API-Based Chatbot-Integrated Mobile Health Education Application for Stunting Prevention in Pregnant Women

Abstract

Stunting remains a major public health issue in Indonesia because it can negatively affect children's physical growth, cognitive development, and long-term quality of life. Improving pregnant women's knowledge of maternal health and nutrition is one preventive effort, yet health information delivery still faces limited access, time constraints, and a lack of interactive educational media. This study aims to develop an Android-based mobile application for maternal health education on stunting prevention, integrated with an API-based chatbot as an accessible and interactive educational medium. The study employed the Research and Development (R&D) method with the Waterfall model, covering requirements analysis, system design, implementation, testing, and maintenance. The application was built using Flutter with Firebase as the backend and the Gemini AI API as the chatbot. System testing used Black Box Testing, Integration Testing, and User Acceptance Testing (UAT) involving ten respondents. Results show that all application features functioned as expected, communication between the application, Firebase, and the Gemini AI API operated successfully, and the UAT score reached 79.8%, categorized as Good. These findings indicate that the developed application is well accepted by users and can effectively support the delivery of maternal health information to assist stunting prevention efforts.