Conversational Search Systems for Health Information Seeking: A Scoping Review of Capabilities, Challenges, and Future Directions

Conversational search systems (CSSs) are emerging as a transformative interface for health information seeking, enabling multi-round, natural language interactions that integrate diverse medical resources. This scoping review synthesizes evidence on the capabilities, limitations, applications, and future directions of CSSs in healthcare. Following PRISMA-ScR guidelines, we systematically searched multidisciplinary databases (2010–2025), screened 3789 records, and included 325 studies addressing CSSs in health contexts. Analysis identified six thematic domains: (1) capabilities and limitations, (2) enhancement methods, (3) clinical applications, (4) trust, user experience, and interaction design, (5) readability, health literacy, and patient communication, and (6) cross-lingual and domain-specific adaptation. Findings show CSSs offer advantages in personalization, structured output, and patient education, but face challenges in accuracy, timeliness, and semantic consistency, particularly in high-risk clinical decision-making. Enhancement strategies such as retrieval-augmented generation (RAG), knowledge graphs (KG), fine-tuning, and composite approaches improve performance, while trust-building requires transparency, empathy, and ethical safeguards. Cross-lingual disparities and cultural adaptability remain critical gaps. Overall, CSSs hold substantial potential to improve health information access and literacy, but safe, equitable, and culturally sensitive integration demands multidimensional optimization in knowledge updating, bias control, and interaction design, alongside clinician oversight, to ensure reliability and maximize public health impact.