Kitchen appliances are frequently used domestic artifacts situated at the point of everyday dietary decision making, making them a promising but underexplored site for health promotion. We explore the concept of relational appliances: everyday household devices designed as embodied social actors that engage users through ongoing, personalized interaction. We focus on the refrigerator, whose unique affordances, including a fixed, sensor-rich environment, private interaction space, and close coupling to food items, support contextualized, conversational engagement during snack choices. We present an initial exploration of this concept through a pilot study deploying an anthropomorphic robotic head inside a household refrigerator. In a home-lab apartment, participants repeatedly retrieved snacks during simulated TV "commercial breaks" while interacting with a human-sized robotic head. Participants were randomized to either a health-promotion condition, in which the robot made healthy snack recommendations, or a social-chat control condition. Outcomes included compliance with recommendations, nutritional quality of selected snacks, and psychosocial measures related to acceptance of the robot. Results suggest that participants found the robot persuasive, socially engaging, and increasingly natural over time, often describing it as helpful, aware, and companionable. Most participants reported greater awareness of their snack decisions and expressed interest in having such a robot in their own home. We discuss implications for designing relational appliances that leverage anthropomorphism, trust, and long-term human-technology relationships for home-based health promotion.

Adolescents are directly affected by preventive health decisions such as vaccination, yet their perspectives are rarely solicited or supported. Most digital interventions for Human Papillomavirus (HPV) vaccination are designed exclusively for parents, implicitly treating adolescents as passive recipients rather than stakeholders with agency. We present the design and evaluation of a mobile intervention that gives adolescents a voice in HPV vaccination decisions alongside their parents. The system uses embodied conversational agents tailored to each audience: parents interact with an animated physician using education and motivational interviewing techniques, while adolescents can choose between an age-appropriate doctor or a narrative fantasy game that conveys HPV facts through play. We report findings from a clinic-based pilot study with 21 parent–adolescent dyads. Results indicate high satisfaction across both audiences, improved HPV knowledge, and increased intent to vaccinate. We discuss design implications for supporting adolescent participation, choice, and agency in decisions about their health.

Abstract Background Neighborhood conditions are key social determinants of health (SDOH) that play a critical role in healthy aging. Incorporating contextual measures into behavioral medicine interventions is essential for creating adaptable, equity-focused health solutions. Yet, few physical activity (PA) interventions explicitly evaluate how these factors influence effectiveness. We conducted a secondary analysis of the Computerized Physical Activity Support for Seniors (COMPASS) Trial to examine whether neighborhood context, measured by the California Healthy Places Index (HPI), moderated intervention effects on PA among Latino/a older adults. Methods The COMPASS trial was a single-blind, cluster-randomized non-inferiority trial comparing an interactive virtual advisor (reference arm) with a trained human peer advisor. PA outcomes, including weekly minutes of walking and moderate-to-vigorous physical activity (MVPA), were assessed with the CHAMPS questionnaire at baseline and 12 months. Neighborhood conditions were measured with the HPI, a composite index of 25 indicators across eight domains (e.g., housing, education, transportation) that reflect place-based SDOH. Scores range from 0 to 100, with higher values indicating more health-supportive environments. Mixed-effects ANCOVA models adjusted for baseline PA, age, and gender, with a random intercept for study site, and tested effect modification via interaction terms between intervention arm and HPI. Results Among 245 Latino/a participants (mean age = 62.3 years; 78.8% female), HPI significantly moderated intervention effects. When modeled continuously, significant interactions were observed for 12-month changes in walking (β = − 2.93; P = .041) and MVPA (β = − 2.54 min/week per HPI point; P = .033). These findings indicated that the human advisor was comparatively more effective in lower-HPI neighborhoods, whereas the virtual advisor produced stronger improvements in higher-HPI neighborhoods. In sensitivity analyses using dichotomized HPI, the interaction was significant for MVPA (β = − 112.9; P = .026) and trended for walking (P = .077). Conclusions Neighborhood context moderated the relative effectiveness of digital versus human-delivered PA interventions. These findings suggest that tailoring delivery strategies, leveraging digital tools in advantaged areas and peer support in under-resourced neighborhoods, may enhance equity in health promotion for older Latino/a adults by explicitly accounting for neighborhood-level social determinants of health. Trial registration Clinicaltrials.gov NCT02111213 Registered April 2, 2014 https://clinicaltrials.gov/study/NCT02111213 .

