IoT-Powered Real-Time InPatient Monitoring System with Seamless Connectivity and Insights

Abstract

IoT driven solutions for efficient and continuous patient monitoring is increasingly needed given that several resource limited and understaffed healthcare facilities require these solutions. In this paper, we describe a scalable and privacy respecting real time in-patient monitoring system coupled with a hybrid edge cloud architecture. The system is powered by an ESP32-C3 and the Gravity: MAX30102 heart and SpO? sensor, and a LM35 sensor for being body temperature. InfluxDB powered edge node is a node which processes sensor data using edge and then stores locally with low latency access and offline functionality. Also, the system synchronizes historical data to a secure cloud database as well as in sync to the database for analysis in advanced analysis and long-term trend monitoring. The real time dashboards and alert mechanisms that healthcare workers are empowered with, enables them to proactively take decisions as opposed to employing manual interventions. The system achieves performance, high reliability, and clinical utility for use in resource poor countries: an important step towards the development of cheap, automated vital tracking systems.

Introduction

The paper proposes a real-time inpatient health monitoring system using Internet of Things (IoT) technologies to address challenges in traditional vital sign monitoring, especially in resource-limited healthcare settings like India. The system employs lightweight, affordable sensors (ESP32-C3 microcontroller, MAX30102 for heart rate and SpO?, LM35 for temperature) connected via a wireless network to continuously collect and stream vital signs.

A hybrid edge-cloud architecture is introduced: data is preprocessed locally at the edge for real-time visualization and alerting on a dashboard, ensuring low latency and immediate response even with intermittent internet. Meanwhile, historical data is securely synchronized and stored in the cloud for long-term analysis and healthcare management. This design balances responsiveness, reliability, data privacy, scalability, and accessibility, making it suitable for both urban and rural environments.

The system uses lightweight protocols (MQTT, HTTP) to optimize bandwidth, with filtering and noise reduction at the edge to improve accuracy. Alerts notify medical staff instantly of critical patient conditions. Performance tests confirm the system’s efficiency, showing lower latency at the edge compared to cloud-only solutions, thereby improving clinical workflows and patient safety.

The literature review highlights prior IoT healthcare systems’ limitations such as cloud dependency, limited parameters, and lack of edge processing, supporting the need for this hybrid model that ensures continuous, secure, and scalable health monitoring.

Conclusion

The presented hybrid edge cloud health monitoring system fulfils the necessary of continuous and reliable patient monitoring in modern healthcare environments. Real time acquisition and preliminary processing of the most important vital health parameters namely heart rate and SpO?, and body temperature is ensured by integration of the MAX30102 and LM35 sensors with ESP32-C3 microcontroller. Edge computing decreases latency dramatically, speeding up reply time in emergencies, and the cloud integration also fits in with storing and accessing remote data in the long run. The system has an efficient data flow, intuitive dashboards and is scalable, adaptable and user friendly. In comparison with conventional monitoring systems, it contributes to reduction of dependence on manual efforts and to the improvement of diagnostics through timely alerts and data-based insights. Thus, the system is shown as a robust solution towards improving inpatient care, particularly in resource constrained or highly burdened clinical environments. However, future improvements can include the addition of additional sensors (ECG and blood pressure modules) to provide a wider scope patient’s health profile. Edge AI/ML algorithms could incorporate predictive analytics permitting early sign predictions by clinicians as signs of deterioration; however, such algorithms would require fine tuning and resource planning for use by clinicians. Usability of mobile apps can also be enhanced by improving mobile app compatibility to be used on multiple platforms and to serve both patients as well as healthcare professionals. Additionally, it is possible to enhance privacy and security of handling medical data by using blockchain data encryption. Since the system is also used in rural or remote healthcare settings, expanding the system to support wearable devices and offline data caching will also make it more versatile and accessible. That is in addition to interoperability with hospital EMR (Electronic Medical Records) systems, allowing clinical workflows to be streamlined. Further optimizing alert generation would be with automated anomaly detection and personally set threshold. OTA (Over the Air) mechanisms will also be used to update the firmware regularly. For the ICUs or elderly care homes, the solution can be extended to support multi patient monitoring hubs. Finally, it can be applied for large scale pilot study to validate its effect on various healthcare settings and to guide future improvements.

References

[1] Yew, H. T., Chung, S. K., Ng, M. F., Chekima, A., Ping, S. Z., & Dargham, J. A. (2020). IoT Based Real-Time Remote Patient Monitoring System. In 16th IEEE International Colloquium on Signal Processing & its Applications (CSPA 2020), Langkawi, Malaysia. IEEE. [2] Ramesha, P. S. A. K., Sindhu, S. A., Sohail, S., & Samba Siva Rao, K. T. (2021). IoT based Remote Patient Health Monitoring System. In 7th International Conference on Advanced Computing & Communication Systems (ICACCS). IEEE. [3] Yew, H. T., Chung, S. K., Ng, M. F., Chekima, A., Ping, S. Z., & Dargham, J. A. (2020). IoT Based Real-Time Remote Patient Monitoring System [Conference paper]. (Paper 3). [4] Abdulmalek, S., Nasir, A., Jabbar, W. A., Almuhaya, M. A. M., Bairagi, A. K., Khan, M. A.-M., & Kee, S.-H. (2022). IoT-Based Healthcare-Monitoring System towards Improving Quality of Life: A Review. Healthcare, 10, 1993. [5] Arefin, T., & Azad, A. K. (2024). Design and Implementation of an IoT Based Remote Health Monitoring System. Journal of Computer and Communications, 12, 37–52. [6] Hassan, M., Lata, T. R., Rani, N., Al-Amin, M., Shak, M. A. A., Mia, L., et al. (2023). IoT-Based Smart Health Monitoring System for Efficient Service in the Medical Sector. International Journal of Engineering Trends and Technology [7] Kaidi, H. M., Izhar, M. A. M., Dziyauddin, R. A., Shaiful, N. E., & Ahmad, R. (2024). A Comprehensive Review on Wireless Healthcare Monitoring: System Components. IEEE Access [8] Hicks, S. A., Strümke, I., Thambawita, V., Hammou, M., Riegler, M. A., Halvorsen, P., et al. (2022). On Evaluation Metrics for Medical Applications of Artificial Intelligence. Scientific Reports [9] Chaari, M. Z., Al-Rahimi, R., & Aljaberi, A. (2021). Real-Time Monitoring of Indoor Healthcare Tracking Using the Internet of Things Based Ibeacon. In Online Engineering and Society 4.0 (pp. 332–342). [10] Jenifer, S., et al. (2022). IoT-Based Health Monitoring System Using Smartphone and Cloud Integration. Journal of Medical Systems, 46, Article 23.

Copyright

Copyright © 2025 Rajdeep Saha, Anushka Rai, Manya Gupta, Dr. E. Saraswathi. 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.