AI Chatbot for Prenatal Nutrition Guidance

Background: Pregnancy imposes significant physical demands, with complications like gestational diabetes (GDM) and pre-eclampsia posing serious risks. Nutrition is crucial for mitigation, but accessing reliable guidance remains challenging. This study evaluates the feasibility of an AI chatbot providing nutritional guidance for managing these conditions. Methods: In a quasi-experimental design, 100 pregnant women will self-select into either the intervention group (n=50, using an AI chatbot) or control group (n=50, receiving standard care). The primary outcome is usability measured by the System Usability Scale (SUS) at 12 weeks, with an expected mean difference of ≥13 points. Secondary outcomes include technology acceptance (Technology Acceptance Model), user engagement, information accuracy, and changes in dietary knowledge/behaviors. Quantitative data will be analyzed using intention-to-treat and t-tests. Semi-structured interviews with 20 participants will explore user experiences through thematic analysis. Expected Results: The AI chatbot is anticipated to demonstrate superior usability and high user acceptance (TAM \>5.0/7), with improvements in dietary knowledge and behavior. Qualitative findings will provide insights into benefits, barriers, and engagement factors. Conclusion: This study will establish an evidence base on AI chatbot feasibility and acceptance for prenatal nutrition, informing tool optimization and future large-scale trials.