Offline Disease Prediction Chatbot for Low-End Devices

Medical assistance remains out of reach for many individuals in areas where hospitals, clinics, and reliable internet are scarce. Conventional AI-driven diagnostic tools depend on continuous connectivity and substantial computational power, making them impractical in low-resource environments. This study introduces a self-contained health advisory chatbot designed to function without an internet connection and operate on devices with minimal hardware capabilities. The chatbot employs a streamlined machine learning model, allowing it to evaluate user symptoms and provide preliminary health guidance efficiently. To enhance accuracy, the system incorporates an interactive questioning strategy, adjusting its responses dynamically based on user inputs. Unlike cloud-based diagnostic solutions, this chatbot runs entirely on local hardware, ensuring reliability even in isolated settings. Performance assessments indicate that this approach successfully delivers meaningful guidance with minimal processing requirements, making it a viable solution for populations with limited access to medical resources. Keywords: Autonomous Health Advisor, Offline AI, Low-Resource Computing, Interactive Diagnosis, Medical Access Solutions, Lightweight Machine Learning, Adaptive Questioning.