Evaluating user experiences with an AI chatbot for health-related social needs: A cross-sectional mixed methods study

Unmet health-related social needs (hrsns) significantly impact health. while screening tools exist, linking individuals to resources remains difficult. chatbots offer a potential solution for personalized, real-time navigation, but their usability and trustworthiness, particularly among high-need populations, need further study. we conducted a mixed-methods study with 128 caregivers to evaluate an ai chatbot, daphne, designed to identify hrsns and recommend resources. data on usability, task load, satisfaction, and trust were collected, along with qualitative feedback and conversation transcripts. regression and pairwise analyses explored associations between demographics, hrsns, and user experience. participants were mostly female (68%), 30–49 (71%), white (44%) or black/african american (36%), relied on medicaid/medicare (83%), and cared for a child with special healthcare needs (78%). they reported high usability (sus = 84.7), low task load (nasa-tlx = 6.8), high satisfaction (nps = 8.0), and high trust (mean = 4.1). nearly all (98%) reported unmet hrsns, including food insecurity (76%) and financial limitations (75%). chatbot sessions averaged 3 minutes/20 turns. daphne achieved 99% intent accuracy in 1,523 turns, focusing on financial, housing, and food needs. usability and trust were consistent across demographics, though higher education and lower income groups showed slight usability decreases. certain hrsns (transportation, utility disruptions) correlated with higher trust and satisfaction, suggesting particular value for users facing structural barriers. daphne demonstrated strong usability and trust across diverse groups. future designs should focus on longitudinal impact and effectiveness for improved accessibility and practical implementation. our study supports digital social care practices and provides empirical evidence that a chatbot can engage vulnerable populations to support unmet hrsns.Author summary: Many families caring for children struggle with everyday challenges such as finding enough food, paying utility bills, securing housing, or getting reliable transportation. These social needs strongly affect health, yet they are usually screened for only during clinic visits, often once a year, leaving families without support when problems arise between visits. Even when needs are identified, caregivers frequently have difficulty finding and accessing available assistance programs. In this study, we tested whether a conversational AI chatbot, called DAPHNE, could help caregivers identify their social needs and connect to relevant resources outside the clinic. Caregivers interacted with the chatbot using realistic scenarios based on common, real-world challenges. They could type freely or use on-screen buttons, similar to everyday messaging apps. We found that caregivers across diverse backgrounds generally found the chatbot easy to use, trustworthy, and efficient. Those facing challenges related to transportation or utilities reported especially high trust and satisfaction. Interactions were brief but effective, suggesting the chatbot fit well into caregivers’ daily lives. Our findings show that a purpose-built healthcare chatbot can support families by improving access to social resources beyond traditional clinic-based screening.