Chatbot for social needs screening and resource sharing with vulnerable families: Iterative design and evaluation study

Abstract Health outcomes are significantly influenced by unmet social needs. Although screening for unmet social needs has become common in healthcare settings, there is often poor linkage to resources after needs are identified. The structural barriers (e.g., staffing, time, space) to helping address social needs could be overcome by a technology-based solution. This study presents the design and evaluation of a chatbot, DAPHNE©, that screens for social needs and links patients to resources. This study used a two-step approach: (1) iterative design with interdisciplinary stakeholder groups and (2) feasibility and usability assessment. Virtual sessions were held with an interdisciplinary group of stakeholders (n=10) using thematic and content analysis to inform the chatbot's design and development. Evaluation included an online survey, focus group interviews, and scenario-based usability testing with community health workers (family advocates) (n=4) and social workers (n=9). The stakeholders emphasized the importance of provider-technology collaboration, inclusive conversational design, and user education. Users found the chatbot's capabilities met expectations and the chatbot was easy to use (System Usability Scale score=72). The stakeholders raised concerns about accuracy of suggested resources, electronic health record integration, and trust with a chatbot. Future research should examine effectiveness, cost- effectiveness, and scalability of chatbot interventions to address social needs.