SYSTEM FOR DETECTING CRITICAL HUMAN HEALTH CONDITIONS BASED ON THE ANALYSIS OF PHYSIOLOGICAL INDICATORS
DOI:
https://doi.org/10.26906/SUNZ.2025.1.143-149Keywords:
health monitoring system, critical conditions, wearable sensors, electrocardiogram, machine learning, classification, MLPClassifier, RandomForestClassifier, telemedicine, biophysiological indicatorsAbstract
Relevance. The modern increase in cardiovascular diseases, diabetes, and psychological disorders, particularly
post-traumatic stress disorder (PTSD), necessitates the implementation of intelligent health monitoring systems. WHO statistics indicate 15 million premature deaths annually, with 32% attributed to cardiovascular diseases. Additionally, the war
in Ukraine has significantly impacted stress levels among the population, increasing mortality risks. Traditional monitoring
methods do not ensure timely detection of critical conditions, making the adoption of AI-based automated solutions essential.
The object of this study is a system for detecting critical human health conditions based on the analysis of biometric indicators and their dynamics using machine learning methods. The aim of the article is to develop and evaluate the effectiveness
of an automatic system for detecting critical health conditions that operates using wearable devices and artificial intelligence
algorithms. To achieve this goal, a stress level classifier based on physiological indicators was implemented, and a comparative analysis of two algorithms, MLPClassifier and RandomForestClassifier, was conducted. As a result of the research, an
architecture for a continuous health monitoring system was proposed, an algorithm for stress level assessment using ECG,
EDA, BCP, and breathing patterns as input parameters were developed, and MLP and Random Forest classifiers were trained,
and tested on a dataset of 65 participants. MLPClassifier demonstrated higher classification accuracy (91.3%), confirming
its effectiveness for monitoring critical health conditions.
Downloads
References
1. Dietrich, O., et al. (2025). An Open-Source Tool for Mapping War Destruction at Scale in Ukraine Using Sentinel-1 Time Series. arXiv:2406.02506, arXiv, 20 Feb. 2025. arXiv.org. https://doi.org/10.48550/arXiv.2406.02506.
2. Barkovska, O., Oliinyk, D., Sorokin, A., Zabroda, I., & Sedlaček, P. (2024). A system for monitoring the progress of rehabilitation of patients with musculoskeletal disorder. Advanced Information Systems, 8(3), 13-24. DOI: https://doi.org/10.20998/2522-9052.2024.3.02
3. Barkovska, O., & Serdechnyi, V. (2024). Intelligent Assistance System for People with Visual Impairments. INNOVATIVE TECHNOLOGIES AND SCIENTIFIC SOLUTIONS FOR INDUSTRIES, (2)28, 6–16. DOI.org (Crossref). https://doi.org/10.30837/2522-9818.2024.28.006. DOI: https://doi.org/10.30837/2522-9818.2024.28.006
4. Kunczik, J., et al. (2022). Breathing pattern monitoring by using remote sensors. Sensors, 22(22), 8854. DOI: https://doi.org/10.3390/s22228854
5. Deng, Z., et al. (2023). Smart Wearable Systems for Health Monitoring. Sensors, 23(5), 2479. https://doi.org/10.3390/s23052479. DOI: https://doi.org/10.3390/s23052479
6. Kaur, B., et al. (2023). Novel Wearable Optical Sensors for Vital Health Monitoring Systems—A Review. Biosensors, 13(2), 181. https://doi.org/10.3390/bios13020181. DOI: https://doi.org/10.3390/bios13020181
7. Olmedo-Aguirre, J. O., et al. (2022). Remote Healthcare for Elderly People Using Wearables: A Review. Biosensors, 12(2), 73. https://doi.org/10.3390/bios12020073. DOI: https://doi.org/10.3390/bios12020073
8. Adeghe, E. P., et al. (2024). A Review of Wearable Technology in Healthcare: Monitoring Patient Health and Enhancing Outcomes. Open Access Research Journal of Multidisciplinary Studies, 7(1), 142–148. https://doi.org/10.53022/oarjms.2024.7.1.0019. DOI: https://doi.org/10.53022/oarjms.2024.7.1.0019
9. Wang, W., et al. (2016). Algorithmic principles of remote PPG. IEEE Transactions on Biomedical Engineering, 64(7), 1479-1491. DOI: https://doi.org/10.1109/TBME.2016.2609282
10. Tırınk, C., et al. (2023). Estimation of body weight based on biometric measurements by using random forest regression, support vector regression and CART algorithms. Animals, 13(5), 798. DOI: https://doi.org/10.3390/ani13050798
11. Di, H., Shafiq, M., & AlRegib, G. (2018). Patch-level MLP classification for improved fault detection. SEG technical program expanded abstracts 2018. Society of Exploration Geophysicists, 2211-2215. DOI: https://doi.org/10.1190/segam2018-2996921.1
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
