Live Health Monitoring System

Abstract

The Live Health Monitoring System predicts the health issues in patients using a machine learning algorithm that was trained on actual health data. After health data is inputted by the user, the system processes and provides an instant prediction of the risk (high or low). The most important health factors which it mostly checks are the heart rate, body temperature, breathing rate, systolic and diastolic blood pressure, and SPO2 levels. In order to offer a user-friendly and interactive interface, HTML, CSS and JavaScript have been used in creating the front end of the site. Python framework was built on the back end, and the machine learning model was incorporated and the data preprocessed with the help of Python modules. The key objectives of the platform are to help track the health condition of a patient in real-time and reduce the use of manual checks. This technique improves convenience and preventive therapy to users and health practitioners because it allows early and distant identification of potential ailments. To implement suitable analysis of the trends in vital conditions and predict potential health risks, the machine learning model was trained on the healthcare dataset. After the user inputs their vitals and the learnt data of the model, the system gives a clear and classification of the risk result. The index phrases include health monitoring, machine learning, vital signs, real-time monitoring, health risk prediction, web application, remote healthcare, Python, data preprocessing, SPO2, and heart rate.

Introduction

The text describes a Live Health Monitoring System designed to continuously track and analyze patient vital signs such as heart rate, body temperature, SpO?, respiration rate, and blood pressure using web technologies and machine learning.

The system aims to improve healthcare by enabling real-time monitoring and early detection of health risks. It uses a web-based interface built with HTML, CSS, and JavaScript, while the backend is developed in Python. A Random Forest machine learning model analyzes patient data to predict potential health issues, supporting preventive and timely medical intervention.

The system is designed to be modular and scalable, allowing future integration with IoT devices, wearables, and additional health parameters like glucose levels and ECG. It also focuses on detecting patterns over time to identify early warning signs that may not be immediately visible.

Existing healthcare solutions are reviewed, including IoT-based monitoring systems, mobile health apps, and AI-based prediction models. However, these systems often lack real-time predictive integration, comprehensive health tracking, or seamless end-to-end architectures.

The research identifies a gap in combining real-time data collection, machine learning prediction, and interactive web-based interfaces in a single system. The proposed solution addresses this by integrating these components into one platform with secure login, data input modules, real-time visualization, and risk prediction.

The system uses standardized medical units (SI units) and demonstrates that the Random Forest model achieves better performance compared to other models like XGBoost and SVM in predicting health conditions.

Conclusion

This analysis demonstrates the steps to develop and implement successfully a Live Health Monitoring System that is capable of measuring health risk levels based on the vital parameters that are provided by the user. The system uses a machine learning model based on the random forest to assess and categorize individuals into low-risk or high-risk groups based on vital signs such as heart rate, body temperature, oxy- gen saturation (SpO 2), respiration rate, and blood pressure. The accuracy of nearly 92 achieved by the model shows that the model has the capacity to make correct prediction without compromising economical use of computers. This is another indication of how ensemble learning techniques can perform well in structured medical data where stability and accuracy are paramount. The proposed system offers a web-based platform, which allows constant and remote observation, unlike the traditional healthcare systems that use direct-person communication and manual observation. Django back-end and HTML, CSS and JavaScript front-end will give ease of access and usability to a wide range of users. Due to this fact, the method is particularly useful in areas where medical facilities are limited in access. On the whole, the investigation enhances the intelligent healthcare systems by integrating predictive analytics with real-time data processors. By making it possible to identify possible health hazards early on, it encourages a move to- wards preventative care. A more advanced algorithm, such as XGBoost or deep learning models, real-time data collection via wearable or IoT sensors, and the ability to store long-term health records in the cloud, as well as multi-class classification of specific medical conditions, are only a few examples of how the system could be enhanced.

