scalable efficient solution one most pressing issues AI, potentially revolutionizing maintenance applicability LLMs. findings underscore feasibility creating more adaptive, responsive, sustainable generative models, opening new avenues future advancements field.

Язык: Английский

Процитировано

7
The potential of Large Language Models for social robots in special education DOI Creative Commons
Evdokia Voultsiou, Εleni Vrochidou, Lefteris Moussiades

и другие.

Progress in Artificial Intelligence, Год журнала: 2025, Номер unknown

Опубликована: Фев. 6, 2025

Язык: Английский

Процитировано

0
Artificial Intelligence vs. Human Expert: Licensed Mental Health Clinicians’ Blinded Evaluation of Ai-Generated and Expert Psychological Advice on Quality, Empathy, and Perceived Authorship DOI
Ludwig Franke Föyen,

Emma Carlotta Marie Zapel,

Mats Lekander

и другие.

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
Balancing Ethics and Opportunities: The Role of AI in Psychotherapy and Counselling DOI Creative Commons
Alexandra Bloch‐Atefi

Deleted Journal, Год журнала: 2025, Номер unknown

Опубликована: Март 2, 2025

The integration of artificial intelligence (AI) into psychotherapy and counselling practices presents both significant opportunities ethical challenges. AI applications, such as automated scheduling, AI-assisted note taking, client engagement tools, predictive analytics for needs, are transforming the delivery mental health care. However, considerations surrounding AI’s role in care complex multifaceted, necessitating careful scrutiny. This paper discusses required responsible implementation technologies counselling, focusing on data protection, consent, preservation therapeutic relationship. It argues that professional bodies educational institutions must collaborate to develop dynamic, adaptable guidelines ensure safe effective use tools. Furthermore, it emphasises need robust protection mechanisms safeguard sensitive information proposes strategies balance benefits with human connection

Язык: Английский

Процитировано

0
MedicalGLM: A Pediatric Medical Question Answering Model with a quality evaluation mechanism DOI
Xin Wang,

Zhaofei Sun,

Pingping Wang

и другие.

Journal of Biomedical Informatics, Год журнала: 2025, Номер unknown, С. 104793 - 104793

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0
General Research Perspectives with Human Spirit in Wider Range for Current Art Therapy DOI

Yu Nishikiori,

Masahiro Bando,

Akiyo Yoshioka

и другие.

Опубликована: Март 18, 2025

In actual medical practice and research, some factors are indispensable, such as practice, art therapy, various research. These will be combined, leading to future health or well-being. activities have groups for publication. They include literature writing, description, storytelling, artworks, artistic performance, music activity, treatment education, physicals dance, play, drama. Measuring would important includes physical, mental, social aspects behaviors. Future research on therapy in healthcare show combined approaches associated with evidence RCTs.

Язык: Английский

Процитировано

0
Embodied Conversational Agents Providing Motivational Interviewing to Improve Health-Related Behaviors: Scoping Review DOI Creative Commons
José Mercado, Ismael Edrein Espinosa‐Curiel, Juan Martı́nez-Miranda

и другие.

Journal of Medical Internet Research, Год журнала: 2023, Номер 25, С. e52097 - e52097

Опубликована: Ноя. 23, 2023

Background Embodied conversational agents (ECAs) are advanced human-like interfaces that engage users in natural face-to-face conversations and interactions. These traits position ECAs as innovative tools for delivering interventions promoting health-related behavior adoption. This includes motivational interviewing (MI), a therapeutic approach combines brief with techniques to encourage the adoption of healthier behaviors. Objective study aims identify health issues addressed by MI interventions, explore key characteristics these (eg, appearance, dialogue mechanism, emotional model), analyze implementation principles within ECAs, examine evaluation methods primary outcomes studies use providing interventions. Methods We conducted scoping review following PRISMA-ScR (Preferred Reporting Items Systematic Reviews Meta-Analyses Extension Scoping Reviews) methodology. Our systematic search covered PubMed, Scopus, IEEE Xplore, ACM Digital, PsycINFO databases papers published between January 2008 December 2022. included describing developed targeting behaviors excluded articles did not describe human appearances without necessary or explanation. In multistage process, 3 independent reviewers performed screening data extraction, collected were synthesized using narrative approach. Results The initial identified 404 articles, which 3.5% (n=14) review. primarily focused on reducing alcohol (n=5, 36%), took female representations (n=9, 64%), gave limited consideration user ethnicity 64%). Most them used rules-driven mechanisms (n=13, 93%), include convey empathy (n=8, 57%) but an automatic recognition emotions (n=12, 86%). Regarding implementation, 14 studies, (21%) all principles, 4 (29%) processes, none techniques. (8/14, acceptability, usability, experience assessments, whereas smaller proportion (4/14, 29%) randomized controlled trials evaluate changes. Overall, reported positive results regarding showed promising changes attitudes, beliefs, motivation, behavior. Conclusions revealed significant advancements aimed at over past 15 years. However, this emphasizes need more in-depth exploration ECA characteristics. addition, there is enhanced integration into ECAs. Although acceptability usability have received considerable attention, compelling argument placing stronger emphasis assessing Consequently, inclusion essential comprehensive intervention evaluations.

Язык: Английский

Процитировано

8