Explore the vast range of titles available.

As 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. This 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. A 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. Most 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). Although 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.

Conversational assistants, such as Siri, Alexa, and Google Assistant, are ubiquitous and are beginning to be used as portals for medical services. However, the potential safety issues of using conversational assistants for medical information by patients and consumers are not understood. To determine the prevalence and nature of the harm that could result from patients or consumers using conversational assistants for medical information. Participants were given medical problems to pose to Siri, Alexa, or Google Assistant, and asked to determine an action to take based on information from the system. Assignment of tasks and systems were randomized across participants, and participants queried the conversational assistants in their own words, making as many attempts as needed until they either reported an action to take or gave up. Participant-reported actions for each medical task were rated for patient harm using an Agency for Healthcare Research and Quality harm scale. Fifty-four subjects completed the study with a mean age of 42 years (SD 18). Twenty-nine (54%) were female, 31 (57%) Caucasian, and 26 (50%) were college educated. Only 8 (15%) reported using a conversational assistant regularly, while 22 (41%) had never used one, and 24 (44%) had tried one \"a few times.\" Forty-four (82%) used computers regularly. Subjects were only able to complete 168 (43%) of their 394 tasks. Of these, 49 (29%) reported actions that could have resulted in some degree of patient harm, including 27 (16%) that could have resulted in death. Reliance on conversational assistants for actionable medical information represents a safety risk for patients and consumers. Patients should be cautioned to not use these technologies for answers to medical questions they intend to act on without further consultation from a health care provider.

Conventional Web-based search engines may be unusable by individuals with low health literacy for finding health-related information, thus precluding their use by this population. We describe a conversational search engine interface designed to allow individuals with low health and computer literacy identify and learn about clinical trials on the Internet. A randomized trial involving 89 participants compared the conversational search engine interface (n=43) to the existing conventional keyword- and facet-based search engine interface (n=46) for the National Cancer Institute Clinical Trials database. Each participant performed 2 tasks: finding a clinical trial for themselves and finding a trial that met prespecified criteria. Results indicated that all participants were more satisfied with the conversational interface based on 7-point self-reported satisfaction ratings (task 1: mean 4.9, SD 1.8 vs mean 3.2, SD 1.8, P<.001; task 2: mean 4.8, SD 1.9 vs mean 3.2, SD 1.7, P<.001) compared to the conventional Web form-based interface. All participants also rated the trials they found as better meeting their search criteria, based on 7-point self-reported scales (task 1: mean 3.7, SD 1.6 vs mean 2.7, SD 1.8, P=.01; task 2: mean 4.8, SD 1.7 vs mean 3.4, SD 1.9, P<.01). Participants with low health literacy failed to find any trials that satisfied the prespecified criteria for task 2 using the conventional search engine interface, whereas 36% (5/14) were successful at this task using the conversational interface (P=.05). Conversational agents can be used to improve accessibility to Web-based searches in general and clinical trials in particular, and can help decrease recruitment bias against disadvantaged populations.

Prior studies have demonstrated the safety risks when patients and consumers use conversational assistants such as Apple's Siri and Amazon's Alexa for obtaining medical information. The aim of this study is to evaluate two approaches to reducing the likelihood that patients or consumers will act on the potentially harmful medical information they receive from conversational assistants. Participants were given medical problems to pose to conversational assistants that had been previously demonstrated to result in potentially harmful recommendations. Each conversational assistant's response was randomly varied to include either a correct or incorrect paraphrase of the query or a disclaimer message-or not-telling the participants that they should not act on the advice without first talking to a physician. The participants were then asked what actions they would take based on their interaction, along with the likelihood of taking the action. The reported actions were recorded and analyzed, and the participants were interviewed at the end of each interaction. A total of 32 participants completed the study, each interacting with 4 conversational assistants. The participants were on average aged 42.44 (SD 14.08) years, 53% (17/32) were women, and 66% (21/32) were college educated. Those participants who heard a correct paraphrase of their query were significantly more likely to state that they would follow the medical advice provided by the conversational assistant (χ =3.1; P=.04). Those participants who heard a disclaimer message were significantly more likely to say that they would contact a physician or health professional before acting on the medical advice received (χ =43.5; P=.001). Designers of conversational systems should consider incorporating both disclaimers and feedback on query understanding in response to user queries for medical advice. Unconstrained natural language input should not be used in systems designed specifically to provide medical advice.

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 .

If 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. This 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. A 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. Likelihood 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. GRACE 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. Plain Language Summary: Government websites such as cdc.gov are often used by U.S. residents for health information. In this study, 39 participants used such websites to determine COVID-19 vaccine eligibility and rated them for easy use. Determining vaccine eligibility was generally unsuccessful, as websites were confusing and hard to use. We recommend improving public health sites to maximize ease of finding important information.