References

[1] S. Patel, H. Park, P. Bonato, L. Chan, and M. Rodgers, ”A review of wearable sensors and systems with application in re- habilitation,” Journal of NeuroEngineering and Rehabilitation, vol. 9, no. 1, pp. 1–17, 2012. [2] A. Mukherjee, D. De, and P. Ghosh, ”Health monitoring system using IoT and machine learning,” IEEE Internet of Things Journal, vol. 6, no. 6, pp. 123–132, 2020. [3] P. Kumar and M. Lee, ”Healthcare monitoring system using wireless sensor network,” International Journal of Ad- vanced Computer Science and Applications, vol. 8, no. 4, pp. 432–438, 2017. [4] S. Ghosh and S. Guha, ”A real-time health monitoring sys- tem based on IoT and machine learning,” Procedia Computer Science, vol. 167, pp. 2145–2153, 2020. [5] M. Chen, Y. Ma, and J. Zhang, ”Wearable 2.0: Enabling human-cloud integration in next generation healthcare sys- tems,” IEEE Communications Magazine, vol. 55, no. 1, pp. 54– 61, 2017. [6] R. Kumar and P. Rajasekaran, ”IoT-based health moni- toring system using machine learning,” International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 5, no. 2, pp. 120–128, 2019. [7] J. He, L. Baxter, and A. Xu, ”Machine learning for health- care: Review, opportunities and challenges,” IEEE Access, vol. 7, pp. 2169–3536, 2019. [8] N. Sharma and V. Kumar, ”Heart disease prediction using machine learning algorithms,” International Journal of Com- puter Applications, vol. 181, no. 13, pp. 1–6, 2018. [9] M. Al-Mamun, M. Rahman, and S. Islam, ”An IoT-based health monitoring system for smart cities,” Sensors, vol. 21, no. 22, p. 7532, 2021. [10] J. Kang et al., ”Real-time health monitoring using wear- able sensors and machine learning,” IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1–11, 2021. [11] M. Singh and R. Kapoor, ”Remote health monitoring system using IoT and cloud computing,” International Journal of Engineering Research Technology, vol. 9, no. 5, pp. 122– 127, 2020. [12] P. Rajendran and R. Jayasree, ”Predictive analytics for healthcare monitoring using IoT,” IEEE Access, vol. 8, pp. 184145–184154, 2020. [13] S. Zhang and J. Shen, ”Deep learning for health infor- matics,” IEEE Journal of Biomedical and Health Informatics, vol. 21, no. 1, pp. 4–21, 2017. [14] A. Gupta and K. Singh, ”IoT-enabled patient health monitoring using machine learning,” International Journal of Innovative Technology and Exploring Engineering, vol. 9, no. 3, pp. 1341–1347, 2020. [15] T. Nguyen and H. Kim, ”Smart healthcare system using IoT and machine learning,” Electronics, vol. 10, no. 14, pp. 1– 15, 2021. [16] M. A. Khan, S. Siddiqui, and A. Khan, ”Health care mon- itoring system using IoT and cloud computing,” International Journal of Advanced Research in Computer Science, vol. 9, no. 1, pp. 240–246, 2018. [17] P. S. Aswin, A. Raj, and M. Lakshmi, ”Smart wear- able device for continuous health monitoring using machine learning,” International Journal of Engineering and Advanced Technology, vol. 8, no. 5, pp. 1805–1810, 2019. [18] S. Rani and R. Ahmed, ”A survey on IoT-based healthcare monitoring systems,” Future Generation Computer Systems, vol. 92, pp. 611–626, 2019. [19] R. Kaur and D. Kaur, ”IoT-based health monitoring and data analysis system,” International Journal of Recent Technology and Engineering, vol. 8, no. 3, pp. 144–148, 2019. [20] Y. LeCun, Y. Bengio, and G. Hinton, ”Deep learning,” Nature, vol. 521, pp. 436–444, 2015. [21] M. B. Rehman, ”Health monitoring system using IoT and deep learning,” Journal of Ambient Intelligence and Human- ized Computing, vol. 12, no. 5, pp. 5471–5482, 2021. [22] A. Das and K. Roy, ”IoT-based predictive health care analytics using cloud and ML,” International Journal of Infor- mation Technology, vol. 13, pp. 1641–1648, 2021. [23] S. H. Alsamhi et al., ”Machine learning for wearable IoTbased applications: A survey,” IEEE Internet of Things Journal, vol. 8, no. 15, pp. 11979–12001, 2021. [24] P. Balasubramanian and A. Choudhary, ”Health monitor- ing using sensor data and ML models,” International Journal of Computer Science and Information Security, vol. 18, no. 8, [25] pp. 134–139, 2020. [26] T. Li, J. Liu, and W. Luo, ”IoT-based smart healthcare monitoring system,” IEEE Access, vol. 7, pp. 135–143, 2019. [27] M. Sood and D. Kaur, ”IoT-based framework for health- care monitoring,” Procedia Computer Science, vol. 167, pp. 1578– 1584, 2020. [28] H. S. Alhumam, ”Smart wearable sensors for human health monitoring: A review,” IEEE Sensors Journal, vol. 22, no. 4, pp. 3534–3546, 2022. [29] P. Jain, R. Mishra, and V. Arora, ”Cloud-enabled IoT- based health monitoring using ML,” IEEE Access, vol. 8, pp. 187917– 187926, 2020. [30] R. Aggarwal and M. Garg, ”AI-powered healthcare: Opportunities and challenges,” Biomedical Signal Processing and Control, vol. 71, p. 103182, 2022. [31] K. B. Shankar, A. Ilayaraja, and D. Gupta, ”Integration of IoT and ML for smart health monitoring,” International Journal of Computer Applications, vol. 183, no. 34, pp. 15–21, 2022.

Copyright

Copyright © 2026 Chellannagari Bhuvana, Lavanya Allaparthi, Galipalli Harshitha, G. Indu. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.