Co-design of a single session intervention chatbot for people on waitlists for eating disorder treatment: a qualitative interview and workshop study

Journal of Eating Disorders, Journal Year: 2025, Volume and Issue: 13(1)

Published: March 11, 2025

Abstract Background Early treatment is critical to improve eating disorder prognosis. Single session interventions have been proposed as a strategy provide short term support people on waitlists for treatment, however, it not always possible access this early intervention. Conversational artificial intelligence agents or “chatbots” reflect unique opportunity attempt fill gap in service provision. The aim of research was co-design novel chatbot capable delivering single intervention adults the waitlist across diagnostic spectrum and ascertain its preliminary acceptability feasibility. Methods A Double Diamond approach employed which included four phases: discover, define, develop, deliver. There were 17 participants total Australia; ten with lived experience an seven registered psychologists working field disorders, who participated online interviews workshops. Thematic content analyses undertaken interview/workshop transcriptions findings from previous phase informing ideas development next phase. final prototype presented deliver Results identified main themes that present phases interviews/workshops: conversational tone, safety risk management, user journey structure, content. Conclusions Overall, feedback positive throughout process both psychologists. Incorporating allowed refinement chatbot. Further required evaluate chatbot’s efficacy settings.

Language: Английский

---

Enhancing parental skills through artificial intelligence‐based conversational agents: The PAT Initiative

Family Relations, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 27, 2025

Abstract Objective We aim to describe the development of a conversational agent (CA) for parenting, termed PAT (Parenting Assistant platform), demonstrate how artificial intelligence (AI) can enhance parenting skills. Background Behavioral problems are most common issues in childhood mental health. Developing and disseminating scalable interventions address early‐stage behavioral high priority. Artificial (AI)‐based CAs offer innovative methods deliver reduce problems. have capability interact through text or voice conversations undergo training using evidence‐based programs. However, research on is limited. Experience The consisted three phases: Phase 1 was purely rule‐based, 2 hybrid (rule‐based format plus large language models), 3 featured an agentic architecture. latest version includes prompt engineering, guardrails, retrieval‐augmented generation, few‐shots learning, context, memory management Although comprehensive empirical results pending, iterative enhancement indicate potential effective digital intervention. architecture aims provide robust, context‐aware interactions support challenges. Implications reach broader population parents personalized tailored their specific needs. Moreover, structured timely support, which family dynamics contribute improved long‐term outcomes both children. Conclusion AI‐based be used as alternatives waitlists; cotherapists; implemented health care, health, school settings. benefits risks different types CA features discussed.

Language: Английский

---

Understanding and overcoming barriers to digital health adoption: a patient and public involvement study

Translational Behavioral Medicine, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 1, 2025

Abstract Background Digital health (DH) technologies provide scalable and cost-effective solutions to improve population but face challenges of uneven adoption high attrition, particularly among vulnerable minority groups. Purpose This study explores factors influencing DH in a multicultural identifies strategies equitable access. Methods Using Patient Public Involvement approach, lay facilitators engaged adults at public eateries Singapore discuss motivations barriers adoption. A semi-structured guide facilitated discussions, followed by an optional socio-demographic survey. Data were analyzed through inductive thematic analysis mapped behavior change theory identify mechanisms action (MoA) techniques (BCTs) support Results Facilitators 118 participants between November 2022 February 2023. Five key themes identified from the discussions: (a) awareness solutions, (b) weighing benefits against burdens, (c) accessibility, (d) trust developers technology, (e) impact user experience. These 13 MoA 26 BCTs, informing five enhance adoption: community-based promotion credible digital literacy training, brief counselling opportune moments healthcare settings, variable rewards tied personal values, policies ensuring accessibility regulation, gamified, user-friendly designs emphasizing feedback behavioral cues. Conclusion Designing implementing that are accessible, trustworthy, motivating—integrated within services promoted community efforts—can address diverse communities may help narrow divide.