Buprenorphine is an effective and safe medication for opioid use disorder that can be delivered in office-based addiction treatment (OBAT). Yet, over half of people who initiate buprenorphine disengage and return to unhealthy opioid use. Accordingly, it is critical to improve OBAT retention. Mobile applications using embodied conversational agents (ECA) have improved care in other chronic diseases and may increase OBAT retention. To explore patient perspectives on how an ECA can support retention in OBAT programs. We conducted a series of 6 focus groups with a single cohort of 8 patients receiving treatment with buprenorphine within an OBAT program. Focus group topics included experiences with treatment initiation and retention, beliefs about barriers to retention, understanding participants’ perspectives for how an application with an ECA could support retention for new patients, and feedback on ECA prototypes. A socioecological model guided our deductive and inductive thematic analyses. Participants had been engaged in care for 4-18 years. They identified how an ECA could address barriers to retention across four levels of the socioecological model. At the society level, the application could provide information about basic needs including housing and food access. At the community level, participants expressed unclarity about buprenorphine and wanted information about dose, side effects and discontinuation strategies that had been verified by their healthcare provider. At the interpersonal level, they endorsed the application’s ability to function as peer-support. They recommended that the agent embodied a peer in recovery and that storytelling related to lived experience would be a constructive tool. An ECA was perceived as a helpful tool to support retention in OBAT by addressing fundamental socioecological needs and by providing information and linkage to resources. Implementation of an ECA system based on these findings should be evaluated in a clinical trial to improve retention in OBAT programs.

BackgroundIf a patient with cancer is identified as having a pathogenic variant, at-risk relatives are eligible for genetic testing, known as cascade testing. However, in the United States, the patient is responsible for informing their family members, and only about 30% of these family members are ultimately informed and complete testing. There is a need to train patients with cancer to communicate risk information and motivate their family members to obtain genetic testing. ObjectiveThis study evaluates “GRACE,” an online relational agent that trains patients with cancer to talk to their family about cancer risk, including role-play simulations that enable patients to practice communication skills. MethodsA quasi-experimental study was conducted with 30 crowd workers with cancer. Primary measures included 5-point pre-post self-reported intent, importance, comfort, and confidence to share genetic test information with family members, as well as knowledge of cancer genetics (KnowGene), satisfaction with (10-item satisfaction measure), and usability of (SUS) the relational agent system. ResultsLikelihood of sharing genetic test information increased significantly pre-post from 4.43 (SD 1.04) to 4.67 (SD .66), Wilcoxon (Z=2.07, P=.04). Importance of sharing genetic test information increased significantly pre-post from 4.47 (SD .82) to 4.77 (SD .50), Wilcoxon (Z=2.46, P=.01). Comfort sharing genetic test information increased pre-post from 4.33 (SD 0.99) to 4.57 (SD 0.90), Wilcoxon (Z=1.811, P=.07). Confidence to share genetic test information increased significantly pre-post from 4.33 (SD 0.994) to 4.63 (SD 0.765), Wilcoxon (Z=2.23, P=.03). Knowledge of cancer genetics did not increase significantly (mean 13.27, range 1.911 to 13.7, SD 1.932, paired t29=1.245, P=.22). Participants gave high scores for usability (SUS score=71%) and satisfaction (6.09 SD 0.96 out of 7.0), significantly greater than neutral, t29=13.445, P<.001) with the relational agent system. ConclusionsGRACE provides communication skills training and information better enabling patients with cancer to reach out to their families, and our preliminary study indicates a potential for future impact. While results were generally positive, these findings should be interpreted with caution due to limitations in the population included in the pilot, the quasi-experimental design and small sample size. Future development should focus on larger-scale evaluation and in-depth follow-up of family communication dynamics following the use of GRACE.

