Coma Patient Monitoring using Artificial Intelligence and Universal Object Interaction

Abstract

The Smart Coma Patient Monitoring System integrates advanced IoT and AI technologies to enhance the monitoring and care of coma patients. By utilizing a suite of sensors such as MPU6050 for motion detection, MAX30100 for heart rate and oxygen saturation levels, and temperature sensors for tracking vital signs, the system ensures comprehensive and continuous monitoring. These sensors collect real-time physiological and movement data, which is transmitted to a centralized web application. Healthcare providers can access the data remotely, enabling constant observation of the patient\'s condition. The system goes beyond traditional monitoring by incorporating an AI-driven machine learning model, specifically XGBoost, to analyze the collected data. This predictive capability identifies potential anomalies or abnormal activities, triggering timely alerts for caregivers. By detecting critical changes in the patient’s condition early, the system facilitates immediate medical intervention, reducing risks and improving patient safety. Furthermore, the predictive analytics empower healthcare professionals with actionable insights, optimizing care management and response strategies. The integration of IoT devices with real-time analytics not only automates monitoring but also ensures a proactive approach to critical care. This innovative combination of technologies enhances the quality of care, supports individualized patient tracking, and fosters better decision-making in urgent medical scenarios. Ultimately, the Smart Coma Patient Monitoring System provides a robust, efficient, and secure solution for improving the safety and well-being of coma patients.

Introduction

1. Introduction and Background

Advancements in healthcare technology, particularly IoT (Internet of Things) and AI (Artificial Intelligence), have significantly improved the monitoring of coma patients, who traditionally require constant human supervision. Limitations such as fatigue, delayed responses, and staff shortages have driven the need for automated systems.

The proposed Smart Coma Patient Monitoring System aims to:

• Continuously track vital signs and movements in real-time.

• Use AI for predictive analytics to identify potential health issues before they become emergencies.

• Enable remote monitoring, reduce manual interventions, and improve overall patient safety.

2. Literature Survey Highlights

Several previous studies introduced IoT-based or smart monitoring systems for coma patients, but often lacked:

• Detailed methodologies

• Specific sensor integration

• Use of predictive AI algorithms

These studies established the groundwork but did not fully leverage modern technologies such as machine learning or robust cloud-based data processing platforms.

3. Proposed System Overview

The system integrates UOI (Universal Object Interaction) and AI technologies to monitor patient vitals and predict abnormalities. Key components include:

Sensors Used:

• MPU6050: Tracks movement and angular changes (detects tremors or abnormal motion).

• MAX30100: Measures heart rate and SpO2 (oxygen saturation).

• Temperature Sensor: Monitors body heat to detect fevers or hypothermia.

Key Features:

• Non-invasive, continuous monitoring

• Wireless transmission to a cloud-based database

• Web dashboard for real-time visualization

• AI model (XGBoost) for anomaly detection and early warnings

• Alerts via SMS, email, or push notifications

• Scalability and integration with hospital systems

• Actionable reports for long-term treatment planning

4. System Implementation

A. Sensor Integration & Hardware Development

Sensors are either wearable or device-mounted, ensuring continuous data collection with time-stamped synchronization.

B. IoT Communication

Data is transmitted via Wi-Fi/Bluetooth to cloud platforms (e.g., AWS IoT, ThingSpeak) using MQTT/HTTP protocols.

C. Web Application Interface

A secure and responsive interface displays:

• Live vitals

• Historical trends

• Alerts and notifications
  Accessible on PCs, tablets, and smartphones.

D. AI & Machine Learning Pipeline

• Uses XGBoost for accurate, real-time predictions.

• Historical data is pre-processed (cleaning, feature engineering).

• Model is trained and validated, then deployed via cloud infrastructure.

E. Notification System

Multi-channel alerts ensure medical staff are promptly informed of any irregularities, regardless of location.

F. Validation & Testing

System undergoes rigorous pre-deployment testing for accuracy, response time, and reliability.

G. Scalability & Maintenance

Easily supports more patients/sensors, with mechanisms for firmware updates and fault tolerance.

5. Methodology – System Modules

Module 1: Sensor Data Acquisition

Gathers real-time physiological data using MPU6050, MAX30100, and temperature sensors via microcontroller.

Module 2: Data Transmission & Interface

Ensures real-time updates and displays them through a secure web dashboard, with historical data storage.

