An Edge-Enabled IoT Healthcare Monitoring Framework Using Raspberry Pi Pico W and Cloud-Based Physiological Data Management
TL;DR
The developed platform establishes a scalable foundation for next-generation smart healthcare systems by combining low-cost embedded hardware, edge computing, and cloud technologies to improve accessibility, reliability, and remote medical monitoring.
Abstract
The rapid growth of the Internet of Medical Things (IoMT) has created significant opportunities for developing intelligent remote healthcare systems capable of continuous patient monitoring. However, many existing low-cost healthcare monitoring solutions are limited by single-parameter sensing, poor interoperability, inadequate cloud integration, and restricted scalability for multi-patient applications. This paper presents the design and development of an edge-enabled IoT-based smart healthcare monitoring platform using the Raspberry Pi Pico W for real-time acquisition, processing, and cloud storage of physiological data. The proposed system integrates three biomedical sensors, namely the MAX30102 sensor for heart rate and blood oxygen (SpO₂) monitoring, the DS18B20 digital sensor for body temperature measurement, and the AD8232 analog front-end for electrocardiogram (ECG) signal acquisition. The embedded edge node performs local signal preprocessing, physiological parameter extraction, timestamp synchronization, and secure wireless transmission of patient data to a cloud database through REST-based communication over Wi-Fi. A cloud-centric architecture is developed using Supabase to provide reliable data storage, multi-node scalability, and seamless integration with future intelligent healthcare applications. The proposed framework supports continuous remote patient monitoring while maintaining a low hardware cost, reduced computational overhead, and efficient data communication. Experimental implementation demonstrates reliable real-time physiological data acquisition, stable cloud synchronization, and effective management of multimodal healthcare data suitable for subsequent analytical and predictive applications. The developed platform establishes a scalable foundation for next-generation smart healthcare systems by combining low-cost embedded hardware, edge computing, and cloud technologies to improve accessibility, reliability, and remote medical monitoring.