Journal of Systems and Software, Journal Year: 2025, Volume and Issue: unknown, P. 112470 - 112470
Published: April 1, 2025
Language: Английский
Journal of the American Medical Informatics Association, Journal Year: 2023, Volume and Issue: 31(3), P. 746 - 761
Published: Dec. 9, 2023
Abstract Objectives Conversational agents (CAs) with emerging artificial intelligence present new opportunities to assist in health interventions but are difficult evaluate, deterring their applications the real world. We aimed synthesize existing evidence and knowledge outline an evaluation framework for CA interventions. Materials Methods conducted a systematic scoping review investigate designs outcome measures used studies that evaluated CAs then nested results into overarching digital proposed by World Health Organization (WHO). Results The included 81 evaluating experimental (n = 59), observational 15) trials, other research 7). Most 72, 89%) were published past 5 years. CA-evaluation includes 4 stages: (1) feasibility/usability, (2) efficacy, (3) effectiveness, (4) implementation, aligning WHO’s stepwise strategy. Across these stages, this article presents essential of different study 8), sample sizes, main categories 7) subcategories 40). functionality, safety information quality, user experience, clinical outcomes, (5) costs cost benefits, (6) usage, adherence, uptake, (7) characteristics implementation research. Furthermore, highlighted areas (potential primary outcomes) gaps across stages. Discussion Conclusion This practical design details support healthcare Protocol registration Open Science Framework (https://osf.io/9hq2v) on March 22, 2021.
Language: Английский
Citations
15
Computers and Education Artificial Intelligence, Journal Year: 2024, Volume and Issue: 7, P. 100291 - 100291
Published: Sept. 6, 2024
Language: Английский
Citations
6
International Journal of Environmental Research and Public Health, Journal Year: 2024, Volume and Issue: 21(2), P. 165 - 165
Published: Jan. 31, 2024
Adolescents continue to face challenges their sexual and reproductive health (SRH) both locally internationally. Digital technologies such as the Internet, text messaging, social media are often viewed valuable tools for disseminating information on SRH. Mobile health, also known mHealth, is a medical public practise that uses these digital communicate information. The literature has revealed mHealth interventions have positive outcome in delivering SRH adolescents. This review aimed synthesise empirical studies evaluate assess extent which promote outcomes among young people. scoping reviewed across four databases, including EBSCOhost, Scopus, Proquest, Cochrane, included 12 articles. findings shown effective enhancing knowledge attitudes people low-middle high-income countries. However, comprehensive longitudinal necessary measure sustainability long-term influence of behaviour. It recommended with artificial intelligence (AI) improvements, there possible path bolstering interventions.
Language: Английский
Citations
4
Current Sexual Health Reports, Journal Year: 2024, Volume and Issue: 17(1)
Published: Dec. 4, 2024
Language: Английский
Citations
4
ACM Journal on Responsible Computing, Journal Year: 2025, Volume and Issue: unknown
Published: Jan. 17, 2025
Traditional health-seeking behaviors, particularly in menstrual health, are deeply rooted local languages, sociocultural norms, and religious beliefs. These factors significantly influence women South Asia other developing regions, often proving detrimental to their physical psychological health. Recognizing the multifaceted nature of these challenges, this paper investigates role generative domain-specific chatbots as a supportive mechanism enhance behaviors among Asian women. Specifically, it aims create assess Mai, conversational agent, which utilizes Roman-Urdu English models provide accurate information, thereby contributing broader effort empowering with knowledge resources. Due lack data domain, our research involves creating dataset from existing sources translating into Roman Urdu, presenting its own set challenges. datasets, specifically curated for research, addressed wide range health topics. Despite being an monolingual model, DialoGPT’s transformer architecture produced favorable results when fine-tuned on Urdu dataset. While version occasionally faced challenges contextual understanding, both achieved promising results. Automatic evaluation metrics indicated strong performance Mai compared baseline models. Likewise, user evaluations yielded average ratings 4.2 4.3 (out 5) chatbots, respectively, more than half medical professionals surveyed expressed willingness recommend dialogue system. Overall, findings highlight transformative potential systems education, room improvement overcoming cultural linguistic barriers women’s information access.