Module 3: AI-Based Analysis

Uses XGBoost for:

• Detecting deviations from normal health parameters

• Predicting future risks based on trends

Module 4: Alert & Notification System

Generates real-time alerts for anomalies and sends notifications through multiple channels for immediate intervention.

Conclusion

The Coma Patient Monitoring System represents a significant advancement in healthcare technology, combining UOI and AI to offer continuous and precise monitoring for coma patients. By integrating sensors such as the MPU6050 for motion detection, MAX30100 for heart rate and oxygen saturation monitoring, and temperature sensors, this system ensures real-time collection of critical physiological data. The deployment of a machine learning model like XGBoost contributes to the predictive accuracy of abnormal conditions, enabling timely alerts to caregivers and healthcare providers. Through seamless integration with a web-based platform, the system facilitates remote accessibility and real-time monitoring, addressing the challenges of traditional coma patient care. It not only improves patient safety but also reduces the manual workload on medical staff, thereby enhancing the overall efficiency of healthcare delivery. The system\'s ability to predict and detect anomalies ensures that critical situations can be addressed promptly, potentially preventing adverse health outcomes.

References

[1] R. Latha, R. Raman, T. S. Kumar, C. J. Rawandale, R. Meenakshi, and C. Srinivasan, \"Automated Health Monitoring System for Coma Patients,\" IEEE Conference Publication, 2020. DOI: 10.1109/ICSSAS57918.2023.10331870. URL: IEEE Xplore. [2] S.K.,S.K., Y. M. G, and T. P, “Smart Health Monitoring System for Coma Patients using IoT,” IEEE Conference Publication, 2023. DOI: 10.1109/ICCMC56507.2022. 10084196. URL: IEEE Xplore. [3] A.L. Virgin, K.A, P.R, R. N. B, and B. K, “Coma Patient Monitoring System,” IET Conference Publication, 2022. DOI: 10.1049/icp.2022. 0929. URL: IEEE Xplore. [4] H. A. Rammo and M. Cevik. “Comatose Patient Monitoring System Based on IOT,,” IET Conference Publication,2023 [5] S.Sathyaraj “IOT based monitoring system for comatose patients” International journal of creative research thoughts publication, 2023 [6] S. C. Koganti, H. Suma, and A. M. Abhishek, “Analysis and monitoring of coma patients using wearable motion sensor system,” Int. J. Sci. Res, vol. 4, no. 9, pp. 1154–1158, 2015. [7] K. Ravikumar and R. Vasuki, “Monitoring and analysis of coma patients using variable motion sensor system,” Drug Invention Today, vol. 11, 04 2019. [8] R. Subha, M. Haritha, B. Nithishna, and S. Monisha, “Coma patient health monitoring system using iot,” in 2020 6th International conference on advanced computing and communication systems (ICACCS), pp. 1454–1457, IEEE, 2020. [9] R. Latha, R. Raman, T. S. Kumar, C. J. Rawandale, R. Meenakshi, and C. Srinivasan, “Automated health monitoring system for coma patients,” in 2023 International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS), pp. 1475–1480, IEEE, 2023. [10] December 2021, Sultana, S., Rahman, S., Rahman, M.A., Chakraborty, N.R., and Hasan, T. a system for integrated health monitoring that is IoT-based. The 6th IEEE International Conference on Computing, Communication, and Automation (ICCCA) will take place in 2021. (pp. 549-554). [11] 2020, March. Subha, R., Haritha, M., Nithishna, B., and Monisha, S.G. IOT system for monitoring the health of coma patients. The sixth ICACCS (International Conference on Advanced Computing and Communicati [12] Aher, V., Jalgaonkar, A., and Mantri, V. 2022. Health Monitoring System for Patients in Coma Using IOT (No. 7507). EasyChair. [13] Internet of Things Based Monitoring System for Comatose Patients by Anayo, O.H., Isaiah, A.I., Edward, U.N., Doris, and Yinka, A.I. [14] V Tamilselvi, S Sribalaji, P Vigneshwaran, P Vinu and J. GeethaRamani, coma base health monitoring system, IEEE. [15] S. Ahammed, N. Hassan, S. H. Cheragee, and A. Z. M. T. Islam, 2021. anIoT-based solution for remote, realtime health monitoring. 8(3), pp. 23–29, I

Copyright

Copyright © 2025 Deepiga R, Harini Sri A R, Jayavarshini M, Kanividya G P, Dr. P. Amudha. 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.