BackgroundPeople living with chronic diseases are increasingly seeking health information online. For individuals with diabetes, traditional educational materials often lack reliability and fail to engage or empower them effectively. Innovative approaches such as retrieval-augmented generation (RAG) powered by large language models have the potential to enhance health literacy by delivering interactive, medically accurate, and user-focused resources based on trusted sources. ObjectiveThis study aimed to evaluate the effectiveness of a custom RAG-based artificial intelligence chatbot designed to improve health literacy on type 2 diabetes mellitus (T2DM) by sourcing information from validated reference documents and attributing sources. MethodsA T2DM chatbot was developed using a fixed prompt and reference documents. Two evaluations were performed: (1) a curated set of 44 questions assessed by specialists for appropriateness (appropriate, partly appropriate, or inappropriate) and source attribution (matched, partly matched, unmatched, or general knowledge) and (2) a simulated consultation of 16 queries reflecting a typical patient’s concerns. ResultsOf the 44 evaluated questions, 32 (73%) responses cited reference documents, and 12 (27%) were attributed to general knowledge. Among the 32 sourced responses, 30 (94%) were deemed fully appropriate, with the remaining 2 (6%) being deemed partly appropriate. Of the 12 general knowledge responses, 1 (8%) was inappropriate. In the 16-question simulated consultation, all responses (100%) were fully appropriate and sourced from the reference documents. ConclusionsA RAG-based large language model chatbot can deliver contextually appropriate, empathetic, and clinically credible responses to T2DM queries. By consistently citing trusted sources and notifying users when relying on general knowledge, this approach enhances transparency and trust. The findings have relevance for health educators, highlighting that patient-centric reference documents—structured to address frequent patient questions—are particularly effective. Moreover, instances in which the chatbot signals that it has drawn on general knowledge can provide opportunities for health educators to refine and expand their materials, ensuring that more future queries are answered from trusted sources. The findings suggest that such chatbots may support patient education, promote self-management, and be readily adapted to other health contexts.

Objective: Pregnant women with gestational diabetes mellitus (GDM) are 50% more likely to develop type II diabetes (T2D) within 6 months to 2 years after giving birth. Therefore, international guidelines recommend it is best practice for women diagnosed with GDM to attend screening for T2D 6-12 weeks postpartum and every 1-3 years thereafter for life. However, uptake of postpartum screening is suboptimal. This study will explore the facilitators of and barriers to attending postpartum screening for T2D that women experience. Study design: This was a prospective qualitative cohort study using thematic analysis.Methods: A total of 27 in-depth, semistructured interviews were conducted over the telephone with women who had recent GDM. Interviews were recorded and transcribed, and data were analysed using thematic analysis.Results: Facilitators of and barriers to attending postpartum screening were identified at three different levels: personal, intervention, and healthcare systems level. The most common facilitators identified were concern for their own health and having the importance of screening explained to them by a health professional. The most common barriers identified were confusion over the test and COVID-19.Conclusion: This study identified several facilitators of and barriers to attending postpartum screening. These findings will help to inform research and interventions for improving rates of attendance at postpartum screening to reduce the subsequent risk of developing T2D.& COPY; 2023 The Author(s). Published by Elsevier Ltd on behalf of The Royal Society for Public Health. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).