
Access to timely healthcare information remains a significant challenge in many rural areas of Ethiopia, including the KonsoDistrict. This research presents the development of a lightweight, web-based chatbot designed to assist patients by providingreal-time responses to general health-related queries. The system is developed using HTML, CSS, and JavaScript andintegrates the Google Gemini API to enable intelligent, natural language interaction.The chatbot aims to reduce the burden on medical staff at Karat District Hospital by handling frequent, non-emergencyinquiries and supporting basic health education. It is designed to be mobile-friendly, accessible with minimal internetconnectivity, and easy to use even for individuals with limited digital literacy. Test scenarios were created using realisticpatient queries related to local health issues such as malaria, maternal care, and vaccination. Although the currentimplementation supports only English, the system is built with scalability in mind, including future enhancements such assupport for local languages (Amharic and Afa Konso), voice input, and integration with hospital services. This solutionrepresents a step toward bridging healthcare access gaps in rural communities using AI and web technologies.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