Language: Английский

---

Artificial Intelligence (AI) and academic publishing in psychiatry

International Journal of Law and Psychiatry, Journal Year: 2025, Volume and Issue: 101, P. 102105 - 102105

Published: May 3, 2025

The current and potential impact of various applications artificial intelligence (AI) to the field academic publishing in psychiatry is subject increasing attention. At present, AI algorithms assist data analysis, allowing researchers process large datasets quickly uncover complex patterns that would be challenging detect manually. In psychiatry, this capability can potentially help integrate from genetics, neuroimaging, clinical assessments. AI-driven natural language processing (NLP) tools might also facilitate systematic reviews meta-analyses by automating extraction synthesis information vast bodies published literature. publishing, streamline publication certain ways. Automated systems screen manuscripts for methodological rigor, ethical compliance, conflicts interest, thereby reducing burden on editors prompting them consider matters, possibly accelerating timeline. AI-powered are already used with dissemination research findings generating summaries identifying key insights, making more accessible a broader audience. future, has enhance psychiatric other Predictive analytics identify emerging trends gaps literature, guiding future studies funding priorities, although remains speculative now. could robust collaborations connecting complementary expertise interests. Additionally, integration digital platforms democratise access cutting-edge research, promote global knowledge sharing, accelerate advancements care. As continues evolve, its hold drive significant progress understanding treating mental disorders. It essential these developments accompanied openness about use clear declarations authors publishers specific work.

Language: Английский

---

Person-Generated Health Data in Women’s Health: Scoping Review (Preprint)

Journal of Medical Internet Research, Journal Year: 2024, Volume and Issue: 26, P. e53327 - e53327

Published: March 26, 2024

Background The increased pervasiveness of digital health technology is producing large amounts person-generated data (PGHD). These can empower people to monitor their promote prevention and management disease. Women make up one the largest groups consumers self-tracking technology. Objective In this scoping review, we aimed (1) identify different areas women’s monitored using PGHD from connected devices, (2) explore personal metrics collected through these technologies, (3) synthesize facilitators barriers adoption use devices. Methods Following PRISMA (Preferred Reporting Items for Systematic Reviews Meta-Analyses) guidelines reviews, searched 5 databases articles published between January 1, 2015, February 29, 2020. Papers were included if they targeted women or female individuals incorporated tools that outside a clinical setting. Results We total 406 papers in review. Articles on steadily 2015 focused spanned several topics, with pregnancy postpartum period being most prevalent followed by cancer. Types used collect mobile apps, wearables, websites, Internet Things smart 2-way messaging, interactive voice response, implantable A thematic analysis 41.4% (168/406) revealed 6 themes regarding collecting PGHD: accessibility connectivity, design functionality, accuracy credibility, (4) audience adoption, (5) impact community service, (6) behavior. Conclusions Leading COVID-19 pandemic, address concerns was steady rise. prominence related reflects strong focus reproductive research highlights opportunities development other topics. Digital acceptable when it relevant target audience, seen as user-friendly, considered personalization preferences while also ensuring measurements credibility information. integration technologies into care will continue evolve, factors such liability provider workload need be considered. While acknowledging diversity individual needs, positively self-care numerous journeys. pandemic has ushered acceptance This study could serve baseline comparison how field evolved result. International Registered Report Identifier (IRRID) RR2-10.2196/26110

Language: Английский

---

Combining AI and human support in mental health: a digital intervention with comparable effectiveness to human-delivered care

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: July 17, 2024

Abstract Escalating global mental health demand exceeds existing clinical capacity. Scalable digital solutions will be essential to expand access high-quality healthcare. This study evaluated the effectiveness of a intervention alleviate mild, moderate and severe symptoms generalized anxiety. structured, evidence-based program combined an Artificial Intelligence (AI) driven conversational agent deliver content with human oversight user support maximize engagement effectiveness. The was compared three propensity-matched real-world patient comparator groups: i) waiting control; ii) face-to-face cognitive behavioral therapy (CBT); iii) remote typed-CBT. Endpoints for effectiveness, engagement, acceptability, safety were collected before, during after intervention, at one-month follow-up. Participants (n=299) used median 6 hours over 53 days. There large clinically meaningful reduction in anxiety group (per-protocol (n=169): change on GAD-7 = −7.4, d 1.6; intention-to-treat (n=299): −5.4, 1.1) that statistically superior control, non-inferior human-delivered care, sustained By combining AI support, achieved outcomes comparable care while significantly reducing required clinician time. These findings highlight immense potential technology scale effective healthcare, address unmet need, ultimately impact quality life economic burden globally.