Background: Millions of United States residents made use of public health websites during the coronavirus disease 2019 (COVID-19) pandemic to obtain information about vaccines and determine vaccine eligibility. Objective: For public health websites to be effective, they must be usable. This study aimed to evaluate the usability of government websites for vaccine information, by examining whether these platforms helped users determine COVID-19 vaccine eligibility accurately and satisfactorily, as well as how health literacy (HL) plays a role in accurate eligibility judgments and satisfaction with the media. Methods: A within-subject experiment was conducted (N = 39), where each participant used two websites and one embodied conversational agent system to determine their own eligibility for vaccination, as well as that of a fictitious persona as a standardized task. The website conditions in the study included the Centers for Disease Control (CDC) website, as well as vaccines.gov and mass.gov. The accuracy of participant-estimated eligibility and usability were further analyzed for association with HL. Key Results: Participants' estimate of vaccine eligibility was generally inaccurate for all website conditions, with an overall rate of 53.8% for correct responses. Participants with low HL had more incorrect responses and confusion, and HL was found to be a significant predictor of eligibility correctness when they were determining their own vaccine eligibility using the CDC website. Participants also reported having a significantly higher ability to find information and were more satisfied when interacting with the embodied conversational agent system, compared to the websites. Conclusions: Government websites—particularly the CDC website—were found to lack usability, especially for those with low HL. High error rates and low satisfaction underscore the need for simplification of public health site content and design and motivate the development of novel education methods for public health communication.

Serious Illness Conversations (SICs), discussions about values and care preferences for patients with life-threatening illness, rarely occur in Emergency Departments (EDs), despite evidence that early conversations improve care alignment and reduce unnecessary interventions. We interviewed 11 ED providers to identify challenges in SICs and opportunities for technology support, with a focus on AI. Our analysis revealed a four-stage SIC workflow (identification, preparation, conduction, documentation) and barriers at each stage, including fragmented patient information, limited time and space, lack of conversational guidance, and burdensome documentation. Providers expressed interest in AI systems for synthesizing information, supporting real-time conversations, and automating documentation, but emphasized concerns about preserving human connection and clinical autonomy. This tension highlights the need for technologies that enhance efficiency without undermining the interpersonal nature of SICs. We propose design guidelines for ambient and peripheral AI systems to support providers while preserving the essential humanity of these conversations.

BackgroundChronic pain is a debilitating condition that disproportionately impacts US veterans who manage numerous negative pain-related outcomes. There is an urgent need for accessible, engaging, and innovative treatments that can help veterans with chronic pain better self-manage their pain at home and improve their daily functioning. Technology-delivered acceptance- and mindfulness-based interventions for pain have shown strong efficacy, particularly when they are engaging and tailored to specific client needs. However, more research is needed to assess the impact of such interventions, particularly in terms of pain-related functioning and quality of life. ObjectiveThe primary aim of this study is to test the efficacy of Veteran Acceptance and Commitment Therapy for Chronic Pain (VACT-CP), an online self-management pain program, compared to an active online control (Online Pain School) for improving pain-related functioning in a 3-site randomized controlled trial. The secondary aim is to explore psychological flexibility as a potential mediator between pain severity and pain-related functioning. MethodsThis study will use a mixed methods approach to examine the efficacy of VACT-CP in a 2-arm, multisite, randomized controlled superiority trial including 200 participants with chronic musculoskeletal pain compared to Online Pain School. Participants will be assigned to 1 of these 2 online interventions. Both interventions will include 7 modules delivered over 7 weeks, with each module lasting approximately 15 minutes. Mixed effects models will be used to analyze the primary hypothesis that participants in the VACT-CP group will have greater improvement in pain-related functioning (Brief Pain Inventory–Interference subscale) than those in the active control group (Online Pain School). The main acceptance and commitment therapy process mediator (ie, Multidimensional Psychological Flexibility Inventory), pain-related functioning outcomes (Brief Pain Inventory–Interference subscale), and quality of life (Veterans RAND 36-Item Health Survey) will be measured at baseline, end of treatment, and 3 and 6 months after treatment. In addition, qualitative exit interviews will be conducted with a random set of 30 VACT-CP users (n=10, 33% per site) to obtain intervention usability, feasibility, and acceptability information. ResultsThe recruitment for this study began in January 2025. It is expected to continue through January 2027. Data collection is expected to be completed by June 2027, and primary data analyses are expected to be completed by early 2028. ConclusionsOnline interventions such as VACT-CP and Online Pain School have the potential to expand access to behavioral interventions that improve quality of life and provide nonpharmacological pain treatment options for veterans experiencing chronic pain. However, research on their impact and underlying mechanisms of change is required to support this area of potential at-home programming. Trial RegistrationClinicalTrials.gov NCT06058624; https://clinicaltrials.gov/study/NCT06058624 International Registered Report Identifier (IRRID)PRR1-10.2196/70601

