Development of an IoT-enabled cost-effective asthma patient monitoring system: Integrating health and indoor environment data with statistical analysis and data visualization

This research aims to develop a cost-effective IoT-based remote health monitoring system tailored for asthma patients to provide real-time feedback and hence minimize the necessity of hospitalization. The system includes monitoring patient health indicators and indoor environmental parameters. This device consists of NodeMCU and Arduino microcontrollers along with sensors such as the max30100 for heart rate and oxygen level sensing, the ds18b20 for body temperature measurement, the dht11 for room temperature and humidity sensing, the optical dust sensor for tracking dust concentration, and the mq-135 gas sensor for detecting harmful gases. The study is divided into two major sections: the front end, which includes the hardware setup with microcontrollers, wires, and sensors, and the back end, which contains software-based database features for real-time monitoring, storage of patient records, and analyses of the collected data to extract valuable insights about the patient's condition. The Blynk IoT platform offers real-time tracking on mobile devices, while the ThingSpeak platform enables graphical depiction on a computer-friendly interface. A Google Spreadsheet database is used to store the acquired data. The system has an integrated alerting system that sends email/SMS alerts to patients and physicians when sensor readings exceed safe levels. A prototypic data analysis section is introduced to assess the collected data through descriptive analysis, graph charting, and box plot visualization. The health measures were examined for a single patient during a week, using statistical tests like ANOVA to detect changes and determine stability, while the environmental elements were assessed throughout a month, capturing trends and patterns. All health sensors were validated by utilizing paired sample t-tests to compare 15 patients' data to that of commercially available devices. This research provides a complete package that provides essential guidance for replicating the device, interpreting and presenting sensor data efficiently to assess the health of asthma patients. Additionally, it proposes future-oriented objective function optimization and enhanced data security measures. The source code of the proposed system is available on GitHub.