Language: Английский
Citations
0
Published: April 24, 2025
Adolescent girls and young women (AGYW) in sub-Saharan Africa face unique barriers to contraceptive access lack AGYW-centered decision-support resources. To empower AGYW make informed choices improve reproductive health outcomes, we developed a tablet-based application provide education decision-making support the pharmacy setting - key source of services for Kenya. We conducted workshops with providers Kenya gather app feedback understand how integrate intervention into setting. Our analysis highlights intermediated interactions multiuser, cooperative effort enable technology use information could inform successful The potential strengths intermediation our implications technological interventions scenarios \lrem{LMICs}\ladd{low- middle-income countries}, including challenges opportunities extending impact different populations integrating resource-constrained healthcare settings.
Language: Английский
Citations
0
BMC Medical Informatics and Decision Making, Journal Year: 2025, Volume and Issue: 25(1)
Published: Feb. 20, 2025
Postnatal care, crucial for preventing and assessing complications after birth, remains low in India. An interactive mHealth community-based postnatal intervention was implemented to promote healthy maternal behaviors through knowledge social support rural Northern However, there is limited information on how virtual health interventions resource-constrained settings are perceived by the users which elements influence their engagement sustained participation. We explored user perceptions of acceptability impact a child pilot tested Punjab State, India, including perspectives barriers facilitators engage with this intervention. This qualitative study embedded within extensive mixed-method research, oriented Realist Evaluation approach. Sixteen participants were recruited from parent study. They identified purposive sampling cover diverse levels attendance In-depth interviews conducted phone. Following translation, framework analysis completed search main themes. Feedback requested moderators during process prioritize local interpretation. Study reported overall satisfaction The mothers appreciated educational material provided communication other professionals. Across context, intervention, actor domains, most commented network connectivity challenges, lack time due household responsibilities, feeling uncomfortable sharing personal experiences. Family buy-in fundamental overcoming high domestic workload baby care. Another facilitator mentioned moderators' guidance using different modalities. Regarding impact, shared that MeSSSSage increased capability motivation breastfeed, seek care as needed, use contraception according preferences. Finally, suggested adding more topics content adjusting dynamics group calls improve identifies novel program setting, users' engaging possible solutions overcome them. These findings enable refinement ongoing providing robust framing its scalability long-term sustainability. On larger scale, conclusions research provide new insights encouragement global stakeholders who aspire neonatal outcomes low-income middle-income countries mHealth. ClinicalTrials.gov NCT04693585 (Registration date: 05/01/21).
Language: Английский
Citations
0
Archives of Sexual Behavior, Journal Year: 2025, Volume and Issue: unknown
Published: March 3, 2025
Language: Английский
Citations
0
Archives of Sexual Behavior, Journal Year: 2025, Volume and Issue: unknown
Published: March 11, 2025
Abstract This study investigated the perspectives of artificial intelligence (AI) language models on complex issue sexting among adolescents, comparing their ability to mediate and manage quality communication topic with traditional parental mediation strategies. Drawing a survey 472 parents, research compared attitudes, patterns, approaches outputs generated by four AI systems. The findings revealed that emphasize restrictive strategies highlight perceived susceptibility severity sexting, while responses were varied. Notably, systems differed in predicting dysfunctional parent–child suggesting divergent implicit ideal dynamics. By AI-generated human reactions, this offers initial insights into significance adolescents regarding potential limitations current promoting improved discussions between parents sensitive topics.
Language: Английский
Citations
0
Journal of Psychosexual Health, Journal Year: 2025, Volume and Issue: unknown
Published: March 17, 2025
Large language model (LLM) chatbots have demonstrated significant capability in patient education by offering accessible, consistent, and personalized information. Their ability to interact real-time adapt responses based on user input makes them valuable tools enhancing knowledge engagement. Sexual developing countries faces substantial challenges. Sociocultural barriers, limited access comprehensive educational resources, stigmatization surrounding sexual health contribute inadequate education. Traditional methods often fail reach remote or underserved populations, there is a general shortage of qualified educators resources. Chatbots present promising solution these They can offer anonymous, culturally sensitive information health, overcoming barriers related stigma privacy. While LLM hold potential improve countries, their implementation must be carefully managed address challenges such as ensuring accuracy cultural sensitivity. There dearth research Hence, unmet need the reliability information, maintaining sensitivity, assessing engagement, integration with traditional methods, exploring long-term impact improving knowledge.
Language: Английский
Citations
0