A virtual museum guide agent that uses human relationship-building behaviors to engage museum visitors is described. The computer animated agent, named “Tinker”, uses nonverbal conversational behavior, empathy, social dialogue, reciprocal self-disclosure and other relational behavior to establish social bonds with users, and encourage continued interaction and repeated visits. Tinker describes exhibits in the museum, gives directions, and discusses technical aspects of her own implementation. Tinker also recognizes returning visitors through biometric analysis of their hand shapes and dialogue cues. Results from two experiments using Tinker are described. In the first, 29 returning visitors are randomized to interact with the agent with the biometric identification turned on or off. In the second experiment, 1,607 visitors are randomized to interact with versions of Tinker that have relationship-building behavior turned on or off. Results indicate that the use of relational behavior leads to significantly greater engagement by museum visitors, measured by session length, number of sessions, and self-reported attitude, as well as learning gains, as measured by a knowledge test, compared to the same agent that does not use relational behavior. Implications for museum exhibits and intelligent tutoring systems are discussed.

Young women from the low-middle-income country of Lesotho in southern Africa frequently report limited knowledge regarding sexual and reproductive health issues and engage in risky sexual behaviors. The purpose of this study is to describe the adaptation of an evidence-based conversational agent system for implementation in Lesotho and provide qualitative data pertaining to the success of the said adaptation. An embodied conversational agent system used to provide preconception health advice in the United States was clinically and culturally adapted for use in the rural country of Lesotho in southern Africa. Inputs from potential end users, health leaders, and district nurses guided the adaptations. Focus group discussions with young women aged 18-28 years who had used the newly adapted system renamed \"Nthabi\" for 3-4 weeks and key informant interviews with Ministry of Health leadership were conducted to explore their views of the acceptability of the said adaptation. Data were analyzed using NVivo software, and a thematic content analysis approach was employed in the study. A total of 33 women aged 18-28 years used Nthabi for 3-4 weeks; eight (24.2%) of them were able to download and use the app on their mobile phones and 25 (75.8%) of them used the app on a tablet provided to them. Focus group participants (  = 33) reported that adaptations were culturally appropriate and provided relevant clinical information. The participants emphasized that the physical characteristics, personal and non-verbal behaviors, utilization of Sesotho words and idioms, and sensitively delivered clinical content were culturally appropriate for Lesotho. The key informants from the Ministry leadership (  = 10) agreed that the adaptation was successful, and that the system holds great potential to improve the delivery of health education in Lesotho. Both groups suggested modifications, such as using the local language and adapting Nthabi for use by boys and young men. Clinically tailored, culturally sensitive, and trustworthy content provided by Nthabi has the potential to improve accessibility of sexual and reproductive health information to young women in the low-middle-income country of Lesotho.

Automated health behavior change interventions show promise, but suffer from high attrition and disuse. The Internet abounds with thousands of personal narrative accounts of health behavior change that could not only provide useful information and motivation for others who are also trying to change, but an endless source of novel, entertaining stories that may keep participants more engaged than messages authored by interventionists. Given a collection of relevant personal health behavior change stories gathered from the Internet, the aim of this study was to develop and evaluate an automated indexing algorithm that could select the best possible story to provide to a user to have the greatest possible impact on their attitudes toward changing a targeted health behavior, in this case weight loss. An indexing algorithm was developed using features informed by theories from behavioral medicine together with text classification and machine learning techniques. The algorithm was trained using a crowdsourced dataset, then evaluated in a 2×2 between-subjects randomized pilot study. One factor compared the effects of participants reading 2 indexed stories vs 2 randomly selected stories, whereas the second factor compared the medium used to tell the stories: text or animated conversational agent. Outcome measures included changes in self-efficacy and decisional balance for weight loss before and after the stories were read. Participants were recruited from a crowdsourcing website (N=103; 53.4%, 55/103 female; mean age 35, SD 10.8 years; 65.0%, 67/103 precontemplation; 19.4%, 20/103 contemplation for weight loss). Participants who read indexed stories exhibited a significantly greater increase in self-efficacy for weight loss compared to the control group (F1,107=5.5, P=.02). There were no significant effects of indexing on change in decisional balance (F1,97=0.05, P=.83) and no significant effects of medium on change in self-efficacy (F1,107=0.04, P=.84) or decisional balance (F1,97=0.78, P=.38). Personal stories of health behavior change can be harvested from the Internet and used directly and automatically in interventions to affect participant attitudes, such as self-efficacy for changing behavior. Such approaches have the potential to provide highly tailored interventions that maximize engagement and retention with minimal intervention development effort.