IoT-Enabled Multi-Parameter Respiratory Health Monitoring System with Spirometry-Based Lung Function Analysis Using Embedded Sensors

Abstract

The increasing need for continuous and remote healthcare has accelerated the adoption of intelligent and portable monitoring solutions for early diagnosis and management of respiratory disorders. This paper presents an IoT-enabled multi-parameter respiratory health monitoring system that integrates spirometry-based lung function analysis with real-time vital sign tracking. The proposed system employs an Arduino Uno microcontroller to interface with a spirometer flow sensor, pulse oximeter (SpO₂) sensor, heart rate sensor, and body temperature sensor. The spirometry module enables measurement of respiratory airflow and estimation of key lung function indicators such as breath rate and peak expiratory flow (PEF), providing deeper insights into pulmonary performance compared to conventional monitoring approaches. The collected physiological data is displayed locally on an LCD and simultaneously transmitted to a cloud platform via a Wi-Fi module, allowing remote access through web or mobile interfaces. An alert mechanism is incorporated to detect abnormal physiological conditions and notify users of timely medical attention. The integration of multi-sensor data within a unified embedded framework enhances system reliability and enables comprehensive health assessment. The proposed system is low-cost, portable, and scalable, making it suitable for home-based monitoring and telemedicine applications. It supports continuous patient supervision, facilitates early detection of respiratory abnormalities, and contributes to improved healthcare accessibility, particularly in remote and underserved regions. Future work will focus on improving signal accuracy through advanced filtering and calibration techniques, integrating machine learning models for predictive health analytics, and enhancing scalability by supporting multiple users and real-time dashboards. Additionally, incorporating wearable form factors and improving energy efficiency will further extend the applicability of the system in continuous and long-term health monitoring scenarios.