A Real-Time IoT-Based System for Early Warning of Physiological Deterioration in Post-Operative Patients

Abstract

The patients in the post-operative state are always at risk of sudden physiological state deterioration. This paper proposes a health monitoring system through periodic short-term physiological data acquisition using an ESP32-based system with ECG and SpO2 sensors. Multimodal vital signals are collected during structured monitoring sessions and sent to a central server for real-time visualization and trend analysis through a web interface. The proposed health monitoring system uses temporal trend analysis with clinical threshold reasoning. This approach helps in the graded assessment of patient state through medically defined parameter ranges rather than binary reasoning. This reduces the chances of false alarms and increases the reliability of the monitoring system. The results show stable system performance with reliable communication and anomaly detection. The proposed approach will be useful in cost-effective deployment of the system.

Introduction

The text describes the development of an IoT-based healthcare monitoring system designed to improve post-operative patient care, especially in general ward settings where continuous ICU-level monitoring is not feasible. Existing IoT health systems use wearable sensors and cloud connectivity to track vital signs like ECG, heart rate, and SpO? in real time, but they often rely on continuous monitoring and simple threshold-based alerts. This leads to problems such as high power consumption, data redundancy, false alarms, and poor scalability outside ICU environments.

To address these issues, the proposed system introduces a periodic monitoring approach using an ESP32-based embedded platform with sensors like MAX30102 (SpO? and heart rate) and AD8232 (ECG). Instead of constant tracking, it collects short-duration physiological data at scheduled intervals and performs temporal trend analysis. This allows the system to detect gradual health deterioration rather than only sudden threshold violations.

A key improvement over existing methods is the use of graded clinical reasoning instead of binary “normal/abnormal” alerts, making the output more aligned with real medical assessment. The system also reduces cost, power usage, and data load while improving interpretability and reducing false alarms

Conclusion

The current study experimentally evaluated a low-cost physiological monitor based on an ESP32, incorporating MAX30102 and AD8232 sensors on 10 healthy subjects. The results demonstrate a 100% data acquisition rate without any false alarms during cloud/CSV logging for 10 minutes. Although this evidence indicates that the technology is ready for implementation in controlled settings, additional testing in older adults who have undergone surgery alongside a gold standard will be required to validate the technology’s effectiveness in detecting early deterioration.

References

[1] “A Health Management System Design for Large-Scale Vertical Mill,” 2020. [2] “Cloud-Assisted Home Health Monitoring System,” 2020. [3] C. Deng, “Data Recognition, Monitoring and Early Warning of Mental Health Signs based on Artificial Intelligence,” Proc. 3rd Int. Conf. Data Science and Information System (ICDSIS), 2025. [4] P. Anirudh et al., “Automatic Patient Monitoring and Alerting System based on IoT,” Proc. 8th Int. Conf. Communication and Electronics Systems (ICCES), 2023 [5] L. Gatzoulis and I. Iakovidis, “Wearable and Portable eHealth Systems: Technological Issues and Opportunities for Personalized Care,” IEEE Eng. Med. Biol. Mag., vol. 26, no. 5, pp. 51–56, 2007. [6] A. Affrose et al., “An Effective Investigation on Health Cloud Based IoT Based Virtual Health Monitoring System,” Proc. 9th Int. Conf. Communication and Electronics Systems (ICCES), 2024. [7] A. Balamanikandan et al., \"IoT-Enabled Advanced Health Monitoring System using ESP32 and UBI DOTS,\" Proc. Int. Conf. IoT Based Control Networks and Intelligent Systems. [8] B. Prashanthi et al., \"AI-Driven Smart Health Monitoring System Using Wearable IoT Devices and Predictive Analytics,\" Proc. Int. Conf. IoT, Communication and Automation Technology (ICICAT), 2024. [9] \"LifeLine: Smart Soldier Health Monitoring and Situational Awareness System Powered by ESP8266 and IoT Integration,\" 2020. [10] V. B. Shalini, \"Smart Health Care Monitoring System based on Internet of Things (IoT),\" Proc. Int. Conf. Artificial Intelligence and Smart Systems (ICAIS), 2021. [11] \"IoT-Enabled Health Monitoring Glove with Machine Learning-Based Risk Classification,\" 2024. [12] \"Automated Health Monitoring Integrating AI and IoT for Continuous Patient Observation,\" 2024. [13] \"IoT ML-Driven Holistic Health Monitoring and Fitness Assessment: Empowering Proactive Wellbeing Management,\" 2024. [14] \"IoT Based Health Risk Monitoring System,\" 2024. [15] \"HOT Watch: IoT-Based Wearable Health Monitoring System,\" 2024. [16] AI-Driven Mobile App for Personalized Health Monitoring,\" 2020 [17] \"Smart Health Monitoring and Anomaly Detection Using Internet of Things (IoT) and Artificial Intelligence (AI),\" 2020. [18] \"Real-Time Disease Monitoring and Alert System for Public Health Safety,\" 2020. [19] \"The Concept of the Home Health Monitoring,\" 2020. [20] “Multi-sensor IoT solution for environmental and health monitoring,” 2025. [21] “A novel prototype-based smart health monitoring system in IoT system,” 2020. [22] I. Kim, “Home health monitoring,” 2014. [23] “Raspberry pi based real-time health monitoring and alert system for enhanced patient care,”

Copyright

Copyright © 2026 Manasvi N. Pawar, Yash G. Patil, Vanshika Y. Pathrabe, Milind N. Patil. 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.