A Real-Time, Location-Aware Remote Patient Monitoring System for Telemedicine Decision Support

Telemedicine has become an integral component of modern healthcare, particularly in contexts where direct patient-physician interaction is limited or unavailable. In such situations, access to objective physiological data, real-time patient localization, and automated alerting can significantly improve situational awareness and support timely clinical decision-making. This paper presents a real-time, location-aware patient monitoring system developed as a low-cost, fully functional demonstration platform to support telemedicine services and risk-based alerting. The proposed system combines wearable-based physiological data acquisition with a mobile application that collects heart rate measurements and geographic coordinates, which are transmitted to a server-side platform for real-time processing, visualization, and alert generation. Patient status is displayed through an interactive map with risk-level indicators and complemented by time-series charts that facilitate the interpretation of physiological trends over time. Incoming data are continuously evaluated using a rule-based risk assessment mechanism, enabling automated email alerts when predefined critical conditions are detected. Alert notifications include relevant physiological values together with direct links to the patient's geographic location, supporting rapid response in emergency or high-risk scenarios. The system is evaluated from a functional and architectural perspective, demonstrating its ability to support remote monitoring, contextual awareness, and decision support in telemedicine settings, including telephone-based consultations. While the platform does not aim to provide clinical validation or long-term medical assessment, it illustrates the practical benefits of integrating wearable data, real-time localization, and automated alerting within a unified telemedicine-oriented framework. In addition, the proposed architecture is designed to support future extensions based on data-driven methods, including machine learning-based risk prediction and preventive health analytics. However, such approaches are not part of the current implementation and are outlined as directions for future research. The main contribution of this work lies in the design and implementation of a low-cost, location-aware telemedicine monitoring system that combines real-time data acquisition, integrated visualization, and actionable alerting within a unified and deployable architecture.