Language: Английский

---

New technology, psychiatry, and the law: Panic, prudence, possibility

International Journal of Law and Psychiatry, Journal Year: 2024, Volume and Issue: 94, P. 101984 - 101984

Published: March 23, 2024

Throughout human history, all new technology has been met with surprise, anxiety, panic, and - eventually prudent adoption of certain aspects specific technological advances. This pattern is evident in the histories most technologies, ranging from steam power nineteenth century, to television twentieth now 'artificial intelligence' (AI) twenty-first century. Each generation believes that advances its era are quantitatively qualitatively different those previous generations, but underlying phenomenon same: shock new, followed by more gradual adjustment (and of) technology. These concerns apparent today relation AI, which reflects interesting incremental on existing rather than stand-alone developments. The usual technologies (e.g., they will replace function) are, perhaps, concerning fields such as mental capacity law, often applies people impaired decision-making who might be especially vulnerable appear capable encroaching disproportionately or other areas core function. paper approaches this topic an historical standpoint, noting both panics past possibilities offered AI today, provided it approached a proportionate, prudent, person-centered way, underpinned appropriate ethical guidance active awareness clinical legal practice.

Language: Английский

---

A New Research Model for Artificial Intelligence–Based Well-Being Chatbot Engagement: Survey Study

JMIR Human Factors, Journal Year: 2024, Volume and Issue: 11, P. e59908 - e59908

Published: Nov. 11, 2024

Artificial intelligence (AI)-based chatbots have emerged as potential tools to assist individuals in reducing anxiety and supporting well-being.

Language: Английский

---

Human-centred design (HCD) and digital transformation of mental health services: A narrative review and personal view from the United Kingdom (Preprint)

Published: Sept. 2, 2024

Mental health services face a multitude of challenges, such as increasing demand, underfunding and limited workforce capacity. The accelerated digital transformation public is positioned by government, private sector some academic researchers the solution. Alongside, human-centred design (HCD) has emerged guiding paradigm for this to ensure user needs are met. We define what HCD are, how they implemented in UK policy context, their role within evolving delivery mental services. Our co-author’s involvement these policies over past five years provides unique insights into decision-making process story. review promises, pitfalls ongoing challenges identified across multi-disciplinary literature. Finally, we propose future research questions options that designed delivered meet population.

Language: Английский

---

The LvL UP Trial: Protocol for a Sequential, Multiple Assignment, Randomized Controlled Trial to Assess the Effectiveness of a Blended Mobile Lifestyle Intervention

Published: Aug. 16, 2024

Background: Blended mobile health (mHealth) interventions – combining self-guided and human support components could play a major role in preventing non-communicable diseases (NCDs) common mental disorders (CMDs). This protocol paper describes sequential, multiple assignment, randomised trial aimed at (i) evaluating the effectiveness cost-effectiveness of LvL UP, an mHealth lifestyle intervention for prevention NCDs CMDs, (ii) establishing optimal blended approach UP that balances effective personalised with scalability.Methods: is 6-month holistic targeting physical activity, diet, emotional regulation. In this trial, young middle-aged Singaporean adults risk developing or CMDs will be randomly allocated to one two initial conditions (‘LvL UP’ ‘comparison’). After 4 weeks, participants categorised as non-responders from group re-randomised into second-stage conditions: continuing (LvL UP) additional motivational interviewing (MI) sessions by trained coaches + adaptive MI). The primary outcome well-being (via Warwick-Edinburgh Mental Wellbeing Scale). Secondary outcomes include anthropometric measurements, resting blood pressure, metabolic profile, status, behaviours (physical diet), work productivity, healthcare utilisation. Outcomes measured baseline, 6 months (post-intervention), 12 (follow-up).Discussion: addition proposed study design contribute increasing evidence on how introduce maximise their while remaining scalable.Trial registration: Pilot was prospectively registered ClinicalTrials.gov (NCT06360029) 7 April 2024.

Language: Английский

---