BackgroundAs large language model (LLM)–based chatbots such as ChatGPT (OpenAI) grow in popularity, it is essential to understand their role in delivering online health information compared to other resources. These chatbots often generate inaccurate content, posing potential safety risks. This motivates the need to examine how users perceive and act on health information provided by LLM-based chatbots. ObjectiveThis study investigates the patterns, perceptions, and actions of users seeking health information online, including LLM-based chatbots. The relationships between online health information–seeking behaviors and important sociodemographic characteristics are examined as well. MethodsA web-based survey of crowd workers was conducted via Prolific. The questionnaire covered sociodemographic information, trust in health care providers, eHealth literacy, artificial intelligence (AI) attitudes, chronic health condition status, online health information source types, perceptions, and actions, such as cross-checking or adherence. Quantitative and qualitative analyses were applied. ResultsMost participants consulted search engines (291/297, 98%) and health-related websites (203/297, 68.4%) for their health information, while 21.2% (63/297) used LLM-based chatbots, with ChatGPT and Microsoft Copilot being the most popular. Most participants (268/297, 90.2%) sought information on health conditions, with fewer seeking advice on medication (179/297, 60.3%), treatments (137/297, 46.1%), and self-diagnosis (62/297, 23.2%). Perceived information quality and trust varied little across source types. The preferred source for validating information from the internet was consulting health care professionals (40/132, 30.3%), while only a very small percentage of participants (5/214, 2.3%) consulted AI tools to cross-check information from search engines and health-related websites. For information obtained from LLM-based chatbots, 19.4% (12/63) of participants cross-checked the information, while 48.4% (30/63) of participants followed the advice. Both of these rates were lower than information from search engines, health-related websites, forums, or social media. Furthermore, use of LLM-based chatbots for health information was negatively correlated with age (ρ=–0.16, P=.006). In contrast, attitudes surrounding AI for medicine had significant positive correlations with the number of source types consulted for health advice (ρ=0.14, P=.01), use of LLM-based chatbots for health information (ρ=0.31, P<.001), and number of health topics searched (ρ=0.19, P<.001). ConclusionsAlthough traditional online sources remain dominant, LLM-based chatbots are emerging as a resource for health information for some users, specifically those who are younger and have a higher trust in AI. The perceived quality and trustworthiness of health information varied little across source types. However, the adherence to health information from LLM-based chatbots seemed more cautious compared to search engines or health-related websites. As LLMs continue to evolve, enhancing their accuracy and transparency will be essential in mitigating any potential risks by supporting responsible information-seeking while maximizing the potential of AI in health contexts.

