Community-Based Healthcare Automation: Development of Integrated IoT Sensor Devices with Mobile and Web Monitoring Systems

IoT technologies are transforming healthcare delivery by enhancing accessibility, efficiency, and personalization, particularly in underserved areas. However, healthcare systems in many remote communities remain constrained by manual processes, data inaccuracy, and limited real-time monitoring, creating critical gaps in patient care and health outcome tracking. This study addresses these challenges by developing an innovative Smart IoT-Based Community Healthcare Management and Monitoring System designed for rural and resource-constrained environments. The system integrates multiple IoT sensors and devices-Raspberry Pi, M5Stack ENV III, LC-081 temperature scanner, Wellect digital blood pressure monitor, and MAX30102 pulse oximeter-to continuously monitor vital signs such as blood pressure, heart rate, oxygen saturation, body temperature, and BMI. A unique Multi-Criteria Decision Analysis (MCDA) framework is employed to compute an Overall Health Score (OHS), enabling personalized, data-driven recommendations for patients and healthcare workers. The system architecture utilizes a dual-database model (SQLite for offline and MySQL for online synchronization), ensuring uninterrupted functionality regardless of internet access. Developed using Python Django for the mobile patient app and PHP for the web-based healthcare provider dashboard, the system allows real-time sensor interaction, graphical trend visualization, and seamless data logging. Testing results validated high accuracy across devices- $\pm 2.5 \mathbf{~ m m H g}$ for blood pressure, 97 % for heart rate and $\text{SpO}_{2}$, and $\pm 0.2^{\circ} \mathrm{C}$ for body temperature-affirming sensor precision and system reliability. While the system demonstrated effective real-time monitoring and proactive health management, sensor calibration and remote network latency challenges remain. Future work will focus on incorporating additional health parameters (e.g., glucose, ECG), integrating machine learning for predictive analytics, and conducting longitudinal studies to validate health impact over time. This project contributes a replicable and scalable digital health solution aligned with global health goals for sustainable and inclusive care.