A SOFTWARE SOLUTION FOR REAL-TIME COLLECTION AND PROCESSING OF MEDICAL DATA FOR EPILEPSY PATIENTS

Authors

DOI:

https://doi.org/10.20998/2079-0023.2024.02.05

Keywords:

real-time monitoring, medical data processing, automation, health indicators, software, system architecture, development technologies

Abstract

The rapid development of computer technologies has significantly impacted various sectors, including healthcare. The ability to collect, process, and visualize medical data in real time is becoming increasingly important, especially for managing chronic conditions such as epilepsy. This paper presents a web-based application designed for real-time monitoring of health indicators, enabling healthcare professionals to track patient data efficiently. The system automates the process of collecting data from fitness trackers, transmitting it via a mobile device to a server, and visualizing it in a web application. Its architecture employs a thin-client model with Node.js for backend logic and React.js for the user interface, ensuring scalability and responsiveness. Key features include real-time data visualization, historical trend analysis, and the ability to export health metrics for further examination. The system architecture follows a modular approach, with a clear separation of concerns between the client-side, server-side, and database components. MongoDB is used as the database provider, offering flexibility in handling large volumes of health data. The system underwent extensive testing in two stages. During the first stage, real-world data collection demonstrated an average data transmission time of less than 112 ms, ensuring compliance with real-time requirements. In the second stage, stress testing with up to 100 simultaneous users showed an average server response time of 145.8 ms and a 95th percentile response time of 167.1 ms. These results confirm the system’s robustness and suitability for deployment in medical facilities. Future work aims to enhance the system by incorporating advanced real-time alert mechanisms and additional health metrics, such as oxygen saturation and activity levels, to provide comprehensive monitoring. The presented solution showcases the potential of integrating modern web technologies into healthcare, contributing to improved patient outcomes and more efficient workflows for medical professionals.

Author Biographies

Andrii Kopp, National Technical University "Kharkiv Polytechnic Institute"

Doctor of Philosophy (PhD), Docent, National Technical University
"Kharkiv Polytechnic Institute", Associate Professor at the Department of  Software Engineering and Management Intelligent Technologies, Kharkiv, Ukraine

Iryna Liutenko, National Technical University "Kharkiv Polytechnic Institute"

Candidate of Technical Sciences (PhD), Docent, National Technical University
"Kharkiv Polytechnic Institute", Associate Professor at the Department of Software Engineering and Management Intelligent Technologies, Kharkiv, Ukraine

Viktor Yamburenko, National Technical University "Kharkiv Polytechnic Institute"

National Technical University "Kharkiv Polytechnic Institute", PhD Student

Andrii Pashniev, National Technical University "Kharkiv Polytechnic Institute"

Candidate of Technical Sciences (PhD), Senior Researcher, National Technical University "Kharkiv Polytechnic Institute", Associate Professor of the Department of Information Systems and Technologies, Kharkiv, Ukraine

References

Brown D. E. Introduction to data mining for medical informatics. Available at: https://pubmed.ncbi.nlm.nih.gov/18194716/ (accessed: 12.09.2023).

Comak E., Polat K., Güneş S., Arslan A. A new medical decision making system: least square support vector machine (LSSVM) with fuzzy weighting pre-processing. Available at: https://journals.scholarsportal.info/details/09574174/v32i0002/409_anmdmsvmwfwp.xml&sub=all (accessed: 18.09.2023).

Ways Data Science Is Reshaping Healthcare. Available at: https://www.altexsoft.com/blog/datascience/7-ways-data-science-is reshapinghealthcare/ (accessed: 20.09.2023).

Survey: 8 in 10 Hospital Leaders Say Predictive Analytics is Important to Future Yet Only One-Third Use It. Available at: https://chimecentral.org/survey-8-10-hospital-leaders-say-predictive-analytics-important-future-yet-one-third-use/ (accessed: 20.09.2023).

Helsi. Available at: https://helsi.me/about (accessed: 02.11.2023).

Medeir. Available at: https://e-life.com.ua/prod-tech/medejr-uk/ (accessed: 02.11.2023).

Medstar Solutions. Available at: https://medstar.ua/uа/ (accessed: 02.11.2023).

Doctor Eleks. Available at: https://doctor.eleks.com/uа/ (accessed: 02.11.2023).

Health 24. Available at: https://h24.ua/ (accessed: 02.11.2023).

Kopniak К. Otsiniuvannia efektyvnosti vprovadzhennia medychnykh informatsiinykh system. Available at: https://jeou.donnu.edu.ua/article/view/4784 (accessed: 04.03.2024).

Gillis A. S. What is a thin client (lean client)? Available at: https://www.techtarget.com/searchnetworking/definition/thin-client (accessed: 09.04.2024).

Mărcuță C., Beyond the Hype Practical Use Cases for Mongodb in Real-world Scenarios. Available at: https://moldstud.com/articles/p-beyond-the-hype-practical-use-cases-for-mongodb-in-real-world-scenarios (accessed: 12.04.2024).

Amengual F. M. The Dual Journey: Healthcare Interoperability and Modernization. Available at: https://www.mongodb.com/blog/post/dual-journey-healthcare-interoperability-modernization (accessed: 12.04.2024).

IoT Communication Protocols with measurements for NB-IoT - Expert Guide. Available at: https://avsystem.com/blog/iot/iot-communication-protocols-with-calculations (accessed: 14.06.2024).

Downloads

Published

2025-01-04

How to Cite

Kopp, A., Liutenko, I., Yamburenko, V., & Pashniev, A. (2025). A SOFTWARE SOLUTION FOR REAL-TIME COLLECTION AND PROCESSING OF MEDICAL DATA FOR EPILEPSY PATIENTS. Bulletin of National Technical University "KhPI". Series: System Analysis, Control and Information Technologies, (2 (12), 30–37. https://doi.org/10.20998/2079-0023.2024.02.05

Issue

Section

MANAGEMENT IN ORGANIZATIONAL SYSTEMS