Learning therapeutic counseling involves significant role-play experience with mock patients, with current manual training methods providing only intermittent granular feedback. We seek to accelerate and optimize counselor training by providing frequent, detailed feedback to trainees as they interact with a simulated patient. Our first application domain involves training motivational interviewing skills for counselors. Motivational interviewing is a collaborative counseling style in which patients are guided to talk about changing their behavior, with empathetic counseling an essential ingredient. We developed and evaluated an LLM-powered training system that features a simulated patient and visualizations of turn-by-turn performance feedback tailored to the needs of counselors learning motivational interviewing. We conducted an evaluation study with professional and student counselors, demonstrating high usability and satisfaction with the system. We present design implications for the development of automated systems that train users in counseling skills and their generalizability to other types of social skills training.

Personalized and tailored health education materials have demonstrated greater effectiveness than generic content. Traditional tailoring methods in health communication typically rely on collecting user data through static forms and applying rule-based techniques to assemble health documents for print or digital delivery. In this project, we developed a novel system that combined a virtual agent (VA) with a large language model (LLM) to generate individualized breast cancer screening pamphlets. The VA conducted interactive interviews to gather user-specific information, including demographics, family history, and lifestyle factors. This information was then used by the LLM to generate a pamphlet that was both tailored and personalized. We conducted a pilot study to evaluate this approach, using breast cancer screening as a representative educational topic. Participants interacted with the virtual agent and provided relevant personal information before being randomized to receive either an LLM-generated pamphlet or a standard, generic pamphlet. We assessed group differences in knowledge, screening intentions, and satisfaction. Results showed that both groups experienced significant knowledge gains, with the Tailored group demonstrating greater improvement. Qualitative feedback revealed that participants who received the personalized and tailored pamphlets perceived the information as more personally relevant, often noting that the content reflected details they had shared during their interaction with the agent. These findings highlight the potential of integrating the VA and LLMs to enhance the personalization and effectiveness of health education materials.

Background Atrial fibrillation (AF) requires long-term adherence to oral anticoagulation and self-care. Methods We conducted a randomized controlled trial of a smartphone-based relational agent and heart rhythm monitor with the primary outcome of anticoagulation adherence and secondary outcomes of quality of life (QOL) and health care utilization. The trial enrolled individuals with Atrial fibrillation (AF) taking anticoagulation. Intervention participants received a smartphone-based relational agent for disease education, adherence monitoring, and self-care, and a heart rate and rhythm monitor. Attention control participants received a smartphone health education application and the same heart monitor. Participants had baseline and 4-, 8-, and 12-month visits. The primary outcome was 12-month proportion of days covered (PDC) ascertained with pharmacy claims. Results From January, 2020 to April, 2022, the trial enrolled 243 participants (age 70.8 ± 9.8 years; 64.2% female; 30.5% Black race). The adjusted mean PDC at 12 months in the intervention arm was 0.88 (95% Confidence Interval [CI], 0.84-0.93) and in the attention control 0.85 (95% CI, 0.81-0.90) with no difference in odds of PDC ≥ 0.80 in intervention compared to the control (Odds Ratio, 1.26 [95% CI, 0.66-2.38]). Self-reported nonadherence and QOL did not differ by study arm. The event rates for health care utilization were significantly less for intervention than attention control participants as measured by emergency room visits and hospitalizations (P < .001) and number of days hospitalized (P = .004). Conclusion The smartphone-based relational agent intervention did not achieve its primary endpoint of increased anticoagulation adherence but did yield decreased health care utilization. Trial registration ClinicalTrials.gov Identifier: NCT04075994

