IoT-Enabled Remote Health Monitoring: Blood Glucose and Other Vital Parameters in Chronic Patients

Chronic diseases such as diabetes, cardiovascular conditions, and respiratory ailments are increasing globally, necessitating continuous and efficient health monitoring. This research develops a multi-sensor IoT-based system for remote, real-time monitoring of vital health parameters including non-invasive blood glucose, heart rate, oxygen saturation (SpO2), and body temperature. The system integrates the MAX30100 sensor for blood glucose, heart rate, and SpO2 measurement, and the DS18B20 sensor for body temperature, all interfaced with a Raspberry Pi 4B microcontroller. Additionally, a SIM7600E GSM/GNSS module provides patient location tracking to enhance emergency response. Data are securely transmitted and stored on a cloud platform and accessed via a cross-platform mobile application, facilitating timely clinical interventions and personalized care. Validation against clinical hospital tests showed approximately 90% accuracy for non-invasive glucose monitoring and over 96% accuracy for other vital signs, demonstrating reliable performance. This low-cost, portable, and pain-free monitoring solution addresses the limitations of traditional invasive methods, improving chronic disease management, reducing hospital visits, and supporting proactive healthcare delivery, particularly in underserved regions. The proposed system was evaluated on 80 participants (male and female, aged 1–80 years) and its performance was compared with standard medical devices. Following calibration using a regression model, glucose readings achieved an overall accuracy of approximately 90%, while the mean errors for SpO₂, heart rate, and body temperature were 2%, 4%, and 3%, respectively. These findings demonstrate that the system provides reliable performance for most physiological parameters. Future work will focus on incorporating advanced machine learning algorithms to enhance glucose prediction, extending the system to monitor additional parameters such as ECG and blood pressure, and conducting large-scale trials with diverse patient populations to confirm its reliability and clinical applicability.