A scalable and efficient patient monitoring framework

Abstract

Scalable and secure patient monitoring is critical for modern healthcare systems, particularly in resource-constrained environments. This paper presents the Scalable and Efficient Patient Monitoring Framework (SEPMF), a novel IoT-driven system that integrates fog computing, the InterPlanetary File System (IPFS), and the IOTA Tangle to enable real-time, decentralized, and secure data processing. The system is implemented using ESP8266 and Raspberry Pi to monitor vital signs such as pulse rate and oxygen saturation. A key feature of SEPMF is the integration of an Artificial Intelligence (AI) module within the fog layer, which enables intelligent, context-aware analysis of patient data. The module uses a Support Vector Machine (SVM) model trained on real-world COVID-19 datasets to predict infection status with 99% accuracy. This allows real-time disease prediction and timely alerts without reliance on centralized cloud infrastructure, improving responsiveness and clinical decision-making. The system employs Elliptic Curve Cryptography (ECC) and Transport Layer Security (TLS)-secured Message Queuing Telemetry Transport (MQTT) protocol to ensure data privacy and integrity during transmission. IPFS provides secure storage, while IOTA records tamper-proof transactions, reinforcing security and trust. Experimental evaluation demonstrates high scalability, with throughput stabilizing at 550 Transactions Per Second (TPS), CPU usage remaining below 50%, and latency decreasing from 0.0033 s to 0.002 s as nodes increase. SEPMF outperforms traditional IoT-based systems in scalability, responsiveness, and security. By combining decentralized architecture, embedded intelligence, and real-time processing, the framework offers a robust, efficient, and secure solution for next-generation patient monitoring in both clinical and remote healthcare environments.