BACKGROUND:Rural individuals with atrial fibrillation (AF) experience challenges to anticoagulation adherence and self-management of the condition. We tested an intervention to improve anticoagulation adherence, quality of life, and health care utilization in rural individuals with AF. METHODS:We randomized rural patients with AF receiving anticoagulation to receive a smartphone-based relational agent (for disease education and adherence guidance) and a heart rate and rhythm monitor for 4 months or a smartphone-based health education app. Adherence was determined with 12-month proportion of days covered (PDC), and secondary outcomes of quality of life and health care utilization from interviews and health records. RESULTS:The trial randomized 270 individuals 1:1 (median [IQR] age 73.1 [67.5-78.6]; 163 [60.4 %] female sex). Over the 4-month intervention, intervention participants used the relational agent a median of 101 (IQR: 72, 110) days. In an intention-to-treat analysis there was no significant difference in 12-month PDC between the intervention and control groups (median [IQR]: intervention 0.97 [0.89-1.00] versus control 0.97 [0.92-1.00]) or in PDC ≥0.80. Intervention participants were more likely to self-report anticoagulation adherence than control at 4 and 8 months (95.7 % vs 88.4 % and 93.0 % vs 78.8 %, respectively) but not at 12 months. There were no significant differences by assigned intervention for the other secondary outcomes. CONCLUSIONS:Randomization to the relational agent intervention was not associated with improved PDC at 12-months but with greater interim self-reported adherence compared to a control. This study demonstrates the successful use of a smartphone-based agent to address adherence among rural individuals with AF.

We introduce HealthDial, a dialogue authoring tool that helps healthcare providers and educators create virtual agents that deliver health education and counseling to patients over multiple conversations. HealthDial leverages large language models (LLMs) to automatically create an initial session-based plan and conversations for each session using text-based patient health education materials as input. Authored dialogue is output in the form of finite state machines for virtual agent delivery so that all content can be validated and no unsafe advice is provided resulting from LLM hallucinations. LLM-drafted dialogue structure and language can be edited by the author in a no-code user interface to ensure validity and optimize clarity and impact. We conducted a feasibility and usability study with counselors and students to test our approach with an authoring task for cancer screening education. Participants used HealthDial and then tested their resulting dialogue by interacting with a 3D-animated virtual agent delivering the dialogue. Through participants' evaluations of the task experience and final dialogues, we show that HealthDial provides a promising first step for counselors to ensure full coverage of their health education materials, while creating understandable and actionable virtual agent dialogue with patients.

The proliferation of Large Language Models and Intelligent Virtual Agents acting as psychotherapists offer expanded mental healthcare access. However, their deployment has led to serious harms due to a lack of methods to evaluate nuanced therapeutic risks. Current evaluation techniques lack the sensitivity to detect subtle changes in patient cognition and behavior during therapy sessions that may lead to subsequent decompensation. We introduce a risk ontology for the evaluation of conversational AI psychotherapists. Developed via literature review, expert interviews, and alignment with clinical criteria (DSM-5) and assessment tools (NEQ, UE-ATR), the ontology provides a structured approach to assessing patient harm.

Large language model (LLM)-based chatbots are transforming online health information search by offering interactive access to resources but raise concerns about inaccurate or harmful content. This study examined how different search methods-Search Engine, standalone Chatbot, and retrieval-augmented Chatbot+-and source credibility (reputable health websites vs. social media) influence user trust and satisfaction. Key findings include: (a) Trust trended higher for chatbots than Search Engine results, regardless of source credibility; (b) Satisfaction was highest with standalone Chatbot, followed by Chatbot+ and Search Engine; (c) Source type had minimal impact unless they were compared side by side. Interestingly, in interviews where participants could compare the methods directly, several participants preferred search engines due to familiarity and response diversity. However, they valued chatbots for their concise, time-saving answers. This study highlights the critical role of user interfaces in fostering trust and satisfaction, emphasizing the need for accurate, responsibly designed chatbots for health information dissemination.

