IoT-Based Isolation Ward Monitoring System Prototype
Open Access
Abstract
The COVID-19 pandemic exposed critical vulnerabilities in healthcare systems worldwide, placing healthcare workers (HCWs) at severe infection risk through direct patient contact. Epidemiological data confirm that HCWs were approximately seven times more likely to develop severe COVID-19 than other occupations, with over 7000 HCW deaths recorded globally by mid-2020. This paper presents the design and laboratory proof-of-concept validation of an IoT-based remote patient-monitoring system prototype—the IoT-Based Isolation Ward Monitoring System Prototype—designed to eliminate unnecessary patient-to-HCW physical contact while maintaining continuous, real-time physiological surveillance. The system integrates multi-sensor hardware comprising an AD8232 ECG module, a MAX30100 pulse oximeter, an NTC thermistor, and an MQ-135 sensor. These sensors interface with an Arduino UNO for data acquisition, while localized edge computing is executed on a Raspberry Pi 3B. A convolutional neural network (CNN) trained on the MIT-BIH Arrhythmia Database classifies heartbeats into five distinct categories. By utilizing SMOTE resampling on 109,446 samples, the network achieves an on-device inference latency of under 200 ms. The sensor data are transmitted to a Firebase Realtime Database via an authenticated REST API, which synchronizes data across dual front-end interfaces: a LabVIEW desktop dashboard for clinical oversight and a cross-platform Flutter mobile application for mobile monitoring. End-to-end technical validation under controlled laboratory conditions confirmed round-trip cloud latencies between 300 and 800 ms, error-free threshold alert generation, and sub-second latency for the integrated chat utility. The proposed system uniquely combines hardware sensing, ML-based ECG classification, cloud storage, a LabVIEW physician dashboard, and bidirectional doctor–patient mobile communication into a single unified, low-cost platform.
Keywords
Funding Information
- Princess Nourah Bint Abdulrahman University (PNURSP2026R209)
This publication has 12 references indexed in Scilit:
- LoRaWAN-based hybrid internet of wearable things system implementation for smart healthcareInternet of Things, 2024
- Self-reported prevalence of asthma and its associated factors among adult rural population in Bangladesh: a cross-sectional study using WHO PEN protocolBMJ Open, 2023
- Development and Validation of the COVID-19 Hospitalized Patient Deterioration IndexThe American Journal of Managed Care, 2023
- TELECOVID: Remote Vital Signs Monitoring of COVID-19 Risk Patients in Home Isolation With an In-Ear WearableIEEE Pervasive Computing, 2021
- An emergency system for monitoring pulse oximetry, peak expiratory flow, and body temperature of patients with COVID-19 at home: Development and preliminary applicationPLOS ONE, 2021
- Remote Patient Monitoring: Health Status Detection and Prediction in IoT-Based Health Care2021
- Machine Learning based Health Monitoring SystemMaterials Today: Proceedings, 2020
- Smart Heart Monitoring: Early Prediction of Heart Problems Through Predictive Analysis of ECG SignalsIEEE Access, 2019
- Remote patient monitoring: a comprehensive studyJournal of Ambient Intelligence and Humanized Computing, 2017
- Effect of Wireless Channels on Detection and Classification of Asthma Attacks in Wireless Remote Health Monitoring SystemsInternational Journal of Telemedicine and Applications, 2014