Background:Atrial fibrillation (AF) is a chronic cardiovascular condition that requires long-term adherence to medications and self-monitoring. Clinical trials for AF have had limited diversity by sex, race and ethnicity, and rural residence, thereby compromising the integrity and generalizability of trial findings. Digital technology coupled with remote strategies has the potential to increase recruitment of individuals from underrepresented demographic and geographic populations, resulting in increased trial diversity, and improvement in the generalizability of interventions for complex diseases such as AF. Objective:This study aimed to summarize the architecture of a research program using remote methods to enhance geographic and demographic diversity in mobile health trials to improve medication adherence. Methods:We developed a programmatic architecture to conduct remote recruitment and assessments of individuals with AF in 2 complementary randomized clinical trials, funded by the National Institutes of Health, to test the effectiveness of a smartphone-based relational agent on adherence to oral anticoagulation. The study team engaged individuals with either rural or metropolitan residences receiving care for AF at health care settings who then provided consent, and underwent baseline assessments and randomization during a remotely conducted telephone visit. Participants were randomized to receive the relational agent intervention or control and subsequently received a study smartphone with installed apps by mail. Participants received a telephone-based training session on device and app usage accompanied by a booklet with pictures and instructions accessible for any level of health or digital literacy. The program included remote methods by mail and telephone to promote retention at 4-, 8-, and 12-month visits and incentivized return of the smartphone following study participation. The program demonstrated excellent participant engagement and retention throughout the duration of the clinical trials. Results:The trials enrolled 513 participants, surpassing recruitment goals for the rural (n=270; target n=264) and metropolitan (n=243; target n=240) studies. A total of 62% (319/513) were women; 31% (75/243) of participants in the metropolitan study were African American, Asian, American Indian or Alaskan native or other races or ethnicities, in contrast to 5% (12/270) in the rural study. Among all participants, 56% (286/513) had less than an associate's degree and 44% (225/513) were characterized as having limited health literacy. Intervention recipients receiving the relational agent used the agent median of 95-98 (IQR, 56-109) days across both studies. Retention exceeded 89% (457/513) at 12 months with study phones used for median 3.3 (IQR, 1-5) participants. Conclusions:We report here the development and implementation of a programmatic architecture for the remote conduct of clinical trials. Our program successfully enhanced trial diversity and composition while providing an innovative mobile health intervention for medication adherence in AF. Our methods provide a model for enhanced recruitment and engagement of diverse participants in cardiovascular trials.

Many laypeople are motivated to improve the health behavior of their family or friends but do not know where to start, especially if the health behavior is potentially stigmatizing or controversial. We present an approach that uses virtual agents to coach community-based volunteers in health counseling techniques, such as motivational interviewing, and allows them to practice these skills in role-playing scenarios. We use this approach in a virtual agent-based system to increase COVID-19 vaccination by empowering users to influence their social network. In a between-subjects comparative design study, we test the effects of agent system interactivity and role-playing functionality on counseling outcomes, with participants evaluated by standardized patients and objective judges. We find that all versions are effective at producing peer counselors who score adequately on a standardized measure of counseling competence, and that participants were significantly more satisfied with interactive virtual agents compared to passive viewing of the training material. We discuss design implications for interpersonal skills training systems based on our findings.

The 3rd edition of the IEEE VR XR Health workshop aims to connect international researchers in medical, health, and wellbeing XR applications. This recurring event is intended to give young researchers a stage to present their earlier works and connect them with more experienced researchers in the field. With 23 workshop paper contributions, one keynote, and a panel discussion, we are striving to advance the development of an international healthcare, wellbeing, and medical XR community.

Smartphone-based conversational agents offer a convenient way to deliver health education, particularly for managing complex health conditions such as chronic diseases. The present study explores using a smartphone-based virtual agent system to aid patients with a chronic heart condition-atrial fibrillation-to manage their health by encouraging the use of a heart rhythm sensor integrated with their smartphones. We report the results of a randomized clinical trial with 240 patients experiencing atrial fibrillation who were provided with smartphones and heart rhythm sensors for 4 months. Participants in the intervention group interacted with a virtual agent, while the control group received general health education via the WebMD app. Intervention participants completed a median 91 interactions with the agent over the 4 months of the study period, and agent features designed to increase engagement-such as storytelling-were effective at increasing use. The agent's promotion of heart rhythm sensor use was effective, with intervention participants taking significantly more heart rhythm readings compared to those in the control group. Participants were followed for 8 months thereafter to assess the sustainability of the effects, specifically focusing on medication adherence.